Sensors

15 pages, 12413 KiB

Open AccessArticle

Deep Learning Correction Algorithm for The Active Optics System

by Wenxiang Li, Chao Kang, Hengrui Guan, Shen Huang, Jinbiao Zhao, Xiaojun Zhou and Jinpeng Li

Sensors 2020, 20(21), 6403; https://doi.org/10.3390/s20216403 - 9 Nov 2020

Cited by 2 | Viewed by 2992

Abstract

The correction of wavefront aberration plays a vital role in active optics. The traditional correction algorithms based on the deformation of the mirror cannot effectively deal with disturbances in the real system. In this study, a new algorithm called deep learning correction algorithm [...] Read more.

The correction of wavefront aberration plays a vital role in active optics. The traditional correction algorithms based on the deformation of the mirror cannot effectively deal with disturbances in the real system. In this study, a new algorithm called deep learning correction algorithm (DLCA) is proposed to compensate for wavefront aberrations and improve the correction capability. The DLCA consists of an actor network and a strategy unit. The actor network is utilized to establish the mapping of active optics systems with disturbances and provide a search basis for the strategy unit, which can increase the search speed; The strategy unit is used to optimize the correction force, which can improve the accuracy of the DLCA. Notably, a heuristic search algorithm is applied to reduce the search time in the strategy unit. The simulation results show that the DLCA can effectively improve correction capability and has good adaptability. Compared with the least square algorithm (LSA), the algorithm we proposed has better performance, indicating that the DLCA is more accurate and can be used in active optics. Moreover, the proposed approach can provide a new idea for further research of active optics. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

28 pages, 7930 KiB

Open AccessArticle

Design Optimization of Resource Allocation in OFDMA-Based Cognitive Radio-Enabled Internet of Vehicles (IoVs)

by Joy Eze, Sijing Zhang, Enjie Liu and Elias Eze

Sensors 2020, 20(21), 6402; https://doi.org/10.3390/s20216402 - 9 Nov 2020

Cited by 12 | Viewed by 2872

Abstract

Joint optimal subcarrier and transmit power allocation with QoS guarantee for enhanced packet transmission over Cognitive Radio (CR)-Internet of Vehicles (IoVs) is a challenge. This open issue is considered in this paper. A novel SNBS-based wireless radio resource scheduling scheme in OFDMA CR-IoV [...] Read more.

Joint optimal subcarrier and transmit power allocation with QoS guarantee for enhanced packet transmission over Cognitive Radio (CR)-Internet of Vehicles (IoVs) is a challenge. This open issue is considered in this paper. A novel SNBS-based wireless radio resource scheduling scheme in OFDMA CR-IoV network systems is proposed. This novel scheduler is termed the SNBS OFDMA-based overlay CR-Assisted Vehicular NETwork (SNO-CRAVNET) scheduling scheme. It is proposed for efficient joint transmit power and subcarrier allocation for dynamic spectral resource access in cellular OFDMA-based overlay CRAVNs in clusters. The objectives of the optimization model applied in this study include (1) maximization of the overall system throughput of the CR-IoV system, (2) avoiding harmful interference of transmissions of the shared channels’ licensed owners (or primary users (PUs)), (3) guaranteeing the proportional fairness and minimum data-rate requirement of each CR vehicular secondary user (CRV-SU), and (4) ensuring efficient transmit power allocation amongst CRV-SUs. Furthermore, a novel approach which uses Lambert-W function characteristics is introduced. Closed-form analytical solutions were obtained by applying time-sharing variable transformation. Finally, a low-complexity algorithm was developed. This algorithm overcame the iterative processes associated with searching for the optimal solution numerically through iterative programming methods. Theoretical analysis and simulation results demonstrated that, under similar conditions, the proposed solutions outperformed the reference scheduler schemes. In comparison to other scheduling schemes that are fairness-considerate, the SNO-CRAVNET scheme achieved a significantly higher overall average throughput gain. Similarly, the proposed time-sharing SNO-CRAVNET allocation based on the reformulated convex optimization problem is shown to be capable of achieving up to 99.987% for the average of the total theoretical capacity. Full article

(This article belongs to the Special Issue IoT Sensing Systems for Traffic Monitoring and for Automated and Connected Vehicles)

► Show Figures

Figure 1

21 pages, 10144 KiB

Open AccessArticle

Analysis on the Possibility of Eliminating Interference from Paraseismic Vibration Signals Induced by the Detonation of Explosive Materials

by Józef Pyra, Maciej Kłaczyński and Rafał Burdzik

Sensors 2020, 20(21), 6401; https://doi.org/10.3390/s20216401 - 9 Nov 2020

Cited by 2 | Viewed by 2859

Abstract

This article presents the results of studies on the impact of acoustic waves on geophones and microphones used to measure airblasts carried out in a reverberation chamber. During the tests, a number of test signals were generated, of which two are presented in [...] Read more.

This article presents the results of studies on the impact of acoustic waves on geophones and microphones used to measure airblasts carried out in a reverberation chamber. During the tests, a number of test signals were generated, of which two are presented in this article: frequency-modulated sine (sine sweep) waves in the 30–300 Hz range, and the result of detonating 3 g of pyrotechnic material inside the chamber. Then, based on the short-time Fourier transform, the spectral subtraction method was used to remove unwanted disruption interfering with the recorded signal. Using MATLAB software, a program was written that was calibrated and adapted to the specifics of the measuring equipment based on the collected test results. As a result, it was possible to clean the signals of interference and obtain a vibration signal propagated by the substrate. The results are based on signals registered in the laboratory and made in field conditions during the detonation of explosive materials. Full article

(This article belongs to the Special Issue Sensing Technology and Data Interpretation in Machine Diagnosis and Systems Condition Monitoring)

► Show Figures

Figure 1

15 pages, 10773 KiB

Open AccessArticle

A Novel Routing Algorithm for the Acceleration of Flow Scheduling in Time-Sensitive Networks

by Jheng-Yu Huang, Ming-Hung Hsu and Chung-An Shen

Sensors 2020, 20(21), 6400; https://doi.org/10.3390/s20216400 - 9 Nov 2020

Cited by 5 | Viewed by 2979

Abstract

IEEE Time-Sensitive Networking (TSN) Task Group specifies a series of standards such as 802.1Qbv for enhancing the management of time-critical flows in real-time networks. Under the IEEE 802.1Qbv standard, the scheduling algorithm is employed to determine the time when a specific gate in [...] Read more.

IEEE Time-Sensitive Networking (TSN) Task Group specifies a series of standards such as 802.1Qbv for enhancing the management of time-critical flows in real-time networks. Under the IEEE 802.1Qbv standard, the scheduling algorithm is employed to determine the time when a specific gate in the network entities is opened or closed so that the real-time requirements for the flows are guaranteed. The computation time of this scheduling algorithm is critical for the system where dynamic network configurations and settings are required. In addition, the network routing where the paths of the flows are determined has a significant impact on the computation time of the network scheduling. This paper presents a novel scheduling-aware routing algorithm to minimize the computation time of the scheduling algorithm in network management. The proposed routing algorithm determines the path for each time-triggered flow by including the consideration of the period of the flow. This decreases the occurrence of path-conflict during the stage of network scheduling. The detailed outline of the proposed algorithm is presented in this paper. The experimental results show that the proposed routing algorithm reduces the computation time of network scheduling by up to 30% and improves the schedulability of time-triggered flows is the network. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

25 pages, 12871 KiB

Open AccessArticle

Physically Plausible Spectral Reconstruction

by Yi-Tun Lin and Graham D. Finlayson

Sensors 2020, 20(21), 6399; https://doi.org/10.3390/s20216399 - 9 Nov 2020

Cited by 16 | Viewed by 4631

Abstract

Spectral reconstruction algorithms recover spectra from RGB sensor responses. Recent methods—with the very best algorithms using deep learning—can already solve this problem with good spectral accuracy. However, the recovered spectra are physically incorrect in that they do not induce the RGBs from which [...] Read more.

Spectral reconstruction algorithms recover spectra from RGB sensor responses. Recent methods—with the very best algorithms using deep learning—can already solve this problem with good spectral accuracy. However, the recovered spectra are physically incorrect in that they do not induce the RGBs from which they are recovered. Moreover, if the exposure of the RGB image changes then the recovery performance often degrades significantly—i.e., most contemporary methods only work for a fixed exposure. In this paper, we develop a physically accurate recovery method: the spectra we recover provably induce the same RGBs. Key to our approach is the idea that the set of spectra that integrate to the same RGB can be expressed as the sum of a unique fundamental metamer (spanned by the camera’s spectral sensitivities and linearly related to the RGB) and a linear combination of a vector space of metameric blacks (orthogonal to the spectral sensitivities). Physically plausible spectral recovery resorts to finding a spectrum that adheres to the fundamental metamer plus metameric black decomposition. To further ensure spectral recovery that is robust to changes in exposure, we incorporate exposure changes in the training stage of the developed method. In experiments we evaluate how well the methods recover spectra and predict the actual RGBs and RGBs under different viewing conditions (changing illuminations and/or cameras). The results show that our method generally improves the state-of-the-art spectral recovery (with more stabilized performance when exposure varies) and provides zero colorimetric error. Moreover, our method significantly improves the color fidelity under different viewing conditions, with up to a 60% reduction in some cases. Full article

(This article belongs to the Special Issue Color & Spectral Sensors)

► Show Figures

Figure 1

11 pages, 2504 KiB

Open AccessLetter

Bacterial Respiration Used as a Proxy to Evaluate the Bacterial Load in Cooling Towers

by Stepan Toman, Bruno Kiilerich, Ian P.G. Marshall and Klaus Koren

Sensors 2020, 20(21), 6398; https://doi.org/10.3390/s20216398 - 9 Nov 2020

Viewed by 3575

Abstract

Evaporative cooling towers to dissipate excess process heat are essential installations in a variety of industries. The constantly moist environment enables substantial microbial growth, causing both operative challenges (e.g., biocorrosion) as well as health risks due to the potential aerosolization of pathogens. Currently, [...] Read more.

Evaporative cooling towers to dissipate excess process heat are essential installations in a variety of industries. The constantly moist environment enables substantial microbial growth, causing both operative challenges (e.g., biocorrosion) as well as health risks due to the potential aerosolization of pathogens. Currently, bacterial levels are monitored using rather slow and infrequent sampling and cultivation approaches. In this study, we describe the use of metabolic activity, namely oxygen respiration, as an alternative measure of bacterial load within cooling tower waters. This method is based on optical oxygen sensors that enable an accurate measurement of oxygen consumption within a closed volume. We show that oxygen consumption correlates with currently used cultivation-based methods (R² = 0.9648). The limit of detection (LOD) for respiration-based bacterial quantification was found to be equal to 1.16 × 10⁴ colony forming units (CFU)/mL. Contrary to the cultivation method, this approach enables faster assessment of the bacterial load with a measurement time of just 30 min compared to 48 h needed for cultivation-based measurements. Furthermore, this approach has the potential to be integrated and automated. Therefore, this method could contribute to more robust and reliable monitoring of bacterial contamination within cooling towers and subsequently increase operational stability and reduce health risks. Full article

(This article belongs to the Special Issue Optical Sensors for Water Monitoring)

► Show Figures

Figure 1

Figure 1
Sketch of an evaporative cooling tower with a water reservoir, fill material and heat exchanger. Microbial communities can thrive within the humid environment, both in planktonic form as well as in biofilms on all surfaces. Full article ">Figure 2
(A): Picture of the measurement vial with the glass magnet (1), rubber stopper (2), thin glass capillary (3), temperature probe (4) and O2 sensor spot with the respective connector (5). (B): Three samples and one control measured at the same time within a water bath kept at 22 °C. Full article ">Figure 3
(A): Principal Coordinates Analysis based on Bray–Curtis distances between ASV relative abundances. The two most significant principal components are shown, axes annotated with percentage of variation explained. (B): Heatmap showing mean percentage abundances for all sample types for the 21 most abundant genera in the dataset. Rows labeled with names ending in “_ASVXX” show ASVs with undefined genera (only defined up to the family level) which are nonetheless more abundant than all genera in the top 21. vE6 is an uncultured family-level group within the Chlamydiales. Full article ">Figure 4
Comparison of the decrease in O2 concentration over time of a pure sample compared to a sample with added glucose and LB medium. The respective respiration rates were determined via linear regression and are displayed within the graph. Full article ">Figure 5
Examples of measured oxygen respiration of an undiluted sample, a 1 + 1 diluted sample and a 1 + 2 diluted sample compared to the negative control. Full article ">Figure 6
Correlation between the numbers of colony forming units (CFUs) in samples measured by plate counts and the oxygen consumption rates measured by the optode system. Data points represent means with the respective standard deviations for each sample (n = 5 for the undiluted sample, 2 for 1 + 1 and 1 + 2 dilutions and 3 for the negative control). The linear regression shown by the blue dotted line has an R2 = 0.9648. Full article ">

19 pages, 3306 KiB

Open AccessArticle

Time-Domain Blind ICI Compensation in Coherent Optical FBMC/OQAM System

by Binqi Wu, Jin Lu, Mingyi Gao, Hongliang Ren, Zichun Le, Yali Qin, Shuqin Guo and Weisheng Hu

Sensors 2020, 20(21), 6397; https://doi.org/10.3390/s20216397 - 9 Nov 2020

Cited by 3 | Viewed by 3643

Abstract

A blind discrete-cosine-transform-based phase noise compensation (BD-PNC) is proposed to compensate the inter-carrier-interference (ICI) in the coherent optical offset-quadrature amplitude modulation (OQAM)-based filter-bank multicarrier (CO-FBMC/OQAM) transmission system. Since the phase noise sample can be approximated by an expansion of the discrete cosine transform [...] Read more.

A blind discrete-cosine-transform-based phase noise compensation (BD-PNC) is proposed to compensate the inter-carrier-interference (ICI) in the coherent optical offset-quadrature amplitude modulation (OQAM)-based filter-bank multicarrier (CO-FBMC/OQAM) transmission system. Since the phase noise sample can be approximated by an expansion of the discrete cosine transform (DCT) in the time-domain, a time-domain compensation model is built for the transmission system. According to the model, phase noise compensation (PNC) depends only on its DCT coefficients. The common phase error (CPE) compensation is firstly performed for the received signal. After that, a pre-decision is made on a part of compensated signals with low decision error probability, and the pre-decision results are used as the estimated values of transmitted signals to calculate the DCT coefficients. Such a partial pre-decision process reduces not only decision error but also the complexity of the BD-PNC method while keeping almost the same performance as in the case of the pre-decision of all compensated signals. Numerical simulations are performed to evaluate the performance of the proposed scheme for a 30 GBaud CO-FBMC/OQAM system. The simulation results show that its bit error rate (BER) performance is improved by more than one order of magnitude through the mitigation of the ICI in comparison with the traditional blind PNC scheme only aiming for CPE compensation. Full article

(This article belongs to the Special Issue Enabling Technology in Optical Fiber Communications: From Device, System to Networking)

► Show Figures

Figure 1

Figure 1
Block diagram of CO-FBMC/OQAM BTB system. Full article ">Figure 2
Block diagram of the proposed blind phase noise compensation scheme. Full article ">Figure 3
Taking the 16-OQAM as an example, the signals with high decision error probability in three shadow regions (<math display="inline"><semantics> <mrow> <msubsup> <mover accent="true"> <mi>a</mi> <mo stretchy="false">^</mo> </mover> <mrow> <mi>n</mi> <mo>,</mo> <mi>m</mi> </mrow> <mo>′</mo> </msubsup> <mo>∈</mo> <mo stretchy="false">[</mo> <mo>−</mo> <mn>2</mn> <mo>−</mo> <mrow> <mi>δ</mi> <mo>/</mo> <mn>2</mn> </mrow> <mo>,</mo> <mo>−</mo> <mn>2</mn> <mo>+</mo> <mi>δ</mi> <mo>/</mo> <mn>2</mn> <mo stretchy="false">]</mo> <mo>∪</mo> <mo stretchy="false">[</mo> <mo>−</mo> <mrow> <mi>δ</mi> <mo>/</mo> <mn>2</mn> </mrow> <mo>,</mo> <mi>δ</mi> <mo>/</mo> <mn>2</mn> <mo stretchy="false">]</mo> <mo>∪</mo> <mo stretchy="false">[</mo> <mn>2</mn> <mo>−</mo> <mrow> <mi>δ</mi> <mo>/</mo> <mn>2</mn> </mrow> <mo>,</mo> <mn>2</mn> <mo>+</mo> <mi>δ</mi> <mo>/</mo> <mn>2</mn> <mo stretchy="false">]</mo> </mrow> </semantics></math>) not being used to perform the pre-decision. Full article ">Figure 4
Time-domain FBMC/OQAM transmitted blocks with overlapped structure. Full article ">Figure 5
(a) BER versus the width of shadow rectangle in a high decision error probability region, δ. (b) BER versus the length of DCT coefficient, L. (c) BER versus the number of subcarriers, M. Full article ">Figure 6
(a) One realization of the real phase noise and its estimations after the M-BPS and BD-PNC methods at <math display="inline"><semantics> <mrow> <mo>∆</mo> <mi>ν</mi> <mo>⋅</mo> <msub> <mi>T</mi> <mi>S</mi> </msub> <mo>=</mo> <mn>1.5</mn> <mo>×</mo> <mn>1</mn> <msup> <mn>0</mn> <mrow> <mo>−</mo> <mn>2</mn> </mrow> </msup> </mrow> </semantics></math> and OSNR = 20 dB for 30 Gbaud CO-FBMC 16-QAM BTB transmission systems with 1024 subcarriers. (b) Illustration of constellations before and after PNC employing M-BPS and BD-PNC at <math display="inline"><semantics> <mrow> <mo>∆</mo> <mi>ν</mi> <mo>⋅</mo> <msub> <mi>T</mi> <mi>S</mi> </msub> <mo>=</mo> <mn>5</mn> <mo>×</mo> <mn>1</mn> <msup> <mn>0</mn> <mrow> <mo>−</mo> <mn>3</mn> </mrow> </msup> </mrow> </semantics></math> and OSNR = 27 dB for 30 Gbaud CO-FBMC 64-QAM BTB systems with 1024 subcarriers. Full article ">Figure 7
OSNR penalty versus <math display="inline"><semantics> <mrow> <mo>∆</mo> <mi>ν</mi> <mo>⋅</mo> <msub> <mi>T</mi> <mi>S</mi> </msub> </mrow> </semantics></math> at a BER of <math display="inline"><semantics> <mrow> <mn>3.8</mn> <mo>×</mo> <mn>1</mn> <msup> <mn>0</mn> <mrow> <mo>−</mo> <mn>3</mn> </mrow> </msup> </mrow> </semantics></math> using M-BPS, the proposed schemes for CO-FBMC 4/16/64-QAM systems with 256 subcarriers (a), 512 subcarriers (b), and 1024 subcarriers (c). Full article ">

46 pages, 2708 KiB

Open AccessFeature PaperEditor’s ChoiceReview

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

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

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

Cited by 254 | Viewed by 35274

Abstract

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

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

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

► Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
Schematic representation of the monitoring goals described in this review and related examples of specific measurement scenarios. Full article ">Figure 2
Schematic representation of the interactions between respiratory physiology, applied sciences, and technological development. The Figure shows how fruitful synergies between different disciplines are essential for the development of respiratory monitoring services. Full article ">Figure 3
Schematic representation of a simple model of ventilatory control (see Nicolò and Sacchetti [<a href="#B22-sensors-20-06396" class="html-bibr">22</a>] for further information). While respiratory rate (the behavioral component of minute ventilation) is substantially influenced by non-metabolic stressors, VT (the metabolic component of minute ventilation) satisfies the metabolic requirements of the human body. As such VT is fine-tuned according to the levels of respiratory rate and the magnitude of metabolic inputs, while fR is influenced by VT to a lesser extent. This model explains why fR is more sensitive than VT to a variety of non-metabolic stressors and corroborates the importance of fR monitoring in different fields of use. Full article ">Figure 4
A conceptual framework for the development of respiratory monitoring services. The framework is composed of ten steps that are numbered and listed on the left-hand side of the figure. Each of the ten steps is accompanied by a graphical example reported on the right-hand side of the figure. Panel (A) reports the thirteen monitoring goals described in this review. The graph in panel (B) is reproduced from Massaroni et al. [<a href="#B5-sensors-20-06396" class="html-bibr">5</a>]. The graph in panel (C) is reproduced from Naranjo-Hernández et al. [<a href="#B157-sensors-20-06396" class="html-bibr">157</a>]. Panel (D) provides an example of the output of some of the sensors used to detect apnea events in sleep laboratories. The graph in panel (E) is slightly modified from Massaroni et al. [<a href="#B24-sensors-20-06396" class="html-bibr">24</a>]. The graph in panel (F) is slightly modified from Lo Presti et al. [<a href="#B290-sensors-20-06396" class="html-bibr">290</a>]. The graph in panel (G) is reproduced from Tomasic et al. [<a href="#B293-sensors-20-06396" class="html-bibr">293</a>]. Panel (H) provides an example of data transmission performance evaluation. The graph in panel (I) is slightly modified from Quinten et al. [<a href="#B116-sensors-20-06396" class="html-bibr">116</a>]. The graph in panel (J) is slightly modified from Gerry et al. [<a href="#B110-sensors-20-06396" class="html-bibr">110</a>]. Full article ">Figure 5
Schematic representation of how respiratory rate (values expressed both in breaths/min and in Hz) may change in response to different stressors. The range of respiratory rate values reported for each stressor has been defined according to the cited references (numbers in square brackets), but these values should only be considered as plausible examples. fR values refer to adults if not otherwise stated. * it is not unusual to observe fR values higher than 65 breaths/min. Mos, months. Full article ">

11 pages, 3089 KiB

Open AccessLetter

GeSi Nanocrystals Photo-Sensors for Optical Detection of Slippery Road Conditions Combining Two Classification Algorithms

by Catalin Palade, Ionel Stavarache, Toma Stoica and Magdalena Lidia Ciurea

Sensors 2020, 20(21), 6395; https://doi.org/10.3390/s20216395 - 9 Nov 2020

Cited by 10 | Viewed by 3138

Abstract

One of the key elements in assessing traffic safety on the roads is the detection of asphalt conditions. In this paper, we propose an optical sensor based on GeSi nanocrystals embedded in SiO₂ matrix that discriminates between different slippery road conditions (wet [...] Read more.

One of the key elements in assessing traffic safety on the roads is the detection of asphalt conditions. In this paper, we propose an optical sensor based on GeSi nanocrystals embedded in SiO₂ matrix that discriminates between different slippery road conditions (wet and icy asphalt and asphalt covered with dirty ice) in respect to dry asphalt. The sensor is fabricated by magnetron sputtering deposition followed by rapid thermal annealing. The photodetector has spectral sensitivity in the 360–1350 nm range and the signal-noise ratio is 10²–10³. The working principle of sensor setup for detection of road conditions is based on the photoresponse (photocurrent) of the sensor under illumination with the light reflected from the asphalt having different reflection coefficients for dry, wet, icy and dirty ice coatings. For this, the asphalt is illuminated sequentially with 980 and 1064 nm laser diodes. A database of these photocurrents is obtained for the different road conditions. We show that the use of both k-nearest neighbor and artificial neural networks classification algorithms enables a more accurate recognition of the class corresponding to a specific road state than in the case of using only one algorithm. This is achieved by comparing the new output sensor data with previously classified data for each algorithm and then by performing an intersection of the algorithms’ results. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Graphical abstract

13 pages, 576 KiB

Open AccessLetter

Use of Functional Linear Models to Detect Associations between Characteristics of Walking and Continuous Responses Using Accelerometry Data

by William F. Fadel, Jacek K. Urbanek, Nancy W. Glynn and Jaroslaw Harezlak

Sensors 2020, 20(21), 6394; https://doi.org/10.3390/s20216394 - 9 Nov 2020

Cited by 2 | Viewed by 2701

Abstract

Various methods exist to measure physical activity. Subjective methods, such as diaries and surveys, are relatively inexpensive ways of measuring one’s physical activity; however, they are prone to measurement error and bias due to self-reporting. Wearable accelerometers offer a non-invasive and objective measure [...] Read more.

Various methods exist to measure physical activity. Subjective methods, such as diaries and surveys, are relatively inexpensive ways of measuring one’s physical activity; however, they are prone to measurement error and bias due to self-reporting. Wearable accelerometers offer a non-invasive and objective measure of one’s physical activity and are now widely used in observational studies. Accelerometers record high frequency data and each produce an unlabeled time series at the sub-second level. An important activity to identify from the data collected is walking, since it is often the only form of activity for certain populations. Currently, most methods use an activity summary which ignores the nuances of walking data. We propose methodology to model specific continuous responses with a functional linear model utilizing spectra obtained from the local fast Fourier transform (FFT) of walking as a predictor. Utilizing prior knowledge of the mechanics of walking, we incorporate this as additional information for the structure of our transformed walking spectra. The methods were applied to the in-the-laboratory data obtained from the Developmental Epidemiologic Cohort Study (DECOS). Full article

(This article belongs to the Special Issue Wearable Movement Sensors for Rehabilitation: From Technology to Clinical Practice)

► Show Figures

Figure 1

Figure 1
Triaxial accelerometer data from the 400 m walk for a single individual (top left) and a zoomed 10 s window (top right). Vector magnitude from the 400 m walk for same individual (bottom left) and zoomed 10 s window (bottom right). Full article ">Figure 2
Pre-processing data. Observed FFT spectra for one participant as described in step 4 of Algorithm 1 (top left). Observed spectra realigned into order domain for the same participant as described in step 6 of Algorithm 1 (top right). Average realigned spectra for all participants as described in step 7 of Algorithm 1 (bottom left). Scaled average spectra for all participants as described in step 9 of Algorithm 1 (bottom right). Full article ">Figure 3
Pre-processed walking spectra (top) and basis functions used for modeling (bottom). The x-axis represents multiples of the frequency of the cadence. Full article ">Figure 4
Estimates of the coefficient function, <math display="inline"><semantics> <mover accent="true"> <mi>β</mi> <mo>˜</mo> </mover> </semantics></math>, (with 95% point-wise confidence band) for the association of walking with age and BMI, as described in <a href="#sec4-sensors-20-06394" class="html-sec">Section 4</a>. The x-axis represents multiples of the frequency of the cadence. Full article ">

19 pages, 3099 KiB

Open AccessArticle

Hybrid Routing, Modulation, Spectrum and Core Allocation Based on Mapping Scheme

by Edson Rodrigues, Eduardo Cerqueira, Denis Rosário and Helder Oliveira

Sensors 2020, 20(21), 6393; https://doi.org/10.3390/s20216393 - 9 Nov 2020

Cited by 4 | Viewed by 2427

Abstract

With the persistently growing popularity of internet traffic, telecom operators are forced to provide high-capacity, cost-efficient, and performance-adaptive connectivity solutions to fulfill the requirements and increase their returns. However, optical networks that make up the core of the Internet gradually reached physical transmission [...] Read more.

With the persistently growing popularity of internet traffic, telecom operators are forced to provide high-capacity, cost-efficient, and performance-adaptive connectivity solutions to fulfill the requirements and increase their returns. However, optical networks that make up the core of the Internet gradually reached physical transmission limits. In an attempt to provide new solutions emerged, the Space-Division Multiplexing Elastic Optical Network emerged as one of the best ways to deal with the network depletion. However, it is necessary to establish lightpaths using routing, modulation, spectrum, and core allocation (RMSCA) algorithms to establish connections in these networks. This article proposes a crosstalk-aware RMSCA algorithm that uses a multi-path and mapping scheme for improving resource allocation. The results show that the proposed algorithm decreases the blocking ratio by up to four orders of magnitude compared with other RMSCA algorithms in the literature. Full article

(This article belongs to the Special Issue Enabling Technology in Optical Fiber Communications: From Device, System to Networking)

► Show Figures

Figure 1

16 pages, 5013 KiB

Open AccessArticle

Capacitive-Coupling Impedance Spectroscopy Using a Non-Sinusoidal Oscillator and Discrete-Time Fourier Transform: An Introductory Study

by Tomiharu Yamaguchi and Akinori Ueno

Sensors 2020, 20(21), 6392; https://doi.org/10.3390/s20216392 - 9 Nov 2020

Cited by 3 | Viewed by 4278

Abstract

In this study, we propose a new short-time impedance spectroscopy method with the following three features: (1) A frequency spectrum of complex impedance for the measured object can be obtained even when the measuring electrodes are capacitively coupled with the object and the [...] Read more.

In this study, we propose a new short-time impedance spectroscopy method with the following three features: (1) A frequency spectrum of complex impedance for the measured object can be obtained even when the measuring electrodes are capacitively coupled with the object and the precise capacitance of the coupling is unknown; (2) the spectrum can be obtained from only one cycle of the non-sinusoidal oscillation waveform without sweeping the oscillation frequency; and (3) a front-end measuring circuit can be built, simply and cheaply, without the need for a digital-to-analog (D-A) converter to synthesize elaborate waveforms comprising multiple frequencies. We built the measurement circuit using the proposed method and then measured the complex impedance spectra of 18 resistive elements connected in series with one of three respective capacitive couplings. With this method, each element’s resistance and each coupling’s capacitance were estimated independently and compared with their nominal values. When the coupling capacitance was set to 10 nF or 1.0 nF, estimated errors for the resistive elements in the range of 2.0–10.0 kΩ were less than 5%. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

29 pages, 536 KiB

Open AccessArticle

Enhancements and Challenges in CoAP—A Survey

by Muhammad Ashar Tariq, Murad Khan, Muhammad Toaha Raza Khan and Dongkyun Kim

Sensors 2020, 20(21), 6391; https://doi.org/10.3390/s20216391 - 9 Nov 2020

Cited by 36 | Viewed by 8452

Abstract

The Internet of Engineering Task (IETF) developed a lighter application protocol (Constrained Application Protocol (CoAP)) for the constrained IoT devices operating in lossy environments. Based on UDP, CoAP is a lightweight and efficient protocol compared to other IoT protocols such as HTTP, MQTT, [...] Read more.

The Internet of Engineering Task (IETF) developed a lighter application protocol (Constrained Application Protocol (CoAP)) for the constrained IoT devices operating in lossy environments. Based on UDP, CoAP is a lightweight and efficient protocol compared to other IoT protocols such as HTTP, MQTT, etc. CoAP also provides reliable communication among nodes in wireless sensor networks in addition to features such as resource observation, resource discovery, congestion control, etc. These capabilities of CoAP have enabled the implementation of CoAP in various domains ranging from home automation to health management systems. The use of CoAP has highlighted its shortcomings over the time. To overcome shortcomings of CoAP, numerous enhancements have been made in basic CoAP architecture. This survey highlights the shortcomings of basic CoAP architecture and enhancements made in it throughout the time. Furthermore, existing challenges and issue in the current CoAP architecture are also discussed. Finally, some applications with CoAP implementation are mentioned in order to realize the viability of CoAP in real world use cases. Full article

(This article belongs to the Special Issue Internet of Underwater Things)

► Show Figures

Figure 1

17 pages, 9686 KiB

Open AccessArticle

Artificial Intelligence-Based Optimal Grasping Control

by Dongeon Kim, Jonghak Lee, Wan-Young Chung and Jangmyung Lee

Sensors 2020, 20(21), 6390; https://doi.org/10.3390/s20216390 - 9 Nov 2020

Cited by 18 | Viewed by 3579

Abstract

A new tactile sensing module was proposed to sense the contact force and location of an object on a robot hand, which was attached on the robot finger. Three air pressure sensors are installed at the tip of the finger to detect the [...] Read more.

A new tactile sensing module was proposed to sense the contact force and location of an object on a robot hand, which was attached on the robot finger. Three air pressure sensors are installed at the tip of the finger to detect the contacting force at the points. To obtain a nominal contact force at the finger from data from the three air pressure sensors, a force estimation was developed based upon the learning of a deep neural network. The data from the three air pressure sensors were utilized as inputs to estimate the contact force at the finger. In the tactile module, the arrival time of the air pressure sensor data has been utilized to recognize the contact point of the robot finger against an object. Using the three air pressure sensors and arrival time, the finger location can be divided into 3 × 3 block locations. The resolution of the contact point recognition was improved to 6 × 4 block locations on the finger using an artificial neural network. The accuracy and effectiveness of the tactile module were verified using real grasping experiments. With this stable grasping, an optimal grasping force was estimated empirically with fuzzy rules for a given object. Full article

(This article belongs to the Special Issue Smart Sensors for Robotic Systems)

► Show Figures

Figure 1

16 pages, 1677 KiB

Open AccessArticle

Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation

by Kyriakos Koritsoglou, Vasileios Christou, Georgios Ntritsos, Georgios Tsoumanis, Markos G. Tsipouras, Nikolaos Giannakeas and Alexandros T. Tzallas

Sensors 2020, 20(21), 6389; https://doi.org/10.3390/s20216389 - 9 Nov 2020

Cited by 17 | Viewed by 4091

Abstract

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor’s accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for [...] Read more.

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor’s accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method’s outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area—resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM). Full article

(This article belongs to the Special Issue Human-Robot Interaction Applications in Internet of Things (IoT) Era)

► Show Figures

Figure 1

Figure 1
The SLR-DS18B20 System Architecture. This diagram depicts the proposed system’s architecture. The Raspberry Pi Zero W (Device 1) is connected to the series of DS18B20 sensors (the sensors are given the number 2) using pins 7, 17, and 25. Pin 7 is responsible for the communication, pin 17 provides 3.3 voltage to the device, while pin 25 is responsible for grounding the circuit. Then, these sensors are inserted into a commercial fridge (device 3). Full article ">Figure 2
Submerge procedure of the reference sensor and the sensor that is going to be calibrated. Initially, we gently stir and submerge the reference sensor, as seen in the left image. Then, we stir and submerge the sensor that is going to be calibrated (right image). Full article ">Figure 3
The AE regarding sampled values for both temperature areas. The AE for each sampled value is depicted with blue dots. The x-axis shows the temperatures, while on the y-axis, the AE calculated using Formula (7). The left diagram shows the 1st temperature zone’s measurement results where the AE ranged from 0 °C to 2.07 °C. The right graph shows the 2nd temperature zone’s measurement results, where the AE went from 0 °C to 2.07 °C. Full article ">Figure 4
The AE regarding predicted values for both temperature areas. The AE for each sampled value is depicted with blue dots. The x-axis shows the temperatures, while on the y-axis, the AE, which was calculated using Formula (7). The left diagram shows the 1st temperature zone’s measurement results where the AE ranged from 0 °C to 0.75 °C. The right diagram shows the 2nd temperature zone’s measurement results, where the AE went from 0 °C to 0.4 °C. Full article ">Figure 5
Comparison between actual and predicted values for the 1st temperature zone. This diagram compares the <math display="inline"><semantics> <mrow> <mover accent="true"> <mrow> <msup> <mi>R</mi> <mn>2</mn> </msup> </mrow> <mo stretchy="true">¯</mo> </mover> </mrow> </semantics></math> for the actual and predicted values. The 95% CI for each category can be seen with a red vertical line. Each CI’s limits are depicted with magenta (actual values), and blue (predicted values) dashed lines. The two Cis do not overlap, which is a strong indication that the error reduction achieved after the application of linear regression is statistically significant. Full article ">Figure 6
Comparison between actual and predicted values for the 2nd temperature zone. This diagram compares the <math display="inline"><semantics> <mrow> <mover accent="true"> <mrow> <msup> <mi>R</mi> <mn>2</mn> </msup> </mrow> <mo stretchy="true">¯</mo> </mover> </mrow> </semantics></math> for the actual and predicted values. The 95% CI for each category can be seen with a red vertical line. The limits for each CI are depicted with magenta (actual values), and blue (predicted values) dashed lines. The two Cis do not overlap, which is a strong indication that the error reduction achieved after the application of linear regression is statistically significant. Full article ">

12 pages, 1966 KiB

Open AccessArticle

A Random Forest Machine Learning Framework to Reduce Running Injuries in Young Triathletes

by Javier Martínez-Gramage, Juan Pardo Albiach, Iván Nacher Moltó, Juan José Amer-Cuenca, Vanessa Huesa Moreno and Eva Segura-Ortí

Sensors 2020, 20(21), 6388; https://doi.org/10.3390/s20216388 - 9 Nov 2020

Cited by 10 | Viewed by 8413

Abstract

Background: The running segment of a triathlon produces 70% of the lower limb injuries. Previous research has shown a clear association between kinematic patterns and specific injuries during running. Methods: After completing a seven-month gait retraining program, a questionnaire was used to assess [...] Read more.

Background: The running segment of a triathlon produces 70% of the lower limb injuries. Previous research has shown a clear association between kinematic patterns and specific injuries during running. Methods: After completing a seven-month gait retraining program, a questionnaire was used to assess 19 triathletes for the incidence of injuries. They were also biomechanically analyzed at the beginning and end of the program while running at a speed of 90% of their maximum aerobic speed (MAS) using surface sensor dynamic electromyography and kinematic analysis. We used classification tree (random forest) techniques from the field of artificial intelligence to identify linear and non-linear relationships between different biomechanical patterns and injuries to identify which styles best prevent injuries. Results: Fewer injuries occurred after completing the program, with athletes showing less pelvic fall and greater activation in gluteus medius during the first phase of the float phase, with increased trunk extension, knee flexion, and decreased ankle dorsiflexion during the initial contact with the ground. Conclusions: The triathletes who had suffered the most injuries ran with increased pelvic drop and less activation in gluteus medius during the first phase of the float phase. Contralateral pelvic drop seems to be an important variable in the incidence of injuries in young triathletes. Full article

(This article belongs to the Special Issue Wearable Sensors & Gait)

► Show Figures

Figure 1

Figure 1
Visual real-time biofeedback during the retraining protocol. Full article ">Figure 2
Importance of the variables, scaled according to the “varImp” method in the caret R library for the complete data set. Full article ">Figure 3
Density plots showing the differences between pre- and post-values obtained before and after the retraining phase. Higher density values on the ordinate axis point out which are the most probable values on the abscissa axis. The difference in pelvic obliquity in the right and left limb (A), ankle dorsiflexion in the initial contact (B), contralateral pelvic drop (C,D), and gluteus medius activation during the first phase of flight (E,F). Full article ">Figure 4
Density plots comparing the differences between injured and non-injured triathletes in terms of the degree of pelvic obliquity between the (A) pre-retraining; (B) and post-retraining phase values. Higher density values on the ordinate axis point out which are the most probable values on the abscissa axis. Full article ">Figure 5
Gluteus medius (right) sEMG plot pre and post. Full article ">Figure 6
Pelvis kinematics before and after retraining protocol. Full article ">

18 pages, 1887 KiB

Open AccessArticle

LiDAR Point Cloud Recognition and Visualization with Deep Learning for Overhead Contact Inspection

by Xiaohan Tu, Cheng Xu, Siping Liu, Shuai Lin, Lipei Chen, Guoqi Xie and Renfa Li

Sensors 2020, 20(21), 6387; https://doi.org/10.3390/s20216387 - 9 Nov 2020

Cited by 20 | Viewed by 4171

Abstract

As overhead contact (OC) is an essential part of power supply systems in high-speed railways, it is necessary to regularly inspect and repair abnormal OC components. Relative to manual inspection, applying LiDAR (light detection and ranging) to OC inspection can improve efficiency, accuracy, [...] Read more.

As overhead contact (OC) is an essential part of power supply systems in high-speed railways, it is necessary to regularly inspect and repair abnormal OC components. Relative to manual inspection, applying LiDAR (light detection and ranging) to OC inspection can improve efficiency, accuracy, and safety, but it faces challenges to efficiently and effectively segment LiDAR point cloud data and identify catenary components. Recent deep learning-based recognition methods are rarely employed to recognize OC components, because they have high computational complexity, while their accuracy needs to be improved. To track these problems, we first propose a lightweight model, RobotNet, with depthwise and pointwise convolutions and an attention module to recognize the point cloud. Second, we optimize RobotNet to accelerate its recognition speed on embedded devices using an existing compilation tool. Third, we design software to facilitate the visualization of point cloud data. Our software can not only display a large amount of point cloud data, but also visualize the details of OC components. Extensive experiments demonstrate that RobotNet recognizes OC components more accurately and efficiently than others. The inference speed of the optimized RobotNet increases by an order of magnitude. RobotNet has lower computational complexity than other studies. The visualization results also show that our recognition method is effective. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

19 pages, 2813 KiB

Open AccessArticle

Attention-Deficit/Hyperactivity Disorder (ADHD): Integrating the MOXO-dCPT with an Eye Tracker Enhances Diagnostic Precision

by Tomer Elbaum, Yoram Braw, Astar Lev and Yuri Rassovsky

Sensors 2020, 20(21), 6386; https://doi.org/10.3390/s20216386 - 9 Nov 2020

Cited by 11 | Viewed by 7051

Abstract

Clinical decision-making may be enhanced when combining psychophysiological sensors with computerized neuropsychological tests. The current study explored the utility of integrating an eye tracker with a commercially available continuous performance test (CPT), the MOXO-dCPT. As part of the study, the performance of adult [...] Read more.

Clinical decision-making may be enhanced when combining psychophysiological sensors with computerized neuropsychological tests. The current study explored the utility of integrating an eye tracker with a commercially available continuous performance test (CPT), the MOXO-dCPT. As part of the study, the performance of adult attention-deficit/hyperactivity disorder (ADHD) patients and healthy controls (n = 43, n = 42, respectively) was compared in the integrated system. More specifically, the MOXO-dCPT has four stages, which differ in their combinations of ecological visual and auditory dynamic distractors. By exploring the participants’ performance in each of the stages, we were able to show that: (a) ADHD patients spend significantly more time gazing at irrelevant areas of interest (AOIs) compared to healthy controls; (b) visual distractors are particularly effective in impacting ADHD patients’ eye movements, suggesting their enhanced utility in diagnostic procedures; (c) combining gaze direction data and conventional CPT indices enhances group prediction, compared to the sole use of conventional indices. Overall, the findings indicate the utility of eye tracker-integrated CPTs and their enhanced diagnostic precision. They also suggest that the use of attention-grabbing visual distractors may be a promising path for the evolution of existing CPTs by shortening their duration and enhancing diagnostic precision. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

Figure 1
Participant field of view (FOV) while performing the MOXO-dCPT, divided into distractibility (gridded) and target areas of interest (AOIs). Full article ">Figure 2
Receiver operating characteristic (ROC) curves for the eye movement distractibility scale and the MOXO-dCPT indices: (a) All stages; (b) visual distractors stage (eye movement distractibility scale: AUC = 0.78, attention: AUC = 0.51, timeliness index: AUC = 0.63, hyperactivity: AUC = 0.59, impulsivity: AUC = 0.60). Additional information regarding the visual distractors stage is presented later (see “<a href="#sec2dot4dot3-sensors-20-06386" class="html-sec">Section 2.4.3</a>. Exploratory Analysis”). Full article ">Figure 3
Eye movement distractibility line plot, of the four distractor-type stages. Error bars represent standard error (SE) of the repeated-measures ANOVA analysis (see <a href="#sensors-20-06386-t004" class="html-table">Table 4</a>). Full article ">Figure 4
Heat maps of the eye distractibility scale, divided according to group (ADHD/controls) and MOXO-dCPT stages (visual/auditory). Full article ">Figure 5
Timeline plot comparing eye movement distractibility scale of ADHD patients and controls. Four distractors stages (non, visual, auditory, and combined) are presented at the top section of the chart, subdivided into blocks one to eight. Each stage includes two consecutive blocks, except for the no distractors stage (blocks 1 and 8). Full article ">

18 pages, 5125 KiB

Open AccessArticle

A New Method of Secure Authentication Based on Electromagnetic Signatures of Chipless RFID Tags and Machine Learning Approaches

by Dragoș Nastasiu, Răzvan Scripcaru, Angela Digulescu, Cornel Ioana, Raymundo De Amorim, Jr., Nicolas Barbot, Romain Siragusa, Etienne Perret and Florin Popescu

Sensors 2020, 20(21), 6385; https://doi.org/10.3390/s20216385 - 9 Nov 2020

Cited by 14 | Viewed by 3896

Abstract

In this study, we present the implementation of a neural network model capable of classifying radio frequency identification (RFID) tags based on their electromagnetic (EM) signature for authentication applications. One important application of the chipless RFID addresses the counterfeiting threat for manufacturers. The [...] Read more.

In this study, we present the implementation of a neural network model capable of classifying radio frequency identification (RFID) tags based on their electromagnetic (EM) signature for authentication applications. One important application of the chipless RFID addresses the counterfeiting threat for manufacturers. The goal is to design and implement chipless RFID tags that possess a unique and unclonable fingerprint to authenticate objects. As EM characteristics are employed, these fingerprints cannot be easily spoofed. A set of 18 tags operating in V band (65–72 GHz) was designed and measured. V band is more sensitive to dimensional variations compared to other applications at lower frequencies, thus it is suitable to highlight the differences between the EM signatures. Machine learning (ML) approaches are used to characterize and classify the 18 EM responses in order to validate the authentication method. The proposed supervised method reached a maximum recognition rate of 100%, surpassing in terms of accuracy most of RFID fingerprinting related work. To determine the best network configuration, we used a random search algorithm. Further tuning was conducted by comparing the results of different learning algorithms in terms of accuracy and loss. Full article

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

► Show Figures

Figure 1

22 pages, 6390 KiB

Open AccessArticle

Cooperative UAV–UGV Autonomous Power Pylon Inspection: An Investigation of Cooperative Outdoor Vehicle Positioning Architecture

by Alvaro Cantieri, Matheus Ferraz, Guido Szekir, Marco Antônio Teixeira, José Lima, André Schneider Oliveira and Marco Aurélio Wehrmeister

Sensors 2020, 20(21), 6384; https://doi.org/10.3390/s20216384 - 9 Nov 2020

Cited by 32 | Viewed by 5561

Abstract

Realizing autonomous inspection, such as that of power distribution lines, through unmanned aerial vehicle (UAV) systems is a key research domain in robotics. In particular, the use of autonomous and semi-autonomous vehicles to execute the tasks of an inspection process can enhance the [...] Read more.

Realizing autonomous inspection, such as that of power distribution lines, through unmanned aerial vehicle (UAV) systems is a key research domain in robotics. In particular, the use of autonomous and semi-autonomous vehicles to execute the tasks of an inspection process can enhance the efficacy and safety of the operation; however, many technical problems, such as those pertaining to the precise positioning and path following of the vehicles, robust obstacle detection, and intelligent control, must be addressed. In this study, an innovative architecture involving an unmanned aircraft vehicle (UAV) and an unmanned ground vehicle (UGV) was examined for detailed inspections of power lines. In the proposed strategy, each vehicle provides its position information to the other, which ensures a safe inspection process. The results of real-world experiments indicate a satisfactory performance, thereby demonstrating the feasibility of the proposed approach. Full article

(This article belongs to the Special Issue UAV-Based Smart Sensor Systems and Applications)

► Show Figures

Graphical abstract

21 pages, 713 KiB

Open AccessArticle

Machine Learning Improvements to Human Motion Tracking with IMUs

by Pedro Manuel Santos Ribeiro, Ana Clara Matos, Pedro Henrique Santos and Jaime S. Cardoso

Sensors 2020, 20(21), 6383; https://doi.org/10.3390/s20216383 - 9 Nov 2020

Cited by 19 | Viewed by 8465

Abstract

Inertial Measurement Units (IMUs) have become a popular solution for tracking human motion. The main problem of using IMU data for deriving the position of different body segments throughout time is related to the accumulation of the errors in the inertial data. The [...] Read more.

Inertial Measurement Units (IMUs) have become a popular solution for tracking human motion. The main problem of using IMU data for deriving the position of different body segments throughout time is related to the accumulation of the errors in the inertial data. The solution to this problem is necessary to improve the use of IMUs for position tracking. In this work, we present several Machine Learning (ML) methods to improve the position tracking of various body segments when performing different movements. Firstly, classifiers were used to identify the periods in which the IMUs were stopped (zero-velocity detection). The models Random Forest, Support Vector Machine (SVM) and neural networks based on Long-Short-Term Memory (LSTM) layers were capable of identifying those periods independently of the motion and body segment with a substantially higher performance than the traditional fixed-threshold zero-velocity detectors. Afterwards, these techniques were combined with ML regression models based on LSTMs capable of estimating the displacement of the sensors during periods of movement. These models did not show significant improvements when compared with the more straightforward double integration of the linear acceleration data with drift removal for translational motion estimate. Finally, we present a model based on LSTMs that combined simultaneously zero-velocity detection with the translational motion of sensors estimate. This model revealed a lower average error for position tracking than the combination of the previously referred methodologies. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

21 pages, 12075 KiB

Open AccessCommunication

Damage Proxy Map of the Beirut Explosion on 4th of August 2020 as Observed from the Copernicus Sensors

by Athos Agapiou

Sensors 2020, 20(21), 6382; https://doi.org/10.3390/s20216382 - 9 Nov 2020

Cited by 15 | Viewed by 5978

Abstract

On the 4th of August 2020, a massive explosion occurred in the harbor area of Beirut, Lebanon, killing more than 100 people and damaging numerous buildings in its proximity. The current article aims to showcase how open access and freely distributed satellite data, [...] Read more.

On the 4th of August 2020, a massive explosion occurred in the harbor area of Beirut, Lebanon, killing more than 100 people and damaging numerous buildings in its proximity. The current article aims to showcase how open access and freely distributed satellite data, such as those of the Copernicus radar and optical sensors, can deliver a damage proxy map of this devastating event. Sentinel-1 radar images acquired just prior (the 24th of July 2020) and after the event (5th of August 2020) were processed and analyzed, indicating areas with significant changes of the VV (vertical transmit, vertical receive) and VH (vertical transmit, horizontal receive) backscattering signal. In addition, an Interferometric Synthetic Aperture Radar (InSAR) analysis was performed for both descending (31st of July 2020 and 6th of August 2020) and ascending (29th of July 2020 and 10th of August 2020) orbits of Sentinel-1 images, indicating relative small ground displacements in the area near the harbor. Moreover, low coherence for these images is mapped around the blast zone. The current study uses the Hybrid Pluggable Processing Pipeline (HyP3) cloud-based system provided by the Alaska Satellite Facility (ASF) for the processing of the radar datasets. In addition, medium-resolution Sentinel-2 optical data were used to support thorough visual inspection and Principal Component Analysis (PCA) the damage in the area. While the overall findings are well aligned with other official reports found on the World Wide Web, which were mainly delivered by international space agencies, those reports were generated after the processing of either optical or radar datasets. In contrast, the current communication showcases how both optical and radar satellite data can be parallel used to map other devastating events. The use of open access and freely distributed Sentinel mission data was found very promising for delivering damage proxies maps after devastating events worldwide. Full article

(This article belongs to the Special Issue Innovations in Photogrammetry and Remote Sensing: Modern Sensors, New Processing Strategies and Frontiers in Applications)

► Show Figures

Figure 1

22 pages, 707 KiB

Open AccessArticle

Analysis of Copernicus’ ERA5 Climate Reanalysis Data as a Replacement for Weather Station Temperature Measurements in Machine Learning Models for Olive Phenology Phase Prediction

by Noelia Oses, Izar Azpiroz, Susanna Marchi, Diego Guidotti, Marco Quartulli and Igor G. Olaizola

Sensors 2020, 20(21), 6381; https://doi.org/10.3390/s20216381 - 9 Nov 2020

Cited by 39 | Viewed by 6409

Abstract

Knowledge of phenological events and their variability can help to determine final yield, plan management approach, tackle climate change, and model crop development. THe timing of phenological stages and phases is known to be highly correlated with temperature which is therefore an essential [...] Read more.

Knowledge of phenological events and their variability can help to determine final yield, plan management approach, tackle climate change, and model crop development. THe timing of phenological stages and phases is known to be highly correlated with temperature which is therefore an essential component for building phenological models. Satellite data and, particularly, Copernicus’ ERA5 climate reanalysis data are easily available. Weather stations, on the other hand, provide scattered temperature data, with fragmentary spatial coverage and accessibility, as such being scarcely efficacious as unique source of information for the implementation of predictive models. However, as ERA5 reanalysis data are not real temperature measurements but reanalysis products, it is necessary to verify whether these data can be used as a replacement for weather station temperature measurements. The aims of this study were: (i) to assess the validity of ERA5 data as a substitute for weather station temperature measurements, (ii) to test different machine learning models for the prediction of phenological phases while using different sets of features, and (iii) to optimize the base temperature of olive tree phenological model. The predictive capability of machine learning models and the performance of different feature subsets were assessed when comparing the recorded temperature data, ERA5 data, and a simple growing degree day phenological model as benchmark. Data on olive tree phenology observation, which were collected in Tuscany for three years, provided the phenological phases to be used as target variables. The results show that ERA5 climate reanalysis data can be used for modelling phenological phases and that these models provide better predictions in comparison with the models trained with weather station temperature measurements. Full article

(This article belongs to the Special Issue Selected Papers from the Global IoT Summit GIoTS 2020)

► Show Figures

Figure 1

25 pages, 1125 KiB

Open AccessArticle

Spatio-Temporal Scale Coded Bag-of-Words

by Divina Govender and Jules-Raymond Tapamo

Sensors 2020, 20(21), 6380; https://doi.org/10.3390/s20216380 - 9 Nov 2020

Cited by 2 | Viewed by 3084

Abstract

The Bag-of-Words (BoW) framework has been widely used in action recognition tasks due to its compact and efficient feature representation. Various modifications have been made to this framework to increase its classification power. This often results in an increased complexity and reduced efficiency. [...] Read more.

The Bag-of-Words (BoW) framework has been widely used in action recognition tasks due to its compact and efficient feature representation. Various modifications have been made to this framework to increase its classification power. This often results in an increased complexity and reduced efficiency. Inspired by the success of image-based scale coded BoW representations, we propose a spatio-temporal scale coded BoW (SC-BoW) for video-based recognition. This involves encoding extracted multi-scale information into BoW representations by partitioning spatio-temporal features into sub-groups based on the spatial scale from which they were extracted. We evaluate SC-BoW in two experimental setups. We first present a general pipeline to perform real-time action recognition with SC-BoW. Secondly, we apply SC-BoW onto the popular Dense Trajectory feature set. Results showed SC-BoW representations to successfully improve performance by 2–7% with low added computational cost. Notably, SC-BoW on Dense Trajectories outperformed more complex deep learning approaches. Thus, scale coding is a low-cost and low-level encoding scheme that increases classification power of the standard BoW without compromising efficiency. Full article

(This article belongs to the Special Issue Data Processing of Intelligent Sensors)

► Show Figures

Figure 1

21 pages, 5088 KiB

Open AccessArticle

Functional Evaluation of a Force Sensor-Controlled Upper-Limb Power-Assisted Exoskeleton with High Backdrivability

by Chang Liu, Hongbo Liang, Naoya Ueda, Peirang Li, Yasutaka Fujimoto and Chi Zhu

Sensors 2020, 20(21), 6379; https://doi.org/10.3390/s20216379 - 9 Nov 2020

Cited by 16 | Viewed by 4436

Abstract

A power-assisted exoskeleton should be capable of reducing the burden on the wearer’s body or rendering his or her work improved and efficient. More specifically, the exoskeleton should be easy to wear, be simple to use, and provide power assistance without hindering the [...] Read more.

A power-assisted exoskeleton should be capable of reducing the burden on the wearer’s body or rendering his or her work improved and efficient. More specifically, the exoskeleton should be easy to wear, be simple to use, and provide power assistance without hindering the wearer’s movement. Therefore, it is necessary to evaluate the backdrivability, range of motion, and power-assist capability of such an exoskeleton. This evaluation identifies the pros and cons of the exoskeleton, and it serves as the basis for its subsequent development. In this study, a lightweight upper-limb power-assisted exoskeleton with high backdrivability was developed. Moreover, a motion capture system was adopted to measure and analyze the workspace of the wearer’s upper limb after the exoskeleton was worn. The results were used to evaluate the exoskeleton’s ability to support the wearer’s movement. Furthermore, a small and compact three-axis force sensor was used for power assistance, and the effect of the power assistance was evaluated by means of measuring the wearer’s surface electromyography, force, and joint angle signals. Overall, the study showed that the exoskeleton could achieve power assistance and did not affect the wearer’s movements. Full article

(This article belongs to the Section Wearables)

► Show Figures

Figure 1

21 pages, 3409 KiB

Open AccessArticle

A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification

by Ahmad M. Karim, Hilal Kaya, Mehmet Serdar Güzel, Mehmet R. Tolun, Fatih V. Çelebi and Alok Mishra

Sensors 2020, 20(21), 6378; https://doi.org/10.3390/s20216378 - 9 Nov 2020

Cited by 20 | Viewed by 3784

Abstract

This paper proposes a novel data classification framework, combining sparse auto-encoders (SAEs) and a post-processing system consisting of a linear system model relying on Particle Swarm Optimization (PSO) algorithm. All the sensitive and high-level features are extracted by using the first auto-encoder which [...] Read more.

This paper proposes a novel data classification framework, combining sparse auto-encoders (SAEs) and a post-processing system consisting of a linear system model relying on Particle Swarm Optimization (PSO) algorithm. All the sensitive and high-level features are extracted by using the first auto-encoder which is wired to the second auto-encoder, followed by a Softmax function layer to classify the extracted features obtained from the second layer. The two auto-encoders and the Softmax classifier are stacked in order to be trained in a supervised approach using the well-known backpropagation algorithm to enhance the performance of the neural network. Afterwards, the linear model transforms the calculated output of the deep stacked sparse auto-encoder to a value close to the anticipated output. This simple transformation increases the overall data classification performance of the stacked sparse auto-encoder architecture. The PSO algorithm allows the estimation of the parameters of the linear model in a metaheuristic policy. The proposed framework is validated by using three public datasets, which present promising results when compared with the current literature. Furthermore, the framework can be applied to any data classification problem by considering minor updates such as altering some parameters including input features, hidden neurons and output classes. Full article

(This article belongs to the Special Issue Convergence of Intelligent Data Acquisition and Advanced Computing Systems)

► Show Figures

Figure 1

12 pages, 2667 KiB

Open AccessLetter

Classification of Aggressive Movements Using Smartwatches

by Franck Tchuente, Natalie Baddour and Edward D. Lemaire

Sensors 2020, 20(21), 6377; https://doi.org/10.3390/s20216377 - 9 Nov 2020

Cited by 8 | Viewed by 2998

Abstract

Recognizing aggressive movements is a challenging task in human activity recognition. Wearable smartwatch technology with machine learning may be a viable approach for human aggressive behavior classification. This research identified a viable classification model and feature selector (CM-FS) combination for separating aggressive from [...] Read more.

Recognizing aggressive movements is a challenging task in human activity recognition. Wearable smartwatch technology with machine learning may be a viable approach for human aggressive behavior classification. This research identified a viable classification model and feature selector (CM-FS) combination for separating aggressive from non-aggressive movements using smartwatch data and determined if only one smartwatch is sufficient for this task. A ranking method was used to select relevant CM-FS models across accuracy, sensitivity, specificity, precision, F-score, and Matthews correlation coefficient (MCC). The Waikato environment for knowledge analysis (WEKA) was used to run 6 machine learning classifiers (random forest, k-nearest neighbors (kNN), multilayer perceptron neural network (MP), support vector machine, naïve Bayes, decision tree) coupled with three feature selectors (ReliefF, InfoGain, Correlation). Microsoft Band 2 accelerometer and gyroscope data were collected during an activity circuit that included aggressive (punching, shoving, slapping, shaking) and non-aggressive (clapping hands, waving, handshaking, opening/closing a door, typing on a keyboard) tasks. A combination of kNN and ReliefF was the best CM-FS model for separating aggressive actions from non-aggressive actions, with 99.6% accuracy, 98.4% sensitivity, 99.8% specificity, 98.9% precision, 0.987 F-score, and 0.984 MCC. kNN and random forest classifiers, combined with any of the feature selectors, generated the top models. Models with naïve Bayes or support vector machines had poor performance for sensitivity, F-score, and MCC. Wearing the smartwatch on the dominant wrist produced the best single-watch results. The kNN and ReliefF combination demonstrated that this smartwatch-based approach is a viable solution for identifying aggressive behavior. This wrist-based wearable sensor approach could be used by care providers in settings where people suffer from dementia or mental health disorders, where random aggressive behaviors often occur. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

17 pages, 10375 KiB

Open AccessArticle

Driver Characteristics Oriented Autonomous Longitudinal Driving System in Car-Following Situation

by Haksu Kim, Kyunghan Min and Myoungho Sunwoo

Sensors 2020, 20(21), 6376; https://doi.org/10.3390/s20216376 - 9 Nov 2020

Cited by 10 | Viewed by 3075

Abstract

Advanced driver assistance system such as adaptive cruise control, traffic jam assistance, and collision warning has been developed to reduce the driving burden and increase driving comfort in the car-following situation. These systems provide automated longitudinal driving to ensure safety and driving performance [...] Read more.

Advanced driver assistance system such as adaptive cruise control, traffic jam assistance, and collision warning has been developed to reduce the driving burden and increase driving comfort in the car-following situation. These systems provide automated longitudinal driving to ensure safety and driving performance to satisfy unspecified individuals. However, drivers can feel a sense of heterogeneity when autonomous longitudinal control is performed by a general speed planning algorithm. In order to solve heterogeneity, a speed planning algorithm that reflects individual driving behavior is required to guarantee harmony with the intention of the driver. In this paper, we proposed a personalized longitudinal driving system in a car-following situation, which mimics personal driving behavior. The system is structured by a multi-layer framework composed of a speed planner and driver parameter manager. The speed planner generates an optimal speed profile by parametric cost function and constraints that imply driver characteristics. Furthermore, driver parameters are determined by the driver parameter manager according to individual driving behavior based on real driving data. The proposed algorithm was validated through driving simulation. The results show that the proposed algorithm mimics the driving style of an actual driver while maintaining safety against collisions with the preceding vehicle. Full article

(This article belongs to the Section Intelligent Sensors)

► Show Figures

Figure 1

8 pages, 1042 KiB

Open AccessLetter

Beryllium-Ion-Selective PEDOT Solid Contact Electrode Based on 9,10-Dinitrobenzo-9-Crown-3-Ether

by Junghwan Kim, Dae Hee Kim, Jin Cheol Yang, Jae Sang Kim, Ji Ha Lee and Sung Ho Jung

Sensors 2020, 20(21), 6375; https://doi.org/10.3390/s20216375 - 9 Nov 2020

Cited by 3 | Viewed by 2892

Abstract

A beryllium(II)-ion-selective poly(ethylenedioxythiophene) (PEDOT) solid contact electrode comprising 9,10-dinitrobenzo-9-crown-3-ether was successfully developed. The all-solid-state contact electrode, with an oxygen-containing cation-sensing membrane combined with an electropolymerized PEDOT layer, exhibited the best response characteristics. The performance of the constructed electrode was evaluated and optimized using [...] Read more.

A beryllium(II)-ion-selective poly(ethylenedioxythiophene) (PEDOT) solid contact electrode comprising 9,10-dinitrobenzo-9-crown-3-ether was successfully developed. The all-solid-state contact electrode, with an oxygen-containing cation-sensing membrane combined with an electropolymerized PEDOT layer, exhibited the best response characteristics. The performance of the constructed electrode was evaluated and optimized using potentiometry, conductance measurements, constant-current chronopotentiometry, and electrochemical impedance spectroscopy (EIS). Under optimized conditions, which were found for an ion-selective membrane (ISM) composition of 3% ionophore, 30% polyvinylchloride (PVC), 64% o-nitro phenyl octyl ether (o-NPOE), and 3% sodium tetraphenylborate (NaTPB), the fabricated electrode exhibited a good performance over a wide concentration range (10^−2.5–10^−7.0 M) and a wide pH range of 2.0–9.0, with a Nernstian slope of 29.5 mV/D for the beryllium (II) ion and a detection limit as low as 10^−7.0 M. The developed electrode shows good selectivity for the beryllium(II) ion over alkali, alkaline earth, transition, and heavy metal ions. Full article

(This article belongs to the Section Chemical Sensors)

► Show Figures

Figure 1

18 pages, 3056 KiB

Open AccessArticle

Temporal Changes in Air Quality According to Land-Use Using Real Time Big Data from Smart Sensors in Korea

by Sung Su Jo, Sang Ho Lee and Yountaik Leem

Sensors 2020, 20(21), 6374; https://doi.org/10.3390/s20216374 - 9 Nov 2020

Cited by 11 | Viewed by 3237

Abstract

This study analyzed the changes in particulate matter concentrations according to land-use over time and the spatial characteristics of the distribution of particulate matter concentrations using big data of particulate matter in Daejeon, Korea, measured by Private Air Quality Monitoring Smart Sensors (PAQMSSs). [...] Read more.

This study analyzed the changes in particulate matter concentrations according to land-use over time and the spatial characteristics of the distribution of particulate matter concentrations using big data of particulate matter in Daejeon, Korea, measured by Private Air Quality Monitoring Smart Sensors (PAQMSSs). Land-uses were classified into residential, commercial, industrial, and green groups according to the primary land-use around the 650-m sensor radius. Data on particulate matter with an aerodynamic diameter <10 µm (PM10) and <2.5 µm (PM2.5) were captured by PAQMSSs from September?October (i.e., fall) in 2019. Differences and variation characteristics of particulate matter concentrations between time periods and land-uses were analyzed and spatial mobility characteristics of the particulate matter concentrations over time were analyzed. The results indicate that the particulate matter concentrations in Daejeon decreased in the order of industrial, housing, commercial and green groups overall; however, the concentrations of the commercial group were higher than those of the residential group during 21:00–23:00, which reflected the vital nighttime lifestyle in the commercial group in Korea. Second, the green group showed the lowest particulate matter concentration and the industrial group showed the highest concentration. Third, the highest particulate matter concentrations were in urban areas where commercial and business functions were centered and in the vicinity of industrial complexes. Finally, over time, the PM10 concentrations were clearly high at noon and low at night, whereas the PM2.5 concentrations were similar at certain areas. Full article

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

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors, Volume 20, Issue 21 (November-1 2020) – 437 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI