Sensors

17 pages, 2031 KiB

Open AccessArticle

Determination of Carbohydrate Composition in Lentils Using Near-Infrared Spectroscopy

by Rocío López-Calabozo, Ângela Liberal, Ângela Fernandes, Isabel Revilla, Isabel C. F. R. Ferreira, Lillian Barros and Ana M. Vivar-Quintana

Sensors 2024, 24(13), 4232; https://doi.org/10.3390/s24134232 (registering DOI) - 29 Jun 2024

Abstract

Carbohydrates are the main components of lentils, accounting for more than 60% of their composition. Their content is influenced by genetic factors, with different contents depending on the variety. These compounds have not only been linked to interesting health benefits, but they also [...] Read more.

Carbohydrates are the main components of lentils, accounting for more than 60% of their composition. Their content is influenced by genetic factors, with different contents depending on the variety. These compounds have not only been linked to interesting health benefits, but they also have a significant influence on the techno-functional properties of lentil-derived products. In this study, the use of near-infrared spectroscopy (NIRS) to predict the concentration of total carbohydrate, fibre, starch, total sugars, fructose, sucrose and raffinose was investigated. For this purpose, six different cultivars of macrosperm (n = 37) and microsperm (n = 43) lentils have been analysed, the samples were recorded whole and ground and the suitability of both recording methods were compared. Different spectral and mathematical pre-treatments were evaluated before developing the calibration models using the Modified Partial Least Squares regression method, with a cross-validation and an external validation. The predictive models developed show excellent coefficients of determination (RSQ > 0.9) for the total sugars and fructose, sucrose, and raffinose. The recording of ground samples allowed for obtaining better models for the calibration of starch content (R > 0.8), total sugars and sucrose (R > 0.93), and raffinose (R > 0.91). The results obtained confirm that there is sufficient information in the NIRS spectral region for the development of predictive models for the quantification of the carbohydrate content in lentils. Full article

(This article belongs to the Collection Sensors and Biosensors for Environmental and Food Applications)

► Show Figures

Figure 1

20 pages, 6398 KiB

Open AccessArticle

Multi-Agent System Based Cooperative Control for Speed Convergence of Virtually Coupled Train Formation

by Chuanzhen Liu and Zhongwei Xu

Sensors 2024, 24(13), 4231; https://doi.org/10.3390/s24134231 (registering DOI) - 29 Jun 2024

Abstract

This paper investigates the problem of spacing control between adjacent trains in train formation and proposes a distributed train-formation speed-convergence cooperative-control algorithm based on barrier Lyapunov function. Considering practical limitations such as communication distance and bandwidth constraints during operation, not all trains can [...] Read more.

This paper investigates the problem of spacing control between adjacent trains in train formation and proposes a distributed train-formation speed-convergence cooperative-control algorithm based on barrier Lyapunov function. Considering practical limitations such as communication distance and bandwidth constraints during operation, not all trains can directly communicate with the leader and obtain the expected trajectory it sends, making it difficult to maintain formation consistency as per the predetermined ideal state. Furthermore, to address the challenge of unknown external disturbances encountered by trains during operation, this paper designs a distributed observer deployed on each train in the formation. This observer can estimate and dynamically compensate for unknown reference trajectories and disturbances solely based on the states of adjacent trains. Additionally, to ensure that the spacing between adjacent trains remains within a predefined range, a safety hard constraint, this paper encodes the spacing hard constraint using barrier Lyapunov function. By integrating nonlinear adaptive control theory to handle model parameter uncertainties, a barrier Lyapunov function-based adaptive control method is proposed, which enables all trains to track the reference trajectory while ensuring that the spacing between them remains within the preset interval, therefore guaranteeing the asymptotic stability of the closed-loop system. Finally, a practical example using data from the Guangzhou Metro Line 22, specifically the route from Shiguang Road Station to Chentougang Station over three stations and two sections, is utilized to validate the effectiveness and robustness of the proposed algorithm. Full article

(This article belongs to the Section Vehicular Sensing)

31 pages, 2015 KiB

Open AccessArticle

Stress Wave Propagation in a Rayleigh–Love Rod with Sudden Cross-Sectional Area Variations Impacted by a Striker Rod

by Chung-Yue Wang, Nguyen Ngoc Thang and Helsin Wang

Sensors 2024, 24(13), 4230; https://doi.org/10.3390/s24134230 (registering DOI) - 29 Jun 2024

Abstract

This paper presents an in-depth study of the stress wave behavior propagating in a Rayleigh–Love rod with sudden cross-sectional area variations. The analytical solutions of stress waves are derived for the reflection and transmission propagation behavior at the interface of the cross-sectional area [...] Read more.

This paper presents an in-depth study of the stress wave behavior propagating in a Rayleigh–Love rod with sudden cross-sectional area variations. The analytical solutions of stress waves are derived for the reflection and transmission propagation behavior at the interface of the cross-sectional area change in the rod, considering inertia and Poisson’s effects on the rod material. Examples solved using the finite element method are provided to verify the correctness of the analytical results. Based on the forward analysis of Rayleigh–Love wave propagation in a rod impacted by a striker rod, an impact-echo-type nondestructive testing (NDT) method is proposed to conduct defect assessment in rod-type structural components with sudden cross-sectional area changes within a cover medium. This proposed NDT method can identify the location, extension, and cross-sectional area drop ratios of an irregular zone in the rod to be inspected. Full article

(This article belongs to the Section Physical Sensors)

14 pages, 1252 KiB

Open AccessArticle

Multisensory Fusion for Unsupervised Spatiotemporal Speaker Diarization

by Paris Xylogiannis, Nikolaos Vryzas, Lazaros Vrysis and Charalampos Dimoulas

Sensors 2024, 24(13), 4229; https://doi.org/10.3390/s24134229 (registering DOI) - 29 Jun 2024

Abstract

Speaker diarization consists of answering the question of “who spoke when” in audio recordings. In meeting scenarios, the task of labeling audio with the corresponding speaker identities can be further assisted by the exploitation of spatial features. This work proposes a framework designed [...] Read more.

Speaker diarization consists of answering the question of “who spoke when” in audio recordings. In meeting scenarios, the task of labeling audio with the corresponding speaker identities can be further assisted by the exploitation of spatial features. This work proposes a framework designed to assess the effectiveness of combining speaker embeddings with Time Difference of Arrival (TDOA) values from available microphone sensor arrays in meetings. We extract speaker embeddings using two popular and robust pre-trained models, ECAPA-TDNN and X-vectors, and calculate the TDOA values via the Generalized Cross-Correlation (GCC) method with Phase Transform (PHAT) weighting. Although ECAPA-TDNN outperforms the Xvectors model, we utilize both speaker embedding models to explore the potential of employing a computationally lighter model when spatial information is exploited. Various techniques for combining the spatial–temporal information are examined in order to determine the best clustering method. The proposed framework is evaluated on two multichannel datasets: the AVLab Speaker Localization dataset and a multichannel dataset (SpeaD-M3C) enriched in the context of the present work with supplementary information from smartphone recordings. Our results strongly indicate that the integration of spatial information can significantly improve the performance of state-of-the-art deep learning diarization models, presenting a 2–3% reduction in DER compared to the baseline approach on the evaluated datasets. Full article

(This article belongs to the Special Issue Multimodal Sensing Technologies for IoT and AI-Enabled Systems)

► Show Figures

Figure 1

10 pages, 2846 KiB

Open AccessArticle

Automated Imaging to Evaluate the Exogenous Gibberellin (Ga₃) Impact on Seedlings from Salt-Stressed Lettuce Seeds

by Mark Iradukunda, Marc W. van Iersel, Lynne Seymour, Guoyu Lu and Rhuanito Soranz Ferrarezi

Sensors 2024, 24(13), 4228; https://doi.org/10.3390/s24134228 (registering DOI) - 29 Jun 2024

Abstract

Salinity stress is a common challenge in plant growth, impacting seed quality, germination, and general plant health. Sodium chloride (NaCl) ions disrupt membranes, causing ion leakage and reducing seed viability. Gibberellic acid (GA₃) treatments have been found to promote germination and [...] Read more.

Salinity stress is a common challenge in plant growth, impacting seed quality, germination, and general plant health. Sodium chloride (NaCl) ions disrupt membranes, causing ion leakage and reducing seed viability. Gibberellic acid (GA₃) treatments have been found to promote germination and mitigate salinity stress on germination and plant growth. ‘Bauer’ and ‘Muir’ lettuce (Lactuca sativa) seeds were soaked in distilled water (control), 100 mM NaCl, 100 mM NaCl + 50 mg/L GA₃, and 100 mM NaCl + 150 mg/L GA₃ in Petri dishes and kept in a dark growth chamber at 25 °C for 24 h. After germination, seedlings were monitored using embedded cameras, capturing red, green, and blue (RGB) images from seeding to final harvest. Despite consistent germination rates, ‘Bauer’ seeds treated with NaCl showed reduced germination. Surprisingly, the ‘Muir’ cultivar’s final dry weight differed across treatments, with the NaCl and high GA₃ concentration combination yielding the poorest results (p < 0.05). This study highlights the efficacy of GA₃ applications in improving germination rates. However, at elevated concentrations, it induced excessive hypocotyl elongation and pale seedlings, posing challenges for two-dimensional imaging. Nonetheless, a sigmoidal regression model using projected canopy size accurately predicted dry weight across growth stages and cultivars, emphasizing its reliability despite treatment variations (R² = 0.96, RMSE = 0.11, p < 0.001). Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

16 pages, 2199 KiB

Open AccessArticle

An Improved U-Net Infrared Small Target Detection Algorithm Based on Multi-Scale Feature Decomposition and Fusion and Attention Mechanism

by Xiangsuo Fan, Wentao Ding, Xuyang Li, Tingting Li, Bo Hu and Yuqiu Shi

Sensors 2024, 24(13), 4227; https://doi.org/10.3390/s24134227 (registering DOI) - 29 Jun 2024

Abstract

Infrared small target detection technology plays a crucial role in various fields such as military reconnaissance, power patrol, medical diagnosis, and security. The advancement of deep learning has led to the success of convolutional neural networks in target segmentation. However, due to challenges [...] Read more.

Infrared small target detection technology plays a crucial role in various fields such as military reconnaissance, power patrol, medical diagnosis, and security. The advancement of deep learning has led to the success of convolutional neural networks in target segmentation. However, due to challenges like small target scales, weak signals, and strong background interference in infrared images, convolutional neural networks often face issues like leakage and misdetection in small target segmentation tasks. To address this, an enhanced U-Net method called MST-UNet is proposed, the method combines multi-scale feature decomposition and fusion and attention mechanisms. The method involves using Haar wavelet transform instead of maximum pooling for downsampling in the encoder to minimize feature loss and enhance feature utilization. Additionally, a multi-scale residual unit is introduced to extract contextual information at different scales, improving sensory field and feature expression. The inclusion of a triple attention mechanism in the encoder structure further enhances multidimensional information utilization and feature recovery by the decoder. Experimental analysis on the NUDT-SIRST dataset demonstrates that the proposed method significantly improves target contour accuracy and segmentation precision, achieving IoU and nIoU values of 80.09% and 80.19%, respectively. Full article

(This article belongs to the Section Sensing and Imaging)

12 pages, 2916 KiB

Open AccessArticle

Pulsed Laser-Bleaching Semiconductor and Photodetector

by Chen Huang, Fei Chen, Ze Zhang, Xin Tang, Meng Zhu, Junjie Sun, Yi Chen, Xin Zhang, Jinghua Yu and Yiwen Zhang

Sensors 2024, 24(13), 4226; https://doi.org/10.3390/s24134226 (registering DOI) - 29 Jun 2024

Abstract

Pulsed lasers alter the optical properties of semiconductors and affect the photoelectric function of the photodetectors significantly, resulting in transient changes known as bleaching. Bleaching has a profound impact on the control and interference of photodetector applications. Experiments using pump–probe techniques have made [...] Read more.

Pulsed lasers alter the optical properties of semiconductors and affect the photoelectric function of the photodetectors significantly, resulting in transient changes known as bleaching. Bleaching has a profound impact on the control and interference of photodetector applications. Experiments using pump–probe techniques have made significant contributions to understanding ultrafast carrier dynamics. However, there are few theoretical studies to the best of our knowledge. Here, carrier dynamic models for semiconductors and photodetectors are established, respectively, employing the rectified carrier drift-diffusion model. The pulsed laser bleaching effect on seven types of semiconductors and photodetectors from visible to long-wave infrared is demonstrated. Additionally, a continuous bleaching method is provided, and the finite-difference time-domain (FDTD) method is used to solve carrier dynamic theory models. Laser parameters for continuous bleaching of semiconductors and photodetectors are calculated. The proposed bleaching model and achieved laser parameters for continuous bleaching are essential for several applications using semiconductor devices, such as infrared detection, biological imaging, and sensing. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

16 pages, 5992 KiB

Open AccessArticle

Low-Cost Imaging to Quantify Germination Rate and Seedling Vigor across Lettuce Cultivars

by Mark Iradukunda, Marc W. van Iersel, Lynne Seymour, Guoyu Lu and Rhuanito Soranz Ferrarezi

Sensors 2024, 24(13), 4225; https://doi.org/10.3390/s24134225 (registering DOI) - 29 Jun 2024

Abstract

The survival and growth of young plants hinge on various factors, such as seed quality and environmental conditions. Assessing seedling potential/vigor for a robust crop yield is crucial but often resource-intensive. This study explores cost-effective imaging techniques for rapid evaluation of seedling vigor, [...] Read more.

The survival and growth of young plants hinge on various factors, such as seed quality and environmental conditions. Assessing seedling potential/vigor for a robust crop yield is crucial but often resource-intensive. This study explores cost-effective imaging techniques for rapid evaluation of seedling vigor, offering a practical solution to a common problem in agricultural research. In the first phase, nine lettuce (Lactuca sativa) cultivars were sown in trays and monitored using chlorophyll fluorescence imaging thrice weekly for two weeks. The second phase involved integrating embedded computers equipped with cameras for phenotyping. These systems captured and analyzed images four times daily, covering the entire growth cycle from seeding to harvest for four specific cultivars. All resulting data were promptly uploaded to the cloud, allowing for remote access and providing real-time information on plant performance. Results consistently showed the ‘Muir’ cultivar to have a larger canopy size and better germination, though ‘Sparx’ and ‘Crispino’ surpassed it in final dry weight. A non-linear model accurately predicted lettuce plant weight using seedling canopy size in the first study. The second study improved prediction accuracy with a sigmoidal growth curve from multiple harvests (R² = 0.88, RMSE = 0.27, p < 0.001). Utilizing embedded computers in controlled environments offers efficient plant monitoring, provided there is a uniform canopy structure and minimal plant overlap. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

10 pages, 358 KiB

Open AccessArticle

Low-Power Magnetic Displacement Sensor Based on RISC-V Embedded System

by Tao Sun, Yue Song and Huiyun Yang

Sensors 2024, 24(13), 4224; https://doi.org/10.3390/s24134224 (registering DOI) - 29 Jun 2024

Abstract

With the emergence of RISC-V architecture in embedded devices, its inherent low-power features have propelled its extensive adoption across various industrial settings. Displacement sensors leveraging Hall sensors and magnetic flux measurement present notable benefits including cost-effectiveness and compact design. This study undertakes the [...] Read more.

With the emergence of RISC-V architecture in embedded devices, its inherent low-power features have propelled its extensive adoption across various industrial settings. Displacement sensors leveraging Hall sensors and magnetic flux measurement present notable benefits including cost-effectiveness and compact design. This study undertakes the porting of Hall sensors onto RISC-V architecture embedded devices, validating their functionality within displacement sensors. Empirical investigations substantiate that the ported system consistently delivers comparable outcomes to those obtained from x86 architecture systems employing PM-MFM methods, affirming its reliability and performance in practical applications. Full article

(This article belongs to the Section Electronic Sensors)

11 pages, 1000 KiB

Open AccessArticle

Impact of Particle Size on the Nonlinear Magnetic Response of Iron Oxide Nanoparticles during Frequency Mixing Magnetic Detection

by Ali Mohammad Pourshahidi, Neha Jean, Corinna Kaulen, Simon Jakobi and Hans-Joachim Krause

Sensors 2024, 24(13), 4223; https://doi.org/10.3390/s24134223 (registering DOI) - 29 Jun 2024

Abstract

Abstract: Magnetic nanoparticles (MNPs), particularly iron oxide nanoparticles (IONPs), play a pivotal role in biomedical applications ranging from magnetic resonance imaging (MRI) enhancement and cancer hyperthermia treatments to biosensing. This study focuses on the synthesis, characterization, and application of IONPs with two different [...] Read more.

Abstract: Magnetic nanoparticles (MNPs), particularly iron oxide nanoparticles (IONPs), play a pivotal role in biomedical applications ranging from magnetic resonance imaging (MRI) enhancement and cancer hyperthermia treatments to biosensing. This study focuses on the synthesis, characterization, and application of IONPs with two different size distributions for frequency mixing magnetic detection (FMMD), a technique that leverages the nonlinear magnetization properties of MNPs for sensitive biosensing. IONPs are synthesized through thermal decomposition and subsequent growth steps. Our findings highlight the critical influence of IONP size on the FMMD signal, demonstrating that larger particles contribute dominantly to the FMMD signal. This research advances our understanding of IONP behavior, underscoring the importance of size in their application in advanced diagnostic tools. Full article

(This article belongs to the Special Issue Frequency Mixing Magnetic Detection of Magnetic Nanoparticles)

11 pages, 1974 KiB

Open AccessArticle

Conductive Hydrogel Tapes for Tripolar EEG: A Promising Solution to Paste-Related Challenges

by Cassidy Considine and Walter Besio

Sensors 2024, 24(13), 4222; https://doi.org/10.3390/s24134222 (registering DOI) - 29 Jun 2024

Abstract

Electroencephalography (EEG) remains pivotal in neuroscience for its non-invasive exploration of brain activity, yet traditional electrodes are plagued with artifacts and the application of conductive paste poses practical challenges. Tripolar concentric ring electrode (TCRE) sensors used for EEG (tEEG) attenuate artifacts automatically, improving [...] Read more.

Electroencephalography (EEG) remains pivotal in neuroscience for its non-invasive exploration of brain activity, yet traditional electrodes are plagued with artifacts and the application of conductive paste poses practical challenges. Tripolar concentric ring electrode (TCRE) sensors used for EEG (tEEG) attenuate artifacts automatically, improving the signal quality. Hydrogel tapes offer a promising alternative to conductive paste, providing mess-free application and reliable electrode–skin contact in locations without hair. Since the electrodes of the TCRE sensors are only 1.0 mm apart, the impedance of the skin-to-electrode impedance-matching medium is critical. This study evaluates four hydrogel tapes’ efficacies in EEG electrode application, comparing impedance and alpha wave characteristics. Healthy adult participants underwent tEEG recordings using different tapes. The results highlight varying impedances and successful alpha wave detection despite increased tape-induced impedance. MATLAB’s EEGLab facilitated signal processing. This study underscores hydrogel tapes’ potential as a convenient and effective alternative to traditional paste, enriching tEEG research methodologies. Two of the conductive hydrogel tapes had significantly higher alpha wave power than the other tapes, but were never significantly lower. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

16 pages, 8759 KiB

Open AccessArticle

Normal-Incidence Germanium Photodetectors Integrate with Polymer Microlenses for Optical Fiber Communication Applications

by Yu-Hsuan Liu, Chia-Peng Lin, Po-Wei Chen, Chia-Tai Tsao, Chun-Chi Lin, Tsung-Ting Wu, Likarn Wang and Neil Na

Sensors 2024, 24(13), 4221; https://doi.org/10.3390/s24134221 (registering DOI) - 29 Jun 2024

Abstract

We present a novel photon-acid diffusion method to integrate polymer microlenses (MLs) on a four-channel, high-speed photo-receiver consisting of normal-incidence germanium (Ge) p-i-n photodiodes (PDs) fabricated on a 200 mm Si substrate. For a 29 µm diameter PD capped with a 54 µm [...] Read more.

We present a novel photon-acid diffusion method to integrate polymer microlenses (MLs) on a four-channel, high-speed photo-receiver consisting of normal-incidence germanium (Ge) p-i-n photodiodes (PDs) fabricated on a 200 mm Si substrate. For a 29 µm diameter PD capped with a 54 µm diameter ML, its dark current, responsivity, 3 dB bandwidth (BW), and effective aperture size at −3 V bias and 850 nm wavelength are measured to be 138 nA, 0.6 A/W, 21.4 GHz, and 54 µm, respectively. The enlarged aperture size significantly decouples the tradeoff between aperture size and BW and enhances the optical fiber misalignment tolerance from ±5 µm to ±15 µm to ease the module packaging precision. The sensitivity of the photo-receiver is measured to be −9.2 dBm at 25.78 Gb/s with a bit error rate of 10⁻¹² using non-return-to-zero (NRZ) transmission. Reliability tests are performed, and the results show that the fabricated Ge PDs integrated with polymer MLs pass the GR-468 reliability assurance standard. The demonstrated photo-receiver, a first of its kind to the best of our knowledge, features decent performance, high yield, high throughput, low cost, and compatibility with complementary metal-oxide-semiconductor (CMOS) fabrication processes, and may be further applied to 400 Gb/s pulse-amplitude modulation four-level (PAM4) communication. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

16 pages, 1596 KiB

Open AccessArticle

Single-Track Magnetic Tape Absolute Position Sensor with Self-Adaptivity

by Zoltán Kántor and Attila Szabó

Sensors 2024, 24(13), 4220; https://doi.org/10.3390/s24134220 (registering DOI) - 28 Jun 2024

Abstract

Abstract: In this study, we demonstrate a single-track magnetic code tape-based absolute position sensor system. Unlike traditional dual-track systems, our method simplifies manufacturing and avoids crosstalk between tracks, offering higher tolerance to alignment errors. The sensing system employs an array of magnetic field [...] Read more.

Abstract: In this study, we demonstrate a single-track magnetic code tape-based absolute position sensor system. Unlike traditional dual-track systems, our method simplifies manufacturing and avoids crosstalk between tracks, offering higher tolerance to alignment errors. The sensing system employs an array of magnetic field sensing elements that recognize the bit sequence encoded on the tape. This approach allows for accurate position determination even when the number of sensing elements is fewer than the number of bits covered, and without the need for specific spacing between sensing elements and bit length. We demonstrate the system’s ability to learn and adapt to various magnetic code patterns, including those that are irregular or have been altered. Our method can identify and localize the sensed magnetic field pattern directly within a self-learned magnetic field map, providing robust performance in diverse conditions. This self-adaptive capability enhances operational safety and reliability, as the system can continue functioning even when the magnetic tape is misaligned or has undergone changes. Full article

(This article belongs to the Special Issue Magnetic Field Sensing and Measurement Techniques)

21 pages, 15538 KiB

Open AccessArticle

Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection

by David O. Santos, Jugurta Montalvão, Charles A. C. Araujo, Ulisses D. E. S. Lebre, Tarso V. Ferreira and Eduardo O. Freire

Sensors 2024, 24(13), 4219; https://doi.org/10.3390/s24134219 (registering DOI) - 28 Jun 2024

Abstract

This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training [...] Read more.

This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates

F_{1}

scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach. Full article

(This article belongs to the Topic Applications in Image Analysis and Pattern Recognition)

16 pages, 1920 KiB

Open AccessArticle

Estimation of Prediction Intervals for Performance Assessment of Building Using Machine Learning

by Khurram Shabbir, Muhammad Umair, Sung-Han Sim, Usman Ali and Mohamed Noureldin

Sensors 2024, 24(13), 4218; https://doi.org/10.3390/s24134218 (registering DOI) - 28 Jun 2024

Abstract

This study utilizes artificial neural networks (ANN) to estimate prediction intervals (PI) for seismic performance assessment of buildings subjected to long-term ground motion. To address the uncertainty quantification in structural health monitoring (SHM), the quality-driven lower upper bound estimation (QD-LUBE) has been opted [...] Read more.

This study utilizes artificial neural networks (ANN) to estimate prediction intervals (PI) for seismic performance assessment of buildings subjected to long-term ground motion. To address the uncertainty quantification in structural health monitoring (SHM), the quality-driven lower upper bound estimation (QD-LUBE) has been opted for global probabilistic assessment of damage at local and global levels, unlike traditional methods. A distribution-free machine learning model has been adopted for enhanced reliability in quantifying uncertainty and ensuring robustness in post-earthquake probabilistic assessments and early warning systems. The distribution-free machine learning model is capable of quantifying uncertainty with high accuracy as compared to previous methods such as the bootstrap method, etc. This research demonstrates the efficacy of the QD-LUBE method in complex seismic risk assessment scenarios, thereby contributing significant enhancement in building resilience and disaster management strategies. This study also validates the findings through fragility curve analysis, offering comprehensive insights into structural damage assessment and mitigation strategies. Full article

(This article belongs to the Special Issue Sensor Systems Empowered by AI, Big Data Processing, and Platform Technology)

20 pages, 1255 KiB

Open AccessArticle

Knee Angle Estimation from Surface EMG during Walking Using Attention-Based Deep Recurrent Neural Networks: Feasibility and Initial Demonstration in Cerebral Palsy

by Mohamed Abdelhady, Diane L. Damiano and Thomas C. Bulea

Sensors 2024, 24(13), 4217; https://doi.org/10.3390/s24134217 (registering DOI) - 28 Jun 2024

Abstract

Accurately estimating knee joint angle during walking from surface electromyography (sEMG) signals can enable more natural control of wearable robotics like exoskeletons. However, challenges exist due to variability across individuals and sessions. This study evaluates an attention-based deep recurrent neural network combining gated [...] Read more.

Accurately estimating knee joint angle during walking from surface electromyography (sEMG) signals can enable more natural control of wearable robotics like exoskeletons. However, challenges exist due to variability across individuals and sessions. This study evaluates an attention-based deep recurrent neural network combining gated recurrent units (GRUs) and an attention mechanism (AM) for knee angle estimation. Three experiments were conducted. First, the GRU-AM model was tested on four healthy adolescents, demonstrating improved estimation compared to GRU alone. A sensitivity analysis revealed that the key contributing muscles were the knee flexor and extensors, highlighting the ability of the AM to focus on the most salient inputs. Second, transfer learning was shown by pretraining the model on an open source dataset before additional training and testing on the four adolescents. Third, the model was progressively adapted over three sessions for one child with cerebral palsy (CP). The GRU-AM model demonstrated robust knee angle estimation across participants with healthy participants (mean RMSE 7 degrees) and participants with CP (RMSE 37 degrees). Further, estimation accuracy improved by 14 degrees on average across successive sessions of walking in the child with CP. These results demonstrate the feasibility of using attention-based deep networks for joint angle estimation in adolescents and clinical populations and support their further development for deployment in wearable robotics. Full article

(This article belongs to the Special Issue EMG Sensors and Signal Processing Technologies)

16 pages, 4079 KiB

Open AccessArticle

Eddy Current Sensor Array for Electromagnetic Sensing and Crack Reconstruction with High Lift-Off in Railway Tracks

by Yuchun Shao, Zihan Xia, Yiqing Ding, Bob Crocker, Scott Saunders, Xue Bai, Anthony Peyton, Daniel Conniffe and Wuliang Yin

Sensors 2024, 24(13), 4216; https://doi.org/10.3390/s24134216 (registering DOI) - 28 Jun 2024

Viewed by 59

Abstract

A reliable and efficient rail track defect detection system is essential for maintaining rail track integrity and avoiding safety hazards and financial losses. Eddy current (EC) testing is a non-destructive technique that can be employed for this purpose. The trade-off between spatial resolution [...] Read more.

A reliable and efficient rail track defect detection system is essential for maintaining rail track integrity and avoiding safety hazards and financial losses. Eddy current (EC) testing is a non-destructive technique that can be employed for this purpose. The trade-off between spatial resolution and lift-off should be carefully considered in practical applications to distinguish closely spaced cracks such as those caused by rolling contact fatigue (RCF). A multi-channel eddy current sensor array has been developed to detect defects on rails. Based on the sensor scanning data, defect reconstruction along the rails is achieved using an inverse algorithm that includes both direct and iterative approaches. In experimental evaluations, the EC system with the developed sensor is used to measure defects on a standard test piece of rail with a probe lift-off of 4–6 mm. The reconstruction results clearly reveal cracks at various depths and spacings on the test piece. Full article

(This article belongs to the Special Issue Electromagnetic Sensing and Its Applications)

12 pages, 540 KiB

Open AccessArticle

When Trustworthiness Meets Face: Facial Design for Social Robots

by Yao Song and Yan Luximon

Sensors 2024, 24(13), 4215; https://doi.org/10.3390/s24134215 (registering DOI) - 28 Jun 2024

Viewed by 85

Abstract

As a technical application in artificial intelligence, a social robot is one of the branches of robotic studies that emphasizes socially communicating and interacting with human beings. Although both robot and behavior research have realized the significance of social robot design for its [...] Read more.

As a technical application in artificial intelligence, a social robot is one of the branches of robotic studies that emphasizes socially communicating and interacting with human beings. Although both robot and behavior research have realized the significance of social robot design for its market success and related emotional benefit to users, the specific design of the eye and mouth shape of a social robot in eliciting trustworthiness has received only limited attention. In order to address this research gap, our study conducted a 2 (eye shape) × 3 (mouth shape) full factorial between-subject experiment. A total of 211 participants were recruited and randomly assigned to the six scenarios in the study. After exposure to the stimuli, perceived trustworthiness and robot attitude were measured accordingly. The results showed that round eyes (vs. narrow eyes) and an upturned-shape mouth or neutral mouth (vs. downturned-shape mouth) for social robots could significantly improve people’s trustworthiness and attitude towards social robots. The effect of eye and mouth shape on robot attitude are all mediated by the perceived trustworthiness. Trustworthy human facial features could be applied to the robot’s face, eliciting a similar trustworthiness perception and attitude. In addition to empirical contributions to HRI, this finding could shed light on the design practice for a trustworthy-looking social robot. Full article

(This article belongs to the Special Issue Challenges in Human-Robot Interactions for Social Robotics)

14 pages, 1795 KiB

Open AccessArticle

Cell–Electrode Models for Impedance Analysis of Epithelial and Endothelial Monolayers Cultured on Microelectrodes

by Wei-Chih Chiu, Wei-Ling Chen, Yi-Ting Lai, Yu-Han Hung and Chun-Min Lo

Sensors 2024, 24(13), 4214; https://doi.org/10.3390/s24134214 (registering DOI) - 28 Jun 2024

Viewed by 96

Abstract

Electric cell–substrate impedance sensing has been used to measure transepithelial and transendothelial impedances of cultured cell layers and extract cell parameters such as junctional resistance, cell–substrate separation, and membrane capacitance. Previously, a three-path cell–electrode model comprising two transcellular pathways and one paracellular pathway [...] Read more.

Electric cell–substrate impedance sensing has been used to measure transepithelial and transendothelial impedances of cultured cell layers and extract cell parameters such as junctional resistance, cell–substrate separation, and membrane capacitance. Previously, a three-path cell–electrode model comprising two transcellular pathways and one paracellular pathway was developed for the impedance analysis of MDCK cells. By ignoring the resistances of the lateral intercellular spaces, we develop a simplified three-path model for the impedance analysis of epithelial cells and solve the model equations in a closed form. The calculated impedance values obtained from this simplified cell–electrode model at frequencies ranging from 31.25 Hz to 100 kHz agree well with the experimental data obtained from MDCK and OVCA429 cells. We also describe how the change in each model-fitting parameter influences the electrical impedance spectra of MDCK cell layers. By assuming that the junctional resistance is much smaller than the specific impedance through the lateral cell membrane, the simplified three-path model reduces to a two-path model, which can be used for the impedance analysis of endothelial cells and other disk-shaped cells with low junctional resistances. The measured impedance spectra of HUVEC and HaCaT cell monolayers nearly coincide with the impedance data calculated from the two-path model. Full article

(This article belongs to the Special Issue Electrical Impedance Spectroscopy Technology)

15 pages, 3523 KiB

Open AccessArticle

Exploring the Efficacy of Nonlinear Filters in CMOS for 2-D Signal Processing for Image Quality Enhancement

by Hector Bandala-Hernandez, Alejandro Bautista-Castillo, José Miguel Rocha-Pérez, Victor Hugo Carbajal Gómez and Alejandro Díaz-Sánchez

Sensors 2024, 24(13), 4213; https://doi.org/10.3390/s24134213 (registering DOI) - 28 Jun 2024

Viewed by 83

Abstract

This study rigorously investigates the effectiveness of nonlinear filters in CMOS for 2-D signal processing to enhance image quality. We comprehensively compare traditional linear filters’ performance, which operate on the principle of linearity, with nonlinear filters, such as the median-median (Med-Med) approach, designed [...] Read more.

This study rigorously investigates the effectiveness of nonlinear filters in CMOS for 2-D signal processing to enhance image quality. We comprehensively compare traditional linear filters’ performance, which operate on the principle of linearity, with nonlinear filters, such as the median-median (Med-Med) approach, designed to handle nonlinear data. To ensure the validity of our findings, we use widely accepted metrics like normalized squared error (NSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) to quantify the differences. Our simulations and experiments, conducted under controlled conditions, demonstrate that nonlinear filters in CMOS outperform linear filters in removing impulse noise and enhancing images. We also address the challenges of implementing these algorithms at the hardware level, focusing on power consumption and chip area optimization. Additionally, we propose a new architecture for the Med-Med filter and validate its functionality through experiments using a 9-pixel image sensor array. Our findings highlight the potential of nonlinear filters in CMOS for real-time image quality enhancement and their applicability in various real-world imaging applications. This research contributes to visual technology by combining theoretical insights with practical implementations, paving the way for more efficient and adaptable imaging systems. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

25 pages, 1069 KiB

Open AccessArticle

Enhancing Monitoring Performance: A Microservices Approach to Monitoring with Spyware Techniques and Prediction Models

by Anubis Graciela de Moraes Rossetto, Darlan Noetzold, Luis Augusto Silva and Valderi Reis Quietinho Leithardt

Sensors 2024, 24(13), 4212; https://doi.org/10.3390/s24134212 (registering DOI) - 28 Jun 2024

Viewed by 84

Abstract

In today’s digital landscape, organizations face significant challenges, including sensitive data leaks and the proliferation of hate speech, both of which can lead to severe consequences such as financial losses, reputational damage, and psychological impacts on employees. This work considers a comprehensive solution [...] Read more.

In today’s digital landscape, organizations face significant challenges, including sensitive data leaks and the proliferation of hate speech, both of which can lead to severe consequences such as financial losses, reputational damage, and psychological impacts on employees. This work considers a comprehensive solution using a microservices architecture to monitor computer usage within organizations effectively. The approach incorporates spyware techniques to capture data from employee computers and a web application for alert management. The system detects data leaks, suspicious behaviors, and hate speech through efficient data capture and predictive modeling. Therefore, this paper presents a comparative performance analysis between Spring Boot and Quarkus, focusing on objective metrics and quantitative statistics. By utilizing recognized tools and benchmarks in the computer science community, the study provides an in-depth understanding of the performance differences between these two platforms. The implementation of Quarkus over Spring Boot demonstrated substantial improvements: memory usage was reduced by up to 80% and CPU usage by 95%, and system uptime decreased by 119%. This solution offers a robust framework for enhancing organizational security and mitigating potential threats through proactive monitoring and predictive analysis while also guiding developers and software architects in making informed technological choices. Full article

(This article belongs to the Special Issue Data Privacy, Security, and Trust in New Technological Trends—2nd Edition)

25 pages, 37446 KiB

Open AccessArticle

Resonant Eddy Current Sensor Design for Corrosion Detection of Reinforcing Steel

by Upeksha Chathurani Thibbotuwa, Ainhoa Cortés, Aurora María Casado and Andoni Irizar

Sensors 2024, 24(13), 4211; https://doi.org/10.3390/s24134211 (registering DOI) - 28 Jun 2024

Viewed by 99

Abstract

This paper introduces an LC resonator-based single-frequency eddy current (EC) sensor designed for corrosion detection in reinforcing bars (rebars) embedded within concrete structures. The work addresses the challenges of the limited detection ranges and reduced sensitivity over longer distances, prevalent in current EC [...] Read more.

This paper introduces an LC resonator-based single-frequency eddy current (EC) sensor designed for corrosion detection in reinforcing bars (rebars) embedded within concrete structures. The work addresses the challenges of the limited detection ranges and reduced sensitivity over longer distances, prevalent in current EC sensor applications. The sensor development process involved a systematic experimental approach to carefully selecting each parameter in the LC resonator. The sensor design aimed to assess the condition of the rebar from a distance of up to 5–6 cm outside the concrete and provide insights into different corrosion levels. By examining the characteristics of the inductors, the parallel resistance

R_{p}

of the eddy current coil was identified as a key parameter reflecting the corrosion conditions in the rebar. The relationship between the

R_{p}

fluctuations and temperature variations was investigated, with the data indicating that an approximately 155

Ω

variation can be expected per 1

^{\circ}

C change within the temperature range of 20–25

^{\circ}

C, allowing for temperature compensation if necessary. Subsequently, the sensor’s performance was evaluated by placing a rebar within a concrete block, where controlled mechanical degradation cycles were applied to simulate uniform corrosion in the rebar. The experimental results show that our EC sensor can detect material loss around the rebar with accuracy of approximately 0.17 mm. Full article

(This article belongs to the Special Issue Electromagnetic Non-destructive Testing and Evaluation)

28 pages, 1233 KiB

Open AccessReview

Recent Advances on Jamming and Spoofing Detection in GNSS

by Katarina Radoš, Marta Brkić and Dinko Begušić

Sensors 2024, 24(13), 4210; https://doi.org/10.3390/s24134210 (registering DOI) - 28 Jun 2024

Viewed by 91

Abstract

Increased interest in the development and integration of navigation and positioning services into a wide range of receivers makes them susceptible to a variety of security attacks such as Global Navigation Satellite Systems (GNSS) jamming and spoofing attacks. The availability of low-cost devices [...] Read more.

Increased interest in the development and integration of navigation and positioning services into a wide range of receivers makes them susceptible to a variety of security attacks such as Global Navigation Satellite Systems (GNSS) jamming and spoofing attacks. The availability of low-cost devices including software-defined radios (SDRs) provides a wide accessibility of affordable platforms that can be used to perform these attacks. Early detection of jamming and spoofing interferences is essential for mitigation and avoidance of service degradation. For these reasons, the development of efficient detection methods has become an important research topic and a number of effective methods has been reported in the literature. This survey offers the reader a comprehensive and systematic review of methods for detection of GNSS jamming and spoofing interferences. The categorization and classification of selected methods according to specific parameters and features is provided with a focus on recent advances in the field. Although many different detection methods have been reported, significant research efforts toward developing new and more efficient methods remain ongoing. These efforts are driven by the rapid development and increased number of attacks that pose high-security risks. The presented review of GNSS jamming and spoofing detection methods may be used for the selection of the most appropriate solution for specific purposes and constraints and also to provide a reference for future research. Full article

(This article belongs to the Special Issue Advanced Localization and Motion Tracking with Dense Wireless Networks)

16 pages, 7124 KiB

Open AccessArticle

Low-Power Wireless Sensor Module for Machine Learning-Based Continuous Monitoring of Nuclear Power Plants

by Jae-Cheol Lee, You-Rak Choi, Doyeob Yeo and Sangook Moon

Sensors 2024, 24(13), 4209; https://doi.org/10.3390/s24134209 (registering DOI) - 28 Jun 2024

Viewed by 111

Abstract

This paper introduces the novel design and implementation of a low-power wireless monitoring system designed for nuclear power plants, aiming to enhance safety and operational efficiency. By utilizing advanced signal-processing techniques and energy-efficient technologies, the system supports real-time, continuous monitoring without the need [...] Read more.

This paper introduces the novel design and implementation of a low-power wireless monitoring system designed for nuclear power plants, aiming to enhance safety and operational efficiency. By utilizing advanced signal-processing techniques and energy-efficient technologies, the system supports real-time, continuous monitoring without the need for frequent battery replacements. This addresses the high costs and risks associated with traditional wired monitoring methods. The system focuses on acoustic and ultrasonic analysis, capturing sound using microphones and processing these signals through heterodyne frequency conversion for effective signal management, accommodating low-power consumption through down-conversion. Integrated with edge computing, the system processes data locally at the sensor level, optimizing response times to anomalies and reducing network load. Practical implementation shows significant reductions in maintenance overheads and environmental impact, thereby enhancing the reliability and safety of nuclear power plant operations. The study also sets the groundwork for future integration of sophisticated machine learning algorithms to advance predictive maintenance capabilities in nuclear energy management. Full article

(This article belongs to the Special Issue Innovations in AI and ML-Based Techniques for Image and Video Analysis from Sensors)

► Show Figures

Figure 1

14 pages, 1163 KiB

Open AccessArticle

Tai Chi Movement Recognition and Precise Intervention for the Elderly Based on Inertial Measurement Units and Temporal Convolutional Neural Networks

by Xiongfeng Li, Limin Zou and Haojie Li

Sensors 2024, 24(13), 4208; https://doi.org/10.3390/s24134208 (registering DOI) - 28 Jun 2024

Viewed by 117

Abstract

(1) Background: The objective of this study was to recognize tai chi movements using inertial measurement units (IMUs) and temporal convolutional neural networks (TCNs) and to provide precise interventions for elderly people. (2) Methods: This study consisted of two parts: firstly, 70 skilled [...] Read more.

(1) Background: The objective of this study was to recognize tai chi movements using inertial measurement units (IMUs) and temporal convolutional neural networks (TCNs) and to provide precise interventions for elderly people. (2) Methods: This study consisted of two parts: firstly, 70 skilled tai chi practitioners were used for movement recognition; secondly, 60 elderly males were used for an intervention study. IMU data were collected from skilled tai chi practitioners performing Bafa Wubu, and TCN models were constructed and trained to classify these movements. Elderly participants were divided into a precision intervention group and a standard intervention group, with the former receiving weekly real-time IMU feedback. Outcomes measured included balance, grip strength, quality of life, and depression. (3) Results: The TCN model demonstrated high accuracy in identifying tai chi movements, with percentages ranging from 82.6% to 94.4%. After eight weeks of intervention, both groups showed significant improvements in grip strength, quality of life, and depression. However, only the precision intervention group showed a significant increase in balance and higher post-intervention scores compared to the standard intervention group. (4) Conclusions: This study successfully employed IMU and TCN to identify Tai Chi movements and provide targeted feedback to older participants. Real-time IMU feedback can enhance health outcome indicators in elderly males. Full article

(This article belongs to the Special Issue Inertial Sensing System for Motion Monitoring)

► Show Figures

Figure 1

18 pages, 3200 KiB

Open AccessArticle

Human Activity Recording Based on Skin-Strain-Actuated Microfluidic Pumping in Asymmetrically Designed Micro-Channels

by Caroline Barbar Askar, Nick Cmager, Rana Altay and I. Emre Araci

Sensors 2024, 24(13), 4207; https://doi.org/10.3390/s24134207 (registering DOI) - 28 Jun 2024

Viewed by 132

Abstract

The capability to record data in passive, image-based wearable sensors can simplify data readouts and eliminate the requirement for the integration of electronic components on the skin. Here, we developed a skin-strain-actuated microfluidic pump (SAMP) that utilizes asymmetric aspect ratio channels for the [...] Read more.

The capability to record data in passive, image-based wearable sensors can simplify data readouts and eliminate the requirement for the integration of electronic components on the skin. Here, we developed a skin-strain-actuated microfluidic pump (SAMP) that utilizes asymmetric aspect ratio channels for the recording of human activity in the fluidic domain. An analytical model describing the SAMP’s operation mechanism as a wearable microfluidic device was established. Fabrication of the SAMP was achieved using soft lithography from polydimethylsiloxane (PDMS). Benchtop experimental results and theoretical predictions were shown to be in good agreement. The SAMP was mounted on human skin and experiments conducted on volunteer subjects demonstrated the SAMP’s capability to record human activity for hundreds of cycles in the fluidic domain through the observation of a stable liquid meniscus. Proof-of-concept experiments further revealed that the SAMP could quantify a single wrist activity repetition or distinguish between three different shoulder activities. Full article

(This article belongs to the Special Issue Soft and Wearable Sensors for Human Health Monitoring)

► Show Figures

Figure 1

16 pages, 5406 KiB

Open AccessArticle

Research on In-Plane Thermal Conductivity Detection of Fuel Cell Bipolar Plates Based on Laser Thermography

by Yang Li, Dexin Hou, Feng Li, Lianghui Huang, Zhihua Huang, Yuehuan Zhang, Yongping Zheng, Leipeng Song, Bingqiang Huang, Zhengshun Fei and Xinjian Xiang

Sensors 2024, 24(13), 4206; https://doi.org/10.3390/s24134206 (registering DOI) - 28 Jun 2024

Viewed by 84

Abstract

The thermal properties of bipolar plates, being key elements of polymer electrolyte membrane fuel cells, significantly affect their heat conduction and management. This study employed an innovative approach known as a heat flow loop integral method to experimentally assess the in-plane thermal conductivity [...] Read more.

The thermal properties of bipolar plates, being key elements of polymer electrolyte membrane fuel cells, significantly affect their heat conduction and management. This study employed an innovative approach known as a heat flow loop integral method to experimentally assess the in-plane thermal conductivity of graphite bipolar plates, addressing the constraints of traditional methods that have strict demands for thermal stimulation, boundary or initial conditions, and sample size. This method employs infrared thermal imaging to gather information from the surface temperature field of the sample, which is induced by laser stimulation. An enclosed test loop on the infrared image of the sample’s surface, situated between the heat source and the sample’s boundary, is utilized to calculate the in-plane heat flow density by integrating the temperature at the sampling locations on the loop and the in-plane thermal conductivity can be determined based on Fourier’s law of heat conduction. The numerical simulation analysis of the graphite models and the experimental tests with aluminum have confirmed the precision and practicality of this method. The results of 1060 aluminum and 6061 aluminum samples, each 1 and 2 mm in thickness, show a deviation between the reference and actual measurements of the in-plane thermal conductivity within 4.3% and repeatability within 2.7%. Using the loop integral method, the in-plane thermal conductivities of three graphite bipolar plates with thicknesses of 0.5 mm, 1 mm, and 1.5 mm were tested, resulting in 311.98 W(m·K)⁻¹, 314.41 W(m·K)⁻¹, and 323.48 W(m·K)⁻¹, with repeatabilities of 0.9%, 3.0%, and 2.0%, respectively. A comparison with the reference value from the simulation model for graphite bipolar plates with the same thickness showed a deviation of 4.7%. The test results for three different thicknesses of graphite bipolar plates show a repeatability of 2.6%, indicating the high consistency and reliability of this measurement method. Consequently, as a supplement to existing technology, this method can achieve a rapid and nondestructive measurement of materials such as graphite bipolar plates’ in-plane thermal conductivity. Full article

(This article belongs to the Topic Applications of Non-destructive Testing Technologies in Materials or Engineering)

► Show Figures

Figure 1

19 pages, 18663 KiB

Open AccessArticle

Synthetic Data Enhancement and Network Compression Technology of Monocular Depth Estimation for Real-Time Autonomous Driving System

by Woomin Jun, Jisang Yoo and Sungjin Lee

Sensors 2024, 24(13), 4205; https://doi.org/10.3390/s24134205 (registering DOI) - 28 Jun 2024

Viewed by 87

Abstract

Accurate 3D image recognition, critical for autonomous driving safety, is shifting from the LIDAR-based point cloud to camera-based depth estimation technologies driven by cost considerations and the point cloud’s limitations in detecting distant small objects. This research aims to enhance MDE (Monocular Depth [...] Read more.

Accurate 3D image recognition, critical for autonomous driving safety, is shifting from the LIDAR-based point cloud to camera-based depth estimation technologies driven by cost considerations and the point cloud’s limitations in detecting distant small objects. This research aims to enhance MDE (Monocular Depth Estimation) using a single camera, offering extreme cost-effectiveness in acquiring 3D environmental data. In particular, this paper focuses on novel data augmentation methods designed to enhance the accuracy of MDE. Our research addresses the challenge of limited MDE data quantities by proposing the use of synthetic-based augmentation techniques: Mask, Mask-Scale, and CutFlip. The implementation of these synthetic-based data augmentation strategies has demonstrably enhanced the accuracy of MDE models by 4.0% compared to the original dataset. Furthermore, this study introduces the RMS (Real-time Monocular Depth Estimation configuration considering Resolution, Efficiency, and Latency) algorithm, designed for the optimization of neural networks to augment the performance of contemporary monocular depth estimation technologies through a three-step process. Initially, it selects a model based on minimum latency and REL criteria, followed by refining the model’s accuracy using various data augmentation techniques and loss functions. Finally, the refined model is compressed using quantization and pruning techniques to minimize its size for efficient on-device real-time applications. Experimental results from implementing the RMS algorithm indicated that, within the required latency and size constraints, the IEBins model exhibited the most accurate REL (absolute RELative error) performance, achieving a

0.0480

REL. Furthermore, the data augmentation combination of the original dataset with Flip, Mask, and CutFlip, alongside the SigLoss loss function, displayed the best REL performance, with a score of

0.0461

. The network compression technique using FP16 was analyzed as the most effective, reducing the model size by 83.4% compared to the original while maintaining the least impact on REL performance and latency. Finally, the performance of the RMS algorithm was validated on the on-device autonomous driving platform, NVIDIA Jetson AGX Orin, through which optimal deployment strategies were derived for various applications and scenarios requiring autonomous driving technologies. Full article

(This article belongs to the Special Issue Sensors for Intelligent Vehicles and Autonomous Driving)

► Show Figures

Figure 1

20 pages, 2492 KiB

Open AccessArticle

IAVRS—International Affective Virtual Reality System: Psychometric Assessment of 360° Images by Using Psychophysiological Data

by Valentina Mancuso, Francesca Borghesi, Alice Chirico, Francesca Bruni, Eleonora Diletta Sarcinella, Elisa Pedroli and Pietro Cipresso

Sensors 2024, 24(13), 4204; https://doi.org/10.3390/s24134204 (registering DOI) - 28 Jun 2024

Viewed by 118

Abstract

Virtual Reality is an effective technique for eliciting emotions. It provides immersive and ecologically valid emotional experiences while maintaining experimental control. Recently, novel VR forms like 360° videos have been used successfully for emotion elicitation. Some preliminary databases of 360° videos for emotion [...] Read more.

Virtual Reality is an effective technique for eliciting emotions. It provides immersive and ecologically valid emotional experiences while maintaining experimental control. Recently, novel VR forms like 360° videos have been used successfully for emotion elicitation. Some preliminary databases of 360° videos for emotion elicitation have been proposed, but they tapped mainly into an emotional dimensional approach and did not include a concurrent physiological assessment of an emotional profile. This study expands on these databases by combining dimensional and discrete approaches to validate a new set of 360° emotion-inducing images. Twenty-six participants viewed 46 immersive images, and their emotional reactions were measured using self-reporting, psychophysiological signals, and eye tracking. The IAVRS database can successfully elicit a wide range of emotional responses, including both positive and negative valence, as well as different levels of arousal. Results reveal an important correspondence between the discrete and dimensional models of emotions. Furthermore, the images that exhibit convergence between the dimensional and discrete emotional models are particularly impactful regarding arousal and valence values. The IAVRS database provides insights into potential relationships between physiological parameters and emotional responses. This preliminary investigation highlights the complexity of emotional elicitation processes and their physiological correlates, suggesting the need for further research to deepen our understanding. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

13 pages, 2020 KiB

Open AccessArticle

Multilayer Perceptron-Based Wearable Exercise-Related Heart Rate Variability Predicts Anxiety and Depression in College Students

by Xiongfeng Li, Limin Zou and Haojie Li

Sensors 2024, 24(13), 4203; https://doi.org/10.3390/s24134203 (registering DOI) - 28 Jun 2024

Viewed by 101

Abstract

(1) Background: This study aims to investigate the correlation between heart rate variability (HRV) during exercise and recovery periods and the levels of anxiety and depression among college students. Additionally, the study assesses the accuracy of a multilayer perceptron-based HRV analysis in predicting [...] Read more.

(1) Background: This study aims to investigate the correlation between heart rate variability (HRV) during exercise and recovery periods and the levels of anxiety and depression among college students. Additionally, the study assesses the accuracy of a multilayer perceptron-based HRV analysis in predicting these emotional states. (2) Methods: A total of 845 healthy college students, aged between 18 and 22, participated in the study. Participants completed self-assessment scales for anxiety and depression (SAS and PHQ-9). HRV data were collected during exercise and for a 5-min period post-exercise. The multilayer perceptron neural network model, which included several branches with identical configurations, was employed for data processing. (3) Results: Through a 5-fold cross-validation approach, the average accuracy of HRV in predicting anxiety levels was 89.3% for no anxiety, 83.6% for mild anxiety, and 74.9% for moderate to severe anxiety. For depression levels, the average accuracy was 90.1% for no depression, 84.2% for mild depression, and 82.1% for moderate to severe depression. The predictive R-squared values for anxiety and depression scores were 0.62 and 0.41, respectively. (4) Conclusions: The study demonstrated that HRV during exercise and recovery in college students can effectively predict levels of anxiety and depression. However, the accuracy of score prediction requires further improvement. HRV related to exercise can serve as a non-invasive biomarker for assessing psychological health. Full article

(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Measuring Human Vital Signs: 2nd Edition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 24, Issue 13 (July-1 2024) – 202 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI