Sensors

18 pages, 6356 KiB

Open AccessArticle

Influence of Mg Doping Levels on the Sensing Properties of SnO₂ Films

by Bouteina Bendahmane, Milena Tomić, Nour El Houda Touidjen, Isabel Gràcia, Stella Vallejos and Farida Mansour

Sensors 2020, 20(7), 2158; https://doi.org/10.3390/s20072158 - 10 Apr 2020

Cited by 12 | Viewed by 4310

Abstract

This work presents the effect of magnesium (Mg) doping on the sensing properties of tin dioxide (SnO₂) thin films. Mg-doped SnO₂ films were prepared via a spray pyrolysis method using three doping concentrations (0.8 at.%, 1.2 at.%, and 1.6 at.%) [...] Read more.

This work presents the effect of magnesium (Mg) doping on the sensing properties of tin dioxide (SnO₂) thin films. Mg-doped SnO₂ films were prepared via a spray pyrolysis method using three doping concentrations (0.8 at.%, 1.2 at.%, and 1.6 at.%) and the sensing responses were obtained at a comparatively low operating temperature (160 °C) compared to other gas sensitive materials in the literature. The morphological, structural and chemical composition analysis of the doped films show local lattice disorders and a proportional decrease in the average crystallite size as the Mg-doping level increases. These results also indicate an excess of Mg (in the samples prepared with 1.6 at.% of magnesium) which causes the formation of a secondary magnesium oxide phase. The films are tested towards three volatile organic compounds (VOCs), including ethanol, acetone, and toluene. The gas sensing tests show an enhancement of the sensing properties to these vapors as the Mg-doping level rises. This improvement is particularly observed for ethanol and, thus, the gas sensing analysis is focused on this analyte. Results to 80 ppm of ethanol, for instance, show that the response of the 1.6 at.% Mg-doped SnO₂ film is four times higher and 90 s faster than that of the 0.8 at.% Mg-doped SnO₂ film. This enhancement is attributed to the Mg-incorporation into the SnO₂ cell and to the formation of MgO within the film. These two factors maximize the electrical resistance change in the gas adsorption stage, and thus, raise ethanol sensitivity. Full article

(This article belongs to the Special Issue Application of Thin Film Materials in Sensors)

► Show Figures

Figure 1

22 pages, 1363 KiB

Open AccessArticle

Energy Management of Smart Home with Home Appliances, Energy Storage System and Electric Vehicle: A Hierarchical Deep Reinforcement Learning Approach

by Sangyoon Lee and Dae-Hyun Choi

Sensors 2020, 20(7), 2157; https://doi.org/10.3390/s20072157 - 10 Apr 2020

Cited by 101 | Viewed by 10466

Abstract

This paper presents a hierarchical deep reinforcement learning (DRL) method for the scheduling of energy consumptions of smart home appliances and distributed energy resources (DERs) including an energy storage system (ESS) and an electric vehicle (EV). Compared to Q-learning algorithms based on a [...] Read more.

This paper presents a hierarchical deep reinforcement learning (DRL) method for the scheduling of energy consumptions of smart home appliances and distributed energy resources (DERs) including an energy storage system (ESS) and an electric vehicle (EV). Compared to Q-learning algorithms based on a discrete action space, the novelty of the proposed approach is that the energy consumptions of home appliances and DERs are scheduled in a continuous action space using an actor–critic-based DRL method. To this end, a two-level DRL framework is proposed where home appliances are scheduled at the first level according to the consumer’s preferred appliance scheduling and comfort level, while the charging and discharging schedules of ESS and EV are calculated at the second level using the optimal solution from the first level along with the consumer environmental characteristics. A simulation study is performed in a single home with an air conditioner, a washing machine, a rooftop solar photovoltaic system, an ESS, and an EV under a time-of-use pricing. Numerical examples under different weather conditions, weekday/weekend, and driving patterns of the EV confirm the effectiveness of the proposed approach in terms of total cost of electricity, state of energy of the ESS and EV, and consumer preference. Full article

(This article belongs to the Special Issue Internet of Things for Smart Homes II)

► Show Figures

Figure 1

26 pages, 646 KiB

Open AccessArticle

P⁴UIoT: Pay-Per-Piece Patch Update Delivery for IoT Using Gradual Release

by Nachiket Tapas, Yechiav Yitzchak, Francesco Longo, Antonio Puliafito and Asaf Shabtai

Sensors 2020, 20(7), 2156; https://doi.org/10.3390/s20072156 - 10 Apr 2020

Cited by 6 | Viewed by 3934

Abstract

P

^{4}

UIoT—pay-per-piece patch update delivery for IoT using gradual release—introduces a distributed framework for delivering patch updates to IoT devices. The framework facilitates distribution via peer-to-peer delivery networks and incentivizes the distribution operation. The peer-to-peer delivery network reduces load by delegating the [...] Read more.

P

^{4}

UIoT—pay-per-piece patch update delivery for IoT using gradual release—introduces a distributed framework for delivering patch updates to IoT devices. The framework facilitates distribution via peer-to-peer delivery networks and incentivizes the distribution operation. The peer-to-peer delivery network reduces load by delegating the patch distribution to the nodes of the network, thereby protecting against a single point of failure and reducing costs. Distributed file-sharing solutions currently available in the literature are limited to sharing popular files among peers. In contrast, the proposed protocol incentivizes peers to distribute patch updates, which might be relevant only to IoT devices, using a blockchain-based lightning network. A manufacturer/owner named vendor of the IoT device commits a bid on the blockchain, which can be publicly verified by the members of the network. The nodes, called distributors, interested in delivering the patch update, compete among each other to exchange a piece of patch update with cryptocurrency payment. The pay-per-piece payments protocol addresses the problem of misbehavior between IoT devices and distributors as either of them may try to take advantage of the other. The pay-per-piece protocol is a form of a gradual release of a commodity like a patch update, where the commodity can be divided into small pieces and exchanged between the sender and the receiver building trust at each step as the transactions progress into rounds. The permissionless nature of the framework enables the proposal to scale as it incentivizes the participation of individual distributors. Thus, compared to the previous solutions, the proposed framework can scale better without any overhead and with reduced costs. A combination of the Bitcoin lightning network for cryptocurrency incentives with the BitTorrent delivery network is used to present a prototype of the proposed framework. Finally, a financial and scalability evaluation of the proposed framework is presented. Full article

(This article belongs to the Special Issue Blockchain in the Internet of Things: Opportunities, Challenges and Solutions)

► Show Figures

Figure 1

21 pages, 3221 KiB

Open AccessArticle

Design, Implementation, and Validation of a Piezoelectric Device to Study the Effects of Dynamic Mechanical Stimulation on Cell Proliferation, Migration and Morphology

by Dahiana Mojena-Medina, Marina Martínez-Hernández, Miguel de la Fuente, Guadalupe García-Isla, Julio Posada, José Luis Jorcano and Pablo Acedo

Sensors 2020, 20(7), 2155; https://doi.org/10.3390/s20072155 - 10 Apr 2020

Cited by 10 | Viewed by 5073

Abstract

Cell functions and behavior are regulated not only by soluble (biochemical) signals but also by biophysical and mechanical cues within the cells’ microenvironment. Thanks to the dynamical and complex cell machinery, cells are genuine and effective mechanotransducers translating mechanical stimuli into biochemical signals, [...] Read more.

Cell functions and behavior are regulated not only by soluble (biochemical) signals but also by biophysical and mechanical cues within the cells’ microenvironment. Thanks to the dynamical and complex cell machinery, cells are genuine and effective mechanotransducers translating mechanical stimuli into biochemical signals, which eventually alter multiple aspects of their own homeostasis. Given the dominant and classic biochemical-based views to explain biological processes, it could be challenging to elucidate the key role that mechanical parameters such as vibration, frequency, and force play in biology. Gaining a better understanding of how mechanical stimuli (and their mechanical parameters associated) affect biological outcomes relies partially on the availability of experimental tools that may allow researchers to alter mechanically the cell’s microenvironment and observe cell responses. Here, we introduce a new device to study in vitro responses of cells to dynamic mechanical stimulation using a piezoelectric membrane. Using this device, we can flexibly change the parameters of the dynamic mechanical stimulation (frequency, amplitude, and duration of the stimuli), which increases the possibility to study the cell behavior under different mechanical excitations. We report on the design and implementation of such device and the characterization of its dynamic mechanical properties. By using this device, we have performed a preliminary study on the effect of dynamic mechanical stimulation in a cell monolayer of an epidermal cell line (HaCaT) studying the effects of 1 Hz and 80 Hz excitation frequencies (in the dynamic stimuli) on HaCaT cell migration, proliferation, and morphology. Our preliminary results indicate that the response of HaCaT is dependent on the frequency of stimulation. The device is economic, easily replicated in other laboratories and can support research for a better understanding of mechanisms mediating cellular mechanotransduction. Full article

(This article belongs to the Section Biosensors)

► Show Figures

Figure 1

12 pages, 4122 KiB

Open AccessArticle

Inlet Effect Caused by Multichannel Structure for Molecular Electronic Transducer Based on a Turbulent-Laminar Flow Model

by Qiuzhan Zhou, Qi He, Yuzhu Chen and Xue Bao

Sensors 2020, 20(7), 2154; https://doi.org/10.3390/s20072154 - 10 Apr 2020

Viewed by 2755

Abstract

The actual fluid form of an electrolyte in a molecular electronic converter is an important factor that causes a decrease in the accuracy of a molecular electronic transducer (MET) liquid motion sensor. To study the actual fluid morphology of an inertial electrolyte in [...] Read more.

The actual fluid form of an electrolyte in a molecular electronic converter is an important factor that causes a decrease in the accuracy of a molecular electronic transducer (MET) liquid motion sensor. To study the actual fluid morphology of an inertial electrolyte in molecular electron transducers, an inlet effect is defined according to the fluid morphology of turbulent-laminar flow, and a numerical simulation model of turbulent-laminar flow is proposed. Based on the turbulent-laminar flow model, this paper studies the variation of the inlet effect intensity when the thickness of the outermost insulating layer is 50 µm and 100 µm, respectively. Meanwhile, the changes of the inlet effect intensity and the error rate of central axial velocity field are also analyzed when the input signal intensity is different. Through the numerical experiment, it verifies that the thickness of the outermost insulating layer and the amplitude of the input signal are two important factors which can affect the inlet effect intensity and also the accuracy of the MET. Therefore, this study can provide a theoretical basis for the quantitative study on the performance optimization of a MET liquid sensor. Full article

(This article belongs to the Special Issue MET Angular and Linear Motion Seismic Sensors)

► Show Figures

Figure 1

18 pages, 710 KiB

Open AccessArticle

Wireless Body Area Network (WBAN)-Based Telemedicine for Emergency Care

by Latha R and Vetrivelan P

Sensors 2020, 20(7), 2153; https://doi.org/10.3390/s20072153 - 10 Apr 2020

Cited by 13 | Viewed by 5781

Abstract

This paper is a collection of telemedicine techniques used by wireless body area networks (WBANs) for emergency conditions. Furthermore, Bayes’ theorem is proposed for predicting emergency conditions. With prior knowledge, the posterior probability can be found along with the observed evidence. The probability [...] Read more.

This paper is a collection of telemedicine techniques used by wireless body area networks (WBANs) for emergency conditions. Furthermore, Bayes’ theorem is proposed for predicting emergency conditions. With prior knowledge, the posterior probability can be found along with the observed evidence. The probability of sending emergency messages can be determined using Bayes’ theorem with the likelihood evidence. It can be viewed as medical decision-making, since diagnosis conditions such as emergency monitoring, delay-sensitive monitoring, and general monitoring are analyzed with its network characteristics, including data rate, cost, packet loss rate, latency, and jitter. This paper explains the network model with 16 variables, with one describing immediate consultation, as well as another three describing emergency monitoring, delay-sensitive monitoring, and general monitoring. The remaining 12 variables are observations related to latency, cost, packet loss rate, data rate, and jitter. Full article

(This article belongs to the Special Issue Wireless Body Area Networks for Health Applications)

► Show Figures

Figure 1

12 pages, 2157 KiB

Open AccessArticle

Biosensors Platform Based on Chitosan/AuNPs/Phthalocyanine Composite Films for the Electrochemical Detection of Catechol. The Role of the Surface Structure

by Coral Salvo-Comino, Alfonso González-Gil, Javier Rodriguez-Valentin, Celia Garcia-Hernandez, Fernando Martin-Pedrosa, Cristina Garcia-Cabezon and Maria Luz Rodriguez-Mendez

Sensors 2020, 20(7), 2152; https://doi.org/10.3390/s20072152 - 10 Apr 2020

Cited by 29 | Viewed by 3949

Abstract

Biosensor platforms consisting of layer by layer films combining materials with different functionalities have been developed and used to obtain improved catechol biosensors. Tyrosinase (Tyr) or laccase (Lac) were deposited onto LbL films formed by layers of a cationic linker (chitosan, CHI) alternating [...] Read more.

Biosensor platforms consisting of layer by layer films combining materials with different functionalities have been developed and used to obtain improved catechol biosensors. Tyrosinase (Tyr) or laccase (Lac) were deposited onto LbL films formed by layers of a cationic linker (chitosan, CHI) alternating with layers of anionic electrocatalytic materials (sulfonated copper phthalocyanine, CuPcS or gold nanoparticles, AuNP). Films with different layer structures were successfully formed. Characterization of surface roughness and porosity was carried out using AFM. Electrochemical responses towards catechol showed that the LbL composites efficiently improved the electron transfer path between Tyr or Lac and the electrode surface, producing an increase in the intensity over the response in the absence of the LbL platform. LbL structures with higher roughness and pore size facilitated the diffusion of catechol, resulting in lower LODs. The [(CHI)-(AuNP)-(CHI)-(CuPcS)]₂-Tyr showed an LOD of 8.55∙10⁻⁴ μM, which was one order of magnitude lower than the 9.55·10⁻³ µM obtained with [(CHI)-(CuPcS)-(CHI)-(AuNP)]₂-Tyr, and two orders of magnitude lower than the obtained with other nanostructured platforms. It can be concluded that the combination of adequate materials with complementary activity and the control of the structure of the platform is an excellent strategy to obtain biosensors with improved performances. Full article

(This article belongs to the Section Biosensors)

► Show Figures

Graphical abstract

16 pages, 1700 KiB

Open AccessArticle

Specific Loss Power of Co/Li/Zn-Mixed Ferrite Powders for Magnetic Hyperthermia

by Gabriele Barrera, Marco Coisson, Federica Celegato, Luca Martino, Priyanka Tiwari, Roshni Verma, Shashank N. Kane, Frédéric Mazaleyrat and Paola Tiberto

Sensors 2020, 20(7), 2151; https://doi.org/10.3390/s20072151 - 10 Apr 2020

Cited by 17 | Viewed by 3745

Abstract

An important research effort on the design of the magnetic particles is increasingly required to optimize the heat generation in biomedical applications, such as magnetic hyperthermia and heat-assisted drug release, considering the severe restrictions for the human body’s exposure to an alternating magnetic [...] Read more.

An important research effort on the design of the magnetic particles is increasingly required to optimize the heat generation in biomedical applications, such as magnetic hyperthermia and heat-assisted drug release, considering the severe restrictions for the human body’s exposure to an alternating magnetic field. Magnetic nanoparticles, considered in a broad sense as passive sensors, show the ability to detect an alternating magnetic field and to transduce it into a localized increase of temperature. In this context, the high biocompatibility, easy synthesis procedure and easily tunable magnetic properties of ferrite powders make them ideal candidates. In particular, the tailoring of their chemical composition and cation distribution allows the control of their magnetic properties, tuning them towards the strict demands of these heat-assisted biomedical applications. In this work, Co_0.76Zn_0.24Fe₂O_4, Li_0.375Zn_0.25Fe_2.375O₄ and ZnFe₂O₄ mixed-structure ferrite powders were synthesized in a ‘dry gel’ form by a sol-gel auto-combustion method. Their microstructural properties and cation distribution were obtained by X-ray diffraction characterization. Static and dynamic magnetic measurements were performed revealing the connection between the cation distribution and magnetic behavior. Particular attention was focused on the effect of Co²⁺ and Li⁺ ions on the magnetic properties at a magnetic field amplitude and the frequency values according to the practical demands of heat-assisted biomedical applications. In this context, the specific loss power (SLP) values were evaluated by ac-hysteresis losses and thermometric measurements at selected values of the dynamic magnetic fields. Full article

(This article belongs to the Special Issue Biosensors with Magnetic Nanocomponents)

► Show Figures

Figure 1

19 pages, 11662 KiB

Open AccessArticle

Bayesian Inversion for Geoacoustic Parameters in Shallow Sea

by Guangxue Zheng, Hanhao Zhu, Xiaohan Wang, Sartaj Khan, Nansong Li and Yangyang Xue

Sensors 2020, 20(7), 2150; https://doi.org/10.3390/s20072150 - 10 Apr 2020

Cited by 14 | Viewed by 3357

Abstract

Geoacoustic parameter inversion is a crucial issue in underwater acoustic research for shallow sea environments and has increasingly become popular in the recent past. This paper investigates the geoacoustic parameters in a shallow sea environment using a single-receiver geoacoustic inversion method based on [...] Read more.

Geoacoustic parameter inversion is a crucial issue in underwater acoustic research for shallow sea environments and has increasingly become popular in the recent past. This paper investigates the geoacoustic parameters in a shallow sea environment using a single-receiver geoacoustic inversion method based on Bayesian theory. In this context, the seabed is regarded as an elastic medium, the acoustic pressure at different positions under low-frequency is chosen as the study object, and the theoretical prediction value of the acoustic pressure is described by the Fast Field Method (FFM). The cost function between the measured and modeled acoustic fields is established under the assumption of Gaussian data errors using Bayesian methodology. The Bayesian inversion method enables the inference of the seabed geoacoustic parameters from the experimental data, including the optimal estimates of these parameters, such as density, sound speed and sound speed attenuation, and quantitative uncertainty estimates. The optimization is carried out by simulated annealing (SA), and the Posterior Probability Density (PPD) is given as the inversion result based on the Gibbs Sampler (GS) algorithm. Inversion results of the experimental data are in good agreement with both measured values and estimates from Genetic Algorithm (GA) inversion result in the same environment. Furthermore, the results also indicate that the sound speed and density in the seabed have fewer uncertainties and are more sensitive to acoustic pressure than the sound speed attenuation. The sea noise could increase the variance of PPD, which has less influence on the sensitive parameters. The mean value of PPD could still reflect the true values of geoacoustic parameters in simulation. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

15 pages, 4644 KiB

Open AccessArticle

Monitoring of Interfacial Debonding of Concrete Filled Pultrusion-GFRP Tubular Column Based on Piezoelectric Smart Aggregate and Wavelet Analysis

by Wenwei Yang, Xia Yang and Shuntao Li

Sensors 2020, 20(7), 2149; https://doi.org/10.3390/s20072149 - 10 Apr 2020

Cited by 16 | Viewed by 2754

Abstract

The concrete filled pultrusion-GFRP (Glass Fiber Reinforced Polymer) tubular column (CFGC) is popular in hydraulic structures or regions with poor environmental conditions due to its excellent corrosion resistance. Considering the influence of concrete hydration heat, shrinkage, and creep, debonding may occur in the [...] Read more.

The concrete filled pultrusion-GFRP (Glass Fiber Reinforced Polymer) tubular column (CFGC) is popular in hydraulic structures or regions with poor environmental conditions due to its excellent corrosion resistance. Considering the influence of concrete hydration heat, shrinkage, and creep, debonding may occur in the interface between the GFRP tube and the concrete, which will greatly reduce the cooperation of the GFRP tube and concrete, and will weaken the mechanical property of CFGC. This paper introduces an active monitoring method based on the piezoelectric transducer. In the active sensing approach, the smart aggregate (SA) embedded in the concrete acted as a driver to transmit a modulated stress wave, and the PZT (Lead Zirconate Titanate) patches attached on the outer surface of CFGC serve as sensors to receive signals and transfer them to the computer for saving. Two groups of experiments were designed with the different debonding areas and thicknesses. The artificial damage of CFGC was identified and located by comparing the value of the delay under pulse excitation and the difference of wavelet-based energy under sweep excitation, and the damage indexes were defined based on the wavelet packet energy to quantify the level of the interface damage. The results showed that the debonding damage area of CFGC can be identified effectively through the active monitoring method, and the damage index can accurately reflect the damage level of the interface of GFRP tube and concrete. Therefore, this method can be used to identify and evaluate the interface debonding of CFGC in real time. In addition, if the method can be combined with remote sensing technology, it can be used as a real-time remote sensing monitoring technology to provide a solution for interface health monitoring of CFGC. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

19 pages, 3457 KiB

Open AccessReview

Parametric Acoustic Array and Its Application in Underwater Acoustic Engineering

by Hanyun Zhou, S.H. Huang and Wei Li

Sensors 2020, 20(7), 2148; https://doi.org/10.3390/s20072148 - 10 Apr 2020

Cited by 30 | Viewed by 7435

Abstract

As a sound transmitting device based on the nonlinear acoustic theory, parametric acoustic array (PAA) is able to generate high directivity and low frequency broadband signals with a small aperture transducer. Due to its predominant technical advantages, PAA has been widely used in [...] Read more.

As a sound transmitting device based on the nonlinear acoustic theory, parametric acoustic array (PAA) is able to generate high directivity and low frequency broadband signals with a small aperture transducer. Due to its predominant technical advantages, PAA has been widely used in a variety of application scenarios of underwater acoustic engineering, such as sub-bottom profile measurement, underwater acoustic communication, and detection of buried targets. In this review paper, we examine some of the important advances in the PAA since it was first proposed by Westervelt in 1963. These advances include theoretical modelling for the PAA, signal processing methods, design considerations and implementation issues, and applications of the PAA in underwater acoustic engineering. Moreover, we highlight some technical challenges which impede further development of the PAA, and correspondingly give a glimpse on its possible extension in the future. This article provides a comprehensive overview of some important works of the PAA and serves as a quick tutorial reference to readers who are interested to further explore and extend this technology, and bring this technology to other application areas. Full article

(This article belongs to the Special Issue Sensing and Probing by Acoustic Fields: Principles, Operation and Technology of Piezoelectric Sensors and Transducers)

► Show Figures

Figure 1

17 pages, 1680 KiB

Open AccessArticle

A Novel Hybrid Algorithm Based on Grey Wolf Optimizer and Fireworks Algorithm

by Zhihang Yue, Sen Zhang and Wendong Xiao

Sensors 2020, 20(7), 2147; https://doi.org/10.3390/s20072147 - 10 Apr 2020

Cited by 41 | Viewed by 5141

Abstract

Grey wolf optimizer (GWO) is a meta-heuristic algorithm inspired by the hierarchy of grey wolves (Canis lupus). Fireworks algorithm (FWA) is a nature-inspired optimization method mimicking the explosion process of fireworks for optimization problems. Both of them have a strong optimal search capability. [...] Read more.

Grey wolf optimizer (GWO) is a meta-heuristic algorithm inspired by the hierarchy of grey wolves (Canis lupus). Fireworks algorithm (FWA) is a nature-inspired optimization method mimicking the explosion process of fireworks for optimization problems. Both of them have a strong optimal search capability. However, in some cases, GWO converges to the local optimum and FWA converges slowly. In this paper, a new hybrid algorithm (named as FWGWO) is proposed, which fuses the advantages of these two algorithms to achieve global optima effectively. The proposed algorithm combines the exploration ability of the fireworks algorithm with the exploitation ability of the grey wolf optimizer (GWO) by setting a balance coefficient. In order to test the competence of the proposed hybrid FWGWO, 16 well-known benchmark functions having a wide range of dimensions and varied complexities are used in this paper. The results of the proposed FWGWO are compared to nine other algorithms, including the standard FWA, the native GWO, enhanced grey wolf optimizer (EGWO), and augmented grey wolf optimizer (AGWO). The experimental results show that the FWGWO effectively improves the global optimal search capability and convergence speed of the GWO and FWA. Full article

(This article belongs to the Special Issue Intelligent Sensors for Positioning, Tracking, Monitoring, Navigation and Smart Sensing in Smart Cities)

► Show Figures

Figure 1

15 pages, 8697 KiB

Open AccessArticle

Tensor-Based Emotional Category Classification via Visual Attention-Based Heterogeneous CNN Feature Fusion

by Yuya Moroto, Keisuke Maeda, Takahiro Ogawa and Miki Haseyama

Sensors 2020, 20(7), 2146; https://doi.org/10.3390/s20072146 - 10 Apr 2020

Cited by 2 | Viewed by 3303

Abstract

The paper proposes a method of visual attention-based emotion classification through eye gaze analysis. Concretely, tensor-based emotional category classification via visual attention-based heterogeneous convolutional neural network (CNN) feature fusion is proposed. Based on the relationship between human emotions and changes in visual attention [...] Read more.

The paper proposes a method of visual attention-based emotion classification through eye gaze analysis. Concretely, tensor-based emotional category classification via visual attention-based heterogeneous convolutional neural network (CNN) feature fusion is proposed. Based on the relationship between human emotions and changes in visual attention with time, the proposed method performs new gaze-based image representation that is suitable for reflecting the characteristics of the changes in visual attention with time. Furthermore, since emotions evoked in humans are closely related to objects in images, our method uses a CNN model to obtain CNN features that can represent their characteristics. For improving the representation ability to the emotional categories, we extract multiple CNN features from our novel gaze-based image representation and enable their fusion by constructing a novel tensor consisting of these CNN features. Thus, this tensor construction realizes the visual attention-based heterogeneous CNN feature fusion. This is the main contribution of this paper. Finally, by applying logistic tensor regression with general tensor discriminant analysis to the newly constructed tensor, the emotional category classification becomes feasible. Since experimental results show that the proposed method enables the emotional category classification with the F1-measure of approximately 0.6, and about 10% improvement can be realized compared to comparative methods including state-of-the-art methods, the effectiveness of the proposed method is verified. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

20 pages, 3332 KiB

Open AccessArticle

YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3

by Guoxu Liu, Joseph Christian Nouaze, Philippe Lyonel Touko Mbouembe and Jae Ho Kim

Sensors 2020, 20(7), 2145; https://doi.org/10.3390/s20072145 - 10 Apr 2020

Cited by 319 | Viewed by 23225

Abstract

Automatic fruit detection is a very important benefit of harvesting robots. However, complicated environment conditions, such as illumination variation, branch, and leaf occlusion as well as tomato overlap, have made fruit detection very challenging. In this study, an improved tomato detection model called [...] Read more.

Automatic fruit detection is a very important benefit of harvesting robots. However, complicated environment conditions, such as illumination variation, branch, and leaf occlusion as well as tomato overlap, have made fruit detection very challenging. In this study, an improved tomato detection model called YOLO-Tomato is proposed for dealing with these problems, based on YOLOv3. A dense architecture is incorporated into YOLOv3 to facilitate the reuse of features and help to learn a more compact and accurate model. Moreover, the model replaces the traditional rectangular bounding box (R-Bbox) with a circular bounding box (C-Bbox) for tomato localization. The new bounding boxes can then match the tomatoes more precisely, and thus improve the Intersection-over-Union (IoU) calculation for the Non-Maximum Suppression (NMS). They also reduce prediction coordinates. An ablation study demonstrated the efficacy of these modifications. The YOLO-Tomato was compared to several state-of-the-art detection methods and it had the best detection performance. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

21 pages, 45267 KiB

Open AccessArticle

Beam Deflection Monitoring Based on a Genetic Algorithm Using Lidar Data

by Michael Bekele Maru, Donghwan Lee, Gichun Cha and Seunghee Park

Sensors 2020, 20(7), 2144; https://doi.org/10.3390/s20072144 - 10 Apr 2020

Cited by 18 | Viewed by 5752

Abstract

The Light Detection And Ranging (LiDAR) system has become a prominent tool in structural health monitoring. Among such systems, Terrestrial Laser Scanning (TLS) is a potential technology for the acquisition of three-dimensional (3D) information to assess structural health conditions. This paper enhances the [...] Read more.

The Light Detection And Ranging (LiDAR) system has become a prominent tool in structural health monitoring. Among such systems, Terrestrial Laser Scanning (TLS) is a potential technology for the acquisition of three-dimensional (3D) information to assess structural health conditions. This paper enhances the application of TLS to damage detection and shape change analysis for structural element specimens. Specifically, estimating the deflection of a structural element with the aid of a Lidar system is introduced in this study. The proposed approach was validated by an indoor experiment by inducing artificial deflection on a simply supported beam. A robust genetic algorithm method is utilized to enhance the accuracy level of measuring deflection using lidar data. The proposed research primarily covers robust optimization of a genetic algorithm control parameter using the Taguchi experiment design. Once the acquired data is defined in terms of plane, which has minimum error, using a genetic algorithm and the deflection of the specimen can be extracted from the shape change analysis. Full article

(This article belongs to the Special Issue Sensors for Nondestructive Testing and Evaluation)

► Show Figures

Graphical abstract

13 pages, 5512 KiB

Open AccessArticle

An Affordable Fabrication of a Zeolite-Based Capacitor for Gas Sensing

by Salvatore Andrea Pullano, Francesco Falcone, Davide C. Critello, Maria Giovanna Bianco, Michele Menniti and Antonino S. Fiorillo

Sensors 2020, 20(7), 2143; https://doi.org/10.3390/s20072143 - 10 Apr 2020

Cited by 12 | Viewed by 3675

Abstract

The development of even more compact, inexpensive, and highly sensitive gas sensors is widespread, even though their performances are still limited and technological improvements are in continuous evolution. Zeolite is a class of material which has received particular attention in different applications due [...] Read more.

The development of even more compact, inexpensive, and highly sensitive gas sensors is widespread, even though their performances are still limited and technological improvements are in continuous evolution. Zeolite is a class of material which has received particular attention in different applications due to its interesting adsorption/desorption capabilities. The behavior of a zeolite 4A modified capacitor has been investigated for the adsorption of nitrogen (N₂), nitric oxide (NO) and 1,1-Difluoroethane (C₂H₄F₂), which are of interest in the field of chemical, biological, radiological, and nuclear threats. Sample measurements were carried out in different environmental conditions, and the variation of the sensor electric capacitance was investigated. The dielectric properties were influenced by the type and concentration of gas species in the environment. Higher changes in capacitance were shown during the adsorption of dry air (+4.2%) and fluorinated gas (+7.3%), while lower dielectric variations were found upon exposure to N₂ (−0.4%) and NO (−0.5%). The proposed approach pointed-out that a simple fabrication process may provide a convenient and affordable fabrication of reusable capacitive gas sensor. Full article

(This article belongs to the Special Issue Fabrication and Machining Technologies for Sensors)

► Show Figures

Figure 1

22 pages, 13332 KiB

Open AccessArticle

Surface Defect System for Long Product Manufacturing Using Differential Topographic Images

by F.J. delaCalle Herrero, Daniel F. García and Rubén Usamentiaga

Sensors 2020, 20(7), 2142; https://doi.org/10.3390/s20072142 - 10 Apr 2020

Cited by 7 | Viewed by 3340

Abstract

Current industrial products must meet quality requirements defined by international standards. Most commercial surface inspection systems give qualitative detections after a long, cumbersome and very expensive configuration process made by the seller company. In this paper, a new surface defect detection method is [...] Read more.

Current industrial products must meet quality requirements defined by international standards. Most commercial surface inspection systems give qualitative detections after a long, cumbersome and very expensive configuration process made by the seller company. In this paper, a new surface defect detection method is proposed based on 3D laser reconstruction. The method compares the long products, scan by scan, with their desired shape and produces differential topographic images of the surface at very high speeds. This work proposes a novel method where the values of the pixels in the images have a direct translation to real-world dimensions, which enables a detection based on the tolerances defined by international standards. These images are processed using computer vision techniques to detect defects and filter erroneous detections using both statistical distributions and a multilayer perceptron. Moreover, a systematic configuration procedure is proposed that is repeatable and can be performed by the manufacturer. The method has been tested using train track rails, which reports better results than two photometric systems including one commercial system, in both defect detection and erroneous detection rate. The method has been validated using a surface inspection rail pattern showing excellent performance. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

15 pages, 5955 KiB

Open AccessArticle

Wi-Fi CSI-Based Outdoor Human Flow Prediction Using a Support Vector Machine

by Masakatsu Ogawa and Hirofumi Munetomo

Sensors 2020, 20(7), 2141; https://doi.org/10.3390/s20072141 - 10 Apr 2020

Cited by 6 | Viewed by 3999

Abstract

This paper proposes a channel state information (CSI)-based prediction method of a human flow that includes activity. The objective of the paper is to predict a human flow in an outdoor road. This human flow prediction is useful for the prediction of the [...] Read more.

This paper proposes a channel state information (CSI)-based prediction method of a human flow that includes activity. The objective of the paper is to predict a human flow in an outdoor road. This human flow prediction is useful for the prediction of the number of passing people and their activity without privacy issues as a result of the absence of any camera systems. In this paper, we assume seven types of activities: one, two, and three people walking; one, two, and three people running; and one person cycling. Since the CSI can effectively express the effect of multipath fading in wireless signals, we expected the CSI to predict the various activities. In our proposed method, the amplitude and phase components are extracted from the measured CSI. The feature values for machine learning are the mean and variance of the maximum eigenvalue derived from the auto-correlation matrix and variance–covariance matrix composed of the amplitude or phase components and the passing time of flow. Using these feature values, we evaluated the prediction accuracy by leave-one-out cross-validation with a linear support vector machine (SVM). As a result, the proposed method achieved the maximum prediction accuracy of 100% for each direction and 99.5% for two directions. Full article

(This article belongs to the Special Issue Machine Learning Models for Wireless Network Monitoring and Data Analysis)

► Show Figures

Figure 1

16 pages, 28099 KiB

Open AccessArticle

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices

by Tomasz Hachaj

Sensors 2020, 20(7), 2140; https://doi.org/10.3390/s20072140 - 10 Apr 2020

Cited by 2 | Viewed by 31317

Abstract

This paper proposes a classifier designed for human facial feature annotation, which is capable of running on relatively cheap, low power consumption autonomous microcomputer systems. An autonomous system is one that depends only on locally available hardware and software—for example, it does not [...] Read more.

This paper proposes a classifier designed for human facial feature annotation, which is capable of running on relatively cheap, low power consumption autonomous microcomputer systems. An autonomous system is one that depends only on locally available hardware and software—for example, it does not use remote services available through the Internet. The proposed solution, which consists of a Histogram of Oriented Gradients (HOG) face detector and a set of neural networks, has comparable average accuracy and average true positive and true negative ratio to state-of-the-art deep neural network (DNN) architectures. However, contrary to DNNs, it is possible to easily implement the proposed method in a microcomputer with very limited RAM memory and without the use of additional coprocessors. The proposed method was trained and evaluated on a large 200,000 image face data set and compared with results obtained by other researchers. Further evaluation proves that it is possible to perform facial image attribute classification using the proposed algorithm on incoming video data captured by an RGB camera sensor of the microcomputer. The obtained results can be easily reproduced, as both the data set and source code can be downloaded. Developing and evaluating the proposed facial image annotation algorithm and its implementation, which is easily portable between various hardware and operating systems (virtually the same code works both on high-end PCs and microcomputers using the Windows and Linux platforms) and which is dedicated for low power consumption devices without coprocessors, is the main and novel contribution of this research. Full article

(This article belongs to the Section State-of-the-Art Sensors Technologies)

► Show Figures

Figure 1

21 pages, 11019 KiB

Open AccessArticle

The Gas Fire Temperature Measurement for Detection of an Object’s Presence on Top of the Burner

by Andrzej Milecki and Dominik Rybarczyk

Sensors 2020, 20(7), 2139; https://doi.org/10.3390/s20072139 - 10 Apr 2020

Cited by 3 | Viewed by 11592

Abstract

This article covers the topic of temperature measurement on top of a gas burner fire in order to recognize pot removal from a gas burner and subsequently, to cut off the gas supply. The possibility of applying a factory-mounted thermocouple was investigated with [...] Read more.

This article covers the topic of temperature measurement on top of a gas burner fire in order to recognize pot removal from a gas burner and subsequently, to cut off the gas supply. The possibility of applying a factory-mounted thermocouple was investigated with the assumption that its output signal could be used to detect the presence of a pot on a gas burner. However, the characteristic of such a thermocouple is not fully linear and as the research has shown that such a thermocouple would not fit enough for the assumed purpose, thus another sensor needs to be used. Therefore, in this paper, the linear thermocouple and IR diode are used. The best localizations of theses sensors were investigated in order to obtain a signal suitable for the pot presence recognition over the burner. These investigations are supported by the use of an infrared camera. In the investigations, the temperature changes also caused by casual air blast or caused by increasing and decreasing the valve opening are recorded and analyzed. Finally, the changes of the thermocouple’s signals are used as an input signal to propose an algorithm for pot absence recognition over the burner. The microprocessor-based circuit with a control unit for detection of the pot absence is designed, built and investigated. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

22 pages, 48850 KiB

Open AccessArticle

Vacant Parking Slot Detection in the Around View Image Based on Deep Learning

by Wei Li, Libo Cao, Lingbo Yan, Chaohui Li, Xiexing Feng and Peijie Zhao

Sensors 2020, 20(7), 2138; https://doi.org/10.3390/s20072138 - 10 Apr 2020

Cited by 48 | Viewed by 11533

Abstract

Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, [...] Read more.

Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parking slot detection method based on deep learning, namely VPS-Net. VPS-Net converts the vacant parking slot detection into a two-step problem, including parking slot detection and occupancy classification. In the parking slot detection stage, we propose a parking slot detection method based on YOLOv3, which combines the classification of the parking slot with the localization of marking points so that various parking slots can be directly inferred using geometric cues. In the occupancy classification stage, we design a customized network whose size of convolution kernel and number of layers are adjusted according to the characteristics of the parking slot. Experiments show that VPS-Net can detect various vacant parking slots with a precision rate of 99.63% and a recall rate of 99.31% in the ps2.0 dataset, and has a satisfying generalizability in the PSV dataset. By introducing a multi-object detection network and a classification network, VPS-Net can detect various vacant parking slots robustly. Full article

(This article belongs to the Section Sensor Networks)

► Show Figures

Figure 1

20 pages, 11395 KiB

Open AccessArticle

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

by Chenpu Li, Qianjian Xing and Zhenguo Ma

Sensors 2020, 20(7), 2137; https://doi.org/10.3390/s20072137 - 10 Apr 2020

Cited by 9 | Viewed by 3322

Abstract

In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning [...] Read more.

In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

17 pages, 2516 KiB

Open AccessArticle

Detection of Atrial Fibrillation Using 1D Convolutional Neural Network

by Chaur-Heh Hsieh, Yan-Shuo Li, Bor-Jiunn Hwang and Ching-Hua Hsiao

Sensors 2020, 20(7), 2136; https://doi.org/10.3390/s20072136 - 10 Apr 2020

Cited by 84 | Viewed by 7457

Abstract

The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which [...] Read more.

The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which results in heavy training computation and high implementation cost. This paper proposes an AF detection method based on an end-to-end 1D convolutional neural network (CNN) architecture to raise the detection accuracy and reduce network complexity. By investigating the impact of major components of a convolutional block on detection accuracy and using grid search to obtain optimal hyperparameters of the CNN, we develop a simple, yet effective 1D CNN. Since the dataset provided by PhysioNet Challenge 2017 contains ECG recordings with different lengths, we also propose a length normalization algorithm to generate equal-length records to meet the requirement of CNN. Experimental results and analysis indicate that our method of 1D CNN achieves an average F₁ score of 78.2%, which has better detection accuracy with lower network complexity, as compared with the existing deep learning-based methods. Full article

(This article belongs to the Special Issue Multimodal Data Fusion and Machine-Learning for Healthcare)

► Show Figures

Figure 1

29 pages, 8755 KiB

Open AccessReview

Chipless RFID Sensors for the Internet of Things: Challenges and Opportunities

by Viviana Mulloni and Massimo Donelli

Sensors 2020, 20(7), 2135; https://doi.org/10.3390/s20072135 - 10 Apr 2020

Cited by 83 | Viewed by 11886

Abstract

Radio-frequency identification (RFID) sensors are one of the fundamental components of the internet of things that aims at connecting every physical object to the cloud for the exchange of information. In this framework, chipless RFIDs are a breakthrough technology because they remove the [...] Read more.

Radio-frequency identification (RFID) sensors are one of the fundamental components of the internet of things that aims at connecting every physical object to the cloud for the exchange of information. In this framework, chipless RFIDs are a breakthrough technology because they remove the cost associated with the chip, being at the same time printable, passive, low-power and suitable for harsh environments. After the important results achieved with multibit chipless tags, there is a clear motivation and interest to extend the chipless sensing functionality to physical, chemical, structural and environmental parameters. These potentialities triggered a strong interest in the scientific and industrial community towards this type of application. Temperature and humidity sensors, as well as localization, proximity, and structural health prototypes, have already been demonstrated, and many other sensing applications are foreseen soon. In this review, both the different architectural approaches available for this technology and the requirements related to the materials employed for sensing are summarized. Then, the state-of-the-art of categories of sensors and their applications are reported and discussed. Finally, an analysis of the current limitations and possible solution strategies for this technology are given, together with an overview of expected future developments. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

16 pages, 4404 KiB

Open AccessArticle

Laser Patterning a Graphene Layer on a Ceramic Substrate for Sensor Applications

by Marcin Lebioda, Ryszard Pawlak, Witold Szymański, Witold Kaczorowski and Agata Jeziorna

Sensors 2020, 20(7), 2134; https://doi.org/10.3390/s20072134 - 10 Apr 2020

Cited by 11 | Viewed by 4009

Abstract

This paper describes a method for patterning the graphene layer and gold electrodes on a ceramic substrate using a Nd:YAG nanosecond fiber laser. The technique enables the processing of both layers and trimming of the sensor parameters. The main aim was to develop [...] Read more.

This paper describes a method for patterning the graphene layer and gold electrodes on a ceramic substrate using a Nd:YAG nanosecond fiber laser. The technique enables the processing of both layers and trimming of the sensor parameters. The main aim was to develop a technique for the effective and efficient shaping of both the sensory layer and the metallic electrodes. The laser shaping method is characterized by high speed and very good shape mapping, regardless of the complexity of the processing. Importantly, the technique enables the simultaneous shaping of both the graphene layer and Au electrodes in a direct process that does not require a complex and expensive masking process, and without damaging the ceramic substrate. Our results confirmed the effectiveness of the developed laser technology for shaping a graphene layer and Au electrodes. The ceramic substrate can be used in the construction of various types of sensors operating in a wide temperature range, especially the cryogenic range. Full article

(This article belongs to the Section Sensor Materials)

► Show Figures

Figure 1

12 pages, 1226 KiB

Open AccessArticle

Thin Film Encapsulation for RF MEMS in 5G and Modern Telecommunication Systems

by Anna Persano, Fabio Quaranta, Antonietta Taurino, Pietro Aleardo Siciliano and Jacopo Iannacci

Sensors 2020, 20(7), 2133; https://doi.org/10.3390/s20072133 - 10 Apr 2020

Cited by 15 | Viewed by 5311

Abstract

In this work, SiN_x/a-Si/SiN_x caps on conductive coplanar waveguides (CPWs) are proposed for thin film encapsulation of radio-frequency microelectromechanical systems (RF MEMS), in view of the application of these devices in fifth generation (5G) and modern telecommunication systems. Simplification and [...] Read more.

In this work, SiN_x/a-Si/SiN_x caps on conductive coplanar waveguides (CPWs) are proposed for thin film encapsulation of radio-frequency microelectromechanical systems (RF MEMS), in view of the application of these devices in fifth generation (5G) and modern telecommunication systems. Simplification and cost reduction of the fabrication process were obtained, using two etching processes in the same barrel chamber to create a matrix of holes through the capping layer and to remove the sacrificial layer under the cap. Encapsulating layers with etch holes of different size and density were fabricated to evaluate the removal of the sacrificial layer as a function of the percentage of the cap perforated area. Barrel etching process parameters also varied. Finally, a full three-dimensional finite element method-based simulation model was developed to predict the impact of fabricated thin film encapsulating caps on RF performance of CPWs. Full article

(This article belongs to the Special Issue RF-MEMS Solutions for Advanced Passive Components)

► Show Figures

Figure 1

12 pages, 1485 KiB

Open AccessArticle

Gait Characteristics under Imposed Challenge Speed Conditions in Patients with Parkinson’s Disease During Overground Walking

by Myeounggon Lee, Changhong Youm, Byungjoo Noh, Hwayoung Park and Sang-Myung Cheon

Sensors 2020, 20(7), 2132; https://doi.org/10.3390/s20072132 - 10 Apr 2020

Cited by 14 | Viewed by 3361

Abstract

Evaluating gait stability at slower or faster speeds and self-preferred speeds based on continuous steps may assist in determining the severity of motor symptoms in Parkinson’s disease (PD) patients. This study aimed to investigate the gait ability at imposed speed conditions in PD [...] Read more.

Evaluating gait stability at slower or faster speeds and self-preferred speeds based on continuous steps may assist in determining the severity of motor symptoms in Parkinson’s disease (PD) patients. This study aimed to investigate the gait ability at imposed speed conditions in PD patients during overground walking. Overall, 74 PD patients and 52 age-matched healthy controls were recruited. Levodopa was administered to patients in the PD group, and all participants completed imposed slower, preferred, and faster speed walking tests along a straight 15-m walkway wearing shoe-type inertial measurement units. Reliability of the slower and faster conditions between the estimated and measured speeds indicated excellent agreement for PD patients and controls. PD patients demonstrated higher gait asymmetry (GA) and coefficient of variance (CV) for stride length and stance phase than the controls at slower speeds and higher CVs for phases for single support, double support, and stance. CV of the double support phase could distinguish between PD patients and controls at faster speeds. The GA and CVs of stride length and phase-related variables were associated with motor symptoms in PD patients. Speed conditions should be considered during gait analysis. Gait variability could evaluate the severity of motor symptoms in PD patients. Full article

(This article belongs to the Special Issue Smart Sensors: Applications and Advances in Human Motion Analysis)

► Show Figures

Figure 1

14 pages, 12221 KiB

Open AccessArticle

Counting Cattle in UAV Images—Dealing with Clustered Animals and Animal/Background Contrast Changes

by Jayme Garcia Arnal Barbedo, Luciano Vieira Koenigkan, Patrícia Menezes Santos and Andrea Roberto Bueno Ribeiro

Sensors 2020, 20(7), 2126; https://doi.org/10.3390/s20072126 - 10 Apr 2020

Cited by 50 | Viewed by 6253

Abstract

The management of livestock in extensive production systems may be challenging, especially in large areas. Using Unmanned Aerial Vehicles (UAVs) to collect images from the area of interest is quickly becoming a viable alternative, but suitable algorithms for extraction of relevant information from [...] Read more.

The management of livestock in extensive production systems may be challenging, especially in large areas. Using Unmanned Aerial Vehicles (UAVs) to collect images from the area of interest is quickly becoming a viable alternative, but suitable algorithms for extraction of relevant information from the images are still rare. This article proposes a method for counting cattle which combines a deep learning model for rough animal location, color space manipulation to increase contrast between animals and background, mathematical morphology to isolate the animals and infer the number of individuals in clustered groups, and image matching to take into account image overlap. Using Nelore and Canchim breeds as a case study, the proposed approach yields accuracies over 90% under a wide variety of conditions and backgrounds. Full article

(This article belongs to the Section Remote Sensors)

► Show Figures

Figure 1

24 pages, 1772 KiB

Open AccessArticle

Mining Massive E-Health Data Streams for IoMT Enabled Healthcare Systems

by Affan Ahmed Toor, Muhammad Usman, Farah Younas, Alvis Cheuk M. Fong, Sajid Ali Khan and Simon Fong

Sensors 2020, 20(7), 2131; https://doi.org/10.3390/s20072131 - 9 Apr 2020

Cited by 36 | Viewed by 5566

Abstract

With the increasing popularity of the Internet-of-Medical-Things (IoMT) and smart devices, huge volumes of data streams have been generated. This study aims to address the concept drift, which is a major challenge in the processing of voluminous data streams. Concept drift refers to [...] Read more.

With the increasing popularity of the Internet-of-Medical-Things (IoMT) and smart devices, huge volumes of data streams have been generated. This study aims to address the concept drift, which is a major challenge in the processing of voluminous data streams. Concept drift refers to overtime change in data distribution. It may occur in the medical domain, for example the medical sensors measuring for general healthcare or rehabilitation, which may switch their roles for ICU emergency operations when required. Detecting concept drifts becomes trickier when the class distributions in data are skewed, which is often true for medical sensors e-health data. Reactive Drift Detection Method (RDDM) is an efficient method for detecting long concepts. However, RDDM has a high error rate, and it does not handle class imbalance. We propose an Enhanced Reactive Drift Detection Method (ERDDM), which systematically generates strategies to handle concept drift with class imbalance in data streams. We conducted experiments to compare ERDDM with three contemporary techniques in terms of prediction error, drift detection delay, latency, and ability to handle data imbalance. The experimentation was done in Massive Online Analysis (MOA) on 48 synthetic datasets customized to possess the capabilities of data streams. ERDDM can handle abrupt and gradual drifts and performs better than all benchmarks in almost all experiments. Full article

(This article belongs to the Special Issue Advanced Machine Learning Tools and Methods for IoMT Sensor Applications)

► Show Figures

Figure 1

14 pages, 6212 KiB

Open AccessArticle

Classification for Penicillium expansum Spoilage and Defect in Apples by Electronic Nose Combined with Chemometrics

by Zhiming Guo, Chuang Guo, Quansheng Chen, Qin Ouyang, Jiyong Shi, Hesham R. El-Seedi and Xiaobo Zou

Sensors 2020, 20(7), 2130; https://doi.org/10.3390/s20072130 - 9 Apr 2020

Cited by 31 | Viewed by 4067

Abstract

It is crucial for the efficacy of the apple storage to apply methods like electronic nose systems for detection and prediction of spoilage or infection by Penicillium expansum. Based on the acquisition of electronic nose signals, selected sensitive feature sensors of spoilage [...] Read more.

It is crucial for the efficacy of the apple storage to apply methods like electronic nose systems for detection and prediction of spoilage or infection by Penicillium expansum. Based on the acquisition of electronic nose signals, selected sensitive feature sensors of spoilage apple and all sensors were analyzed and compared by the recognition effect. Principal component analysis (PCA), principle component analysis-discriminant analysis (PCA-DA), linear discriminant analysis (LDA), partial least squares discriminate analysis (PLS-DA) and K-nearest neighbor (KNN) were used to establish the classification model of apple with different degrees of corruption. PCA-DA has the best prediction, the accuracy of training set and prediction set was 100% and 97.22%, respectively. synergy interval (SI), genetic algorithm (GA) and competitive adaptive reweighted sampling (CARS) are three selection methods used to accurately and quickly extract appropriate feature variables, while constructing a PLS model to predict plaque area. Among them, the PLS model with unique variables was optimized by CARS method, and the best prediction result of the area of the rotten apple was obtained. The best results are as follows: R_c = 0.953, root mean square error of calibration (RMSEC) = 1.28, R_p = 0.972, root mean square error of prediction (RMSEP) = 1.01. The results demonstrated that the electronic nose has a potential application in the classification of rotten apples and the quantitative detection of spoilage area. Full article

(This article belongs to the Special Issue Non-destructive Sensors and Machine Learning for Food Safety & Quality Inspection)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 20, Issue 7 (April-1 2020) – 354 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI