Previous Issue
Volume 21, April-2
sensors-logo

Journal Browser

Journal Browser

Sensors, Volume 21, Issue 9 (May-1 2021) – 342 articles

  • 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 Readerexternal link to open them.
Order results
Result details
Select all
Export citation of selected articles as:
Open AccessArticle
Nonparametric Frequency Response Identification for Dc-Dc Converters Based on Spectral Analysis with Automatic Determination of the Perturbation Amplitude
by , , and
Sensors 2021, 21(9), 3234; https://doi.org/10.3390/s21093234 (registering DOI) - 07 May 2021
Abstract
Digital control for high switching frequency converter enables new features on DC-DC power conversion for a minimum cost. Frequency response identification is one such enabled functionality used in auto tunning, measurement of components to assess the converter’s state of health, or system stability [...] Read more.
Digital control for high switching frequency converter enables new features on DC-DC power conversion for a minimum cost. Frequency response identification is one such enabled functionality used in auto tunning, measurement of components to assess the converter’s state of health, or system stability monitoring. High accuracy, flexibility to operate in open or closed loop, and minimum impact in the converter’s regular operation are the frequency response identification system’s goals. We propose in this paper a nonparametric identification system addressing these main goals. First, it can autoadjust the perturbation size to reduce the perturbation’s impact on the converter’s output quantities. Second, as it is based on spectral analysis, it is suitable for open and closed-loop operation. Third, we demonstrate the identification system’s high accuracy, achieving a very low difference between the experimental measurements and the discrete model used as reference. Full article
Show Figures

Figure 1

Open AccessArticle
Intelligent Tire Sensor-Based Real-Time Road Surface Classification Using an Artificial Neural Network
by , , and
Sensors 2021, 21(9), 3233; https://doi.org/10.3390/s21093233 (registering DOI) - 07 May 2021
Abstract
Vehicles today have many advanced driver assistance control systems that improve vehicle safety and comfort. With the development of more sophisticated vehicle electronic control and autonomous driving technology, the need and effort to estimate road surface conditions is increasing. In this paper, a [...] Read more.
Vehicles today have many advanced driver assistance control systems that improve vehicle safety and comfort. With the development of more sophisticated vehicle electronic control and autonomous driving technology, the need and effort to estimate road surface conditions is increasing. In this paper, a real-time road surface classification algorithm, based on a deep neural network, is developed using a database collected through an intelligent tire sensor system with a three-axis accelerometer installed inside the tire. Two representative types of network, fully connected neural network (FCNN) and convolutional neural network (CNN), are learned with each of the three-axis acceleration sensor signals, and their performances were compared to obtain an optimal learning network result. The learning results show that the road surface type can be classified in real-time with sufficient accuracy when the longitudinal and vertical axis acceleration signals are trained with the CNN. In order to improve classification accuracy, a CNN with multiple input that can simultaneously learn 2-axis or 3-axis acceleration signals is suggested. In addition, by analyzing how the accuracy of the network is affected by number of classes and length of input data, which is related to delay of classification, the appropriate network can be selected according to the application. The proposed real-time road surface classification algorithm is expected to be utilized with various vehicle electronic control systems and makes a contribution to improving vehicle performance. Full article
(This article belongs to the Section Intelligent Sensors)
Show Figures

Figure 1

Open AccessCommunication
Data Link with a High-Power Pulsed Quantum Cascade Laser Operating at the Wavelength of 4.5 µm
by
Sensors 2021, 21(9), 3231; https://doi.org/10.3390/s21093231 (registering DOI) - 07 May 2021
Abstract
This article is a short study of the application of high-power quantum cascade lasers and photodetectors in medium-infrared optical wireless communications (OWC). The link range is mainly determined by the transmitted beam parameters and the performance of the light sensor. The light power [...] Read more.
This article is a short study of the application of high-power quantum cascade lasers and photodetectors in medium-infrared optical wireless communications (OWC). The link range is mainly determined by the transmitted beam parameters and the performance of the light sensor. The light power and the photodetector noise directly determine the signal-to-noise power ratio. This ratio could be maximized in the case of minimizing the radiation losses caused by atmospheric attenuation. It can be obtained by applying both radiation sources and sensors operated in the medium infrared range decreasing the effects of absorption, scattering or scintillation, beam spreading, and beam wandering. The development of a new class of laser sources based on quantum cascade structures becomes a prospective alternative. Regarding the literature, there are descriptions of some preliminary research applying these lasers in data transmission. To provide a high data transfer rate, continuous wave (cw) lasers are commonly used. However, they are characterized by low power (a few tens of mWatts) limiting their link range. Also, only a few high-power pulsed lasers (a few hundreds of mWatts) were tested. Due to their limited pulse duty cycle, the obtained modulation bandwidth was lower than 1 MHz. The main goal of this study is to experimentally determine the capabilities of the currently developed state-of-the-art high-power pulsed quantum cascade (QC) lasers and photodetectors in OWC systems. Finally, the data link range using optical pulses of a QC laser of ~2 W, operated at the wavelength of ~4.5 µm, is discussed. Full article
(This article belongs to the Special Issue Mid-Infrared Sensors and Applications)
Show Figures

Figure 1

Open AccessReview
Cement-Based Piezoelectric Ceramic Composites for Sensing Elements: A Comprehensive State-of-the-Art Review
by , , , , and
Sensors 2021, 21(9), 3230; https://doi.org/10.3390/s21093230 (registering DOI) - 07 May 2021
Abstract
Compatibility, a critical issue between sensing material and host structure, significantly influences the detecting performance (e.g., sensitive, signal-to-noise ratio) of the embedded sensor. To address this issue in concrete-based infrastructural health monitoring, cement-based piezoelectric composites (piezoelectric ceramic particles as a function phase and [...] Read more.
Compatibility, a critical issue between sensing material and host structure, significantly influences the detecting performance (e.g., sensitive, signal-to-noise ratio) of the embedded sensor. To address this issue in concrete-based infrastructural health monitoring, cement-based piezoelectric composites (piezoelectric ceramic particles as a function phase and cementitious materials as a matrix) have attracted continuous attention in the past two decades, dramatically exhibiting superior durability, sensitivity, and compatibility. This review paper performs a synthetical overview of recent advances in theoretical analysis, characterization and simulation, materials selection, the fabrication process, and application of the cement-based piezoelectric composites. The critical issues of each part are also presented. The influencing factors of the materials and fabrication process on the final performance of composites are further discussed. Meanwhile, the application of the composite as a sensing element for various monitoring techniques is summarized. Further study on the experiment and simulation, materials, fabrication technique, and application are also pointed out purposefully. Full article
(This article belongs to the Special Issue Acoustic Emission Sensors for Structural Health Monitoring)
Show Figures

Figure 1

Open AccessArticle
PPTFH: Robust Local Descriptor Based on Point-Pair Transformation Features for 3D Surface Matching
by , , , , , and
Sensors 2021, 21(9), 3229; https://doi.org/10.3390/s21093229 (registering DOI) - 07 May 2021
Viewed by 95
Abstract
Three-dimensional feature description for a local surface is a core technology in 3D computer vision. Existing descriptors perform poorly in terms of distinctiveness and robustness owing to noise, mesh decimation, clutter, and occlusion in real scenes. In this paper, we propose a 3D [...] Read more.
Three-dimensional feature description for a local surface is a core technology in 3D computer vision. Existing descriptors perform poorly in terms of distinctiveness and robustness owing to noise, mesh decimation, clutter, and occlusion in real scenes. In this paper, we propose a 3D local surface descriptor using point-pair transformation feature histograms (PPTFHs) to address these challenges. The generation process of the PPTFH descriptor consists of three steps. First, a simple but efficient strategy is introduced to partition the point-pair sets on the local surface into four subsets. Then, three feature histograms corresponding to each point-pair subset are generated by the point-pair transformation features, which are computed using the proposed Darboux frame. Finally, all the feature histograms of the four subsets are concatenated into a vector to generate the overall PPTFH descriptor. The performance of the PPTFH descriptor is evaluated on several popular benchmark datasets, and the results demonstrate that the PPTFH descriptor achieves superior performance in terms of descriptiveness and robustness compared with state-of-the-art algorithms. The benefits of the PPTFH descriptor for 3D surface matching are demonstrated by the results obtained from five benchmark datasets. Full article
(This article belongs to the Special Issue Computer Vision for 3D Perception and Applications)
Show Figures

Figure 1

Open AccessReview
A Systematic Review of Location Aware Schemes in the Internet of Things
by , , and
Sensors 2021, 21(9), 3228; https://doi.org/10.3390/s21093228 - 06 May 2021
Viewed by 161
Abstract
The rapid development in wireless technologies is positioning the Internet of Things (IoT) as an essential part of our daily lives. Localization is one of the most attractive applications related to IoT. In the past few years, localization has been gaining attention because [...] Read more.
The rapid development in wireless technologies is positioning the Internet of Things (IoT) as an essential part of our daily lives. Localization is one of the most attractive applications related to IoT. In the past few years, localization has been gaining attention because of its applicability in safety, health monitoring, environment monitoring, and security. As a result, various localization-based wireless frameworks are being presented to improve such applications’ performances based on specific key performance indicators (KPIs). Therefore, this paper explores the recently proposed localization schemes in IoT. Initially, this paper explains the major KPIs of localization. After that, a thorough comparison of recently proposed localization schemes based on the KPIs is presented. The comparison includes an overview, architecture, network structure, performance parameters, and target KPIs. At the end, possible future directions are presented for the researchers working in this domain. Full article
(This article belongs to the Special Issue Wireless Sensor Networks in the IoT: New Challenges)
Open AccessArticle
ResSANet: Learning Geometric Information for Point Cloud-Processing
by , , , and
Sensors 2021, 21(9), 3227; https://doi.org/10.3390/s21093227 - 06 May 2021
Viewed by 132
Abstract
Point clouds with rich local geometric information have potentially huge implications in several applications, especially in areas of robotic manipulation and autonomous driving. However, most point cloud processing methods cannot extract enough geometric features from a raw point cloud, which restricts the performance [...] Read more.
Point clouds with rich local geometric information have potentially huge implications in several applications, especially in areas of robotic manipulation and autonomous driving. However, most point cloud processing methods cannot extract enough geometric features from a raw point cloud, which restricts the performance of their downstream tasks such as point cloud classification, shape retrieval and part segmentation. In this paper, the authors propose a new method where a convolution based on geometric primitives is adopted to accurately represent the elusive shape in the form of a point cloud to fully extract hidden geometric features. The key idea of the proposed approach is building a brand-new convolution net named ResSANet on the basis of geometric primitives to learn hierarchical geometry information. Two different modules are devised in our network, Res-SA and Res­SA­2, to achieve feature fusion at different levels in ResSANet. This work achieves classification accuracy up to 93.2% on the ModelNet40 dataset and the shape retrieval with an effect of 87.4%. The part segmentation experiment also achieves an accuracy of 83.3% (class mIoU) and 85.3% (instance mIoU) on ShapeNet dataset. It is worth mentioning that the number of parameters in this work is just 1.04M while the network depth is minimal. Experimental results and comparisons with state-of-the-art methods demonstrate that our approach can achieve superior performance. Full article
(This article belongs to the Section Remote Sensors)
Open AccessArticle
Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions
by , , and
Sensors 2021, 21(9), 3226; https://doi.org/10.3390/s21093226 - 06 May 2021
Viewed by 144
Abstract
Considering various fault states under severe working conditions, the comprehensive feature extraction from the raw vibration signal is still a challenge for the diagnosis task of rolling bearing. To deal with strong coupling and high nonlinearity of the vibration signal, this article proposes [...] Read more.
Considering various fault states under severe working conditions, the comprehensive feature extraction from the raw vibration signal is still a challenge for the diagnosis task of rolling bearing. To deal with strong coupling and high nonlinearity of the vibration signal, this article proposes a novel multilocation and multikernel scale learning network based on deep convolution encoder (DCE) and bidirectional short-term memory network (BiLSTM). The former multifeature learning network of this article proposed combines the skip connection and the DCE network. The network can automatically extract and fuse global and local features from different network depth and time scales of the raw vibration signal. Then, the former network as the input of the latter network is fed into the feature protection layer for further mining sensitive and complementary features. Consequently, the proposed network scheme can perform well in generalization capability. The performance of the proposed method is verified on the two kinds of bearing datasets. The diagnostic results demonstrate that the proposed method can diagnose multiple fault types more accurately. Also, the method performs better in load and speed adaptation compared with other intelligent fault classification methods. Full article
(This article belongs to the Special Issue Artificial Intelligence for Data-Driven Fault Detection and Diagnosis)
Open AccessArticle
The Effects of Individual Differences, Non-Stationarity, and the Importance of Data Partitioning Decisions for Training and Testing of EEG Cross-Participant Models
by , and
Sensors 2021, 21(9), 3225; https://doi.org/10.3390/s21093225 - 06 May 2021
Viewed by 134
Abstract
EEG-based deep learning models have trended toward models that are designed to perform classification on any individual (cross-participant models). However, because EEG varies across participants due to non-stationarity and individual differences, certain guidelines must be followed for partitioning data into training, validation, and [...] Read more.
EEG-based deep learning models have trended toward models that are designed to perform classification on any individual (cross-participant models). However, because EEG varies across participants due to non-stationarity and individual differences, certain guidelines must be followed for partitioning data into training, validation, and testing sets, in order for cross-participant models to avoid overestimation of model accuracy. Despite this necessity, the majority of EEG-based cross-participant models have not adopted such guidelines. Furthermore, some data repositories may unwittingly contribute to the problem by providing partitioned test and non-test datasets for reasons such as competition support. In this study, we demonstrate how improper dataset partitioning and the resulting improper training, validation, and testing of a cross-participant model leads to overestimated model accuracy. We demonstrate this mathematically, and empirically, using five publicly available datasets. To build the cross-participant models for these datasets, we replicate published results and demonstrate how the model accuracies are significantly reduced when proper EEG cross-participant model guidelines are followed. Our empirical results show that by not following these guidelines, error rates of cross-participant models can be underestimated between 35% and 3900%. This misrepresentation of model performance for the general population potentially slows scientific progress toward truly high-performing classification models. Full article
(This article belongs to the Special Issue Intelligent Biosignal Analysis Methods)
Open AccessArticle
Quantification of Blood Flow Velocity in the Human Conjunctival Microvessels Using Deep Learning-Based Stabilization Algorithm
by , , , and
Sensors 2021, 21(9), 3224; https://doi.org/10.3390/s21093224 - 06 May 2021
Viewed by 139
Abstract
The quantification of blood flow velocity in the human conjunctiva is clinically essential for assessing microvascular hemodynamics. Since the conjunctival microvessel is imaged in several seconds, eye motion during image acquisition causes motion artifacts limiting the accuracy of image segmentation performance and measurement [...] Read more.
The quantification of blood flow velocity in the human conjunctiva is clinically essential for assessing microvascular hemodynamics. Since the conjunctival microvessel is imaged in several seconds, eye motion during image acquisition causes motion artifacts limiting the accuracy of image segmentation performance and measurement of the blood flow velocity. In this paper, we introduce a novel customized optical imaging system for human conjunctiva with deep learning-based segmentation and motion correction. The image segmentation process is performed by the Attention-UNet structure to achieve high-performance segmentation results in conjunctiva images with motion blur. Motion correction processes with two steps—registration and template matching—are used to correct for large displacements and fine movements. The image displacement values decrease to 4–7 μm during registration (first step) and less than 1 μm during template matching (second step). With the corrected images, the blood flow velocity is calculated for selected vessels considering temporal signal variances and vessel lengths. These methods for resolving motion artifacts contribute insights into studies quantifying the hemodynamics of the conjunctiva, as well as other tissues. Full article
(This article belongs to the Special Issue Computer Aided Diagnosis Sensors)
Open AccessArticle
Generating Instructive Questions from Multiple Articles to Guide Reading in E-Bibliotherapy
by , , , and
Sensors 2021, 21(9), 3223; https://doi.org/10.3390/s21093223 - 06 May 2021
Viewed by 145
Abstract
E-Bibliotherapy deals with adolescent psychological stress by manually or automatically recommending multiple reading articles around their stressful events, using electronic devices as a medium. To make E-Bibliotherapy really useful, generating instructive questions before their reading is an important step. Such a question shall [...] Read more.
E-Bibliotherapy deals with adolescent psychological stress by manually or automatically recommending multiple reading articles around their stressful events, using electronic devices as a medium. To make E-Bibliotherapy really useful, generating instructive questions before their reading is an important step. Such a question shall (a) attract teens’ attention; (b) convey the essential message of the reading materials so as to improve teens’ active comprehension; and most importantly (c) highlight teens’ stress to enable them to generate emotional resonance and thus willingness to pursue the reading. Therefore in this paper, we propose to generate instructive questions from the multiple recommended articles to guide teens to read. Four solutions based on the neural encoder-decoder model are presented to tackle the task. For model training and testing, we construct a novel large-scale QA dataset named TeenQA, which is specific to adolescent stress. Due to the extensibility of question expressions, we incorporate three groups of automatic evaluation metrics as well as one group of human evaluation metrics to examine the quality of the generated questions. The experimental results show that the proposed Encoder-Decoder with Summary on Contexts with Feature-rich embeddings (ED-SoCF) solution can generate good questions for guiding reading, achieving comparable performance on some semantic similarity metrics with that of humans. Full article
(This article belongs to the Special Issue Sensors and Wearable Technologies for Cognitive Aid)
Open AccessArticle
Horizontal Review on Video Surveillance for Smart Cities: Edge Devices, Applications, Datasets, and Future Trends
by , , and
Sensors 2021, 21(9), 3222; https://doi.org/10.3390/s21093222 (registering DOI) - 06 May 2021
Viewed by 172
Abstract
The automation strategy of today’s smart cities relies on large IoT (internet of Things) systems that collect big data analytics to gain insights. Although there have been recent reviews in this field, there is a remarkable gap that addresses four sides of the [...] Read more.
The automation strategy of today’s smart cities relies on large IoT (internet of Things) systems that collect big data analytics to gain insights. Although there have been recent reviews in this field, there is a remarkable gap that addresses four sides of the problem. Namely, the application of video surveillance in smart cities, algorithms, datasets, and embedded systems. In this paper, we discuss the latest datasets used, the algorithms used, and the recent advances in embedded systems to form edge vision computing are introduced. Moreover, future trends and challenges are addressed. Full article
(This article belongs to the Special Issue Artificial Intelligence and Their Applications in Smart Cities)
Show Figures

Figure 1

Open AccessArticle
Detecting Attention Levels in ADHD Children with a Video Game and the Measurement of Brain Activity with a Single-Channel BCI Headset
by , , , , , and
Sensors 2021, 21(9), 3221; https://doi.org/10.3390/s21093221 - 06 May 2021
Viewed by 141
Abstract
Attentional biomarkers in attention deficit hyperactivity disorder are difficult to detect using only behavioural testing. We explored whether attention measured by a low-cost EEG system might be helpful to detect a possible disorder at its earliest stages. The GokEvolution application was designed to [...] Read more.
Attentional biomarkers in attention deficit hyperactivity disorder are difficult to detect using only behavioural testing. We explored whether attention measured by a low-cost EEG system might be helpful to detect a possible disorder at its earliest stages. The GokEvolution application was designed to train attention and to provide a measure to identify attentional problems in children early on. Attention changes registered with NeuroSky MindWave in combination with the CARAS-R psychological test were used to characterise the attentional profiles of 52 non-ADHD and 23 ADHD children aged 7 to 12 years old. The analyses revealed that the GokEvolution was valuable in measuring attention through its use of EEG–BCI technology. The ADHD group showed lower levels of attention and more variability in brain attentional responses when compared to the control group. The application was able to map the low attention profiles of the ADHD group when compared to the control group and could distinguish between participants who completed the task and those who did not. Therefore, this system could potentially be used in clinical settings as a screening tool for early detection of attentional traits in order to prevent their development. Full article
(This article belongs to the Section Electronic Sensors)
Show Figures

Figure 1

Open AccessArticle
Rapid Determination of Low Heavy Metal Concentrations in Grassland Soils around Mining Using Vis–NIR Spectroscopy: A Case Study of Inner Mongolia, China
by , , , , , , and
Sensors 2021, 21(9), 3220; https://doi.org/10.3390/s21093220 - 06 May 2021
Viewed by 174
Abstract
Proximal sensing offers a novel means for determination of the heavy metal concentration in soil, facilitating low cost and rapid analysis over large areas. In this respect, spectral data and model variables play an important role. Thus far, no attempts have been made [...] Read more.
Proximal sensing offers a novel means for determination of the heavy metal concentration in soil, facilitating low cost and rapid analysis over large areas. In this respect, spectral data and model variables play an important role. Thus far, no attempts have been made to estimate soil heavy metal content using continuum-removal (CR), different preprocessing and statistical methods, and different modeling variables. Considering the adsorption and retention of heavy metals in spectrally active constituents in soil, this study proposes a method for determining low heavy metal concentrations in soil using spectral bands associated with soil organic matter (SOM) and visible–near-infrared (Vis–NIR). To rapidly determine the concentration of heavy metals using hyperspectral data, partial least squares regression (PLSR), principal component regression (PCR), and support vector machine regression (SVMR) statistical methods and 16 preprocessing combinations were developed and explored to determine an optimal combination. The results showed that the multiplicative scatter correction and standard normal variate preprocessing methods evaluated with the second derivative spectral transformation method could accurately determine soil Cr and Ni concentrations. The root-mean-square error (RMSE) values of Vis–NIR model combinations with PLSR, PCR, and SVMR were 0.34, 3.42, and 2.15 for Cr, and 0.07, 1.78, and 1.14 for Ni, respectively. Soil Cr and Ni showed strong spectral responses to the Vis–NIR spectral band. The R2 value of the Vis–NIR-based PLSR model was higher than 0.99, and the RMSE value was 0.07–0.34, suggesting higher stability and accuracy. The results were more accurate for Ni than Cr, and PLSR showed the best performance, followed by SVMR and PCR. This perspective has critical implications for guiding quantitative biogeochemical analysis using proximal sensing data. Full article
Show Figures

Figure 1

Open AccessArticle
Band-Selection of a Portal LED-Induced Autofluorescence Multispectral Imager to Improve Oral Cancer Detection
by , , , , and
Sensors 2021, 21(9), 3219; https://doi.org/10.3390/s21093219 (registering DOI) - 06 May 2021
Viewed by 157
Abstract
This aim of this study was to find effective spectral bands for the early detection of oral cancer. The spectral images in different bands were acquired using a self-made portable light-emitting diode (LED)-induced autofluorescence multispectral imager equipped with 365 and 405 nm excitation [...] Read more.
This aim of this study was to find effective spectral bands for the early detection of oral cancer. The spectral images in different bands were acquired using a self-made portable light-emitting diode (LED)-induced autofluorescence multispectral imager equipped with 365 and 405 nm excitation LEDs, emission filters with center wavelengths of 470, 505, 525, 532, 550, 595, 632, 635, and 695 nm, and a color image sensor. The spectral images of 218 healthy points in 62 healthy participants and 218 tumor points in 62 patients were collected in the ex vivo trials at China Medical University Hospital. These ex vivo trials were similar to in vivo because the spectral images of anatomical specimens were immediately acquired after the on-site tumor resection. The spectral images associated with red, blue, and green filters correlated with and without nine emission filters were quantized by four computing method, including summated intensity, the highest number of the intensity level, entropy, and fractional dimension. The combination of four computing methods, two excitation light sources with two intensities, and 30 spectral bands in three experiments formed 264 classifiers. The quantized data in each classifier was divided into two groups: one was the training group optimizing the threshold of the quantized data, and the other was validating group tested under this optimized threshold. The sensitivity, specificity, and accuracy of each classifier were derived from these tests. To identify the influential spectral bands based on the area under the region and the testing results, a single-layer network learning process was used. This was compared to conventional rules-based approaches to show its superior and faster performance. Consequently, four emission filters with the center wavelengths of 470, 505, 532, and 550 nm were selected by an AI-based method and verified using a rule-based approach. The sensitivities of six classifiers using these emission filters were more significant than 90%. The average sensitivity of these was about 96.15%, the average specificity was approximately 69.55%, and the average accuracy was about 82.85%. Full article
(This article belongs to the Special Issue Advances in Spectroscopy and Spectral Imaging)
Show Figures

Figure 1

Open AccessArticle
Pig Weight and Body Size Estimation Using a Multiple Output Regression Convolutional Neural Network: A Fast and Fully Automatic Method
by , , and
Sensors 2021, 21(9), 3218; https://doi.org/10.3390/s21093218 - 06 May 2021
Viewed by 176
Abstract
Pig weight and body size are important indicators for producers. Due to the increasing scale of pig farms, it is increasingly difficult for farmers to quickly and automatically obtain pig weight and body size. Due to this problem, we focused on a multiple [...] Read more.
Pig weight and body size are important indicators for producers. Due to the increasing scale of pig farms, it is increasingly difficult for farmers to quickly and automatically obtain pig weight and body size. Due to this problem, we focused on a multiple output regression convolutional neural network (CNN) to estimate pig weight and body size. DenseNet201, ResNet152 V2, Xception and MobileNet V2 were modified into multiple output regression CNNs and trained on modeling data. By comparing the estimated performance of each model on test data, modified Xception was selected as the optimal estimation model. Based on pig height, body shape, and contour, the mean absolute error (MAE) of the model to estimate body weight (BW), shoulder width (SW), shoulder height (SH), hip width (HW), hip width (HH), and body length (BL) were 1.16 kg, 0.33 cm, 1.23 cm, 0.38 cm, 0.66 cm, and 0.75 cm, respectively. The coefficient of determination (R2) value between the estimated and measured results was in the range of 0.9879–0.9973. Combined with the LabVIEW software development platform, this method can estimate pig weight and body size accurately, quickly, and automatically. This work contributes to the automatic management of pig farms. Full article
Show Figures

Figure 1

Open AccessArticle
Plantar Pressure Variability and Asymmetry in Elderly Performing 60-Minute Treadmill Brisk-Walking: Paving the Way towards Fatigue-Induced Instability Assessment Using Wearable In-Shoe Pressure Sensors
by , , , , , , , and
Sensors 2021, 21(9), 3217; https://doi.org/10.3390/s21093217 - 06 May 2021
Viewed by 165
Abstract
Evaluation of potential fatigue for the elderly could minimize their risk of injury and thus encourage them to do more physical exercises. Fatigue-related gait instability was often assessed by the changes of joint kinematics, whilst planar pressure variability and asymmetry parameters may complement [...] Read more.
Evaluation of potential fatigue for the elderly could minimize their risk of injury and thus encourage them to do more physical exercises. Fatigue-related gait instability was often assessed by the changes of joint kinematics, whilst planar pressure variability and asymmetry parameters may complement and provide better estimation. We hypothesized that fatigue condition (induced by the treadmill brisk-walking task) would lead to instability and could be reflected by the variability and asymmetry of plantar pressure. Fifteen elderly adults participated in the 60-min brisk walking trial on a treadmill without a pause, which could ensure that the fatigue-inducing effect is continuous and participants will not recover halfway. The plantar pressure data were extracted at baseline, the 30th minute, and the 60th minute. The median of contact time, peak pressure, and pressure-time integrals in each plantar region was calculated, in addition to their asymmetry and variability. After 60 min of brisk walking, there were significant increases in peak pressure at the medial and lateral arch regions, and central metatarsal regions, in addition to their impulses (p < 0.05). In addition, the variability of plantar pressure at the medial arch was significantly increased (p < 0.05), but their asymmetry was decreased. On the other hand, the contact time was significantly increased at all plantar regions (p < 0.05). The weakened muscle control and shock absorption upon fatigue could be the reason for the increased peak pressure, impulse, and variability, while the improved symmetry and prolonged plantar contact time could be a compensatory mechanism to restore stability. The outcome of this study can facilitate the development of gait instability or fatigue assessment using wearable in-shoe pressure sensors. Full article
(This article belongs to the Special Issue Sensors in Biomechanics)
Show Figures

Figure 1

Open AccessArticle
Noise Radar Technology: Waveforms Design and Field Trials
by , , and
Sensors 2021, 21(9), 3216; https://doi.org/10.3390/s21093216 (registering DOI) - 06 May 2021
Viewed by 170
Abstract
Performance of continuous emission noise radar systems are affected by the sidelobes of the output of the matched filter, with significant effects on detection and dynamic range. Hence, the sidelobe level has to be controlled by a careful design of the transmitted waveform [...] Read more.
Performance of continuous emission noise radar systems are affected by the sidelobes of the output of the matched filter, with significant effects on detection and dynamic range. Hence, the sidelobe level has to be controlled by a careful design of the transmitted waveform and of the transmit/receive parts of the radar. In this context, the average transmitted power has to be optimized by choosing waveforms with a peak-to-average power ratio as close to the unity as possible. However, after coherent demodulation and acquisition of the received signal and of the reference signal at the transmitting antenna port, the goodness (low sidelobes) of the output from the matched filter can be considerably reduced by the deleterious effects due to the radar hardware, including the analog-to-digital converter (ADC). This paper aims to solve the above problems from both the theoretical and the practical viewpoint and recommends the use of tailored waveforms for mitigating the dynamic range issues. The new findings are corroborated by the results from two noise radar demonstrators operating in Germany (rural environment) and in Turkey (coast and sea environment) and the related lessons learnt. Full article
Show Figures

Figure 1

Open AccessArticle
V-Spline: An Adaptive Smoothing Spline for Trajectory Reconstruction
by , , , and
Sensors 2021, 21(9), 3215; https://doi.org/10.3390/s21093215 (registering DOI) - 06 May 2021
Viewed by 170
Abstract
Trajectory reconstruction is the process of inferring the path of a moving object between successive observations. In this paper, we propose a smoothing spline—which we name the V-spline—that incorporates position and velocity information and a penalty term that controls acceleration. We introduce an [...] Read more.
Trajectory reconstruction is the process of inferring the path of a moving object between successive observations. In this paper, we propose a smoothing spline—which we name the V-spline—that incorporates position and velocity information and a penalty term that controls acceleration. We introduce an adaptive V-spline designed to control the impact of irregularly sampled observations and noisy velocity measurements. A cross-validation scheme for estimating the V-spline parameters is proposed, and, in simulation studies, the V-spline shows superior performance to existing methods. Finally, an application of the V-spline to vehicle trajectory reconstruction in two dimensions is given, in which the penalty term is allowed to further depend on known operational characteristics of the vehicle. Full article
Show Figures

Figure 1

Open AccessArticle
Enhancement of Speed and Accuracy Trade-Off for Sports Ball Detection in Videos—Finding Fast Moving, Small Objects in Real Time
by , , and
Sensors 2021, 21(9), 3214; https://doi.org/10.3390/s21093214 - 06 May 2021
Viewed by 215
Abstract
The detection and localization of the ball in sport videos is crucial to better understand events and actions occurring in those sports. Despite recent advances in the field of object detection, the automatic detection of balls remains a challenging task due to the [...] Read more.
The detection and localization of the ball in sport videos is crucial to better understand events and actions occurring in those sports. Despite recent advances in the field of object detection, the automatic detection of balls remains a challenging task due to the unsteady nature of balls in images. In this paper, we address the detection of small, fast-moving balls in sport video data and introduce a real-time ball detection approach based on the YOLOv3 object detection model. We apply specific adjustments to the network architecture and training process in order to enhance the detection accuracy and speed: We facilitate an efficient integration of motion information, avoiding a complex modification of the network architecture. Furthermore, we present a customized detection approach that is designed to primarily focus on the detection of small objects. We integrate domain-specific knowledge to adapt image pre-processing and a data augmentation strategy that takes advantage of the special features of balls in images in order to improve the generalization ability of the detection network. We demonstrate that the general trade-off between detection speed and accuracy of the YOLOv3 model can be enhanced in consideration of domain-specific prior knowledge. Full article
(This article belongs to the Special Issue Sensor Technology for Sports Science)
Show Figures

Figure 1

Open AccessArticle
Objective Assessment of Regional Stiffness in Vastus Lateralis with Different Measurement Methods: A Reliability Study
by , , , , and
Sensors 2021, 21(9), 3213; https://doi.org/10.3390/s21093213 - 06 May 2021
Viewed by 179
Abstract
The objective of this study was to evaluate the reliability of four methods of assessing vastus lateralis (VL) stiffness, and to describe the influence of structural characteristics on them. The stiffness of the dominant lower-limb’s VL was evaluated in 53 healthy participants (28.4 [...] Read more.
The objective of this study was to evaluate the reliability of four methods of assessing vastus lateralis (VL) stiffness, and to describe the influence of structural characteristics on them. The stiffness of the dominant lower-limb’s VL was evaluated in 53 healthy participants (28.4 ± 9.1 years) with shear wave elastography (SWE), strain elastography (SE), myotonometry and tensiomyography (TMG). The SWE, SE and myotonometry were performed at 50%, and TMG was assessed at 30%, of the length from the upper pole of the patella to the greater trochanter. The thickness of the VL, adipose tissue and superficial connective tissue was also measured with ultrasound. Three repeated measurements were acquired to assess reliability, using intraclass correlation coefficients (ICC). Pearson’s correlation coefficients were calculated to determine the relationships between methodologic assessments and between structural characteristics and stiffness assessments of the VL. Myotonometry (ICC = 0.93; 95%-CI = 0.89,0.96) and TMG (ICC = 0.89; 95%-CI = 0.82,0.94) showed excellent inter-day reliability whereas with SWE (ICC = 0.62; 95%-CI = 0.41,0.77) and SE (ICC = 0.71; 95%-CI = 0.57,0.81) reliability was moderate. Significant correlations were found between myotonometry and VL thickness (r = 0.361; p = 0.008), adipose tissue thickness (r = −0.459; p = 0.001) and superficial connective tissue thickness (r = 0.340; p = 0.013). Myotonometry and TMG showed the best reliability values, although myotonometry stiffness values were influenced by the structural variables of the supra-adjacent tissue. Full article
Show Figures

Figure 1

Open AccessArticle
Detection of Postural Control in Young and Elderly Adults Using Deep and Machine Learning Methods with Joint–Node Plots
Sensors 2021, 21(9), 3212; https://doi.org/10.3390/s21093212 (registering DOI) - 05 May 2021
Viewed by 282
Abstract
Postural control decreases with aging. Thus, an efficient and accurate method of detecting postural control is needed. We enrolled 35 elderly adults (aged 82.06 ± 8.74 years) and 20 healthy young adults (aged 21.60 ± 0.60 years) who performed standing tasks for 40 [...] Read more.
Postural control decreases with aging. Thus, an efficient and accurate method of detecting postural control is needed. We enrolled 35 elderly adults (aged 82.06 ± 8.74 years) and 20 healthy young adults (aged 21.60 ± 0.60 years) who performed standing tasks for 40 s, performed six times. The coordinates of 15 joint nodes were captured using a Kinect device (30 Hz). We plotted joint positions into a single 2D figure (named a joint–node plot, JNP) once per second for up to 40 s. A total of 15 methods combining deep and machine learning for postural control classification were investigated. The accuracy, sensitivity, specificity, positive predicted value (PPV), negative predicted value (NPV), and kappa values of the selected methods were assessed. The highest PPV, NPV, accuracy, sensitivity, specificity, and kappa values were higher than 0.9 in validation testing. The presented method using JNPs demonstrated strong performance in detecting the postural control ability of young and elderly adults. Full article
(This article belongs to the Special Issue Advances and Application of Human Movement Sensors)
Show Figures

Figure 1

Open AccessCommunication
An Analytic Model for Negative Obstacle Detection with Lidar and Numerical Validation Using Physics-Based Simulation
Sensors 2021, 21(9), 3211; https://doi.org/10.3390/s21093211 (registering DOI) - 05 May 2021
Viewed by 369
Abstract
Negative obstacles have long been a challenging aspect of autonomous navigation for ground vehicles. However, as terrestrial lidar sensors have become lighter and less costly, they have increasingly been deployed on small, low-flying UAV, affording an opportunity to use these sensors to aid [...] Read more.
Negative obstacles have long been a challenging aspect of autonomous navigation for ground vehicles. However, as terrestrial lidar sensors have become lighter and less costly, they have increasingly been deployed on small, low-flying UAV, affording an opportunity to use these sensors to aid in autonomous navigation. In this work, we develop an analytical model for predicting the ability of UAV or UGV mounted lidar sensors to detect negative obstacles. This analytical model improves upon past work in this area because it takes the sensor rotation rate and vehicle speed into account, as well as being valid for both large and small view angles. This analytical model is used to predict the influence of velocity on detection range for a negative obstacle and determine a limiting speed when accounting for vehicle stopping distance. Finally, the analytical model is validated with a physics-based simulator in realistic terrain. The results indicate that the analytical model is valid for altitudes above 10 m and show that there are drastic improvements in negative obstacle detection when using a UAV-mounted lidar. It is shown that negative obstacle detection ranges for various UAV-mounted lidar are 60–110 m, depending on the speed of the UAV and the type of lidar used. In contrast, detection ranges for UGV mounted lidar are found to be less than 10 m. Full article
(This article belongs to the Section Sensors and Robotics)
Show Figures

Figure 1

Open AccessArticle
Random Access Using Deep Reinforcement Learning in Dense Mobile Networks
Sensors 2021, 21(9), 3210; https://doi.org/10.3390/s21093210 - 05 May 2021
Viewed by 259
Abstract
5G and Beyond 5G mobile networks use several high-frequency spectrum bands such as the millimeter-wave (mmWave) bands to alleviate the problem of bandwidth scarcity. However high-frequency bands do not cover larger distances. The coverage problem is addressed by using a heterogeneous network which [...] Read more.
5G and Beyond 5G mobile networks use several high-frequency spectrum bands such as the millimeter-wave (mmWave) bands to alleviate the problem of bandwidth scarcity. However high-frequency bands do not cover larger distances. The coverage problem is addressed by using a heterogeneous network which comprises numerous small and macrocells, defined by transmission and reception points (TRxPs). For such a network, random access is considered a challenging function in which users attempt to select an efficient TRxP by random access within a given time. Ideally, an efficient TRxP is less congested, minimizing delays in users’ random access. However, owing to the nature of random access, it is not feasible to deploy a centralized controller estimating the congestion level of each cell and deliver this information back to users during random access. To solve this problem, we establish an optimization problem and employ a reinforcement-learning-based scheme. The proposed scheme estimates congestion of TRxPs in service and selects the optimal access point. Mathematically, this approach is beneficial in approximating and minimizing a random access delay function. Through simulation, we demonstrate that our proposed deep learning-based algorithm improves performance on random access. Notably, the average access delay is improved by 58.89% from the original 3GPP algorithm, and the probability of successful access also improved. Full article
Open AccessArticle
Cooperative Fusion Based Passive Multistatic Radar Detection
Sensors 2021, 21(9), 3209; https://doi.org/10.3390/s21093209 - 05 May 2021
Viewed by 243
Abstract
Passive multistatic radars have gained a lot of interest in recent years as they offer many benefits contrary to conventional radars. Here in this research, our aim is detection of target in a passive multistatic radar system. The system contains a single transmitter [...] Read more.
Passive multistatic radars have gained a lot of interest in recent years as they offer many benefits contrary to conventional radars. Here in this research, our aim is detection of target in a passive multistatic radar system. The system contains a single transmitter and multiple spatially distributed receivers comprised of both the surveillance and reference antennas. The system consists of two main parts: 1. Local receiver, and 2. Fusion center. Each local receiver detects the signal, processes it, and passes the information to the fusion center for final detection. To take the advantage of spatial diversity, we apply major fusion techniques consisting of hard fusion and soft fusion for the case of multistatic passive radars. Hard fusion techniques are analyzed for the case of different local radar detectors. In terms of soft fusion, a blind technique called equal gain soft fusion technique with random matrix theory-based local detector is analytically and theoretically analyzed under null hypothesis along with the calculation of detection threshold. Furthermore, six novel random matrix theory-based soft fusion techniques are proposed. All the techniques are blind in nature and hence do not require any knowledge of transmitted signal or channel information. Simulation results illustrate that proposed fusion techniques increase detection performance to a reasonable extent compared to other blind fusion techniques. Full article
(This article belongs to the Section Radar Sensors)
Open AccessArticle
Ball-Catching System Using Image Processing and an Omni-Directional Wheeled Mobile Robot
Sensors 2021, 21(9), 3208; https://doi.org/10.3390/s21093208 - 05 May 2021
Viewed by 270
Abstract
The ball-catching system examined in this research, which was composed of an omni-directional wheeled mobile robot and an image processing system that included a dynamic stereo vision camera and a static camera, was used to capture a thrown ball. The thrown ball was [...] Read more.
The ball-catching system examined in this research, which was composed of an omni-directional wheeled mobile robot and an image processing system that included a dynamic stereo vision camera and a static camera, was used to capture a thrown ball. The thrown ball was tracked by the dynamic stereo vision camera, and the omni-directional wheeled mobile robot was navigated through the static camera. A Kalman filter with deep learning was used to decrease the visual measurement noises and to estimate the ball’s position and velocity. The ball’s future trajectory and landing point was predicted by estimating its position and velocity. Feedback linearization was used to linearize the omni-directional wheeled mobile robot model and was then combined with a proportional-integral-derivative (PID) controller. The visual tracking algorithm was initially simulated numerically, and then the performance of the designed system was verified experimentally. We verified that the designed system was able to precisely catch a thrown ball. Full article
(This article belongs to the Special Issue Perceptual Deep Learning in Image Processing and Computer Vision)
Show Figures

Figure 1

Open AccessSystematic Review
The Effects of Powered Exoskeleton Gait Training on Cardiovascular Function and Gait Performance: A Systematic Review
Sensors 2021, 21(9), 3207; https://doi.org/10.3390/s21093207 (registering DOI) - 05 May 2021
Viewed by 243
Abstract
Patients with neurological impairments often experience physical deconditioning, resulting in reduced fitness and health. Powered exoskeleton training may be a successful method to combat physical deconditioning and its comorbidities, providing patients with a valuable and novel experience. This systematic review aimed to conduct [...] Read more.
Patients with neurological impairments often experience physical deconditioning, resulting in reduced fitness and health. Powered exoskeleton training may be a successful method to combat physical deconditioning and its comorbidities, providing patients with a valuable and novel experience. This systematic review aimed to conduct a search of relevant literature, to examine the effects of powered exoskeleton training on cardiovascular function and gait performance. Two electronic database searches were performed (2 April 2020 to 12 February 2021) and manual reference list searches of relevant manuscripts were completed. Studies meeting the inclusion criteria were systematically reviewed in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. n = 63 relevant titles were highlighed; two further titles were identified through manual reference list searches. Following analysis n = 23 studies were included. Data extraction details included; sample size, age, gender, injury, the exoskeleton used, intervention duration, weekly sessions, total sessions, session duration and outcome measures. Results indicated that exoskeleton gait training elevated energy expenditure greater than wheelchair propulsion and improved gait function. Patients exercised at a moderate-intensity. Powered exoskeletons may increase energy expenditure to a similar level as non-exoskeleton walking, which may improve cardiovascular function more effectively than wheelchair propulsion alone. Full article
(This article belongs to the Special Issue State-of-the-Art Sensors Technologies in Ireland 2020)
Show Figures

Figure 1

Open AccessCommunication
A UAV-Based Air Quality Evaluation Method for Determining Fugitive Emissions from a Quarry during the Railroad Life Cycle
Sensors 2021, 21(9), 3206; https://doi.org/10.3390/s21093206 - 05 May 2021
Viewed by 197
Abstract
Gravel is used in railway infrastructure to reduce environmental impacts and noise, but gravel on tracks must be replaced continuously because it deforms due to wear and weathering. It is therefore necessary to review the entire railroad life cycle. In this study, an [...] Read more.
Gravel is used in railway infrastructure to reduce environmental impacts and noise, but gravel on tracks must be replaced continuously because it deforms due to wear and weathering. It is therefore necessary to review the entire railroad life cycle. In this study, an unmanned aerial vehicle (UAV) was used to measure resuspended dust over a wide area. The dust was generated from transport movements in relation to the operation of a quarry, which represents the first stage of the railway life cycle. The dust was measured at Gangwon-do quarry using a Sniffer4D module, which can provide measurements at 1 s intervals through a light scattering method and has high reliability (R2 = 0.95 for PM2.5, R2 = 0.88 for PM10). The hourly generation of fugitive dust was calculated as 2937.5 g/h for PM2.5 and 4293.2 g/h for PM10. The social cost of dust generation was calculated as KRW 36.59 billion. The amount of dust generated per hour at the quarry was ~12 times greater than that generated by the operation of a regulator as a maintenance vehicle, with the largest amount of fugitive dust generated by the washing-type vehicle. This is the first study to measure the amount of fugitive dust generated in real time at 1 s intervals by monitoring the first stage of the railroad life cycle over a wide area using a Sniffer4D module attached to a UAV. This method can be replicated for use in various studies. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

Open AccessArticle
Cross-Layer-Aided Opportunistic Routing for Sparse Underwater Wireless Sensor Networks
Sensors 2021, 21(9), 3205; https://doi.org/10.3390/s21093205 - 05 May 2021
Viewed by 185
Abstract
Underwater wireless sensor networks (UWSNs) have emerged as a promising technology to monitor and explore the oceans instead of traditional undersea wireline instruments. Traditional routing protocols are inefficient for UWSNs due to the specific nature of the underwater environment. In contrast, Opportunistic Routing [...] Read more.
Underwater wireless sensor networks (UWSNs) have emerged as a promising technology to monitor and explore the oceans instead of traditional undersea wireline instruments. Traditional routing protocols are inefficient for UWSNs due to the specific nature of the underwater environment. In contrast, Opportunistic Routing (OR) protocols establish an online route for each transmission, which can well adapt with time-varying underwater channel. Cross-layer design is an effective approach to combine the metrics from different layers to optimize an OR routing in UWSNs. However, typical cross-layer OR routing protocols that are designed for UWSNs suffer from congestion problem at high traffic loads. In this paper, a Cross-Layer-Aided Opportunistic Routing Protocol (CLOR) is proposed to reduce the congestion in multi-hop sparse UWSNs. The CLOR consists of a negotiation phase and transmission phase. In the negotiation phase, the cross-layer information in fuzzy logic is utilized to attain an optimal forwarder node. In the transmission phase, to improve the transmission performance, a burst transmission strategy with network coding is exploited. Finally, we perform simulations of the proposed CLOR protocol in a specific sea region. Simulation results show that CLOR significantly improves the network performances at various traffic rates compared to existing protocols. Full article
(This article belongs to the Special Issue Underwater Wireless Sensor Networks)
Show Figures

Figure 1

Open AccessArticle
Hand Gesture Recognition Using EGaIn-Silicone Soft Sensors
Sensors 2021, 21(9), 3204; https://doi.org/10.3390/s21093204 - 05 May 2021
Viewed by 195
Abstract
Exploiting hand gestures for non-verbal communication has extraordinary potential in HCI. A data glove is an apparatus widely used to recognize hand gestures. To improve the functionality of the data glove, a highly stretchable and reliable signal-to-noise ratio sensor is indispensable. To do [...] Read more.
Exploiting hand gestures for non-verbal communication has extraordinary potential in HCI. A data glove is an apparatus widely used to recognize hand gestures. To improve the functionality of the data glove, a highly stretchable and reliable signal-to-noise ratio sensor is indispensable. To do this, the study focused on the development of soft silicone microchannel sensors using a Eutectic Gallium-Indium (EGaIn) liquid metal alloy and a hand gesture recognition system via the proposed data glove using the soft sensor. The EGaIn-silicone sensor was uniquely designed to include two sensing channels to monitor the finger joint movements and to facilitate the EGaIn alloy injection into the meander-type microchannels. We recruited 15 participants to collect hand gesture dataset investigating 12 static hand gestures. The dataset was exploited to estimate the performance of the proposed data glove in hand gesture recognition. Additionally, six traditional classification algorithms were studied. From the results, a random forest shows the highest classification accuracy of 97.3% and a linear discriminant analysis shows the lowest accuracy of 87.4%. The non-linearity of the proposed sensor deteriorated the accuracy of LDA, however, the other classifiers adequately overcame it and performed high accuracies (>90%). Full article
(This article belongs to the Special Issue Intelligent Sensors for Monitoring Physical Activities)
Show Figures

Figure 1

Previous Issue
Back to TopTop