Sensors

23 pages, 3763 KiB

Open AccessEditor’s ChoiceReview

Morphological Effects in SnO₂ Chemiresistors for Ethanol Detection: A Review in Terms of Central Performances and Outliers

by Andrea Ponzoni

Sensors 2021, 21(1), 29; https://doi.org/10.3390/s21010029 - 23 Dec 2020

Cited by 18 | Viewed by 3478

Abstract

SnO₂ is one of the most studied materials in gas sensing and is often used as a benchmark for other metal oxide-based gas sensors. To optimize its structural and functional features, the fine tuning of the morphology in nanoparticles, nanowires, nanosheets and [...] Read more.

SnO₂ is one of the most studied materials in gas sensing and is often used as a benchmark for other metal oxide-based gas sensors. To optimize its structural and functional features, the fine tuning of the morphology in nanoparticles, nanowires, nanosheets and their eventual hierarchical organization has become an active field of research. In this paper, the different SnO₂ morphologies reported in literature in the last five years are systematically compared in terms of response amplitude through a statistical approach. To have a dataset as homogeneous as possible, which is necessary for a reliable comparison, the analysis is carried out on sensors based on pure SnO₂, focusing on ethanol detection in a dry air background as case study. Concerning the central performances of each morphology, results indicate that none clearly outperform the others, while a few individual materials emerge as remarkable outliers with respect to the whole dataset. The observed central performances and outliers may represent a suitable reference for future research activities in the field. Full article

(This article belongs to the Special Issue Gas Sensing Materials)

► Show Figures

Figure 1

31 pages, 5086 KiB

Open AccessEditor’s ChoiceArticle

Ultra Stable Molecular Sensors by Submicron Referencing and Why They Should Be Interrogated by Optical Diffraction—Part II. Experimental Demonstration

by Andreas Frutiger, Karl Gatterdam, Yves Blickenstorfer, Andreas Michael Reichmuth, Christof Fattinger and János Vörös

Sensors 2021, 21(1), 9; https://doi.org/10.3390/s21010009 - 22 Dec 2020

Cited by 7 | Viewed by 5320

Abstract

Label-free optical biosensors are an invaluable tool for molecular interaction analysis. Over the past 30 years, refractometric biosensors and, in particular, surface plasmon resonance have matured to the de facto standard of this field despite a significant cross reactivity to environmental and experimental [...] Read more.

Label-free optical biosensors are an invaluable tool for molecular interaction analysis. Over the past 30 years, refractometric biosensors and, in particular, surface plasmon resonance have matured to the de facto standard of this field despite a significant cross reactivity to environmental and experimental noise sources. In this paper, we demonstrate that sensors that apply the spatial affinity lock-in principle (part I) and perform readout by diffraction overcome the drawbacks of established refractometric biosensors. We show this with a direct comparison of the cover refractive index jump sensitivity as well as the surface mass resolution of an unstabilized diffractometric biosensor with a state-of-the-art Biacore 8k. A combined refractometric diffractometric biosensor demonstrates that a refractometric sensor requires a much higher measurement precision than the diffractometric to achieve the same resolution. In a conceptual and quantitative discussion, we elucidate the physical reasons behind and define the figure of merit of diffractometric biosensors. Because low-precision unstabilized diffractometric devices achieve the same resolution as bulky stabilized refractometric sensors, we believe that label-free optical sensors might soon move beyond the drug discovery lab as miniaturized, mass-produced environmental/medical sensors. In fact, combined with the right surface chemistry and recognition element, they might even bring the senses of smell/taste to our smart devices. Full article

(This article belongs to the Special Issue Advanced Biophotonic Sensors)

► Show Figures

Figure 1

32 pages, 796 KiB

Open AccessEditor’s ChoiceReview

A Survey of Smartphone-Based Indoor Positioning System Using RF-Based Wireless Technologies

by Santosh Subedi and Jae-Young Pyun

Sensors 2020, 20(24), 7230; https://doi.org/10.3390/s20247230 - 17 Dec 2020

Cited by 71 | Viewed by 8392

Abstract

In recent times, social and commercial interests in location-based services (LBS) are significantly increasing due to the rise in smart devices and technologies. The global navigation satellite systems (GNSS) have long been employed for LBS to navigate and determine accurate and reliable location [...] Read more.

In recent times, social and commercial interests in location-based services (LBS) are significantly increasing due to the rise in smart devices and technologies. The global navigation satellite systems (GNSS) have long been employed for LBS to navigate and determine accurate and reliable location information in outdoor environments. However, the GNSS signals are too weak to penetrate buildings and unable to provide reliable indoor LBS. Hence, GNSS’s incompetence in the indoor environment invites extensive research and development of an indoor positioning system (IPS). Various technologies and techniques have been studied for IPS development. This paper provides an overview of the available smartphone-based indoor localization solutions that rely on radio frequency technologies. As fingerprinting localization is mostly accepted for IPS development owing to its good localization accuracy, we discuss fingerprinting localization in detail. In particular, our analysis is more focused on practical IPS that are realized using a smartphone and Wi-Fi/Bluetooth Low Energy (BLE) as a signal source. Furthermore, we elaborate on the challenges of practical IPS, the available solutions and comprehensive performance comparison, and present some future trends in IPS development. Full article

(This article belongs to the Special Issue Indoor Positioning and Navigation)

► Show Figures

Figure 1

19 pages, 6036 KiB

Open AccessEditor’s ChoiceArticle

Robust Building Extraction for High Spatial Resolution Remote Sensing Images with Self-Attention Network

by Dengji Zhou, Guizhou Wang, Guojin He, Tengfei Long, Ranyu Yin, Zhaoming Zhang, Sibao Chen and Bin Luo

Sensors 2020, 20(24), 7241; https://doi.org/10.3390/s20247241 - 17 Dec 2020

Cited by 31 | Viewed by 3444

Abstract

Building extraction from high spatial resolution remote sensing images is a hot spot in the field of remote sensing applications and computer vision. This paper presents a semantic segmentation model, which is a supervised method, named Pyramid Self-Attention Network (PISANet). Its structure is [...] Read more.

Building extraction from high spatial resolution remote sensing images is a hot spot in the field of remote sensing applications and computer vision. This paper presents a semantic segmentation model, which is a supervised method, named Pyramid Self-Attention Network (PISANet). Its structure is simple, because it contains only two parts: one is the backbone of the network, which is used to learn the local features (short distance context information around the pixel) of buildings from the image; the other part is the pyramid self-attention module, which is used to obtain the global features (long distance context information with other pixels in the image) and the comprehensive features (includes color, texture, geometric and high-level semantic feature) of the building. The network is an end-to-end approach. In the training stage, the input is the remote sensing image and corresponding label, and the output is probability map (the probability that each pixel is or is not building). In the prediction stage, the input is the remote sensing image, and the output is the extraction result of the building. The complexity of the network structure was reduced so that it is easy to implement. The proposed PISANet was tested on two datasets. The result shows that the overall accuracy reached 94.50 and 96.15%, the intersection-over-union reached 77.45 and 87.97%, and F1 index reached 87.27 and 93.55%, respectively. In experiments on different datasets, PISANet obtained high overall accuracy, low error rate and improved integrity of individual buildings. Full article

(This article belongs to the Special Issue Mobile Multi-Sensors in Positioning, Navigation, and Mapping Applications)

► Show Figures

Figure 1

15 pages, 2356 KiB

Open AccessEditor’s ChoiceArticle

A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction

by Chengying Zhao, Xianzhen Huang, Yuxiong Li and Muhammad Yousaf Iqbal

Sensors 2020, 20(24), 7109; https://doi.org/10.3390/s20247109 - 11 Dec 2020

Cited by 70 | Viewed by 5029

Abstract

In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted [...] Read more.

In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted more attention. The convolution neural network (CNN) is a kind of deep neural network widely used in RUL prediction. It shows great potential for application in RUL prediction. A CNN is used to extract the features of time-series data according to the spatial feature method. This way of processing features without considering the time dimension will affect the prediction accuracy of the model. On the contrary, the commonly used long short-term memory (LSTM) network considers the timing of the data. However, compared with CNN, it lacks spatial data extraction capabilities. This paper proposes a double-channel hybrid prediction model based on the CNN and a bidirectional LSTM network to avoid those drawbacks. The sliding time window is used for data preprocessing, and an improved piece-wise linear function is used for model validating. The prediction model is evaluated using the C-MAPSS dataset provided by NASA. The predicted results show the proposed prediction model to have a better prediction performance compared with other state-of-the-art models. Full article

(This article belongs to the Special Issue Deep Learning, Artificial Neural Networks and Sensors for Fault Diagnosis)

► Show Figures

Figure 1

72 pages, 22070 KiB

Open AccessEditor’s ChoiceReview

InAsSb-Based Infrared Photodetectors: Thirty Years Later On

by Antoni Rogalski, Piotr Martyniuk, Malgorzata Kopytko, Pawel Madejczyk and Sanjay Krishna

Sensors 2020, 20(24), 7047; https://doi.org/10.3390/s20247047 - 9 Dec 2020

Cited by 51 | Viewed by 7950

Abstract

In 1989, one author of this paper (A.R.) published the very first review paper on InAsSb infrared detectors. During the last thirty years, many scientific breakthroughs and technological advances for InAsSb-based photodetectors have been made. Progress in advanced epitaxial methods contributed considerably to [...] Read more.

In 1989, one author of this paper (A.R.) published the very first review paper on InAsSb infrared detectors. During the last thirty years, many scientific breakthroughs and technological advances for InAsSb-based photodetectors have been made. Progress in advanced epitaxial methods contributed considerably to the InAsSb improvement. Current efforts are directed towards the photodetector’s cut-off wavelength extension beyond lattice-available and lattice-strained binary substrates. It is suspected that further improvement of metamorphic buffers for epitaxial layers will lead to lower-cost InAsSb-based focal plane arrays on large-area alternative substrates like GaAs and silicon. Most photodetector reports in the last decade are devoted to the heterostructure and barrier architectures operating in high operating temperature conditions. In the paper, at first InAsSb growth methods are briefly described. Next, the fundamental material properties are reviewed, stressing electrical and optical aspects limiting the photodetector performance. The last part of the paper highlights new ideas in design of InAsSb-based bulk and superlattice infrared detectors and focal plane arrays. Their performance is compared with the state-of-the-art infrared detector technologies. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

37 pages, 22464 KiB

Open AccessEditor’s ChoiceReview

Optical Fiber Sensors by Direct Laser Processing: A Review

by David Pallarés-Aldeiturriaga, Pablo Roldán-Varona, Luis Rodríguez-Cobo and José Miguel López-Higuera

Sensors 2020, 20(23), 6971; https://doi.org/10.3390/s20236971 - 6 Dec 2020

Cited by 23 | Viewed by 6223

Abstract

The consolidation of laser micro/nano processing technologies has led to a continuous increase in the complexity of optical fiber sensors. This new avenue offers novel possibilities for advanced sensing in a wide set of application sectors and, especially in the industrial and medical [...] Read more.

The consolidation of laser micro/nano processing technologies has led to a continuous increase in the complexity of optical fiber sensors. This new avenue offers novel possibilities for advanced sensing in a wide set of application sectors and, especially in the industrial and medical fields. In this review, the most important transducing structures carried out by laser processing in optical fiber are shown. The work covers different types of fiber Bragg gratings with an emphasis in the direct-write technique and their most interesting inscription configurations. Along with gratings, cladding waveguide structures in optical fibers have reached notable importance in the development of new optical fiber transducers. That is why a detailed study is made of the different laser inscription configurations that can be adopted, as well as their current applications. Microcavities manufactured in optical fibers can be used as both optical transducer and hybrid structure to reach advanced soft-matter optical sensing approaches based on optofluidic concepts. These in-fiber cavities manufactured by femtosecond laser irradiation followed by chemical etching are promising tools for biophotonic devices. Finally, the enhanced Rayleigh backscattering fibers by femtosecond laser dots inscription are also discussed, as a consequence of the new sensing possibilities they enable. Full article

(This article belongs to the Collection Optical Fiber Sensors)

► Show Figures

Figure 1

20 pages, 17834 KiB

Open AccessEditor’s ChoiceArticle

Hyperspectral Imaging for Glioblastoma Surgery: Improving Tumor Identification Using a Deep Spectral-Spatial Approach

by Francesca Manni, Fons van der Sommen, Himar Fabelo, Svitlana Zinger, Caifeng Shan, Erik Edström, Adrian Elmi-Terander, Samuel Ortega, Gustavo Marrero Callicó and Peter H. N. de With

Sensors 2020, 20(23), 6955; https://doi.org/10.3390/s20236955 - 5 Dec 2020

Cited by 35 | Viewed by 5236

Abstract

The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal resection may result in neurological deficits. On the other hand, accurate intraoperative identification of the tumor boundaries may be very difficult, resulting in subtotal [...] Read more.

The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal resection may result in neurological deficits. On the other hand, accurate intraoperative identification of the tumor boundaries may be very difficult, resulting in subtotal resections. Histological examination of biopsies can be used repeatedly to help achieve gross total resection but this is not practically feasible due to the turn-around time of the tissue analysis. Therefore, intraoperative techniques to recognize tissue types are investigated to expedite the clinical workflow for tumor resection and improve outcome by aiding in the identification and removal of the malignant lesion. Hyperspectral imaging (HSI) is an optical imaging technique with the power of extracting additional information from the imaged tissue. Because HSI images cannot be visually assessed by human observers, we instead exploit artificial intelligence techniques and leverage a Convolutional Neural Network (CNN) to investigate the potential of HSI in twelve in vivo specimens. The proposed framework consists of a 3D–2D hybrid CNN-based approach to create a joint extraction of spectral and spatial information from hyperspectral images. A comparison study was conducted exploiting a 2D CNN, a 1D DNN and two conventional classification methods (SVM, and the SVM classifier combined with the 3D–2D hybrid CNN) to validate the proposed network. An overall accuracy of 80% was found when tumor, healthy tissue and blood vessels were classified, clearly outperforming the state-of-the-art approaches. These results can serve as a basis for brain tumor classification using HSI, and may open future avenues for image-guided neurosurgical applications. Full article

(This article belongs to the Special Issue Trends and Prospects in Medical Hyperspectral Imagery)

► Show Figures

Figure 1

22 pages, 2261 KiB

Open AccessEditor’s ChoiceReview

The Application of Prussian Blue Nanoparticles in Tumor Diagnosis and Treatment

by Xiaoran Gao, Qiaowen Wang, Cui Cheng, Shujin Lin, Ting Lin, Chun Liu and Xiao Han

Sensors 2020, 20(23), 6905; https://doi.org/10.3390/s20236905 - 3 Dec 2020

Cited by 23 | Viewed by 5159

Abstract

Prussian blue nanoparticles (PBNPs) have attracted increasing research interest in immunosensors, bioimaging, drug delivery, and application as therapeutic agents due to their large internal pore volume, tunable size, easy synthesis and surface modification, good thermal stability, and favorable biocompatibility. This review first outlines [...] Read more.

Prussian blue nanoparticles (PBNPs) have attracted increasing research interest in immunosensors, bioimaging, drug delivery, and application as therapeutic agents due to their large internal pore volume, tunable size, easy synthesis and surface modification, good thermal stability, and favorable biocompatibility. This review first outlines the effect of tumor markers using PBNPs-based immunosensors which have a sandwich-type architecture and competitive-type structure. Metal ion doped PBNPs which were used as T₁-weight magnetic resonance and photoacoustic imaging agents to improve image quality and surface modified PBNPs which were used as drug carriers to decrease side effects via passive or active targeting to tumor sites are also summarized. Moreover, the PBNPs with high photothermal efficiency and excellent catalase-like activity were promising for photothermal therapy and O₂ self-supplied photodynamic therapy of tumors. Hence, PBNPs-based multimodal imaging-guided combinational tumor therapies (such as chemo, photothermal, and photodynamic therapies) were finally reviewed. This review aims to inspire broad interest in the rational design and application of PBNPs for detecting and treating tumors in clinical research. Full article

(This article belongs to the Special Issue Multifunctional Materials Sensors for Theranostic Nanomedicine)

► Show Figures

Figure 1

14 pages, 3619 KiB

Open AccessEditor’s ChoiceArticle

Real-Time Plant Leaf Counting Using Deep Object Detection Networks

by Michael Buzzy, Vaishnavi Thesma, Mohammadreza Davoodi and Javad Mohammadpour Velni

Sensors 2020, 20(23), 6896; https://doi.org/10.3390/s20236896 - 3 Dec 2020

Cited by 52 | Viewed by 6412

Abstract

The use of deep neural networks (DNNs) in plant phenotyping has recently received considerable attention. By using DNNs, valuable insights into plant traits can be readily achieved. While these networks have made considerable advances in plant phenotyping, the results are processed too slowly [...] Read more.

The use of deep neural networks (DNNs) in plant phenotyping has recently received considerable attention. By using DNNs, valuable insights into plant traits can be readily achieved. While these networks have made considerable advances in plant phenotyping, the results are processed too slowly to allow for real-time decision-making. Therefore, being able to perform plant phenotyping computations in real-time has become a critical part of precision agriculture and agricultural informatics. In this work, we utilize state-of-the-art object detection networks to accurately detect, count, and localize plant leaves in real-time. Our work includes the creation of an annotated dataset of Arabidopsis plants captured using Cannon Rebel XS camera. These images and annotations have been complied and made publicly available. This dataset is then fed into a Tiny-YOLOv3 network for training. The Tiny-YOLOv3 network is then able to converge and accurately perform real-time localization and counting of the leaves. We also create a simple robotics platform based on an Android phone and iRobot create2 to demonstrate the real-time capabilities of the network in the greenhouse. Additionally, a performance comparison is conducted between Tiny-YOLOv3 and Faster R-CNN. Unlike Tiny-YOLOv3, which is a single network that does localization and identification in a single pass, the Faster R-CNN network requires two steps to do localization and identification. While with Tiny-YOLOv3, inference time, F1 Score, and false positive rate (FPR) are improved compared to Faster R-CNN, other measures such as difference in count (DiC) and AP are worsened. Specifically, for our implementation of Tiny-YOLOv3, the inference time is under 0.01 s, the F1 Score is over 0.94, and the FPR is around 24%. Last, transfer learning using Tiny-YOLOv3 to detect larger leaves on a model trained only on smaller leaves is implemented. The main contributions of the paper are in creating dataset (shared with the research community), as well as the trained Tiny-YOLOv3 network for leaf localization and counting. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

15 pages, 665 KiB

Open AccessEditor’s ChoiceArticle

Design of a Scalable and Fast YOLO for Edge-Computing Devices

by Byung-Gil Han, Joon-Goo Lee, Kil-Taek Lim and Doo-Hyun Choi

Sensors 2020, 20(23), 6779; https://doi.org/10.3390/s20236779 - 27 Nov 2020

Cited by 29 | Viewed by 7651

Abstract

With the increase in research cases of the application of a convolutional neural network (CNN)-based object detection technology, studies on the light-weight CNN models that can be performed in real time on the edge-computing devices are also increasing. This paper proposed scalable convolutional [...] Read more.

With the increase in research cases of the application of a convolutional neural network (CNN)-based object detection technology, studies on the light-weight CNN models that can be performed in real time on the edge-computing devices are also increasing. This paper proposed scalable convolutional blocks that can be easily designed CNN networks of You Only Look Once (YOLO) detector which have the balanced processing speed and accuracy of the target edge-computing devices considering different performances by exchanging the proposed blocks simply. The maximum number of kernels of the convolutional layer was determined through simple but intuitive speed comparison tests for three edge-computing devices to be considered. The scalable convolutional blocks were designed in consideration of the limited maximum number of kernels to detect objects in real time on these edge-computing devices. Three scalable and fast YOLO detectors (SF-YOLO) which designed using the proposed scalable convolutional blocks compared the processing speed and accuracy with several conventional light-weight YOLO detectors on the edge-computing devices. When compared with YOLOv3-tiny, SF-YOLO was seen to be 2 times faster than the previous processing speed but with the same accuracy as YOLOv3-tiny, and also, a 48% improved processing speed than the YOLOv3-tiny-PRN which is the processing speed improvement model. Also, even in the large SF-YOLO model that focuses on the accuracy performance, it achieved a 10% faster processing speed with better accuracy of 40.4% [email protected] in the MS COCO dataset than YOLOv4-tiny model. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

22 pages, 1035 KiB

Open AccessEditor’s ChoiceReview

Advances in Sensor Technologies in the Era of Smart Factory and Industry 4.0

by Tahera Kalsoom, Naeem Ramzan, Shehzad Ahmed and Masood Ur-Rehman

Sensors 2020, 20(23), 6783; https://doi.org/10.3390/s20236783 - 27 Nov 2020

Cited by 133 | Viewed by 21680

Abstract

The evolution of intelligent manufacturing has had a profound and lasting effect on the future of global manufacturing. Industry 4.0 based smart factories merge physical and cyber technologies, making the involved technologies more intricate and accurate; improving the performance, quality, controllability, management, and [...] Read more.

The evolution of intelligent manufacturing has had a profound and lasting effect on the future of global manufacturing. Industry 4.0 based smart factories merge physical and cyber technologies, making the involved technologies more intricate and accurate; improving the performance, quality, controllability, management, and transparency of manufacturing processes in the era of the internet-of-things (IoT). Advanced low-cost sensor technologies are essential for gathering data and utilizing it for effective performance by manufacturing companies and supply chains. Different types of low power/low cost sensors allow for greatly expanded data collection on different devices across the manufacturing processes. While a lot of research has been carried out with a focus on analyzing the performance, processes, and implementation of smart factories, most firms still lack in-depth insight into the difference between traditional and smart factory systems, as well as the wide set of different sensor technologies associated with Industry 4.0. This paper identifies the different available sensor technologies of Industry 4.0, and identifies the differences between traditional and smart factories. In addition, this paper reviews existing research that has been done on the smart factory; and therefore provides a broad overview of the extant literature on smart factories, summarizes the variations between traditional and smart factories, outlines different types of sensors used in a smart factory, and creates an agenda for future research that encompasses the vigorous evolution of Industry 4.0 based smart factories. Full article

(This article belongs to the Special Issue Next-Generation Internet of Things (IoT): Opportunities, Challenges, and Solutions)

► Show Figures

Figure 1

17 pages, 1483 KiB

Open AccessEditor’s ChoiceArticle

Is Standardization Necessary for Sharing of a Large Mid-Infrared Soil Spectral Library?

by Shree R. S. Dangal and Jonathan Sanderman

Sensors 2020, 20(23), 6729; https://doi.org/10.3390/s20236729 - 25 Nov 2020

Cited by 25 | Viewed by 4292

Abstract

Recent developments in diffuse reflectance soil spectroscopy have increasingly focused on building and using large soil spectral libraries with the purpose of supporting many activities relevant to monitoring, mapping and managing soil resources. A potential limitation of using a mid-infrared (MIR) spectral library [...] Read more.

Recent developments in diffuse reflectance soil spectroscopy have increasingly focused on building and using large soil spectral libraries with the purpose of supporting many activities relevant to monitoring, mapping and managing soil resources. A potential limitation of using a mid-infrared (MIR) spectral library developed by another laboratory is the need to account for inherent differences in the signal strength at each wavelength associated with different instrumental and environmental conditions. Here we apply predictive models built using the USDA National Soil Survey Center–Kellogg Soil Survey Laboratory (NSSC-KSSL) MIR spectral library (n = 56,155) to samples sets of European and US origin scanned on a secondary spectrometer to assess the need for calibration transfer using a piecewise direct standardization (PDS) approach in transforming spectra before predicting carbon cycle relevant soil properties (bulk density, CaCO₃, organic carbon, clay and pH). The European soil samples were from the land use/cover area frame statistical survey (LUCAS) database available through the European Soil Data Center (ESDAC), while the US soil samples were from the National Ecological Observatory Network (NEON). Additionally, the performance of the predictive models on PDS transfer spectra was tested against the direct calibration models built using samples scanned on the secondary spectrometer. On independent test sets of European and US origin, PDS improved predictions for most but not all soil properties with memory based learning (MBL) models generally outperforming partial least squares regression and Cubist models. Our study suggests that while good-to-excellent results can be obtained without calibration transfer, for most of the cases presented in this study, PDS was necessary for unbiased predictions. The MBL models also outperformed the direct calibration models for most of the soil properties. For laboratories building new spectroscopy capacity utilizing existing spectral libraries, it appears necessary to develop calibration transfer using PDS or other calibration transfer techniques to obtain the least biased and most precise predictions of different soil properties. Full article

(This article belongs to the Special Issue Proximal and Remote Soil Sensing Technologies for Multiscale Soil Investigation)

► Show Figures

Figure 1

25 pages, 1252 KiB

Open AccessEditor’s ChoiceArticle

A Modular Experimentation Methodology for 5G Deployments: The 5GENESIS Approach

by Almudena Díaz Zayas, Giuseppe Caso, Özgü Alay, Pedro Merino, Anna Brunstrom, Dimitris Tsolkas and Harilaos Koumaras

Sensors 2020, 20(22), 6652; https://doi.org/10.3390/s20226652 - 20 Nov 2020

Cited by 18 | Viewed by 4653

Abstract

The high heterogeneity of 5G use cases requires the extension of the traditional per-component testing procedures provided by certification organizations, in order to devise and incorporate methodologies that cover the testing requirements from vertical applications and services. In this paper, we introduce an [...] Read more.

The high heterogeneity of 5G use cases requires the extension of the traditional per-component testing procedures provided by certification organizations, in order to devise and incorporate methodologies that cover the testing requirements from vertical applications and services. In this paper, we introduce an experimentation methodology that is defined in the context of the 5GENESIS project, which aims at enabling both the testing of network components and validation of E2E KPIs. The most important contributions of this methodology are its modularity and flexibility, as well as the open-source software that was developed for its application, which enable lightweight adoption of the methodology in any 5G testbed. We also demonstrate how the methodology can be used, by executing and analyzing different experiments in a 5G Non-Standalone (NSA) deployment at the University of Malaga. The key findings of the paper are an initial 5G performance assessment and KPI analysis and the detection of under-performance issues at the application level. Those findings highlight the need for reliable testing and validation procedures towards a fair benchmarking of generic 5G services and applications. Full article

(This article belongs to the Special Issue Experimentation in 5G and beyond Networks: State of the Art and the Way Forward)

► Show Figures

Figure 1

20 pages, 6081 KiB

Open AccessEditor’s ChoiceArticle

An Integrated Deep Learning Method towards Fault Diagnosis of Hydraulic Axial Piston Pump

by Shengnan Tang, Shouqi Yuan, Yong Zhu and Guangpeng Li

Sensors 2020, 20(22), 6576; https://doi.org/10.3390/s20226576 - 18 Nov 2020

Cited by 25 | Viewed by 3635

Abstract

A hydraulic axial piston pump is the essential component of a hydraulic transmission system and plays a key role in modern industry. Considering varying working conditions and the implicity of frequent faults, it is difficult to accurately monitor the machinery faults in the [...] Read more.

A hydraulic axial piston pump is the essential component of a hydraulic transmission system and plays a key role in modern industry. Considering varying working conditions and the implicity of frequent faults, it is difficult to accurately monitor the machinery faults in the actual operating process by using current fault diagnosis methods. Hence, it is urgent and significant to investigate effective and precise fault diagnosis approaches for pumps. Owing to the advantages of intelligent fault diagnosis methods in big data processing, methods based on deep learning have accomplished admirable performance for fault diagnosis of rotating machinery. The prevailing convolutional neural network (CNN) displays desirable automatic learning ability. Therefore, an integrated intelligent fault diagnosis method is proposed based on CNN and continuous wavelet transform (CWT), combining the feature extraction and classification. Firstly, CWT is used to convert the raw vibration signals into time-frequency representations and achieve the extraction of image features. Secondly, a new framework of deep CNN is established via designing the convolutional layers and sub-sampling layers. The learning process and results are visualized by t-distributed stochastic neighbor embedding (t-SNE). The results of the experiment present a higher classification accuracy compared with other models. It is demonstrated that the proposed approach is effective and stable for fault diagnosis of a hydraulic axial piston pump. Full article

(This article belongs to the Special Issue Deep Learning, Artificial Neural Networks and Sensors for Fault Diagnosis)

► Show Figures

Figure 1

17 pages, 538 KiB

Open AccessEditor’s ChoiceArticle

MQTTset, a New Dataset for Machine Learning Techniques on MQTT

by Ivan Vaccari, Giovanni Chiola, Maurizio Aiello, Maurizio Mongelli and Enrico Cambiaso

Sensors 2020, 20(22), 6578; https://doi.org/10.3390/s20226578 - 18 Nov 2020

Cited by 132 | Viewed by 11734

Abstract

IoT networks are increasingly popular nowadays to monitor critical environments of different nature, significantly increasing the amount of data exchanged. Due to the huge number of connected IoT devices, security of such networks and devices is therefore a critical issue. Detection systems assume [...] Read more.

IoT networks are increasingly popular nowadays to monitor critical environments of different nature, significantly increasing the amount of data exchanged. Due to the huge number of connected IoT devices, security of such networks and devices is therefore a critical issue. Detection systems assume a crucial role in the cyber-security field: based on innovative algorithms such as machine learning, they are able to identify or predict cyber-attacks, hence to protect the underlying system. Nevertheless, specific datasets are required to train detection models. In this work we present MQTTset, a dataset focused on the MQTT protocol, widely adopted in IoT networks. We present the creation of the dataset, also validating it through the definition of a hypothetical detection system, by combining the legitimate dataset with cyber-attacks against the MQTT network. Obtained results demonstrate how MQTTset can be used to train machine learning models to implement detection systems able to protect IoT contexts. Full article

(This article belongs to the Special Issue Intelligent and Adaptive Security in Internet of Things)

► Show Figures

Figure 1

14 pages, 719 KiB

Open AccessEditor’s ChoiceArticle

A Privacy-Preserving Healthcare Framework Using Hyperledger Fabric

by Charalampos Stamatellis, Pavlos Papadopoulos, Nikolaos Pitropakis, Sokratis Katsikas and William J. Buchanan

Sensors 2020, 20(22), 6587; https://doi.org/10.3390/s20226587 - 18 Nov 2020

Cited by 87 | Viewed by 8888

Abstract

Electronic health record (EHR) management systems require the adoption of effective technologies when health information is being exchanged. Current management approaches often face risks that may expose medical record storage solutions to common security attack vectors. However, healthcare-oriented blockchain solutions can provide a [...] Read more.

Electronic health record (EHR) management systems require the adoption of effective technologies when health information is being exchanged. Current management approaches often face risks that may expose medical record storage solutions to common security attack vectors. However, healthcare-oriented blockchain solutions can provide a decentralized, anonymous and secure EHR handling approach. This paper presents PREHEALTH, a privacy-preserving EHR management solution that uses distributed ledger technology and an Identity Mixer (Idemix). The paper describes a proof-of-concept implementation that uses the Hyperledger Fabric’s permissioned blockchain framework. The proposed solution is able to store patient records effectively whilst providing anonymity and unlinkability. Experimental performance evaluation results demonstrate the scheme’s efficiency and feasibility for real-world scale deployment. Full article

(This article belongs to the Collection Security, Trust and Privacy in New Computing Environments)

► Show Figures

Figure 1

16 pages, 1549 KiB

Open AccessEditor’s ChoiceArticle

Dense-RefineDet for Traffic Sign Detection and Classification

by Chang Sun, Yibo Ai, Sheng Wang and Weidong Zhang

Sensors 2020, 20(22), 6570; https://doi.org/10.3390/s20226570 - 17 Nov 2020

Cited by 19 | Viewed by 3321

Abstract

Detecting and classifying real-life small traffic signs from large input images is difficult due to their occupying fewer pixels relative to larger targets. To address this challenge, we proposed a deep-learning-based model (Dense-RefineDet) that applies a single-shot, object-detection framework (RefineDet) to maintain a [...] Read more.

Detecting and classifying real-life small traffic signs from large input images is difficult due to their occupying fewer pixels relative to larger targets. To address this challenge, we proposed a deep-learning-based model (Dense-RefineDet) that applies a single-shot, object-detection framework (RefineDet) to maintain a suitable accuracy–speed trade-off. We constructed a dense connection-related transfer-connection block to combine high-level feature layers with low-level feature layers to optimize the use of the higher layers to obtain additional contextual information. Additionally, we presented an anchor-design method to provide suitable anchors for detecting small traffic signs. Experiments using the Tsinghua-Tencent 100K dataset demonstrated that Dense-RefineDet achieved competitive accuracy at high-speed detection (0.13 s/frame) of small-, medium-, and large-scale traffic signs (recall: 84.3%, 95.2%, and 92.6%; precision: 83.9%, 95.6%, and 94.0%). Moreover, experiments using the Caltech pedestrian dataset indicated that the miss rate of Dense-RefineDet was 54.03% (pedestrian height > 20 pixels), which outperformed other state-of-the-art methods. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

13 pages, 4975 KiB

Open AccessEditor’s ChoiceArticle

Hollow-Core Negative Curvature Fiber with High Birefringence for Low Refractive Index Sensing Based on Surface Plasmon Resonance Effect

by Shi Qiu, Jinhui Yuan, Xian Zhou, Feng Li, Qiwei Wang, Yuwei Qu, Binbin Yan, Qiang Wu, Kuiru Wang, Xinzhu Sang, Keping Long and Chongxiu Yu

Sensors 2020, 20(22), 6539; https://doi.org/10.3390/s20226539 - 16 Nov 2020

Cited by 30 | Viewed by 3109

Abstract

In this paper, a hollow-core negative curvature fiber (HC-NCF) with high birefringence is proposed for low refractive index (RI) sensing based on surface plasmon resonance effect. In the design, the cladding region of the HC-NCF is composed of only one ring of eight [...] Read more.

In this paper, a hollow-core negative curvature fiber (HC-NCF) with high birefringence is proposed for low refractive index (RI) sensing based on surface plasmon resonance effect. In the design, the cladding region of the HC-NCF is composed of only one ring of eight silica tubes, and two of them are selectively filled with the gold wires. The influences of the gold wires-filled HC-NCF structure parameters on the propagation characteristic are investigated by the finite element method. Moreover, the sensing performances in the low RI range of 1.20–1.34 are evaluated by the traditional confinement loss method and novel birefringence analysis method, respectively. The simulation results show that for the confinement loss method, the obtained maximum sensitivity, resolution, and figure of merit of the gold wires-filled HC-NCF-based sensor are −5700 nm/RIU, 2.63 × 10⁻⁵ RIU, and 317 RIU⁻¹, respectively. For the birefringence analysis method, the obtained maximum sensitivity, resolution, and birefringence of the gold wires-filled HC-NCF-based sensor are −6100 nm/RIU, 2.56 × 10⁻⁵ RIU, and 1.72 × 10⁻³, respectively. It is believed that the proposed gold wires-filled HC-NCF-based low RI sensor has important applications in the fields of biochemistry and medicine. Full article

(This article belongs to the Special Issue Advanced Fiber Photonic Devices and Sensors)

► Show Figures

Figure 1

16 pages, 4446 KiB

Open AccessEditor’s ChoiceArticle

Optimal Frontier-Based Autonomous Exploration in Unconstructed Environment Using RGB-D Sensor

by Liang Lu, Carlos Redondo and Pascual Campoy

Sensors 2020, 20(22), 6507; https://doi.org/10.3390/s20226507 - 14 Nov 2020

Cited by 27 | Viewed by 4333

Abstract

Aerial robots are widely used in search and rescue applications because of their small size and high maneuvering. However, designing an autonomous exploration algorithm is still a challenging and open task, because of the limited payload and computing resources on board UAVs. This [...] Read more.

Aerial robots are widely used in search and rescue applications because of their small size and high maneuvering. However, designing an autonomous exploration algorithm is still a challenging and open task, because of the limited payload and computing resources on board UAVs. This paper presents an autonomous exploration algorithm for the aerial robots that shows several improvements for being used in the search and rescue tasks. First of all, an RGB-D sensor is used to receive information from the environment and the OctoMap divides the environment into obstacles, free and unknown spaces. Then, a clustering algorithm is used to filter the frontiers extracted from the OctoMap, and an information gain based cost function is applied to choose the optimal frontier. At last, the feasible path is given by A* path planner and a safe corridor generation algorithm. The proposed algorithm has been tested and compared with baseline algorithms in three different environments with the map resolutions of

0.2

m, and

0.3

m. The experimental results show that the proposed algorithm has a shorter exploration path and can save more exploration time when compared with the state of the art. The algorithm has also been validated in the real flight experiments. Full article

(This article belongs to the Special Issue Sensors for Unmanned Aircraft Systems and Related Technologies)

► Show Figures

Graphical abstract

21 pages, 2933 KiB

Open AccessEditor’s ChoiceArticle

Enhanced LoRaWAN Adaptive Data Rate for Mobile Internet of Things Devices

by Arshad Farhad, Dae-Ho Kim, Santosh Subedi and Jae-Young Pyun

Sensors 2020, 20(22), 6466; https://doi.org/10.3390/s20226466 - 12 Nov 2020

Cited by 38 | Viewed by 5006

Abstract

A long-range wide area network (LoRaWAN) is one of the leading communication technologies for Internet of Things (IoT) applications. In order to fulfill the IoT-enabled application requirements, LoRaWAN employs an adaptive data rate (ADR) mechanism at both the end device (ED) and the [...] Read more.

A long-range wide area network (LoRaWAN) is one of the leading communication technologies for Internet of Things (IoT) applications. In order to fulfill the IoT-enabled application requirements, LoRaWAN employs an adaptive data rate (ADR) mechanism at both the end device (ED) and the network server (NS). NS-managed ADR aims to offer a reliable and battery-efficient resource to EDs by managing the spreading factor (SF) and transmit power (TP). However, such management is severely affected by the lack of agility in adapting to the variable channel conditions. Thus, several hours or even days may be required to converge at a level of stable and energy-efficient communication. Therefore, we propose two NS-managed ADRs, a Gaussian filter-based ADR (G-ADR) and an exponential moving average-based ADR (EMA-ADR). Both of the proposed schemes operate as a low-pass filter to resist rapid changes in the signal-to-noise ratio of received packets at the NS. The proposed methods aim to allocate the best SF and TP to both static and mobile EDs by seeking to reduce the convergence period in the confirmed mode of LoRaWAN. Based on the simulation results, we show that the G-ADR and EMA-ADR schemes reduce the convergence period in a static scenario by 16% and 68%, and in a mobility scenario by 17% and 81%, respectively, as compared to typical ADR. Moreover, we show that the proposed schemes are successful in reducing the energy consumption and enhancing the packet success ratio. Full article

(This article belongs to the Special Issue Massive and Reliable Sensor Communications with LPWANs Technologies)

► Show Figures

Graphical abstract

38 pages, 15895 KiB

Open AccessEditor’s ChoiceArticle

IRT and GPR Techniques for Moisture Detection and Characterisation in Buildings

by Iván Garrido, Mercedes Solla, Susana Lagüela and Norberto Fernández

Sensors 2020, 20(22), 6421; https://doi.org/10.3390/s20226421 - 10 Nov 2020

Cited by 32 | Viewed by 4530

Abstract

The integrity, comfort, and energy demand of a building can be negatively affected by the presence of moisture in its walls. Therefore, it is essential to identify and characterise this building pathology with the most appropriate technologies to perform the required prevention and [...] Read more.

The integrity, comfort, and energy demand of a building can be negatively affected by the presence of moisture in its walls. Therefore, it is essential to identify and characterise this building pathology with the most appropriate technologies to perform the required prevention and maintenance tasks. This paper proposes the joint application of InfraRed Thermography (IRT) and Ground-Penetrating Radar (GPR) for the detection and classification of moisture in interior walls of a building according to its severity level. The IRT method is based on the study of the temperature distribution of the thermal images acquired without an application of artificial thermal excitation for the detection of superficial moisture (less than 15 mm deep in plaster with passive IRT). Additionally, in order to characterise the level of moisture severity, the Evaporative Thermal Index (ETI) was obtained for each of the moisture areas. As for GPR, with measuring capacity from 10 mm up to 30 cm depth with a 2300 MHz antenna, several algorithms were developed based on the amplitude and spectrum of the received signals for the detection and classification of moisture through the inner layers of the wall. In this work, the complementarity of both methods has proven to be an effective approach to investigate both superficial and internal moisture and their severity. Specifically, IRT allowed estimating superficial water movement, whereas GPR allowed detecting points of internal water accumulation. Thus, through the combination of both techniques, it was possible to provide an interpretation of the water displacement from the exterior surface to the interior surface of the wall, and to give a relative depth of water inside the wall. Therefore, it was concluded that more information and greater reliability can be gained by using complementary IRT-GPR, showing the benefits of combining both techniques in the building sector. Full article

(This article belongs to the Special Issue Infrared Thermography and Additional Non-Destructive Testing for Building, Structure and Material Inspections)

► Show Figures

Figure 1

46 pages, 2708 KiB

Open AccessFeature PaperEditor’s ChoiceReview

The Importance of Respiratory Rate Monitoring: From Healthcare to Sport and Exercise

by Andrea Nicolò, Carlo Massaroni, Emiliano Schena and Massimo Sacchetti

Sensors 2020, 20(21), 6396; https://doi.org/10.3390/s20216396 - 9 Nov 2020

Cited by 183 | Viewed by 27365

Abstract

Respiratory rate is a fundamental vital sign that is sensitive to different pathological conditions (e.g., adverse cardiac events, pneumonia, and clinical deterioration) and stressors, including emotional stress, cognitive load, heat, cold, physical effort, and exercise-induced fatigue. The sensitivity of respiratory rate to these [...] Read more.

Respiratory rate is a fundamental vital sign that is sensitive to different pathological conditions (e.g., adverse cardiac events, pneumonia, and clinical deterioration) and stressors, including emotional stress, cognitive load, heat, cold, physical effort, and exercise-induced fatigue. The sensitivity of respiratory rate to these conditions is superior compared to that of most of the other vital signs, and the abundance of suitable technological solutions measuring respiratory rate has important implications for healthcare, occupational settings, and sport. However, respiratory rate is still too often not routinely monitored in these fields of use. This review presents a multidisciplinary approach to respiratory monitoring, with the aim to improve the development and efficacy of respiratory monitoring services. We have identified thirteen monitoring goals where the use of the respiratory rate is invaluable, and for each of them we have described suitable sensors and techniques to monitor respiratory rate in specific measurement scenarios. We have also provided a physiological rationale corroborating the importance of respiratory rate monitoring and an original multidisciplinary framework for the development of respiratory monitoring services. This review is expected to advance the field of respiratory monitoring and favor synergies between different disciplines to accomplish this goal. Full article

(This article belongs to the Collection Respiratory Monitoring for Healthcare, Sport and Physical Activity: Sensors, Techniques and Applications)

► Show Figures

Graphical abstract

27 pages, 1710 KiB

Open AccessEditor’s ChoiceArticle

Smart Helmet 5.0 for Industrial Internet of Things Using Artificial Intelligence

by Israel Campero-Jurado, Sergio Márquez-Sánchez, Juan Quintanar-Gómez, Sara Rodríguez and Juan M. Corchado

Sensors 2020, 20(21), 6241; https://doi.org/10.3390/s20216241 - 1 Nov 2020

Cited by 61 | Viewed by 17768

Abstract

Information and communication technologies (ICTs) have contributed to advances in Occupational Health and Safety, improving the security of workers. The use of Personal Protective Equipment (PPE) based on ICTs reduces the risk of accidents in the workplace, thanks to the capacity of the [...] Read more.

Information and communication technologies (ICTs) have contributed to advances in Occupational Health and Safety, improving the security of workers. The use of Personal Protective Equipment (PPE) based on ICTs reduces the risk of accidents in the workplace, thanks to the capacity of the equipment to make decisions on the basis of environmental factors. Paradigms such as the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI) make it possible to generate PPE models feasibly and create devices with more advanced characteristics such as monitoring, sensing the environment and risk detection between others. The working environment is monitored continuously by these models and they notify the employees and their supervisors of any anomalies and threats. This paper presents a smart helmet prototype that monitors the conditions in the workers’ environment and performs a near real-time evaluation of risks. The data collected by sensors is sent to an AI-driven platform for analysis. The training dataset consisted of 11,755 samples and 12 different scenarios. As part of this research, a comparative study of the state-of-the-art models of supervised learning is carried out. Moreover, the use of a Deep Convolutional Neural Network (ConvNet/CNN) is proposed for the detection of possible occupational risks. The data are processed to make them suitable for the CNN and the results are compared against a Static Neural Network (NN), Naive Bayes Classifier (NB) and Support Vector Machine (SVM), where the CNN had an accuracy of 92.05% in cross-validation. Full article

(This article belongs to the Special Issue Developing “Smartness” in Emerging Environments and Applications with Focus on the Internet of Things (IoT))

► Show Figures

Figure 1

17 pages, 625 KiB

Open AccessEditor’s ChoiceArticle

Optimal Placement of Social Digital Twins in Edge IoT Networks

by Olga Chukhno, Nadezhda Chukhno, Giuseppe Araniti, Claudia Campolo, Antonio Iera and Antonella Molinaro

Sensors 2020, 20(21), 6181; https://doi.org/10.3390/s20216181 - 30 Oct 2020

Cited by 26 | Viewed by 4322

Abstract

In next-generation Internet of Things (IoT) deployments, every object such as a wearable device, a smartphone, a vehicle, and even a sensor or an actuator will be provided with a digital counterpart (twin) with the aim of augmenting the physical object’s capabilities and [...] Read more.

In next-generation Internet of Things (IoT) deployments, every object such as a wearable device, a smartphone, a vehicle, and even a sensor or an actuator will be provided with a digital counterpart (twin) with the aim of augmenting the physical object’s capabilities and acting on its behalf when interacting with third parties. Moreover, such objects can be able to interact and autonomously establish social relationships according to the Social Internet of Things (SIoT) paradigm. In such a context, the goal of this work is to provide an optimal solution for the social-aware placement of IoT digital twins (DTs) at the network edge, with the twofold aim of reducing the latency (i) between physical devices and corresponding DTs for efficient data exchange, and (ii) among DTs of friend devices to speed-up the service discovery and chaining procedures across the SIoT network. To this aim, we formulate the problem as a mixed-integer linear programming model taking into account limited computing resources in the edge cloud and social relationships among IoT devices. Full article

(This article belongs to the Special Issue Cloud and Edge Computing for the Next Generation of Internet of Things Applications)

► Show Figures

Figure 1

28 pages, 6253 KiB

Open AccessEditor’s ChoiceReview

A Critical Review of Electrochemical Glucose Sensing: Evolution of Biosensor Platforms Based on Advanced Nanosystems

by Vuslat B. Juska and Martyn E. Pemble

Sensors 2020, 20(21), 6013; https://doi.org/10.3390/s20216013 - 23 Oct 2020

Cited by 114 | Viewed by 13112

Abstract

The research field of glucose biosensing has shown remarkable growth and development since the first reported enzyme electrode in 1962. Extensive research on various immobilization methods and the improvement of electron transfer efficiency between the enzyme and the electrode have led to the [...] Read more.

The research field of glucose biosensing has shown remarkable growth and development since the first reported enzyme electrode in 1962. Extensive research on various immobilization methods and the improvement of electron transfer efficiency between the enzyme and the electrode have led to the development of various sensing platforms that have been constantly evolving with the invention of advanced nanostructures and their nano-composites. Examples of such nanomaterials or composites include gold nanoparticles, carbon nanotubes, carbon/graphene quantum dots and chitosan hydrogel composites, all of which have been exploited due to their contributions as components of a biosensor either for improving the immobilization process or for their electrocatalytic activity towards glucose. This review aims to summarize the evolution of the biosensing aspect of these glucose sensors in terms of the various generations and recent trends based on the use of applied nanostructures for glucose detection in the presence and absence of the enzyme. We describe the history of these biosensors based on commercialized systems, improvements in the understanding of the surface science for enhanced electron transfer, the various sensing platforms developed in the presence of the nanomaterials and their performances. Full article

(This article belongs to the Special Issue Nanomaterials as Key for Next Generation Sensors)

► Show Figures

Figure 1

22 pages, 4212 KiB

Open AccessEditor’s ChoiceArticle

Path Planning for Multi-Arm Manipulators Using Deep Reinforcement Learning: Soft Actor–Critic with Hindsight Experience Replay

by Evan Prianto, MyeongSeop Kim, Jae-Han Park, Ji-Hun Bae and Jung-Su Kim

Sensors 2020, 20(20), 5911; https://doi.org/10.3390/s20205911 - 19 Oct 2020

Cited by 61 | Viewed by 7022

Abstract

Since path planning for multi-arm manipulators is a complicated high-dimensional problem, effective and fast path generation is not easy for the arbitrarily given start and goal locations of the end effector. Especially, when it comes to deep reinforcement learning-based path planning, high-dimensionality makes [...] Read more.

Since path planning for multi-arm manipulators is a complicated high-dimensional problem, effective and fast path generation is not easy for the arbitrarily given start and goal locations of the end effector. Especially, when it comes to deep reinforcement learning-based path planning, high-dimensionality makes it difficult for existing reinforcement learning-based methods to have efficient exploration which is crucial for successful training. The recently proposed soft actor–critic (SAC) is well known to have good exploration ability due to the use of the entropy term in the objective function. Motivated by this, in this paper, a SAC-based path planning algorithm is proposed. The hindsight experience replay (HER) is also employed for sample efficiency and configuration space augmentation is used in order to deal with complicated configuration space of the multi-arms. To show the effectiveness of the proposed algorithm, both simulation and experiment results are given. By comparing with existing results, it is demonstrated that the proposed method outperforms the existing results. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

35 pages, 718 KiB

Open AccessEditor’s ChoiceArticle

Security Requirements for the Internet of Things: A Systematic Approach

by Shantanu Pal, Michael Hitchens, Tahiry Rabehaja and Subhas Mukhopadhyay

Sensors 2020, 20(20), 5897; https://doi.org/10.3390/s20205897 - 19 Oct 2020

Cited by 77 | Viewed by 8670

Abstract

There has been a tremendous growth in the number of smart devices and their applications (e.g., smart sensors, wearable devices, smart phones, smart cars, etc.) in use in our everyday lives. This is accompanied by a new form of interconnection between the physical [...] Read more.

There has been a tremendous growth in the number of smart devices and their applications (e.g., smart sensors, wearable devices, smart phones, smart cars, etc.) in use in our everyday lives. This is accompanied by a new form of interconnection between the physical and digital worlds, commonly known as the Internet of Things (IoT). This is a paradigm shift, where anything and everything can be interconnected via a communication medium. In such systems, security is a prime concern and protecting the resources (e.g., applications and services) from unauthorized access needs appropriately designed security and privacy solutions. Building secure systems for the IoT can only be achieved through a thorough understanding of the particular needs of such systems. The state of the art is lacking a systematic analysis of the security requirements for the IoT. Motivated by this, in this paper, we present a systematic approach to understand the security requirements for the IoT, which will help designing secure IoT systems for the future. In developing these requirements, we provide different scenarios and outline potential threats and attacks within the IoT. Based on the characteristics of the IoT, we group the possible threats and attacks into five areas, namely communications, device/services, users, mobility and integration of resources. We then examine the existing security requirements for IoT presented in the literature and detail our approach for security requirements for the IoT. We argue that by adhering to the proposed requirements, an IoT system can be designed securely by achieving much of the promised benefits of scalability, usability, connectivity, and flexibility in a practical and comprehensive manner. Full article

(This article belongs to the Special Issue Signal Processing Techniques for Smart Sensor Communications)

► Show Figures

Figure 1

17 pages, 8619 KiB

Open AccessEditor’s ChoiceArticle

Multi-Constellation Software-Defined Receiver for Doppler Positioning with LEO Satellites

by Farzan Farhangian and René Landry, Jr.

Sensors 2020, 20(20), 5866; https://doi.org/10.3390/s20205866 - 16 Oct 2020

Cited by 54 | Viewed by 5863

Abstract

A Multi-Constellation Software-Defined Receiver (MC-SDR) is designed and implemented to extract the Doppler measurements of Low Earth Orbit (LEO) satellite’s downlink signals, such as Orbcomm, Iridium-Next, Globalstar, Starlink, OneWeb, SpaceX, etc. The Doppler positioning methods, as one of the main localization algorithms, need [...] Read more.

A Multi-Constellation Software-Defined Receiver (MC-SDR) is designed and implemented to extract the Doppler measurements of Low Earth Orbit (LEO) satellite’s downlink signals, such as Orbcomm, Iridium-Next, Globalstar, Starlink, OneWeb, SpaceX, etc. The Doppler positioning methods, as one of the main localization algorithms, need a highly accurate receiver design to track the Doppler as a measurement for Extended Kalman Filter (EKF)-based positioning. In this paper, the designed receiver has been used to acquire and track the Doppler shifts of two different kinds of LEO constellations. The extracted Doppler shifts of one Iridium-Next satellite as a burst-based simplex downlink signal and two Orbcomm satellites as continuous signals are considered. Also, with having the Two-Line Element (TLE) for each satellite, the position, and orbital elements of each satellite are known. Finally, the accuracy of the designed receiver is validated using an EKF-based stationary positioning algorithm with an adaptive measurement matrix. Satellite detection and Doppler tracking results are analyzed for each satellite. The positioning results for a stationary receiver showed an accuracy of about 132 m, which means 72% accuracy advancements compared to single constellation positioning. Full article

(This article belongs to the Special Issue Mobile Multi-Sensors in Positioning, Navigation, and Mapping Applications)

► Show Figures

Figure 1

23 pages, 5093 KiB

Open AccessEditor’s ChoiceArticle

Parkinson’s Disease Tremor Detection in the Wild Using Wearable Accelerometers

by Rubén San-Segundo, Ada Zhang, Alexander Cebulla, Stanislav Panev, Griffin Tabor, Katelyn Stebbins, Robyn E. Massa, Andrew Whitford, Fernando de la Torre and Jessica Hodgins

Sensors 2020, 20(20), 5817; https://doi.org/10.3390/s20205817 - 14 Oct 2020

Cited by 41 | Viewed by 6437

Abstract

Continuous in-home monitoring of Parkinson’s Disease (PD) symptoms might allow improvements in assessment of disease progression and treatment effects. As a first step towards this goal, we evaluate the feasibility of a wrist-worn wearable accelerometer system to detect PD tremor in the wild [...] Read more.

Continuous in-home monitoring of Parkinson’s Disease (PD) symptoms might allow improvements in assessment of disease progression and treatment effects. As a first step towards this goal, we evaluate the feasibility of a wrist-worn wearable accelerometer system to detect PD tremor in the wild (uncontrolled scenarios). We evaluate the performance of several feature sets and classification algorithms for robust PD tremor detection in laboratory and wild settings. We report results for both laboratory data with accurate labels and wild data with weak labels. The best performance was obtained using a combination of a pre-processing module to extract information from the tremor spectrum (based on non-negative factorization) and a deep neural network for learning relevant features and detecting tremor segments. We show how the proposed method is able to predict patient self-report measures, and we propose a new metric for monitoring PD tremor (i.e., percentage of tremor over long periods of time), which may be easier to estimate the start and end time points of each tremor event while still providing clinically useful information. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

20 pages, 9332 KiB

Open AccessEditor’s ChoiceArticle

A Framework for an Indoor Safety Management System Based on Digital Twin

by Zhansheng Liu, Anshan Zhang and Wensi Wang

Sensors 2020, 20(20), 5771; https://doi.org/10.3390/s20205771 - 12 Oct 2020

Cited by 69 | Viewed by 7090

Abstract

With the development of the next generation of information technology, an increasing amount of attention is being paid to smart residential spaces, including smart cities, smart buildings, and smart homes. Building indoor safety intelligence is an important research topic. However, current indoor safety [...] Read more.

With the development of the next generation of information technology, an increasing amount of attention is being paid to smart residential spaces, including smart cities, smart buildings, and smart homes. Building indoor safety intelligence is an important research topic. However, current indoor safety management methods cannot comprehensively analyse safety data, owing to a poor combination of safety management and building information. Additionally, the judgement of danger depends significantly on the experience of the safety management staff. In this study, digital twins (DTs) are introduced to building indoor safety management. A framework for an indoor safety management system based on DT is proposed which exploits the Internet of Things (IoT), building information modelling (BIM), the Internet, and support vector machines (SVMs) to improve the level of intelligence for building indoor safety management. A DT model (DTM) is developed using BIM integrated with operation information collected by IoT sensors. The trained SVM model is used to automatically obtain the types and levels of danger by processing the data in the DTM. The Internet is a medium for interactions between people and systems. A building in the bobsleigh and sled stadium for the Beijing Winter Olympics is considered as an example; the proposed system realises the functions of the scene display of the operation status, danger warning and positioning, danger classification and level assessment, and danger handling suggestions. Full article

(This article belongs to the Special Issue Machine Learning for IoT Applications and Digital Twins)

► Show Figures

Figure 1

21 pages, 9450 KiB

Open AccessEditor’s ChoiceReview

Microfluidics in Gas Sensing and Artificial Olfaction

by Guilherme Rebordão, Susana I. C. J. Palma and Ana C. A. Roque

Sensors 2020, 20(20), 5742; https://doi.org/10.3390/s20205742 - 9 Oct 2020

Cited by 21 | Viewed by 7117

Abstract

Rapid, real-time, and non-invasive identification of volatile organic compounds (VOCs) and gases is an increasingly relevant field, with applications in areas such as healthcare, agriculture, or industry. Ideal characteristics of VOC and gas sensing devices used for artificial olfaction include portability and affordability, [...] Read more.

Rapid, real-time, and non-invasive identification of volatile organic compounds (VOCs) and gases is an increasingly relevant field, with applications in areas such as healthcare, agriculture, or industry. Ideal characteristics of VOC and gas sensing devices used for artificial olfaction include portability and affordability, low power consumption, fast response, high selectivity, and sensitivity. Microfluidics meets all these requirements and allows for in situ operation and small sample amounts, providing many advantages compared to conventional methods using sophisticated apparatus such as gas chromatography and mass spectrometry. This review covers the work accomplished so far regarding microfluidic devices for gas sensing and artificial olfaction. Systems utilizing electrical and optical transduction, as well as several system designs engineered throughout the years are summarized, and future perspectives in the field are discussed. Full article

(This article belongs to the Special Issue Gas Sensing Materials)

► Show Figures

Graphical abstract

15 pages, 6912 KiB

Open AccessEditor’s ChoiceArticle

Real-Time Fruit Recognition and Grasping Estimation for Robotic Apple Harvesting

by Hanwen Kang, Hongyu Zhou, Xing Wang and Chao Chen

Sensors 2020, 20(19), 5670; https://doi.org/10.3390/s20195670 - 4 Oct 2020

Cited by 101 | Viewed by 7340

Abstract

Robotic harvesting shows a promising aspect in future development of agricultural industry. However, there are many challenges which are still presented in the development of a fully functional robotic harvesting system. Vision is one of the most important keys among these challenges. Traditional [...] Read more.

Robotic harvesting shows a promising aspect in future development of agricultural industry. However, there are many challenges which are still presented in the development of a fully functional robotic harvesting system. Vision is one of the most important keys among these challenges. Traditional vision methods always suffer from defects in accuracy, robustness, and efficiency in real implementation environments. In this work, a fully deep learning-based vision method for autonomous apple harvesting is developed and evaluated. The developed method includes a light-weight one-stage detection and segmentation network for fruit recognition and a PointNet to process the point clouds and estimate a proper approach pose for each fruit before grasping. Fruit recognition network takes raw inputs from RGB-D camera and performs fruit detection and instance segmentation on RGB images. The PointNet grasping network combines depth information and results from the fruit recognition as input and outputs the approach pose of each fruit for robotic arm execution. The developed vision method is evaluated on RGB-D image data which are collected from both laboratory and orchard environments. Robotic harvesting experiments in both indoor and outdoor conditions are also included to validate the performance of the developed harvesting system. Experimental results show that the developed vision method can perform highly efficient and accurate to guide robotic harvesting. Overall, the developed robotic harvesting system achieves 0.8 on harvesting success rate and cycle time is 6.5 s. Full article

(This article belongs to the Section Sensors and Robotics)

► Show Figures

Figure 1

19 pages, 462 KiB

Open AccessEditor’s ChoiceReview

A Review of the State of the Art in Non-Contact Sensing for COVID-19

by William Taylor, Qammer H. Abbasi, Kia Dashtipour, Shuja Ansari, Syed Aziz Shah, Arslan Khalid and Muhammad Ali Imran

Sensors 2020, 20(19), 5665; https://doi.org/10.3390/s20195665 - 3 Oct 2020

Cited by 72 | Viewed by 8946

Abstract

COVID-19, caused by SARS-CoV-2, has resulted in a global pandemic recently. With no approved vaccination or treatment, governments around the world have issued guidance to their citizens to remain at home in efforts to control the spread of the disease. The goal of [...] Read more.

COVID-19, caused by SARS-CoV-2, has resulted in a global pandemic recently. With no approved vaccination or treatment, governments around the world have issued guidance to their citizens to remain at home in efforts to control the spread of the disease. The goal of controlling the spread of the virus is to prevent strain on hospitals. In this paper, we focus on how non-invasive methods are being used to detect COVID-19 and assist healthcare workers in caring for COVID-19 patients. Early detection of COVID-19 can allow for early isolation to prevent further spread. This study outlines the advantages and disadvantages and a breakdown of the methods applied in the current state-of-the-art approaches. In addition, the paper highlights some future research directions, which need to be explored further to produce innovative technologies to control this pandemic. Full article

(This article belongs to the Special Issue Sensing and Data Analysis Techniques for Intelligent Healthcare)

► Show Figures

Figure 1

18 pages, 9497 KiB

Open AccessEditor’s ChoiceArticle

Dual Circularly Polarized Planar Four-Port MIMO Antenna with Wide Axial-Ratio Bandwidth

by Sachin Kumar, Gwan Hui Lee, Dong Hwi Kim, Hyun Chul Choi and Kang Wook Kim

Sensors 2020, 20(19), 5610; https://doi.org/10.3390/s20195610 - 30 Sep 2020

Cited by 39 | Viewed by 4168

Abstract

A broadband compact-sized planar four-port multiple-input–multiple-output (MIMO) antenna with polarization diversity is presented. The proposed dual circularly polarized (CP) MIMO antenna consists of four G-shaped monopole elements, two of which are left-hand CP and the other two are right-hand CP. A vertical line [...] Read more.

A broadband compact-sized planar four-port multiple-input–multiple-output (MIMO) antenna with polarization diversity is presented. The proposed dual circularly polarized (CP) MIMO antenna consists of four G-shaped monopole elements, two of which are left-hand CP and the other two are right-hand CP. A vertical line strip in the G-shaped radiating element acts in balancing the vertical and horizontal electric field components to obtain 90° phase difference between them for circular polarization. Also, an I-shaped strip is incorporated between the ground planes of the G-shaped antenna elements to obtain equal voltage level in the proposed MIMO configuration. The dual circular polarization mechanism of the proposed MIMO/diversity antenna is analysed from the vector current distributions. The impedance bandwidth (S₁₁ ≤ –10 dB) of the MIMO antenna is 105.9% (4–13 GHz) and the 3 dB axial ratio bandwidth (ARBW) is 67.7% (4.2–8.5 GHz), which is suitable for C-band applications. The overall size of the MIMO antenna is 70 × 68 × 1.6 mm³, and the minimum isolation between the resonating elements is 18 dB. The envelope correlation coefficient is less than 0.25, and the peak gain within the resonating band is 6.4 dBi. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

19 pages, 5146 KiB

Open AccessEditor’s ChoiceArticle

Measuring Three-Dimensional Temperature Distributions in Steel–Concrete Composite Slabs Subjected to Fire Using Distributed Fiber Optic Sensors

by Yi Bao, Matthew S. Hoehler, Christopher M. Smith, Matthew Bundy and Genda Chen

Sensors 2020, 20(19), 5518; https://doi.org/10.3390/s20195518 - 26 Sep 2020

Cited by 15 | Viewed by 3704

Abstract

Detailed information about temperature distribution can be important to understand structural behavior in fire. This study develops a method to image three-dimensional temperature distributions in steel–concrete composite slabs using distributed fiber optic sensors. The feasibility of the method is explored using six 1.2 [...] Read more.

Detailed information about temperature distribution can be important to understand structural behavior in fire. This study develops a method to image three-dimensional temperature distributions in steel–concrete composite slabs using distributed fiber optic sensors. The feasibility of the method is explored using six 1.2 m × 0.9 m steel–concrete composite slabs instrumented with distributed sensors and thermocouples subjected to fire for over 3 h. Dense point clouds of temperature in the slabs were measured using the distributed sensors. The results show that the distributed sensors operated at material temperatures up to 960 °C with acceptable accuracy for many structural fire applications. The measured non-uniform temperature distributions indicate a spatially distributed thermal response in steel–concrete composite slabs, which can only be adequately captured using approaches that provide a high density of through-depth data points. Full article

(This article belongs to the Special Issue Innovative Sensors for Civil Infrastructure Condition Assessment)

► Show Figures

Graphical abstract

15 pages, 3111 KiB

Open AccessEditor’s ChoiceArticle

Millimeter-Wave Array Radar-Based Human Gait Recognition Using Multi-Channel Three-Dimensional Convolutional Neural Network

by Xinrui Jiang, Ye Zhang, Qi Yang, Bin Deng and Hongqiang Wang

Sensors 2020, 20(19), 5466; https://doi.org/10.3390/s20195466 - 23 Sep 2020

Cited by 33 | Viewed by 4256

Abstract

At present, there are two obvious problems in radar-based gait recognition. First, the traditional radar frequency band is difficult to meet the requirements of fine identification with due to its low carrier frequency and limited micro-Doppler resolution. Another significant problem is that radar [...] Read more.

At present, there are two obvious problems in radar-based gait recognition. First, the traditional radar frequency band is difficult to meet the requirements of fine identification with due to its low carrier frequency and limited micro-Doppler resolution. Another significant problem is that radar signal processing is relatively complex, and the existing signal processing algorithms are poor in real-time usability, robustness and universality. This paper focuses on the two basic problems of human gait detection with radar and proposes a human gait classification and recognition method based on millimeter-wave array radar. Based on deep-learning technology, a multi-channel three-dimensional convolution neural network is proposed on the basis of improving the residual network, which completes the classification and recognition of human gait through the hierarchical extraction and fusion of multi-dimensional features. Taking the three-dimensional coordinates, motion speed and intensity of strong scattering points in the process of target motion as network inputs, multi-channel convolution is used to extract motion features, and the classification and recognition of typical daily actions are completed. The experimental results show that we have more than 92.5% recognition accuracy for common gait categories such as jogging and normal walking. Full article

(This article belongs to the Section Electronic Sensors)

► Show Figures

Figure 1

26 pages, 22557 KiB

Open AccessEditor’s ChoiceArticle

The Use of Low-Cost Unmanned Aerial Vehicles in the Process of Building Models for Cultural Tourism, 3D Web and Augmented/Mixed Reality Applications

by Tomasz Templin and Dariusz Popielarczyk

Sensors 2020, 20(19), 5457; https://doi.org/10.3390/s20195457 - 23 Sep 2020

Cited by 36 | Viewed by 5534

Abstract

Unmanned Aerial Systems (UAS) are widely used in low-cost photogrammetry. Even small Unmanned Aerial Vehicles (UAV) can deliver valuable data for the inventory of inaccessible and dangerous areas or objects. The acquisition of data for 3D object modeling is a complicated, time-consuming, and [...] Read more.

Unmanned Aerial Systems (UAS) are widely used in low-cost photogrammetry. Even small Unmanned Aerial Vehicles (UAV) can deliver valuable data for the inventory of inaccessible and dangerous areas or objects. The acquisition of data for 3D object modeling is a complicated, time-consuming, and cost-intensive process. It requires the use of expensive equipment and often manual work as well as professional software. These are major barriers limiting the development of modern tourist platforms that promote local attractions. Information technologies offer new opportunities for the development of the services market, including the development of smart tourism services, as an integral part of the smart city concept. 3D models are an important element of this process as they form the basis for the use of new visualization technologies, such as Virtual, Mixed, and Augmented Reality (VR/MR/AR). 3D modeling provides a new opportunity to use AR/MR technology to present information about objects, virtual tours of the historic buildings, and their promotion. It also creates an opportunity to preserve the architectural heritage and preventive maintenance of buildings. Despite the increasing use of new measuring platforms and computer modeling techniques, the implementation of 3D building models in smart tourism services is still limited, focusing more on the results of scientific projects rather than on the implementation of the new ones. The paper presents an universal methodology for the inventory of historical buildings using low-cost UAVs. It describes the most important aspects related to the process of planning UAV measurement missions and photogrammetric data acquisition. The construction of 3D models and the possibilities of their further use to build smart tourism services based on Web/AR/MR/VR technology was also presented. Full article

(This article belongs to the Special Issue Sensors for Imaging Cultural Heritage: Technologies, Methods and Data Processing)

► Show Figures

Figure 1

20 pages, 1096 KiB

Open AccessEditor’s ChoiceArticle

ARIES: A Novel Multivariate Intrusion Detection System for Smart Grid

by Panagiotis Radoglou Grammatikis, Panagiotis Sarigiannidis, Georgios Efstathopoulos and Emmanouil Panaousis

Sensors 2020, 20(18), 5305; https://doi.org/10.3390/s20185305 - 16 Sep 2020

Cited by 36 | Viewed by 5059

Abstract

The advent of the Smart Grid (SG) raises severe cybersecurity risks that can lead to devastating consequences. In this paper, we present a novel anomaly-based Intrusion Detection System (IDS), called ARIES (smArt gRid Intrusion dEtection System), which is capable of protecting efficiently SG [...] Read more.

The advent of the Smart Grid (SG) raises severe cybersecurity risks that can lead to devastating consequences. In this paper, we present a novel anomaly-based Intrusion Detection System (IDS), called ARIES (smArt gRid Intrusion dEtection System), which is capable of protecting efficiently SG communications. ARIES combines three detection layers that are devoted to recognising possible cyberattacks and anomalies against (a) network flows, (b) Modbus/Transmission Control Protocol (TCP) packets and (c) operational data. Each detection layer relies on a Machine Learning (ML) model trained using data originating from a power plant. In particular, the first layer (network flow-based detection) performs a supervised multiclass classification, recognising Denial of Service (DoS), brute force attacks, port scanning attacks and bots. The second layer (packet-based detection) detects possible anomalies related to the Modbus packets, while the third layer (operational data based detection) monitors and identifies anomalies upon operational data (i.e., time series electricity measurements). By emphasising on the third layer, the ARIES Generative Adversarial Network (ARIES GAN) with novel error minimisation functions was developed, considering mainly the reconstruction difference. Moreover, a novel reformed conditional input was suggested, consisting of random noise and the signal features at any given time instance. Based on the evaluation analysis, the proposed GAN network overcomes the efficacy of conventional ML methods in terms of Accuracy and the F1 score. Full article

(This article belongs to the Special Issue Cybersecurity and Privacy-Preserving in Modern Smart Grid)

► Show Figures

Figure 1

16 pages, 3125 KiB

Open AccessEditor’s ChoiceArticle

Remote Insects Trap Monitoring System Using Deep Learning Framework and IoT

by Balakrishnan Ramalingam, Rajesh Elara Mohan, Sathian Pookkuttath, Braulio Félix Gómez, Charan Satya Chandra Sairam Borusu, Tey Wee Teng and Yokhesh Krishnasamy Tamilselvam

Sensors 2020, 20(18), 5280; https://doi.org/10.3390/s20185280 - 15 Sep 2020

Cited by 53 | Viewed by 9636

Abstract

Insect detection and control at an early stage are essential to the built environment (human-made physical spaces such as homes, hotels, camps, hospitals, parks, pavement, food industries, etc.) and agriculture fields. Currently, such insect control measures are manual, tedious, unsafe, and time-consuming labor [...] Read more.

Insect detection and control at an early stage are essential to the built environment (human-made physical spaces such as homes, hotels, camps, hospitals, parks, pavement, food industries, etc.) and agriculture fields. Currently, such insect control measures are manual, tedious, unsafe, and time-consuming labor dependent tasks. With the recent advancements in Artificial Intelligence (AI) and the Internet of things (IoT), several maintenance tasks can be automated, which significantly improves productivity and safety. This work proposes a real-time remote insect trap monitoring system and insect detection method using IoT and Deep Learning (DL) frameworks. The remote trap monitoring system framework is constructed using IoT and the Faster RCNN (Region-based Convolutional Neural Networks) Residual neural Networks 50 (ResNet50) unified object detection framework. The Faster RCNN ResNet 50 object detection framework was trained with built environment insects and farm field insect images and deployed in IoT. The proposed system was tested in real-time using four-layer IoT with built environment insects image captured through sticky trap sheets. Further, farm field insects were tested through a separate insect image database. The experimental results proved that the proposed system could automatically identify the built environment insects and farm field insects with an average of 94% accuracy. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

23 pages, 4849 KiB

Open AccessEditor’s ChoiceArticle

Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19

by Bosheng Qin and Dongxiao Li

Sensors 2020, 20(18), 5236; https://doi.org/10.3390/s20185236 - 14 Sep 2020

Cited by 181 | Viewed by 12062

Abstract

The rapid worldwide spread of Coronavirus Disease 2019 (COVID-19) has resulted in a global pandemic. Correct facemask wearing is valuable for infectious disease control, but the effectiveness of facemasks has been diminished, mostly due to improper wearing. However, there have not been any [...] Read more.

The rapid worldwide spread of Coronavirus Disease 2019 (COVID-19) has resulted in a global pandemic. Correct facemask wearing is valuable for infectious disease control, but the effectiveness of facemasks has been diminished, mostly due to improper wearing. However, there have not been any published reports on the automatic identification of facemask-wearing conditions. In this study, we develop a new facemask-wearing condition identification method by combining image super-resolution and classification networks (SRCNet), which quantifies a three-category classification problem based on unconstrained 2D facial images. The proposed algorithm contains four main steps: Image pre-processing, facial detection and cropping, image super-resolution, and facemask-wearing condition identification. Our method was trained and evaluated on the public dataset Medical Masks Dataset containing 3835 images with 671 images of no facemask-wearing, 134 images of incorrect facemask-wearing, and 3030 images of correct facemask-wearing. Finally, the proposed SRCNet achieved 98.70% accuracy and outperformed traditional end-to-end image classification methods using deep learning without image super-resolution by over 1.5% in kappa. Our findings indicate that the proposed SRCNet can achieve high-accuracy identification of facemask-wearing conditions, thus having potential applications in epidemic prevention involving COVID-19. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Graphical abstract

17 pages, 10180 KiB

Open AccessEditor’s ChoiceArticle

Helping the Blind to Get through COVID-19: Social Distancing Assistant Using Real-Time Semantic Segmentation on RGB-D Video

by Manuel Martinez, Kailun Yang, Angela Constantinescu and Rainer Stiefelhagen

Sensors 2020, 20(18), 5202; https://doi.org/10.3390/s20185202 - 12 Sep 2020

Cited by 38 | Viewed by 6854

Abstract

The current COVID-19 pandemic is having a major impact on our daily lives. Social distancing is one of the measures that has been implemented with the aim of slowing the spread of the disease, but it is difficult for blind people to comply [...] Read more.

The current COVID-19 pandemic is having a major impact on our daily lives. Social distancing is one of the measures that has been implemented with the aim of slowing the spread of the disease, but it is difficult for blind people to comply with this. In this paper, we present a system that helps blind people to maintain physical distance to other persons using a combination of RGB and depth cameras. We use a real-time semantic segmentation algorithm on the RGB camera to detect where persons are and use the depth camera to assess the distance to them; then, we provide audio feedback through bone-conducting headphones if a person is closer than 1.5 m. Our system warns the user only if persons are nearby but does not react to non-person objects such as walls, trees or doors; thus, it is not intrusive, and it is possible to use it in combination with other assistive devices. We have tested our prototype system on one blind and four blindfolded persons, and found that the system is precise, easy to use, and amounts to low cognitive load. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

26 pages, 1595 KiB

Open AccessEditor’s ChoiceReview

Emotion Recognition in Immersive Virtual Reality: From Statistics to Affective Computing

by Javier Marín-Morales, Carmen Llinares, Jaime Guixeres and Mariano Alcañiz

Sensors 2020, 20(18), 5163; https://doi.org/10.3390/s20185163 - 10 Sep 2020

Cited by 112 | Viewed by 14870

Abstract

Emotions play a critical role in our daily lives, so the understanding and recognition of emotional responses is crucial for human research. Affective computing research has mostly used non-immersive two-dimensional (2D) images or videos to elicit emotional states. However, immersive virtual reality, which [...] Read more.

Emotions play a critical role in our daily lives, so the understanding and recognition of emotional responses is crucial for human research. Affective computing research has mostly used non-immersive two-dimensional (2D) images or videos to elicit emotional states. However, immersive virtual reality, which allows researchers to simulate environments in controlled laboratory conditions with high levels of sense of presence and interactivity, is becoming more popular in emotion research. Moreover, its synergy with implicit measurements and machine-learning techniques has the potential to impact transversely in many research areas, opening new opportunities for the scientific community. This paper presents a systematic review of the emotion recognition research undertaken with physiological and behavioural measures using head-mounted displays as elicitation devices. The results highlight the evolution of the field, give a clear perspective using aggregated analysis, reveal the current open issues and provide guidelines for future research. Full article

(This article belongs to the Special Issue Emotion and Stress Recognition Related Sensors and Machine Learning Technologies)

► Show Figures

Figure 1

15 pages, 1793 KiB

Open AccessEditor’s ChoiceArticle

Assessment of Smoke Contamination in Grapevine Berries and Taint in Wines Due to Bushfires Using a Low-Cost E-Nose and an Artificial Intelligence Approach

by Sigfredo Fuentes, Vasiliki Summerson, Claudia Gonzalez Viejo, Eden Tongson, Nir Lipovetzky, Kerry L. Wilkinson, Colleen Szeto and Ranjith R. Unnithan

Sensors 2020, 20(18), 5108; https://doi.org/10.3390/s20185108 - 8 Sep 2020

Cited by 34 | Viewed by 4230

Abstract

Bushfires are increasing in number and intensity due to climate change. A newly developed low-cost electronic nose (e-nose) was tested on wines made from grapevines exposed to smoke in field trials. E-nose readings were obtained from wines from five experimental treatments: (i) low-density [...] Read more.

Bushfires are increasing in number and intensity due to climate change. A newly developed low-cost electronic nose (e-nose) was tested on wines made from grapevines exposed to smoke in field trials. E-nose readings were obtained from wines from five experimental treatments: (i) low-density smoke exposure (LS), (ii) high-density smoke exposure (HS), (iii) high-density smoke exposure with in-canopy misting (HSM), and two controls: (iv) control (C; no smoke treatment) and (v) control with in-canopy misting (CM; no smoke treatment). These e-nose readings were used as inputs for machine learning algorithms to obtain a classification model, with treatments as targets and seven neurons, with 97% accuracy in the classification of 300 samples into treatments as targets (Model 1). Models 2 to 4 used 10 neurons, with 20 glycoconjugates and 10 volatile phenols as targets, measured: in berries one hour after smoke (Model 2; R = 0.98; R² = 0.95; b = 0.97); in berries at harvest (Model 3; R = 0.99; R² = 0.97; b = 0.96); in wines (Model 4; R = 0.99; R² = 0.98; b = 0.98). Model 5 was based on the intensity of 12 wine descriptors determined via a consumer sensory test (Model 5; R = 0.98; R² = 0.96; b = 0.97). These models could be used by winemakers to assess near real-time smoke contamination levels and to implement amelioration strategies to minimize smoke taint in wines following bushfires. Full article

(This article belongs to the Special Issue Implementation of Sensors and Artificial Intelligence for Environmental Hazards Assessment in Urban, Agriculture and Forestry Systems)

► Show Figures

Figure 1

24 pages, 4042 KiB

Open AccessEditor’s ChoiceReview

3D Deep Learning on Medical Images: A Review

by Satya P. Singh, Lipo Wang, Sukrit Gupta, Haveesh Goli, Parasuraman Padmanabhan and Balázs Gulyás

Sensors 2020, 20(18), 5097; https://doi.org/10.3390/s20185097 - 7 Sep 2020

Cited by 286 | Viewed by 21074

Abstract

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural [...] Read more.

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field. Full article

(This article belongs to the Special Issue Machine Learning for Biomedical Imaging and Sensing)

► Show Figures

Figure 1

24 pages, 25591 KiB

Open AccessEditor’s ChoiceArticle

Social Distance Monitor with a Wearable Magnetic Field Proximity Sensor

by Sizhen Bian, Bo Zhou and Paul Lukowicz

Sensors 2020, 20(18), 5101; https://doi.org/10.3390/s20185101 - 7 Sep 2020

Cited by 35 | Viewed by 10455

Abstract

Social distancing and contact/exposure tracing are accepted to be critical strategies in the fight against the COVID-19 epidemic. They are both closely connected to the ability to reliably establish the degree of proximity between people in real-world environments. We proposed, implemented, and evaluated [...] Read more.

Social distancing and contact/exposure tracing are accepted to be critical strategies in the fight against the COVID-19 epidemic. They are both closely connected to the ability to reliably establish the degree of proximity between people in real-world environments. We proposed, implemented, and evaluated a wearable proximity sensing system based on an oscillating magnetic field that overcomes many of the weaknesses of the current state of the art Bluetooth based proximity detection. In this paper, we first described the underlying physical principle, proposed a protocol for the identification and coordination of the transmitter (which is compatible with the current smartphone-based exposure tracing protocols). Subsequently, the system architecture and implementation were described, finally an elaborate characterization and evaluation of the performance (both in systematic lab experiments and in real-world settings) were performed. Our work demonstrated that the proposed system is much more reliable than the widely-used Bluetooth-based approach, particularly when it comes to distinguishing between distances above and below the 2.0 m threshold due to the magnetic field’s physical properties. Full article

(This article belongs to the Special Issue Magnetic Sensors 2020)

► Show Figures

Figure 1

15 pages, 1336 KiB

Open AccessEditor’s ChoiceArticle

An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning

by Taiyu Zhu, Kezhi Li, Lei Kuang, Pau Herrero and Pantelis Georgiou

Sensors 2020, 20(18), 5058; https://doi.org/10.3390/s20185058 - 6 Sep 2020

Cited by 38 | Viewed by 5672

Abstract

(1) Background: People living with type 1 diabetes (T1D) require self-management to maintain blood glucose (BG) levels in a therapeutic range through the delivery of exogenous insulin. However, due to the various variability, uncertainty and complex glucose dynamics, optimizing the doses of insulin [...] Read more.

(1) Background: People living with type 1 diabetes (T1D) require self-management to maintain blood glucose (BG) levels in a therapeutic range through the delivery of exogenous insulin. However, due to the various variability, uncertainty and complex glucose dynamics, optimizing the doses of insulin delivery to minimize the risk of hyperglycemia and hypoglycemia is still an open problem. (2) Methods: In this work, we propose a novel insulin bolus advisor which uses deep reinforcement learning (DRL) and continuous glucose monitoring to optimize insulin dosing at mealtime. In particular, an actor-critic model based on deep deterministic policy gradient is designed to compute mealtime insulin doses. The proposed system architecture uses a two-step learning framework, in which a population model is first obtained and then personalized by subject-specific data. Prioritized memory replay is adopted to accelerate the training process in clinical practice. To validate the algorithm, we employ a customized version of the FDA-accepted UVA/Padova T1D simulator to perform in silico trials on 10 adult subjects and 10 adolescent subjects. (3) Results: Compared to a standard bolus calculator as the baseline, the DRL insulin bolus advisor significantly improved the average percentage time in target range (70–180 mg/dL) from

74.1 % \pm 8.4 %

to

80.9 % \pm 6.9 %

(

p < 0.01

) and

54.9 % \pm 12.4 %

to

61.6 % \pm 14.1 %

(

p < 0.01

) in the the adult and adolescent cohorts, respectively, while reducing hypoglycemia. (4) Conclusions: The proposed algorithm has the potential to improve mealtime bolus insulin delivery in people with T1D and is a feasible candidate for future clinical validation. Full article

(This article belongs to the Special Issue Sensor Technologies: Artificial Intelligence for Diabetes Management)

► Show Figures

Figure 1

17 pages, 1968 KiB

Open AccessEditor’s ChoiceArticle

Near-Infrared Spectroscopy as a Rapid Screening Method for the Determination of Total Anthocyanin Content in Sambucus Fructus

by Stefan Stuppner, Sophia Mayr, Anel Beganovic, Krzysztof Beć, Justyna Grabska, Urban Aufschnaiter, Magdalena Groeneveld, Matthias Rainer, Thomas Jakschitz, Günther K. Bonn and Christian W. Huck

Sensors 2020, 20(17), 4983; https://doi.org/10.3390/s20174983 - 2 Sep 2020

Cited by 31 | Viewed by 4476

Abstract

Elderberry (Sambucus nigra L., fructus) is a very potent herbal drug, deriving from traditional European medicine (TEM). Ripe elderberries are rich in anthocyanins, flavonols, flavonol esters, flavonol glycosides, lectins, essential oils, unsaturated fatty acids and vitamins. Nevertheless, unripe elderflower fruits contain a [...] Read more.

Elderberry (Sambucus nigra L., fructus) is a very potent herbal drug, deriving from traditional European medicine (TEM). Ripe elderberries are rich in anthocyanins, flavonols, flavonol esters, flavonol glycosides, lectins, essential oils, unsaturated fatty acids and vitamins. Nevertheless, unripe elderflower fruits contain a certain amount of sambunigrin, a toxic cyanogenic glycoside, whose concentration decreases in the ripening process. Therefore, quality assurance must be carried out. The standard method described in literature is the photometric determination (pH-differential method) of the total anthocyanin content (TAC) that is the highest when the berries are ripe. The drawback of the pH-differential method is the extensive sample preparation and the low accuracy of the method. Therefore, the goal of this publication was to develop a fast non invasive near-infrared (NIR) method for the determination of TAC in whole berries. TAC of elderberries was measured using pH-differentiation method where TAC values of 632.87 mg/kg to 4342.01 mg/kg were measured. Additionally, cyanidin-3-O-glucoside, cyanidin-3-O-sambubioside and cyanidin-3-O-sambubioside-5-O-glucoside which represent more than 98% of TAC in elderberry were quantified using ultra high performance liquid chromatography-multiple wavelength detection—ultra high resolution-quadrupole-time of flight-mass spectrometry (UHPLC-MWD-UHR-Q-TOF-MS) and their sum parameter was determined, ranging between 499.43 mg/kg and 8199.07 mg/kg. Using those two methods as reference, whole elderberries were investigated by NIR spectroscopy with the Büchi NIRFlex N-500 benchtop spectrometer. According to the constructed partial least squares regression (PLSR) models the performance was as follows: a relative standard deviation (RSD_PLSR) of 13.5% and root mean square error of calibration (RMSECV/RMSEC) of 1.31 for pH-differentiation reference and a RSD_PLSR of 12.9% and RMSECV/RMSEC of 1.28 for the HPLC reference method. In this study, we confirm that it is possible to perform a NIR screening for TAC in whole elderberries. Using quantum chemical calculations, we obtained detailed NIR band assignments of the analyzed compounds and interpreted the wavenumber regions established in PLSR models as meaningful for anthocyanin content. The NIR measurement turned out to be a fast and cost-efficient alternative for the determination of TAC compared to pH-differential method and UHPLC-MWD-UHR-Q-TOF-MS. Due to the benefit of no sample preparation and extraction the technology can be considered as sustainable green technology. With the above mentioned inversely proportional ratio of TAC to total amount of toxic cyanogenic glycosides, NIR proves to be a reliable screening method for the ideal harvest time with maximal content of TAC and lowest content of cyanogenic glycosides in elderberry. Full article

(This article belongs to the Special Issue Breakthroughs and Challenges in Food Quality Assessment Using Advanced Rapid Techniques: Electronic Tongue, Electronic Nose, and Near-Infrared Spectroscopy)

► Show Figures

Graphical abstract

16 pages, 2731 KiB

Open AccessEditor’s ChoiceArticle

Vision Measurement of Tunnel Structures with Robust Modelling and Deep Learning Algorithms

by Xiangyang Xu and Hao Yang

Sensors 2020, 20(17), 4945; https://doi.org/10.3390/s20174945 - 1 Sep 2020

Cited by 44 | Viewed by 3618

Abstract

The health monitoring of tunnel structures is vital to the safe operation of railway transportation systems. With the increasing mileage of tunnels, regular inspection and health monitoring are urgently demanded for the tunnel structures, especially for information regarding deformation and damage. However, traditional [...] Read more.

The health monitoring of tunnel structures is vital to the safe operation of railway transportation systems. With the increasing mileage of tunnels, regular inspection and health monitoring are urgently demanded for the tunnel structures, especially for information regarding deformation and damage. However, traditional methods of tunnel inspection are time-consuming, expensive and highly dependent on human subjectivity. In this paper, an automatic tunnel monitoring method is investigated based on image data which is collected through the moving vision measurement unit consisting of camera array. Furthermore, geometric modelling and crack inspection algorithms are proposed where a robust three-dimensional tunnel model is reconstructed utilizing a B-spline method and crack identification is conducted by means of a Mask R-CNN network. The innovation of this investigation is that we combine the robust modelling which could be applied for the deformation analysis and the crack detection where a deep learning method is employed to recognize the tunnel cracks intelligently based on image sensors. In this study, experiments were conducted on a subway tunnel structure several kilometers long, and a robust three-dimensional model is generated and the cracks are identified automatically with the image data. The superiority of this proposal is that the comprehensive information of geometry deformation and crack damage can ensure the reliability and improve the accuracy of health monitoring. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

18 pages, 3576 KiB

Open AccessEditor’s ChoiceArticle

New Strategy for Improving the Accuracy of Aircraft Positioning Based on GPS SPP Solution

by Kamil Krasuski, Adam Ciećko, Mieczysław Bakuła and Damian Wierzbicki

Sensors 2020, 20(17), 4921; https://doi.org/10.3390/s20174921 - 31 Aug 2020

Cited by 17 | Viewed by 3121

Abstract

The paper describes and presents a new calculation strategy for the determination of the aircraft’s resultant position using the GPS (Global Positioning System) SPP (Single Point Positioning) code method. The paper developed a concept of using the weighted average model with the use [...] Read more.

The paper describes and presents a new calculation strategy for the determination of the aircraft’s resultant position using the GPS (Global Positioning System) SPP (Single Point Positioning) code method. The paper developed a concept of using the weighted average model with the use of measuring weights to improve the quality of determination of the coordinates and accuracy of GPS SPP positioning. In this research, measurement weights were used as a function of the number of GPS satellites being tracked, and geometric PDOP (Position Dilution of Precision) coefficient. The calculations were made using navigation data recorded by two independent GPS receivers: Thales Mobile Mapper and Topcon HiPerPro. On the basis of the obtained results, it was found that the RMS (Root Mean Square) accuracy of positioning for XYZ geocentric coordinates was better than 1.2% to 33.7% for the weighted average method compared to a single GPS SPP solution. The proposed approach is therefore of practical application in air navigation to improve the quality of aircraft positioning. Full article

(This article belongs to the Special Issue GNSS Sensors in Aerial Navigation)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI