Next Issue
Volume 20, August-2
Previous Issue
Volume 20, July-2
 
 
sensors-logo

Journal Browser

Journal Browser

Sensors, Volume 20, Issue 15 (August-1 2020) – 290 articles

Cover Story (view full-size image): The adoption of Internet of Things (IoT) technologies in scenarios such as agriculture, coast preservation or connectivity survival against disasters involves the deployment of IoT devices in remote areas. The uneven relief of this zone makes it difficult to provide uniform coverage even using low-power wide area network (LPWAN) solutions, such as LoRa, due to the blockage of communication paths. In this work, we aim at mounting LPWAN gateways in drones in order to generate airborne network segments providing enhanced connectivity to sensor nodes wherever needed. The presented architecture takes advantage of multi-access edge computing (MEC) technologies to enable data preprocessing by virtualizing network functions on-board. Results showed notable coverage improvements by employing drone-mounted LoRa gateways when compared to traditional fixed LoRa infrastructure. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
22 pages, 7648 KiB  
Article
A Fault Diagnosis Approach for Rolling Bearing Integrated SGMD, IMSDE and Multiclass Relevance Vector Machine
by Xiaoan Yan, Ying Liu and Minping Jia
Sensors 2020, 20(15), 4352; https://doi.org/10.3390/s20154352 - 04 Aug 2020
Cited by 23 | Viewed by 3286
Abstract
The vibration signal induced by bearing local fault has strong nonstationary and nonlinear property, which indicates that the conventional methods are difficult to recognize bearing fault patterns effectively. Hence, to obtain an efficient diagnosis result, the paper proposes an intelligent fault diagnosis approach [...] Read more.
The vibration signal induced by bearing local fault has strong nonstationary and nonlinear property, which indicates that the conventional methods are difficult to recognize bearing fault patterns effectively. Hence, to obtain an efficient diagnosis result, the paper proposes an intelligent fault diagnosis approach for rolling bearing integrated symplectic geometry mode decomposition (SGMD), improved multiscale symbolic dynamic entropy (IMSDE) and multiclass relevance vector machine (MRVM). Firstly, SGMD is employed to decompose the original bearing vibration signal into several symplectic geometry components (SGC), which is aimed at reconstructing the original bearing vibration signal and achieving the purpose of noise reduction. Secondly, the bat algorithm (BA)-based optimized IMSDE is presented to evaluate the complexity of reconstruction signal and extract bearing fault features, which can solve the problems of missing of partial fault information existing in the original multiscale symbolic dynamic entropy (MSDE). Finally, IMSDE-based bearing fault features are fed to MRVM for achieving the identification of bearing fault categories. The validity of the proposed method is verified by the experimental and contrastive analysis. The results show that our approach can precisely identify different fault patterns of rolling bearings. Moreover, our approach can achieve higher recognition accuracy than several existing methods involved in this paper. This study provides a new research idea for improvement of bearing fault identification. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Graphical abstract

10 pages, 5530 KiB  
Letter
Wideband Dual-Polarized VHF Antenna for Space Observation Applications
by Alexandru Tatomirescu and Alina Badescu
Sensors 2020, 20(15), 4351; https://doi.org/10.3390/s20154351 - 04 Aug 2020
Cited by 4 | Viewed by 4847
Abstract
This work presents the design for an antenna element that can be used in radio arrays for the monitoring and detecting of radio emissions from cosmic particles’ interactions in the atmosphere. For these applications, the pattern stability over frequency is the primary design [...] Read more.
This work presents the design for an antenna element that can be used in radio arrays for the monitoring and detecting of radio emissions from cosmic particles’ interactions in the atmosphere. For these applications, the pattern stability over frequency is the primary design goal. The proposed antenna has a high gain over a relative bandwidth of 88%, a beamwidth of 2.13 steradians, a small group delay variation and a very stable radiation pattern across the frequency bandwidth of 110 to 190 MHz. It is dual polarized and has a simple mechanical structure which is easy and inexpensive to manufacture. The measurements show that the ground has insignificant impact on the overall radiation pattern. Full article
(This article belongs to the Special Issue Antennas and Propagation)
Show Figures

Figure 1

17 pages, 5856 KiB  
Article
Design of the VRLA Battery Real-Time Monitoring System Based on Wireless Communication
by Rui Lu, Jiwu Lu, Ping Liu, Min He and Jiangwei Liu
Sensors 2020, 20(15), 4350; https://doi.org/10.3390/s20154350 - 04 Aug 2020
Cited by 4 | Viewed by 4719
Abstract
The VRLA (valve-regulated lead-acid) battery is an important part of a direct current (DC) power system. In order to resolve issues of large volume, complicated wiring, and single function for a battery monitoring system at present, we propose to build a novel intelligent-health-monitoring [...] Read more.
The VRLA (valve-regulated lead-acid) battery is an important part of a direct current (DC) power system. In order to resolve issues of large volume, complicated wiring, and single function for a battery monitoring system at present, we propose to build a novel intelligent-health-monitoring system. The system is based on the ZigBee wireless communication module for collecting voltage, temperature, internal resistance, and battery current in real-time. A general packet radio service (GPRS) network is employed for interacting data with the cloud-monitoring platform. The system can predict the remaining capacity of the battery combined with the software algorithm for realizing real-time monitoring of the battery’s health status and fault-warning, providing a basis for ensuring the safe and reliable operation of the battery. In addition, the system effectively integrates most of the circuits of the battery status collector onto one chip, which greatly reduces the size and the power consumption of the collector and also provides a possibility for embedding each VRLA battery with a chip that can monitor the health status during the whole life. The test results indicate that the system has the characteristics of real-time monitoring, high precision, small-volume, and comprehensive functions. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

18 pages, 2032 KiB  
Article
LdsConv: Learned Depthwise Separable Convolutions by Group Pruning
by Wenxiang Lin, Yan Ding, Hua-Liang Wei, Xinglin Pan and Yutong Zhang
Sensors 2020, 20(15), 4349; https://doi.org/10.3390/s20154349 - 04 Aug 2020
Cited by 1 | Viewed by 3825
Abstract
Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity [...] Read more.
Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning. It integrates the pruning technique into the design of convolutional filters, formulated as a generic convolutional unit that can be used as a direct replacement of convolutions without any adjustments of the architecture. To show the effectiveness of the proposed method, experiments are carried out using the state-of-the-art convolutional neural networks (CNNs), including ResNet, DenseNet, SE-ResNet and MobileNet, respectively. The results show that by simply replacing the original convolution with LdsConv in these CNNs, it can achieve a significantly improved accuracy while reducing computational cost. For the case of ResNet50, the FLOPs can be reduced by 40.9%, meanwhile the accuracy on the associated ImageNet increases. Full article
(This article belongs to the Special Issue Visual and Camera Sensors)
Show Figures

Figure 1

16 pages, 989 KiB  
Review
Enabling Older Adults’ Health Self-Management through Self-Report and Visualization—A Systematic Literature Review
by Gabriela Cajamarca, Valeria Herskovic and Pedro O. Rossel
Sensors 2020, 20(15), 4348; https://doi.org/10.3390/s20154348 - 04 Aug 2020
Cited by 17 | Viewed by 4690
Abstract
Aging is associated with a progressive decline in health, resulting in increased medical care and costs. Mobile technology may facilitate health self-management, thus increasing the quality of care and reducing costs. Although the development of technology offers opportunities in monitoring the health of [...] Read more.
Aging is associated with a progressive decline in health, resulting in increased medical care and costs. Mobile technology may facilitate health self-management, thus increasing the quality of care and reducing costs. Although the development of technology offers opportunities in monitoring the health of older adults, it is not clear whether these technologies allow older adults to manage their health data themselves. This paper presents a review of the literature on mobile health technologies for older adults, focusing on whether these technologies enable the visualization of monitored data and the self-reporting of additional information by the older adults. The systematic search considered studies published between 2009 and 2019 in five online databases. We screened 609 articles and identified 95 that met our inclusion and exclusion criteria. Smartphones and tablets are the most frequently reported technology for older adults to enter additional data to the one that is monitored automatically. The recorded information is displayed on the monitoring device and screens of external devices such as computers. Future designs of mobile health technology should allow older users to enter additional information and visualize data; this could enable them to understand their own data as well as improve their experience with technology. Full article
(This article belongs to the Special Issue Selected Papers from UCAmI 2019)
Show Figures

Figure 1

12 pages, 2845 KiB  
Letter
Influence of Surface and Bulk Defects on Contactless Resistivity Measurements of CdTe and Related Compounds
by Jan Franc, Roman Grill and Jakub Zázvorka
Sensors 2020, 20(15), 4347; https://doi.org/10.3390/s20154347 - 04 Aug 2020
Viewed by 2275
Abstract
We analyzed the influence of parameters of deep levels in the bulk and conditions on the surface on transient charge responses of semi-insulating samples (CdTe and GaAs). We studied the dependence on the applied bias step used for the experimental evaluation of resistivity [...] Read more.
We analyzed the influence of parameters of deep levels in the bulk and conditions on the surface on transient charge responses of semi-insulating samples (CdTe and GaAs). We studied the dependence on the applied bias step used for the experimental evaluation of resistivity in contactless measurement setups. We used simulations based on simultaneous solutions of 1D drift diffusion and Poisson’s equations as the main investigation tool. We found out that the resistivity can be reliably determined by the transient contactless method in materials with a large density of deep levels in the bulk (e.g., semi-insulating GaAs) when the response curve is described by a single exponential. In contrast, the materials with the low deep-level density, like semiconductor radiation detector materials (e.g., CdTe, CdZnTe, etc.), usually exhibit a complex response to applied bias, depending on the surface conditions. We show that a single exponential fit does not represent the true relaxation time and resistivity, in this case. A two-exponential fit can be used for a rough estimate of bulk material resistivity only in a limit of low-applied bias, when the response curve approaches a single-exponential shape. A decreasing of the bias leads to a substantially improved agreement between the evaluated and true relaxation time, which is also consistent with the approaching of the relaxation curve to the single-exponential shape. Full article
Show Figures

Figure 1

18 pages, 5434 KiB  
Article
Walking Strategies and Performance Evaluation for Human-Exoskeleton Systems under Admittance Control
by Chiawei Liang and Tesheng Hsiao
Sensors 2020, 20(15), 4346; https://doi.org/10.3390/s20154346 - 04 Aug 2020
Cited by 5 | Viewed by 2674
Abstract
Lower-limb exoskeletons as walking assistive devices have been intensively investigated in recent decades. In these studies, intention detection and performance evaluation are important topics. In our previous studies, we proposed a disturbance observer (DOB)-based torque estimation algorithm and an admittance control law to [...] Read more.
Lower-limb exoskeletons as walking assistive devices have been intensively investigated in recent decades. In these studies, intention detection and performance evaluation are important topics. In our previous studies, we proposed a disturbance observer (DOB)-based torque estimation algorithm and an admittance control law to shape the admittance of the human-exoskeleton system (HES) and comply with the user’s walking intention. These algorithms have been experimentally verified under the condition of no ground reaction force (GRF) in our previous studies. In this paper, we devised and integrated with the exoskeleton control system a sensing and communication module on each foot to measure and compensate for GRF. Rigorous theoretical analysis was performed and the sufficient conditions for the robust stability of the closed-loop system were derived. Then, we conducted level ground assistive walking repeatedly with different test subjects and exhaustive combinations of admittance parameters. In addition, we proposed two tractable and physically insightful performance indices called normalized energy consumption index (NECI) and walking distance in a fixed period of time to quantitatively evaluate the performance for different admittance parameters. We also compared the energy consumption for users walking with and without the exoskeleton. The results show that the proposed admittance control law reduces the energy consumption of the user during level ground walking. Full article
(This article belongs to the Special Issue Sensor-Based Assistive Devices and Technology)
Show Figures

Figure 1

13 pages, 5274 KiB  
Article
Estimating Vertical Ground Reaction Force during Walking Using a Single Inertial Sensor
by Xianta Jiang, Christopher Napier, Brett Hannigan, Janice J. Eng and Carlo Menon
Sensors 2020, 20(15), 4345; https://doi.org/10.3390/s20154345 - 04 Aug 2020
Cited by 24 | Viewed by 6008
Abstract
The vertical ground reaction force (vGRF) and its passive and active peaks are important gait parameters and of great relevance for musculoskeletal injury analysis and prevention, the detection of gait abnormities, and the evaluation of lower-extremity prostheses. Most currently available methods to estimate [...] Read more.
The vertical ground reaction force (vGRF) and its passive and active peaks are important gait parameters and of great relevance for musculoskeletal injury analysis and prevention, the detection of gait abnormities, and the evaluation of lower-extremity prostheses. Most currently available methods to estimate the vGRF require a force plate. However, in real-world scenarios, gait monitoring would not be limited to a laboratory setting. This paper reports a novel solution using machine learning algorithms to estimate the vGRF and the timing and magnitude of its peaks from data collected by a single inertial measurement unit (IMU) on one of the lower limb locations. Nine volunteers participated in this study, walking on a force plate-instrumented treadmill at various speeds. Four IMUs were worn on the foot, shank, distal thigh, and proximal thigh, respectively. A random forest model was employed to estimate the vGRF from data collected by each of the IMUs. We evaluated the performance of the models against the gold standard measurement of the vGRF generated by the treadmill. The developed model achieved a high accuracy with a correlation coefficient, root mean square error, and normalized root mean square error of 1.00, 0.02 body weight (BW), and 1.7% in intra-participant testing, and 0.97, 0.10 BW, and 7.15% in inter-participant testing, respectively, for the shank location. The difference between the reference and estimated passive force peak values was 0.02 BW and 0.14 BW with a delay of −0.14% and 0.57% of stance duration for the intra- and inter-participant testing, respectively; the difference between the reference and estimated active force peak values was 0.02 BW and 0.08 BW with a delay of 0.45% and 1.66% of stance duration for the intra- and inter-participant evaluation, respectively. We concluded that vertical ground reaction force can be estimated using only a single IMU via machine learning algorithms. This research sheds light on the development of a portable wearable gait monitoring system reporting the real-time vGRF in real-life scenarios. Full article
(This article belongs to the Collection Sensors for Gait, Human Movement Analysis, and Health Monitoring)
Show Figures

Figure 1

15 pages, 9500 KiB  
Article
Design of a Large-Scale Piezoelectric Transducer Network Layer and Its Reliability Verification for Space Structures
by Yuanqiang Ren, Jingya Tao and Zhaopeng Xue
Sensors 2020, 20(15), 4344; https://doi.org/10.3390/s20154344 - 04 Aug 2020
Cited by 6 | Viewed by 3044
Abstract
As an effective structural health monitoring (SHM) technology, the piezoelectric transducer (PZT) and guided wave-based monitoring methods have attracted growing interest in the space field. When facing the large-scale monitoring requirements of space structures, a lot of PZTs are needed and may cause [...] Read more.
As an effective structural health monitoring (SHM) technology, the piezoelectric transducer (PZT) and guided wave-based monitoring methods have attracted growing interest in the space field. When facing the large-scale monitoring requirements of space structures, a lot of PZTs are needed and may cause problems regarding to additional weight of connection cables, placement efficiency and performance consistency. The PZT layer is a promising solution against these problems. However, the current PZT layers still face challenges from large-scale lightweight monitoring and the lack of reliability assessment under extreme space service conditions. In this paper, a large-scale PZT network layer (LPNL) design method is proposed to overcome these challenges, by adopting a large-scale lightweight PZT network design method and network splitting–recombination based integration strategy. The developed LPNL offers the advantages of being large size, lightweight, ultra-thin, flexible, customized in shape and highly reliable. A series of extreme environmental tests are performed to verify the reliability of the developed LPNL under space service environment, including extreme temperature conditions, vibration at different flying phases, landing impact, and flying overload. Results show that the developed LPNL can withstand these harsh environmental conditions and presents high reliability and functionality. Full article
(This article belongs to the Special Issue Piezoelectric Transducers Based Structural Health Monitoring)
Show Figures

Figure 1

16 pages, 10497 KiB  
Article
Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM
by Franco Hidalgo and Thomas Bräunl
Sensors 2020, 20(15), 4343; https://doi.org/10.3390/s20154343 - 04 Aug 2020
Cited by 24 | Viewed by 3759
Abstract
Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, [...] Read more.
Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, but not extensively for underwater scenarios. In this paper (I) we characterize underwater images where light and suspended particles alter considerably the images captured, (II) evaluate the performance of common interest points detectors and descriptors in a variety of underwater scenes and conditions towards vSLAM in terms of the number of features matched in subsequent video frames, the precision of the descriptors and the processing time. This research justifies the usage of feature detectors in vSLAM for underwater scenarios and present its challenges and limitations. Full article
(This article belongs to the Special Issue Intelligence and Autonomy for Underwater Robotic Vehicles)
Show Figures

Figure 1

19 pages, 2744 KiB  
Article
Methodology for Energy Optimization in Wastewater Treatment Plants. Phase III: Implementation of an Integral Control System for the Aeration Stage in the Biological Process of Activated Sludge and the Membrane Biological Reactor
by Ana Belén Lozano Avilés, Francisco Del Cerro Velázquez and Mercedes Lloréns Pascual del Riquelme
Sensors 2020, 20(15), 4342; https://doi.org/10.3390/s20154342 - 04 Aug 2020
Cited by 5 | Viewed by 3443
Abstract
The proposed methodology for optimizing energy efficiency, based on good management of the aeration process through the implementation of an appropriate control strategy, achieved reductions of more than 40% in energy consumption at the San Pedro del Pinatar Wastewater Treatment Plant (WWTP) (Murcia, [...] Read more.
The proposed methodology for optimizing energy efficiency, based on good management of the aeration process through the implementation of an appropriate control strategy, achieved reductions of more than 40% in energy consumption at the San Pedro del Pinatar Wastewater Treatment Plant (WWTP) (Murcia, Spain). Phases I and II of this methodology managed to reduce the oxygen needs of the microorganisms in the biological system, optimize the efficiency of oxygen transfer to the biological reactor and redesign the installation to correct abnormal energy loss situations. In addition, we established the basis for Phase III, which implemented a control strategy to achieve stable values close to the setpoints of the fundamental operating parameters of the aeration process. The control system is based on the measurements recorded by strategically installed sensors and mathematical algorithms based on models, achieving an expert adaptive-predictive system that regulates aeration both in the biological stage by activated sludge and the aeration of the installed ultrafiltration membrane system. The objectives were: (i) to achieve automatic execution of the best management strategy; (ii) to reduce the energy demand; (iii) to improve the operation and stability of the process; (iv) to reduce operating costs; and (v) to contribute to the fulfillment of the sustainable development objectives. Full article
(This article belongs to the Section Chemical Sensors)
Show Figures

Figure 1

19 pages, 500 KiB  
Article
Evaluation of an IoT Application-Scoped Access Control Model over a Publish/Subscribe Architecture Based on FIWARE
by Alejandro Pozo, Álvaro Alonso and Joaquín Salvachúa
Sensors 2020, 20(15), 4341; https://doi.org/10.3390/s20154341 - 04 Aug 2020
Cited by 6 | Viewed by 2921
Abstract
The Internet of Things (IoT) brings plenty of opportunities to enhance society’s activities, from improving a factory’s production chain to facilitating people’s household tasks. However, it has also brought new security breaches, compromising privacy and authenticity. IoT devices are vulnerable to being accessed [...] Read more.
The Internet of Things (IoT) brings plenty of opportunities to enhance society’s activities, from improving a factory’s production chain to facilitating people’s household tasks. However, it has also brought new security breaches, compromising privacy and authenticity. IoT devices are vulnerable to being accessed from the Internet; they lack sufficient resources to face cyber-attack threats. Keeping a balance between access control and the devices’ resource consumption has become one of the highest priorities of IoT research. In this paper, we evaluate an access control architecture based on the IAACaaS (IoT application-Scoped Access Control as a Service) model with the aim of protecting IoT devices that communicate using the Publish/Subscribe pattern. IAACaaS is based on the OAuth 2.0 authorization framework, which externalizes the identity and access control infrastructure of applications. In our evaluation, we implement the model using FIWARE Generic Enablers and deploy them for a smart buildings use case with a wireless communication. Then, we compare the performance of two different approaches in the data-sharing between sensors and the Publish/Subscribe broker, using Constrained Application Protocol (CoAP) and Hypertext Transfer Protocol (HTTP) protocols. We conclude that the integration of Publish/Subscribe IoT deployments with IAACaaS adds an extra layer of security and access control without compromising the system’s performance. Full article
(This article belongs to the Special Issue Security and Privacy in Wireless Sensor Network)
Show Figures

Figure 1

11 pages, 2420 KiB  
Letter
Non-Enzymatic Glucose Sensing Based on Incorporation of Carbon Nanotube into Zn-Co-S Ball-in-Ball Hollow Sphere
by Han-Wei Chang, Chia-Wei Su, Jia-Hao Tian and Yu-Chen Tsai
Sensors 2020, 20(15), 4340; https://doi.org/10.3390/s20154340 - 04 Aug 2020
Cited by 8 | Viewed by 2898
Abstract
Zn-Co-S ball-in-ball hollow sphere (BHS) was successfully prepared by solvothermal sulfurization method. An efficient strategy to synthesize Zn-Co-S BHS consisted of multilevel structures by controlling the ionic exchange reaction was applied to obtain great performance electrode material. Carbon nanotubes (CNTs) as a conductive [...] Read more.
Zn-Co-S ball-in-ball hollow sphere (BHS) was successfully prepared by solvothermal sulfurization method. An efficient strategy to synthesize Zn-Co-S BHS consisted of multilevel structures by controlling the ionic exchange reaction was applied to obtain great performance electrode material. Carbon nanotubes (CNTs) as a conductive agent were uniformly introduced with Zn-Co-S BHS to form Zn-Co-S BHS/CNTs and expedited the considerable electrocatalytic behavior toward glucose electro-oxidation in alkaline medium. In this study, characterization with scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray photoelectron spectroscopy (XPS), and X-ray diffraction (XRD) was used for investigating the morphological and physical/chemical properties and further evaluating the feasibility of Zn-Co-S BHS/CNTs in non-enzymatic glucose sensing. Electrochemical methods (cyclic voltammetry (CV) and chronoamperometry (CA)) were performed to investigate the glucose sensing performance of Zn-Co-S BHS/CNTs. The synergistic effect of Faradaic redox couple species of Zn-Co-S BHS and unique conductive network of CNTs exhibited excellent electrochemical catalytic ability towards the glucose electro-oxidation, which revealed linear range from 5 to 100 μM with high sensitivity of 2734.4 μA mM−1 cm−2, excellent detection limit of 2.98 μM, and great selectivity in the presence of dopamine, uric acid, ascorbic acid, and fructose. Thus, Zn-Co-S BHS/CNTs would be expected to be a promising material for non-enzymatic glucose sensing. Full article
(This article belongs to the Section Nanosensors)
Show Figures

Graphical abstract

14 pages, 3579 KiB  
Article
Wristbands Containing Accelerometers for Objective Arm Swing Analysis in Patients with Parkinson’s Disease
by Domiciano Rincón, Jaime Valderrama, Maria Camila González, Beatriz Muñoz, Jorge Orozco, Linda Montilla, Yor Castaño and Andrés Navarro
Sensors 2020, 20(15), 4339; https://doi.org/10.3390/s20154339 - 04 Aug 2020
Cited by 10 | Viewed by 4058
Abstract
In patients with Parkinson’s disease (PD), arm swing changes are common, even in the early stages, and these changes are usually evaluated subjectively by an expert. In this article, hypothesize that arm swing changes can be detected using a low-cost, cloud-based, wearable, sensor [...] Read more.
In patients with Parkinson’s disease (PD), arm swing changes are common, even in the early stages, and these changes are usually evaluated subjectively by an expert. In this article, hypothesize that arm swing changes can be detected using a low-cost, cloud-based, wearable, sensor system that incorporates triaxial accelerometers. The aim of this work is to develop a low-cost, assistive diagnostic tool for use in quantifying the arm swing kinematics of patients with PD. Ten patients with PD and 11 age-matched, healthy subjects are included in the study. Four feature extraction techniques were applied: (i) Asymmetry estimation based on root mean square (RMS) differences between arm movements; (ii) posterior–anterior phase and cycle regularity through autocorrelation; (iii) tremor energy, established using Fourier transform analysis; and (iv) signal complexity through the fractal dimension by wavelet analysis. The PD group showed significant (p < 0.05) reductions in arm swing RMS values, higher arm swing asymmetry, higher anterior–posterior phase regularities, greater “high energy frequency” signals, and higher complexity in their XZ plane signals. Therefore, the novel, portable system provides a reliable means to support clinical practice in PD assessment. Full article
(This article belongs to the Special Issue Wearable Motion Sensors Applied in Older Adults)
Show Figures

Figure 1

21 pages, 4851 KiB  
Article
Robust Fine Registration of Multisensor Remote Sensing Images Based on Enhanced Subpixel Phase Correlation
by Zhen Ye, Jian Kang, Jing Yao, Wenping Song, Sicong Liu, Xin Luo, Yusheng Xu and Xiaohua Tong
Sensors 2020, 20(15), 4338; https://doi.org/10.3390/s20154338 - 04 Aug 2020
Cited by 18 | Viewed by 3432
Abstract
Automatic fine registration of multisensor images plays an essential role in many remote sensing applications. However, it is always a challenging task due to significant radiometric and textural differences. In this paper, an enhanced subpixel phase correlation method is proposed, which embeds phase [...] Read more.
Automatic fine registration of multisensor images plays an essential role in many remote sensing applications. However, it is always a challenging task due to significant radiometric and textural differences. In this paper, an enhanced subpixel phase correlation method is proposed, which embeds phase congruency-based structural representation, L1-norm-based rank-one matrix approximation with adaptive masking, and stable robust model fitting into the conventional calculation framework in the frequency domain. The aim is to improve the accuracy and robustness of subpixel translation estimation in practical cases. In addition, template matching using the enhanced subpixel phase correlation is integrated to realize reliable fine registration, which is able to extract a sufficient number of well-distributed and high-accuracy tie points and reduce the local misalignment for coarsely coregistered multisensor remote sensing images. Experiments undertaken with images from different satellites and sensors were carried out in two parts: tie point matching and fine registration. The results of qualitative analysis and quantitative comparison with the state-of-the-art area-based and feature-based matching methods demonstrate the effectiveness and reliability of the proposed method for multisensor matching and registration. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

23 pages, 9015 KiB  
Article
A Data Fusion Modeling Framework for Retrieval of Land Surface Temperature from Landsat-8 and MODIS Data
by Guohui Zhao, Yaonan Zhang, Junlei Tan, Cong Li and Yanrun Ren
Sensors 2020, 20(15), 4337; https://doi.org/10.3390/s20154337 - 04 Aug 2020
Cited by 8 | Viewed by 3377
Abstract
Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a [...] Read more.
Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies. Full article
(This article belongs to the Special Issue Satellite Remote Sensing in Environmental Monitoring)
Show Figures

Figure 1

18 pages, 682 KiB  
Article
LoRaWAN Gateway Placement Model for Dynamic Internet of Things Scenarios
by Nagib Matni, Jean Moraes, Helder Oliveira, Denis Rosário and Eduardo Cerqueira
Sensors 2020, 20(15), 4336; https://doi.org/10.3390/s20154336 - 04 Aug 2020
Cited by 25 | Viewed by 4821
Abstract
Extended Range Wide Area Network (LoRaWAN) has recently gained a lot of attention from the industrial and research community for dynamic Internet of Things (IoT) applications. IoT devices broadcast messages for neighbor gateways that deliver the message to the application server through an [...] Read more.
Extended Range Wide Area Network (LoRaWAN) has recently gained a lot of attention from the industrial and research community for dynamic Internet of Things (IoT) applications. IoT devices broadcast messages for neighbor gateways that deliver the message to the application server through an IP network. Hence, it is required to deploy LoRaWAN gateways, i.e., network planning, and optimization, in an environment while considering Operational Expenditure (OPEX) and Capital Expenditure (CAPEX) along with Quality of Service (QoS) requirements. In this article, we introduced a LoRaWAN gateway placement model for dynamic IoT applications called DPLACE. It divides the IoT devices into groups with some degree of similarity between them to allow for the placement of LoRaWAN gateways that can serve these devices in the best possible way. Specifically, DPLACE computes the number of LoRaWAN gateways based on the Gap statistics method. Afterward, DPLACE uses K-Means and Fuzzy C-means algorithms to calculate the LoRaWAN gateway placement. The simulations’ results proved the benefits of DPLACE compared to state-of-the-art LoRaWAN gateway placement models in terms of OPEX, CAPEX, and QoS. Full article
(This article belongs to the Special Issue LoRa Sensor Network)
Show Figures

Figure 1

25 pages, 7575 KiB  
Article
10 MHz Thin-Film PZT-Based Flexible PMUT Array: Finite Element Design and Characterization
by Jeong Nyeon Kim, Tianning Liu, Thomas N. Jackson, Kyusun Choi, Susan Trolier-McKinstry, Richard L. Tutwiler and Judith A. Todd
Sensors 2020, 20(15), 4335; https://doi.org/10.3390/s20154335 - 04 Aug 2020
Cited by 7 | Viewed by 4820
Abstract
Piezoelectric micromachined ultrasound transducers (PMUT) incorporating lead zirconate titanate PbZr0.52Ti0.48O3 (PZT) thin films were investigated for miniaturized high-frequency ultrasound systems. A recently developed process to remove a PMUT from an underlying silicon (Si) substrate has enabled curved arrays [...] Read more.
Piezoelectric micromachined ultrasound transducers (PMUT) incorporating lead zirconate titanate PbZr0.52Ti0.48O3 (PZT) thin films were investigated for miniaturized high-frequency ultrasound systems. A recently developed process to remove a PMUT from an underlying silicon (Si) substrate has enabled curved arrays to be readily formed. This research aimed to improve the design of flexible PMUT arrays using PZFlex, a finite element method software package. A 10 MHz PMUT 2D array working in 3-1 mode was designed. A circular unit-cell was structured from the top, with concentric layers of platinum (Pt)/PZT/Pt/titanium (Ti) on a polyimide (PI) substrate. Pulse-echo and spectral response analyses predicted a center frequency of 10 MHz and bandwidth of 87% under water load and air backing. A 2D array, consisting of the 256 (16 × 16) unit-cells, was created and characterized in terms of pulse-echo and spectral responses, surface displacement profiles, crosstalk, and beam profiles. The 2D array showed: decreased bandwidth due to protracted oscillation decay and guided wave effects; mechanical focal length at 2.9 mm; 3.7 mm depth of field for -6 dB; and -55.6 dB crosstalk. Finite element-based virtual prototyping identified figures of merit—center frequency, bandwidth, depth of field, and crosstalk—that could be optimized to design robust, flexible PMUT arrays. Full article
(This article belongs to the Section Electronic Sensors)
Show Figures

Figure 1

15 pages, 859 KiB  
Article
An Irregular Graph Based Network Code for Low-Latency Content Distribution
by Weiwei Yang and Ye Li
Sensors 2020, 20(15), 4334; https://doi.org/10.3390/s20154334 - 04 Aug 2020
Cited by 1 | Viewed by 1989
Abstract
To fulfill the increasing demand on low-latency content distribution, this paper considers content distribution using generation-based network coding with the belief propagation decoder. We propose a framework to design generation-based network codes via characterizing them as building an irregular graph, and design the [...] Read more.
To fulfill the increasing demand on low-latency content distribution, this paper considers content distribution using generation-based network coding with the belief propagation decoder. We propose a framework to design generation-based network codes via characterizing them as building an irregular graph, and design the code by evaluating the graph. The and-or tree evaluation technique is extended to analyze the decoding performance. By allowing for non-constant generation sizes, we formulate optimization problems based on the analysis to design degree distributions from which generation sizes are drawn. Extensive simulation results show that the design may achieve both low decoding cost and transmission overhead as compared to existing schemes using constant generation sizes, and satisfactory decoding speed can be achieved. The scheme would be of interest to scenarios where (1) the network topology is not known, dynamically changing, and/or has cycles due to cooperation between end users, and (2) computational/memory costs of nodes are of concern but network transmission rate is spare. Full article
(This article belongs to the Section Internet of Things)
Show Figures

Figure 1

20 pages, 1182 KiB  
Article
Iterative Learning Control for a Soft Exoskeleton with Hip and Knee Joint Assistance
by Chunjie Chen, Yu Zhang, Yanjie Li, Zhuo Wang, Yida Liu, Wujing Cao and Xinyu Wu
Sensors 2020, 20(15), 4333; https://doi.org/10.3390/s20154333 - 04 Aug 2020
Cited by 34 | Viewed by 6103
Abstract
Walking on different terrains leads to different biomechanics, which motivates the development of exoskeletons for assisting on walking according to the type of a terrain. The design of a lightweight soft exoskeleton that simultaneously assists multiple joints in the lower limb is presented [...] Read more.
Walking on different terrains leads to different biomechanics, which motivates the development of exoskeletons for assisting on walking according to the type of a terrain. The design of a lightweight soft exoskeleton that simultaneously assists multiple joints in the lower limb is presented in this paper. It is used to assist both hip and knee joints in a single system, the assistance force is directly applied to the hip joint flexion and the knee joint extension, while indirectly to the hip extension also. Based on the biological torque of human walking at three different slopes, a novel strategy is developed to improve the performance of assistance. A parameter optimal iterative learning control (POILC) method is introduced to reduce the error generated due to the difference between the wearing position and the biological features of the different wearers. In order to obtain the metabolic rate, three subjects walked on a treadmill, for 10 min on each terrain, at a speed of 4 km/h under both conditions of wearing and not wearing the soft exoskeleton. Results showed that the metabolic rate was decreased with the increasing slope of the terrain. The reductions in the net metabolic rate in the experiments on the downhill, flat ground, and uphill were, respectively, 9.86%, 12.48%, and 22.08% compared to the condition of not wearing the soft exoskeleton, where their corresponding absolute values were 0.28 W/kg, 0.72 W/kg, and 1.60 W/kg. Full article
(This article belongs to the Special Issue Wearable Devices: Applications in Older Adults)
Show Figures

Figure 1

17 pages, 4778 KiB  
Article
Distribution Transformer Parameters Detection Based on Low-Frequency Noise, Machine Learning Methods, and Evolutionary Algorithm
by Daniel Jancarczyk, Marcin Bernaś and Tomasz Boczar
Sensors 2020, 20(15), 4332; https://doi.org/10.3390/s20154332 - 04 Aug 2020
Cited by 8 | Viewed by 3079
Abstract
The paper proposes a method of automatic detection of parameters of a distribution transformer (model, type, and power) from a distance, based on its low-frequency noise spectra. The spectra are registered by sensors and processed by a method based on evolutionary algorithms and [...] Read more.
The paper proposes a method of automatic detection of parameters of a distribution transformer (model, type, and power) from a distance, based on its low-frequency noise spectra. The spectra are registered by sensors and processed by a method based on evolutionary algorithms and machine learning. The method, as input data, uses the frequency spectra of sound pressure levels generated during operation by transformers in the real environment. The model also uses the background characteristic to take under consideration the changing working conditions of the transformers. The method searches for frequency intervals and its resolution using both a classic genetic algorithm and particle swarm optimization. The interval selection was verified using five state-of-the-art machine learning algorithms. The research was conducted on 16 different distribution transformers. As a result, a method was proposed that allows the detection of a specific transformer model, its type, and its power with an accuracy greater than 84%, 99%, and 87%, respectively. The proposed optimization process using the genetic algorithm increased the accuracy by up to 5%, at the same time reducing the input data set significantly (from 80% up to 98%). The machine learning algorithms were selected, which were proven efficient for this task. Full article
Show Figures

Figure 1

30 pages, 25100 KiB  
Article
Autonomous Scene Exploration for Robotics: A Conditional Random View-Sampling and Evaluation Using a Voxel-Sorting Mechanism for Efficient Ray Casting
by João Santos, Miguel Oliveira, Rafael Arrais and Germano Veiga
Sensors 2020, 20(15), 4331; https://doi.org/10.3390/s20154331 - 04 Aug 2020
Cited by 5 | Viewed by 3150
Abstract
Carrying out the task of the exploration of a scene by an autonomous robot entails a set of complex skills, such as the ability to create and update a representation of the scene, the knowledge of the regions of the scene which are [...] Read more.
Carrying out the task of the exploration of a scene by an autonomous robot entails a set of complex skills, such as the ability to create and update a representation of the scene, the knowledge of the regions of the scene which are yet unexplored, the ability to estimate the most efficient point of view from the perspective of an explorer agent and, finally, the ability to physically move the system to the selected Next Best View (NBV). This paper proposes an autonomous exploration system that makes use of a dual OcTree representation to encode the regions in the scene which are occupied, free, and unknown. The NBV is estimated through a discrete approach that samples and evaluates a set of view hypotheses that are created by a conditioned random process which ensures that the views have some chance of adding novel information to the scene. The algorithm uses ray-casting defined according to the characteristics of the RGB-D sensor, and a mechanism that sorts the voxels to be tested in a way that considerably speeds up the assessment. The sampled view that is estimated to provide the largest amount of novel information is selected, and the system moves to that location, where a new exploration step begins. The exploration session is terminated when there are no more unknown regions in the scene or when those that exist cannot be observed by the system. The experimental setup consisted of a robotic manipulator with an RGB-D sensor assembled on its end-effector, all managed by a Robot Operating System (ROS) based architecture. The manipulator provides movement, while the sensor collects information about the scene. Experimental results span over three test scenarios designed to evaluate the performance of the proposed system. In particular, the exploration performance of the proposed system is compared against that of human subjects. Results show that the proposed approach is able to carry out the exploration of a scene, even when it starts from scratch, building up knowledge as the exploration progresses. Furthermore, in these experiments, the system was able to complete the exploration of the scene in less time when compared to human subjects. Full article
(This article belongs to the Section Sensors and Robotics)
Show Figures

Figure 1

23 pages, 13788 KiB  
Article
A New Volumetric Fusion Strategy with Adaptive Weight Field for RGB-D Reconstruction
by Xinqi Liu, Jituo Li and Guodong Lu
Sensors 2020, 20(15), 4330; https://doi.org/10.3390/s20154330 - 03 Aug 2020
Cited by 4 | Viewed by 2648
Abstract
High-quality 3D reconstruction results are very important in many application fields. However, current texture generation methods based on point sampling and fusion often produce blur. To solve this problem, we propose a new volumetric fusion strategy which can be embedded in the current [...] Read more.
High-quality 3D reconstruction results are very important in many application fields. However, current texture generation methods based on point sampling and fusion often produce blur. To solve this problem, we propose a new volumetric fusion strategy which can be embedded in the current online and offline reconstruction framework as a basic module to achieve excellent geometry and texture effects. The improvement comes from two aspects. Firstly, we establish an adaptive weight field to evaluate and adjust the reliability of data from RGB-D images by using a probabilistic and heuristic method. By using this adaptive weight field to guide the voxel fusion process, we can effectively preserve the local texture structure of the mesh, avoid wrong texture problems and suppress the influence of outlier noise on the geometric surface. Secondly, we use a new texture fusion strategy that combines replacement, integration, and fixedness operations to fuse and update voxel texture to reduce blur. Experimental results demonstrate that compared with the classical KinectFusion, our approach can significantly improve the accuracy in geometry and texture clarity, and can achieve equivalent texture reconstruction effects in real-time as the offline reconstruction methods such as intrinsic3d, even better in relief scenes. Full article
(This article belongs to the Special Issue Intelligent Sensors and Computer Vision)
Show Figures

Figure 1

20 pages, 1763 KiB  
Article
Sensorized Tip for Monitoring People with Multiple Sclerosis that Require Assistive Devices for Walking
by Asier Brull, Asier Zubizarreta, Itziar Cabanes and Ana Rodriguez-Larrad
Sensors 2020, 20(15), 4329; https://doi.org/10.3390/s20154329 - 03 Aug 2020
Cited by 10 | Viewed by 3492
Abstract
Multiple Sclerosis (MS) is a neurological degenerative disease with high impact on our society. In order to mitigate its effects, proper rehabilitation therapy is mandatory, in which individualisation is a key factor. Technological solutions can provide the information required for this purpose, by [...] Read more.
Multiple Sclerosis (MS) is a neurological degenerative disease with high impact on our society. In order to mitigate its effects, proper rehabilitation therapy is mandatory, in which individualisation is a key factor. Technological solutions can provide the information required for this purpose, by monitoring patients and extracting relevant indicators. In this work, a novel Sensorized Tip is proposed for monitoring People with Multiple Sclerosis (PwMS) that require Assistive Devices for Walking (ADW) such as canes or crutches. The developed Sensorized Tip can be adapted to the personal ADW of each patient to reduce its impact, and provides sensor data while naturally walking in the everyday activities. This data that can be processed to obtain relevant indicators that helps assessing the status of the patient. Different from other approaches, a full validation of the proposed processing algorithms is carried out in this work, and a preliminary study-case is carried out with PwMS considering a set of indicators obtained from the Sensorized Tip’s processed data. Results of the preliminary study-case demonstrate the potential of the device to monitor and characterise patient status. Full article
(This article belongs to the Collection Sensors for Gait, Human Movement Analysis, and Health Monitoring)
Show Figures

Figure 1

13 pages, 4485 KiB  
Article
Multifunctional Smart Ball Sensor for Wireless Structural Health Monitoring in a Fire Situation
by Minsu Kim, Insol Hwang, Minho Seong, Jaemook Choi, Myunggun Kim, Hee-Du Lee, Kyung-Jae Shin, Hungsun Son, Hoon Sohn, Junho Choi, Hoon Eui Jeong and Moon Kyu Kwak
Sensors 2020, 20(15), 4328; https://doi.org/10.3390/s20154328 - 03 Aug 2020
Viewed by 3859
Abstract
A variety of sensor systems have been developed to monitor the structural health status of buildings and infrastructures. However, most sensor systems for structural health monitoring (SHM) are difficult to use in extreme conditions, such as a fire situation, because of their vulnerability [...] Read more.
A variety of sensor systems have been developed to monitor the structural health status of buildings and infrastructures. However, most sensor systems for structural health monitoring (SHM) are difficult to use in extreme conditions, such as a fire situation, because of their vulnerability to high temperature and physical shocks, as well as time-consuming installation process. Here, we present a smart ball sensor (SBS) that can be immediately installed on surfaces of structures, stably measure vital SHM data in real time and wirelessly transmit the data in a high-temperature fire situation. The smart ball sensor mainly consists of sensor and data transmission module, heat insulator and adhesive module. With the integrated device configuration, the SBS can be strongly attached to the target surface with maximum adhesion force of 233.7-N and stably detect acceleration and temperature of the structure without damaging the key modules of the systems even at high temperatures of up to 500 °C while ensuring wireless transmission of the data. Field tests for a model pre-engineered building (PEB) structure demonstrate the validity of the smart ball sensor as an instantly deployable, high-temperature SHM system. This SBS can be used for SHM of a wider variety of structures and buildings beyond PEB structures. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

20 pages, 5062 KiB  
Article
Micromachined Vibrating Ring Gyroscope Architecture with High-Linearity, Low Quadrature Error and Improved Mode Ordering
by Zezhang Li, Shiqiao Gao, Lei Jin, Haipeng Liu and Shaohua Niu
Sensors 2020, 20(15), 4327; https://doi.org/10.3390/s20154327 - 03 Aug 2020
Cited by 8 | Viewed by 3208
Abstract
A new micromachined vibrating ring gyroscope (VRG) architecture with low quadrature error and high-linearity is proposed, which successfully optimizes the working modes to first order resonance mode of the structure. The improved mode ordering can significantly reduce the vibration sensitivity of the device [...] Read more.
A new micromachined vibrating ring gyroscope (VRG) architecture with low quadrature error and high-linearity is proposed, which successfully optimizes the working modes to first order resonance mode of the structure. The improved mode ordering can significantly reduce the vibration sensitivity of the device by adopting the hinge-frame mechanism. The frequency difference ratio is introduced to represent the optimization effect of modal characteristic. Furthermore, the influence of the structural parameters of hinge-frame mechanism on frequency difference ratio is clarified through analysis of related factors, which contributes to a more effective design of hinge-frame structure. The designed VRG architecture accomplishes the goal of high-linearity by using combination hinge and variable-area capacitance strategy, in contrast to the conventional approach via variable-separation drive/sense strategy. Finally, finite element method (FEM) simulations are carried out to investigate the stiffness, modal analysis, linearity, and decoupling characteristics of the design. The simulation results are sufficiently in agreement with theoretical calculations. Meanwhile, the hinge-frame mechanism can be widely applied in other existing ring gyroscopes, and the new design provides a path towards ultra-high performance for VRG. Full article
(This article belongs to the Special Issue MEMS Actuators and Sensors 2022)
Show Figures

Figure 1

12 pages, 2718 KiB  
Perspective
Ion Selective Amperometric Biosensors for Environmental Analysis of Nitrate, Nitrite and Sulfate
by Niels Peter Revsbech, Michael Nielsen and Deby Fapyane
Sensors 2020, 20(15), 4326; https://doi.org/10.3390/s20154326 - 03 Aug 2020
Cited by 15 | Viewed by 4262
Abstract
Inorganic ions that can be redox-transformed by living cells can be sensed by biosensors, where the redox transformation gives rise to a current in a measuring circuit. Such biosensors may be based on enzymes, or they may be based on application of whole [...] Read more.
Inorganic ions that can be redox-transformed by living cells can be sensed by biosensors, where the redox transformation gives rise to a current in a measuring circuit. Such biosensors may be based on enzymes, or they may be based on application of whole cells. In this review focus will be on biosensors for the environmentally important ions NO3, NO2, and SO42−, and for comparison alternative sensor-based detection will also be mentioned. The developed biosensors are generally characterized by a high degree of specificity, but unfortunately also by relatively short lifetimes. There are several investigations where biosensor measurement of NO3 and NO2 have given new insight into the functioning of nitrogen transformations in man-made and natural environments such as sediments and biofilms, but the biosensors have not become routine tools. Future modifications resulting in better long-term stability may enable such general use. Full article
(This article belongs to the Special Issue Ion Selective Electrodes and Optodes)
Show Figures

Figure 1

15 pages, 4159 KiB  
Article
Real-Time Detection of Railway Track Component via One-Stage Deep Learning Networks
by Tiange Wang, Fangfang Yang and Kwok-Leung Tsui
Sensors 2020, 20(15), 4325; https://doi.org/10.3390/s20154325 - 03 Aug 2020
Cited by 26 | Viewed by 4703
Abstract
Railway inspection has always been a critical task to guarantee the safety of the railway transportation. The development of deep learning technologies brings new breakthroughs in the accuracy and speed of image-based railway inspection application. In this work, a series of one-stage deep [...] Read more.
Railway inspection has always been a critical task to guarantee the safety of the railway transportation. The development of deep learning technologies brings new breakthroughs in the accuracy and speed of image-based railway inspection application. In this work, a series of one-stage deep learning approaches, which are fast and accurate at the same time, are proposed to inspect the key components of railway track including rail, bolt, and clip. The inspection results show that the enhanced model, the second version of you only look once (YOLOv2), presents the best component detection performance with 93% mean average precision (mAP) at 35 image per second (IPS), whereas the feature pyramid network (FPN) based model provides a smaller mAP and much longer inference time. Besides, the detection performances of more deep learning approaches are evaluated under varying input sizes, where larger input size usually improves the detection accuracy but results in a longer inference time. Overall, the YOLO series models could achieve faster speed under the same detection accuracy. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

32 pages, 4280 KiB  
Article
Decentralized Mesh-Based Model Predictive Control for Swarms of UAVs
by Salvatore Rosario Bassolillo, Egidio D’Amato, Immacolata Notaro, Luciano Blasi and Massimiliano Mattei
Sensors 2020, 20(15), 4324; https://doi.org/10.3390/s20154324 - 03 Aug 2020
Cited by 21 | Viewed by 3457
Abstract
This paper deals with the design of a decentralized guidance and control strategy for a swarm of unmanned aerial vehicles (UAVs), with the objective of maintaining a given connection topology with assigned mutual distances while flying to a target area. In the absence [...] Read more.
This paper deals with the design of a decentralized guidance and control strategy for a swarm of unmanned aerial vehicles (UAVs), with the objective of maintaining a given connection topology with assigned mutual distances while flying to a target area. In the absence of obstacles, the assigned topology, based on an extended Delaunay triangulation concept, implements regular and connected formation shapes. In the presence of obstacles, this technique is combined with a model predictive control (MPC) that allows forming independent sub-swarms optimizing the formation spreading to avoid obstacles and collisions between neighboring vehicles. A custom numerical simulator was developed in a Matlab/Simulink environment to prove the effectiveness of the proposed guidance and control scheme in several 2D operational scenarios with obstacles of different sizes and increasing number of aircraft. Full article
(This article belongs to the Special Issue Sensors for Aerial Unmanned Systems)
Show Figures

Figure 1

14 pages, 419 KiB  
Article
A Hybrid Feature Selection and Extraction Methods for Sleep Apnea Detection Using Bio-Signals
by Xilin Li, Sai Ho Ling and Steven Su
Sensors 2020, 20(15), 4323; https://doi.org/10.3390/s20154323 - 03 Aug 2020
Cited by 14 | Viewed by 2875
Abstract
People with sleep apnea (SA) are at increased risk of having stroke and cardiovascular diseases. Polysomnography (PSG) is used to detect SA. This paper conducts feature selection from PSG signals and uses a support vector machine (SVM) to detect SA. To analyze SA, [...] Read more.
People with sleep apnea (SA) are at increased risk of having stroke and cardiovascular diseases. Polysomnography (PSG) is used to detect SA. This paper conducts feature selection from PSG signals and uses a support vector machine (SVM) to detect SA. To analyze SA, the Physionet Apnea Database was used to obtain various features. Electrocardiography (ECG), oxygen saturation (SaO2), airflow, abdominal, and thoracic signals were used to provide various frequency-, time-domain and non-linear features (n = 87). To analyse the significance of these features, firstly, two evaluation measures, the rank-sum method and the analysis of variance (ANOVA) were used to evaluate the significance of the features. These features were then classified according to their significance. Finally, different class feature sets were presented as inputs for an SVM classifier to detect the onset of SA. The hill-climbing feature selection algorithm and the k-fold cross-validation method were applied to evaluate each classification performance. Through the experiments, we discovered that the best feature set (including the top-five significant features) obtained the best classification performance. Furthermore, we plotted receiver operating characteristic (ROC) curves to examine the performance of the SVM, and the results showed the SVM with Linear kernel (regularization parameter = 1) outperformed other classifiers (area under curve = 95.23%, sensitivity = 94.29%, specificity = 96.17%). The results confirm that feature subsets based on multiple bio-signals have the potential to identify patients with SA. The use of a smaller subset avoids dimensionality problems and reduces the computational load. Full article
(This article belongs to the Special Issue Artificial Intelligence in Medical Sensors)
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop