Sensors

4 pages, 195 KiB

Open AccessEditorial

Special Issue “Wearable and BAN Sensors for Physical Rehabilitation and eHealth Architectures”

by Maria de Fátima Domingues, Andrea Sciarrone and Ayman Radwan

Sensors 2021, 21(24), 8509; https://doi.org/10.3390/s21248509 - 20 Dec 2021

Viewed by 2730

The demographic shift of the population toward an increased number of elder citizens, together with the sedentary lifestyle we are adopting, is reflected in the increasingly debilitated physical health of the population [...] Full article

(This article belongs to the Special Issue Wearable and BAN Sensors for Physical Rehabilitation and eHealth Architectures)

27 pages, 8458 KiB

Open AccessArticle

Research Active Posterior Rhinomanometry Tomography Method for Nasal Breathing Determining Violations

by Oleg G. Avrunin, Yana V. Nosova, Ibrahim Younouss Abdelhamid, Sergii V. Pavlov, Natalia O. Shushliapina, Natalia A. Bouhlal, Ainur Ormanbekova, Aigul Iskakova and Damian Harasim

Sensors 2021, 21(24), 8508; https://doi.org/10.3390/s21248508 - 20 Dec 2021

Cited by 24 | Viewed by 4662

Abstract

This study analyzes the existing methods for studying nasal breathing. The aspects of verifying the results of rhinomanometric diagnostics according to the data of spiral computed tomography are considered, and the methodological features of dynamic posterior active rhinomanometry and the main indicators of [...] Read more.

This study analyzes the existing methods for studying nasal breathing. The aspects of verifying the results of rhinomanometric diagnostics according to the data of spiral computed tomography are considered, and the methodological features of dynamic posterior active rhinomanometry and the main indicators of respiration are also analyzed. The possibilities of testing respiratory olfactory disorders are considered, the analysis of errors in rhinomanometric measurements is carried out. In the conclusions, practical recommendations are given that have been developed for the design and operation of tools for functional diagnostics of nasal breathing disorders. It is advisable, according to the data of dynamic rhinomanometry, to assess the functioning of the nasal valve by the shape of the air flow rate signals during forced breathing and the structures of the soft palate by the residual nasopharyngeal pressure drop. It is imperative to take into account not only the maximum coefficient of aerodynamic nose drag, but also the values of the pressure drop and air flow rate in the area of transition to the turbulent quadratic flow regime. From the point of view of the physiology of the nasal response, it is necessary to look at the dynamic change to the current mode, given the hour of the forced response, so that it will ensure the maximum possible acidity in the legend. When planning functional rhinosurgical operations, it is necessary to apply the calculation method using computed tomography, which makes it possible to predict the functional result of surgery. Full article

(This article belongs to the Special Issue Application and Technology Trends in Optoelectronic Sensors)

► Show Figures

Figure 1

35 pages, 3069 KiB

Open AccessReview

A Review on Computer Aided Diagnosis of Acute Brain Stroke

by Mahesh Anil Inamdar, Udupi Raghavendra, Anjan Gudigar, Yashas Chakole, Ajay Hegde, Girish R. Menon, Prabal Barua, Elizabeth Emma Palmer, Kang Hao Cheong, Wai Yee Chan, Edward J. Ciaccio and U. Rajendra Acharya

Sensors 2021, 21(24), 8507; https://doi.org/10.3390/s21248507 - 20 Dec 2021

Cited by 34 | Viewed by 9544

Abstract

Amongst the most common causes of death globally, stroke is one of top three affecting over 100 million people worldwide annually. There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and [...] Read more.

Amongst the most common causes of death globally, stroke is one of top three affecting over 100 million people worldwide annually. There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and hemorrhagic stroke (due to bleeding), both of which can result, if untreated, in permanently damaged brain tissue. The discovery that the affected brain tissue (i.e., ‘ischemic penumbra’) can be salvaged from permanent damage and the bourgeoning growth in computer aided diagnosis has led to major advances in stroke management. Abiding to the Preferred Reporting Items for Systematic Review and Meta–Analyses (PRISMA) guidelines, we have surveyed a total of 177 research papers published between 2010 and 2021 to highlight the current status and challenges faced by computer aided diagnosis (CAD), machine learning (ML) and deep learning (DL) based techniques for CT and MRI as prime modalities for stroke detection and lesion region segmentation. This work concludes by showcasing the current requirement of this domain, the preferred modality, and prospective research areas. Full article

(This article belongs to the Special Issue Innovations in Biomedical Imaging)

► Show Figures

Figure 1

34 pages, 8448 KiB

Open AccessArticle

Development of a Microwave Sensor for Solid and Liquid Substances Based on Closed Loop Resonator

by Aiswarya S, Sreedevi K. Menon, Massimo Donelli and Meenu L

Sensors 2021, 21(24), 8506; https://doi.org/10.3390/s21248506 - 20 Dec 2021

Cited by 13 | Viewed by 4630

Abstract

In this work, a compact dielectric sensor for the detection of adulteration in solid and liquid samples using planar resonators is presented. Six types of filter prototypes operating at 2.4 GHz are presented, optimized, numerically assessed, fabricated and experimentally validated. The obtained experimental [...] Read more.

In this work, a compact dielectric sensor for the detection of adulteration in solid and liquid samples using planar resonators is presented. Six types of filter prototypes operating at 2.4 GHz are presented, optimized, numerically assessed, fabricated and experimentally validated. The obtained experimental results provided an error less than 6% with respect to the simulated results. Moreover, a size reduction of about 69% was achieved for the band stop filter and a 75% reduction for band pass filter compared to standard sensors realized using open/short circuited stub microstrip lines. From the designed filters, the miniaturised filter with Q of 95 at 2.4 GHz and size of 35 mm × 35 mm is formulated as a sensor and is validated theoretically and experimentally. The designed sensor shows better sensitivity, and it depends upon the dielectric property of the sample to be tested. Simulation and experimental validation of the designed sensor is carried out by loading different samples onto the sensor. The adulteration detection of various food samples using the designed sensor is experimentally validated and shows excellent sensing on adding adulterants to the original sample. The sensitivity of the sensor is analyzed by studying the variations in resonant frequency, scattering parameters, phase and Q factor with variation in the dielectric property of the sample loaded onto the sensor. Full article

(This article belongs to the Special Issue Antenna and Microwave Sensors)

► Show Figures

Figure 1

19 pages, 20377 KiB

Open AccessArticle

Autonomous System for Lake Ice Monitoring

by Ilya Aslamov, Georgiy Kirillin, Mikhail Makarov, Konstantin Kucher, Ruslan Gnatovsky and Nikolay Granin

Sensors 2021, 21(24), 8505; https://doi.org/10.3390/s21248505 - 20 Dec 2021

Cited by 6 | Viewed by 4106

Abstract

Continuous monitoring of ice cover belongs to the key tasks of modern climate research, providing up-to-date information on climate change in cold regions. While a strong advance in ice monitoring worldwide has been provided by the recent development of remote sensing methods, quantification [...] Read more.

Continuous monitoring of ice cover belongs to the key tasks of modern climate research, providing up-to-date information on climate change in cold regions. While a strong advance in ice monitoring worldwide has been provided by the recent development of remote sensing methods, quantification of seasonal ice cover is impossible without on-site autonomous measurements of the mass and heat budget. In the present study, we propose an autonomous monitoring system for continuous in situ measuring of vertical temperature distribution in the near-ice air, the ice strata and the under-ice water layer for several months with simultaneous records of solar radiation incoming at the lake surface and passing through the snow and ice covers as well as snow and ice thicknesses. The use of modern miniature analog and digital sensors made it possible to make a compact, energy efficient measurement system with high precision and spatial resolution and characterized by easy deployment and transportation. In particular, the high resolution of the ice thickness probe of 0.05 mm allows to resolve the fine-scale processes occurring in low-flow environments, such as freshwater lakes. Several systems were tested in numerous studies in Lake Baikal and demonstrated a high reliability in deriving the ice heat balance components during ice-covered periods. Full article

(This article belongs to the Special Issue Marine Sensors: Recent Advances and Challenges)

► Show Figures

Figure 1

13 pages, 4091 KiB

Open AccessPerspective

Combining Action Observation Treatment with a Brain–Computer Interface System: Perspectives on Neurorehabilitation

by Fabio Rossi, Federica Savi, Andrea Prestia, Andrea Mongardi, Danilo Demarchi and Giovanni Buccino

Sensors 2021, 21(24), 8504; https://doi.org/10.3390/s21248504 - 20 Dec 2021

Cited by 8 | Viewed by 4527

Abstract

Action observation treatment (AOT) exploits a neurophysiological mechanism, matching an observed action on the neural substrates where that action is motorically represented. This mechanism is also known as mirror mechanism. In a typical AOT session, one can distinguish an observation phase and an [...] Read more.

Action observation treatment (AOT) exploits a neurophysiological mechanism, matching an observed action on the neural substrates where that action is motorically represented. This mechanism is also known as mirror mechanism. In a typical AOT session, one can distinguish an observation phase and an execution phase. During the observation phase, the patient observes a daily action and soon after, during the execution phase, he/she is asked to perform the observed action at the best of his/her ability. Indeed, the execution phase may sometimes be difficult for those patients where motor impairment is severe. Although, in the current practice, the physiotherapist does not intervene on the quality of the execution phase, here, we propose a stimulation system based on neurophysiological parameters. This perspective article focuses on the possibility to combine AOT with a brain–computer interface system (BCI) that stimulates upper limb muscles, thus facilitating the execution of actions during a rehabilitation session. Combining a rehabilitation tool that is well-grounded in neurophysiology with a stimulation system, such as the one proposed, may improve the efficacy of AOT in the treatment of severe neurological patients, including stroke patients, Parkinson’s disease patients, and children with cerebral palsy. Full article

(This article belongs to the Special Issue Computer-Aided and Game-Based Telerehabilitation and Telemonitoring Platforms)

► Show Figures

Figure 1

Figure 1
Typical BCI acquisition chain. After acquiring the EEG signal, the frequency components outside the band of interest are filtered out. Then, the power of the signal is estimated, followed by the extraction of its features to be used to classify if FES needs to be applied or not. Full article ">Figure 2
Overview of the system. The patient is instructed to perform the reaching of an object, typically. EEG electrodes are placed on the motor areas and stabilized by a comfortable helmet. sEMG and inertial sensors are placed on the limb of interest, next to the stimulation electrodes. A central unit processes acquired data to activate the FES when the subject needs help to reach the target. A monitor provides feedbacks encouraging the user. Full article ">Figure 3
Activity flow of an execution session. After the indication of the task to perform, the subject is required to execute the action. The four sensors are continuously monitored, and for each of them a proper feature is extracted and recorded (e.g., signal power from EEG, limb trajectory from the IMUs). The information obtained by EEG, EMG and IMUs is combined and processed to evaluate how the subject body is reacting, and to decide if the FES must be applied to assist the execution. Therefore, FES parameters are tuned depending on the decision of the processing stage, stabilizing the movement by stimulating one or more muscles, if necessary. Lastly, if the task consists of reaching for an object, the subject is encouraged until the BCC sensors detect the touch of the target. Full article ">

22 pages, 1285 KiB

Open AccessArticle

Predictive Machine Learning Models and Survival Analysis for COVID-19 Prognosis Based on Hematochemical Parameters

by Nicola Altini, Antonio Brunetti, Stefano Mazzoleni, Fabrizio Moncelli, Ilenia Zagaria, Berardino Prencipe, Erika Lorusso, Enrico Buonamico, Giovanna Elisiana Carpagnano, Davide Fiore Bavaro, Mariacristina Poliseno, Annalisa Saracino, Annalisa Schirinzi, Riccardo Laterza, Francesca Di Serio, Alessia D’Introno, Francesco Pesce and Vitoantonio Bevilacqua

Sensors 2021, 21(24), 8503; https://doi.org/10.3390/s21248503 - 20 Dec 2021

Cited by 11 | Viewed by 4488

Abstract

The coronavirus disease 2019 (COVID-19) pandemic has affected hundreds of millions of individuals and caused millions of deaths worldwide. Predicting the clinical course of the disease is of pivotal importance to manage patients. Several studies have found hematochemical alterations in COVID-19 patients, such [...] Read more.

The coronavirus disease 2019 (COVID-19) pandemic has affected hundreds of millions of individuals and caused millions of deaths worldwide. Predicting the clinical course of the disease is of pivotal importance to manage patients. Several studies have found hematochemical alterations in COVID-19 patients, such as inflammatory markers. We retrospectively analyzed the anamnestic data and laboratory parameters of 303 patients diagnosed with COVID-19 who were admitted to the Polyclinic Hospital of Bari during the first phase of the COVID-19 global pandemic. After the pre-processing phase, we performed a survival analysis with Kaplan–Meier curves and Cox Regression, with the aim to discover the most unfavorable predictors. The target outcomes were mortality or admission to the intensive care unit (ICU). Different machine learning models were also compared to realize a robust classifier relying on a low number of strongly significant factors to estimate the risk of death or admission to ICU. From the survival analysis, it emerged that the most significant laboratory parameters for both outcomes was C-reactive protein min;

H R = 17.963

(95% CI 6.548–49.277, p < 0.001) for death,

H R = 1.789

(95% CI 1.000–3.200, p = 0.050) for admission to ICU. The second most important parameter was Erythrocytes max;

H R = 1.765

(95% CI 1.141–2.729, p < 0.05) for death,

H R = 1.481

(95% CI 0.895–2.452, p = 0.127) for admission to ICU. The best model for predicting the risk of death was the decision tree, which resulted in ROC-AUC of 89.66%, whereas the best model for predicting the admission to ICU was support vector machine, which had ROC-AUC of 95.07%. The hematochemical predictors identified in this study can be utilized as a strong prognostic signature to characterize the severity of the disease in COVID-19 patients. Full article

(This article belongs to the Special Issue Modeling COVID-19 with Artificial Intelligence and Machine/Statistical Learning Techniques from Sensor Data and other Potential Applications)

► Show Figures

Figure 1

18 pages, 994 KiB

Open AccessArticle

Subjective and Objective User Behavior Disparity: Towards Balanced Visual Design and Color Adjustment

by Anna Lewandowska, Agnieszka Olejnik-Krugly, Jarosław Jankowski and Malwina Dziśko

Sensors 2021, 21(24), 8502; https://doi.org/10.3390/s21248502 - 20 Dec 2021

Cited by 7 | Viewed by 3924

Abstract

Interactive environments create endless possibilities for the design of websites, games, online platforms, and mobile applications. Their visual aspects and functional characteristics influence the user experience. Depending on the project, the purpose of the environment can be oriented toward marketing targets, user experience, [...] Read more.

Interactive environments create endless possibilities for the design of websites, games, online platforms, and mobile applications. Their visual aspects and functional characteristics influence the user experience. Depending on the project, the purpose of the environment can be oriented toward marketing targets, user experience, or accessibility. Often, these conflicting aspects should be integrated within a single project, and a search for trade-offs is needed. One of these conflicts involves a disparity in user behavior concerning declared preferences and real observed activity in terms of visual attention. Taking into account accessibility guidelines (WCAG) further complicates the problem. In our study, we focused on the analysis of color combinations and their contrast in terms of user-friendliness; visual intensity, which is important for attracting user attention; and recommendations from the Web Accessibility Guidelines (WCAG). We took up the challenge to reduce the disparity between user preferences and WCAG contrast, on one hand, and user natural behavior registered with an eye-tracker, on the other. However, we left the choice of what is more important—human conscious reaction or objective user behavior results—to the designer. The former corresponds to user-friendliness, while the latter, visual intensity, is consistent with marketing expectations. The results show that the ranking of visual objects characterized by different levels of contrast differs when considering the perspectives of user experience, commercial goals, and objective recording. We also propose an interactive tool with the possibility of assigning weights to each criterion to generate a ranking of objects. Full article

(This article belongs to the Section Biosensors)

► Show Figures

Figure 1

21 pages, 2905 KiB

Open AccessArticle

LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection

by Abid Mehmood

Sensors 2021, 21(24), 8501; https://doi.org/10.3390/s21248501 - 20 Dec 2021

Cited by 14 | Viewed by 4131

Abstract

The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details [...] Read more.

The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation. Full article

(This article belongs to the Section Sensor Networks)

► Show Figures

Figure 1

Figure 1
The overall architecture of the proposed LightAnomalyNet framework. Full article ">Figure 2
(a) Process of generating SG3I images from sequential video frames; (b) Example of SG3I generation for URFD dataset. Full article ">Figure 3
Sample SG3I images generated for Avenue (row 1), Mini-Drone Video (row 2), and Hockey Fights (row 3) datasets. Full article ">Figure 4
Proposed architecture of the lightweight CNN and the analysis of learnable parameters at each layer of the network. Note that the total of all learnable parameters for the proposed structure of the CNN is 7154. Full article ">Figure 5
Confusion matrix of the proposed framework on: (a) UR Fall dataset (b) Avenue dataset (c) Mini-Drone Video dataset (d) Hockey Fights dataset. Full article ">Figure 6
ROC curve and AUC values for: (a) UR Fall dataset (b) Avenue dataset (c) Mini-Drone Video dataset (d) Hockey Fights dataset. Full article ">Figure 7
Comparison of classification results on different splits of: (a) UR Fall dataset (b) Avenue dataset (c) Mini-Drone Video dataset (d) Hockey Fights dataset. Full article ">

15 pages, 1820 KiB

Open AccessArticle

Resource Prediction-Based Edge Collaboration Scheme for Improving QoE

by Jinho Park and Kwangsue Chung

Sensors 2021, 21(24), 8500; https://doi.org/10.3390/s21248500 - 20 Dec 2021

Cited by 3 | Viewed by 2502

Abstract

Recent years have witnessed a growth in the Internet of Things (IoT) applications and devices; however, these devices are unable to meet the increased computational resource needs of the applications they host. Edge servers can provide sufficient computing resources. However, when the number [...] Read more.

Recent years have witnessed a growth in the Internet of Things (IoT) applications and devices; however, these devices are unable to meet the increased computational resource needs of the applications they host. Edge servers can provide sufficient computing resources. However, when the number of connected devices is large, the task processing efficiency decreases due to limited computing resources. Therefore, an edge collaboration scheme that utilizes other computing nodes to increase the efficiency of task processing and improve the quality of experience (QoE) was proposed. However, existing edge server collaboration schemes have low QoE because they do not consider other edge servers’ computing resources or communication time. In this paper, we propose a resource prediction-based edge collaboration scheme for improving QoE. We estimate computing resource usage based on the tasks received from the devices. According to the predicted computing resources, the edge server probabilistically collaborates with other edge servers. The proposed scheme is based on the delay model, and uses the greedy algorithm. It allocates computing resources to the task considering the computation and buffering time. Experimental results show that the proposed scheme achieves a high QoE compared with existing schemes because of the high success rate and low completion time. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

Figure 1
Edge collaborative network environment. Full article ">Figure 2
Operation of the proposed scheme. Full article ">Figure 3
Flow chart of collaboration decision in the proposed scheme. Full article ">Figure 4
Network topology of edge servers in our simulation. Full article ">Figure 5
QoE of collaboration schemes for Task 1: (a) Success rate; (b) Completion time; (c) Processing time; (d) Communication time. Full article ">Figure 6
QoE of collaboration schemes for various tasks: (a) Success rate; (b) Completion time; (c) Processing time; (d) Communication time. Full article ">Figure 7
Success rate of Task 1, Task 2, and Task 3: (a) Task 1; (b) Task 2; (c) Task 3. Full article ">Figure 8
Completion time of Task 1, Task 2, and Task 3: (a) Task 1; (b) Task 2; (c) Task 3. Full article ">

13 pages, 25164 KiB

Open AccessArticle

Strength Development Monitoring of Cemented Paste Backfill Using Guided Waves

by Wen He, Changsong Zheng, Shenhai Li, Wenfang Shi and Kui Zhao

Sensors 2021, 21(24), 8499; https://doi.org/10.3390/s21248499 - 20 Dec 2021

Cited by 3 | Viewed by 2916

Abstract

The strength of cemented paste backfill (CPB) directly affects mining safety and progress. At present, in-situ backfill strength is obtained by conducting uniaxial compression tests on backfill core samples. At the same time, it is time-consuming, and the integrity of samples cannot be [...] Read more.

The strength of cemented paste backfill (CPB) directly affects mining safety and progress. At present, in-situ backfill strength is obtained by conducting uniaxial compression tests on backfill core samples. At the same time, it is time-consuming, and the integrity of samples cannot be guaranteed. Therefore guided wave technique as a nondestructive inspection method is proposed for the strength development monitoring of cemented paste backfill. In this paper, the acoustic parameters of guided wave propagation in the different cement-tailings ratios (1:4, 1:8) and different curing times (within 42 d) of CPBs were measured. Combined with the uniaxial compression strength of CPB, relationships between CPB strength and the guided wave acoustic parameters were established. Results indicate that with the increase of backfill curing time, the guided wave velocity decreases sharply at first; on the contrary, attenuation of guided waves increases dramatically. Finally, both velocity and attenuation tend to be stable. When the CPB strength increases with curing time, guided wave velocity shows an exponentially decreasing trend, while the guided wave attenuation shows an exponentially increasing trend with the increase of the CPB strength. Based on the relationship curves between CPB strength and guided wave velocity and attenuation, the guided wave technique in monitoring the strength development of CPB proves feasible. Full article

(This article belongs to the Special Issue Smart Sensors for Structural Health Monitoring and Nondestructive Evaluation)

► Show Figures

Figure 1

18 pages, 1513 KiB

Open AccessArticle

Lateral and Longitudinal Driving Behavior Prediction Based on Improved Deep Belief Network

by Lei Yang, Chunqing Zhao, Chao Lu, Lianzhen Wei and Jianwei Gong

Sensors 2021, 21(24), 8498; https://doi.org/10.3390/s21248498 - 20 Dec 2021

Cited by 6 | Viewed by 3514

Abstract

Accurately predicting driving behavior can help to avoid potential improper maneuvers of human drivers, thus guaranteeing safe driving for intelligent vehicles. In this paper, we propose a novel deep belief network (DBN), called MSR-DBN, by integrating a multi-target sigmoid regression (MSR) layer with [...] Read more.

Accurately predicting driving behavior can help to avoid potential improper maneuvers of human drivers, thus guaranteeing safe driving for intelligent vehicles. In this paper, we propose a novel deep belief network (DBN), called MSR-DBN, by integrating a multi-target sigmoid regression (MSR) layer with DBN to predict the front wheel angle and speed of the ego vehicle. Precisely, the MSR-DBN consists of two sub-networks: one is for the front wheel angle, and the other one is for speed. This MSR-DBN model allows ones to optimize lateral and longitudinal behavior predictions through a systematic testing method. In addition, we consider the historical states of the ego vehicle and surrounding vehicles and the driver’s operations as inputs to predict driving behaviors in a real-world environment. Comparison of the prediction results of MSR-DBN with a general DBN model, back propagation (BP) neural network, support vector regression (SVR), and radical basis function (RBF) neural network, demonstrates that the proposed MSR-DBN outperforms the others in terms of accuracy and robustness. Full article

(This article belongs to the Section Vehicular Sensing)

► Show Figures

Figure 1

19 pages, 6182 KiB

Open AccessArticle

Hyperspectral Estimation of Winter Wheat Leaf Area Index Based on Continuous Wavelet Transform and Fractional Order Differentiation

by Changchun Li, Yilin Wang, Chunyan Ma, Fan Ding, Yacong Li, Weinan Chen, Jingbo Li and Zhen Xiao

Sensors 2021, 21(24), 8497; https://doi.org/10.3390/s21248497 - 20 Dec 2021

Cited by 22 | Viewed by 3509

Abstract

Leaf area index (LAI) is highly related to crop growth, and the traditional LAI measurement methods are field destructive and unable to be acquired by large-scale, continuous, and real-time means. In this study, fractional order differential and continuous wavelet transform were used to [...] Read more.

Leaf area index (LAI) is highly related to crop growth, and the traditional LAI measurement methods are field destructive and unable to be acquired by large-scale, continuous, and real-time means. In this study, fractional order differential and continuous wavelet transform were used to process the canopy hyperspectral reflectance data of winter wheat, the fractional order differential spectral bands and wavelet energy coefficients with more sensitive to LAI changes were screened by correlation analysis, and the optimal subset regression and support vector machine were used to construct the LAI estimation models for different growth stages. The precision evaluation results showed that the LAI estimation models constructed by using wavelet energy coefficients combined with a support vector machine at the jointing stage, fractional order differential combined with support vector machine at the booting stage, and wavelet energy coefficients combined with optimal subset regression at the flowering and filling stages had the best prediction performance. Among these, both flowering and filling stages could be used as the best growth stages for LAI estimation with modeling and validation R² of 0.87 and 0.71, 0.84 and 0.77, respectively. This study can provide technical reference for LAI estimation of crops based on remote sensing technology. Full article

(This article belongs to the Special Issue Methodologies Used in Remote Sensing Data Analysis and Remote Sensors for Precision Agriculture)

► Show Figures

Figure 1

17 pages, 1518 KiB

Open AccessArticle

Collision-Aware Routing Using Multi-Objective Seagull Optimization Algorithm for WSN-Based IoT

by Preetha Jagannathan, Sasikumar Gurumoorthy, Andrzej Stateczny, Parameshachari Bidare Divakarachar and Jewel Sengupta

Sensors 2021, 21(24), 8496; https://doi.org/10.3390/s21248496 - 20 Dec 2021

Cited by 71 | Viewed by 3503

Abstract

In recent trends, wireless sensor networks (WSNs) have become popular because of their cost, simple structure, reliability, and developments in the communication field. The Internet of Things (IoT) refers to the interconnection of everyday objects and sharing of information through the Internet. Congestion [...] Read more.

In recent trends, wireless sensor networks (WSNs) have become popular because of their cost, simple structure, reliability, and developments in the communication field. The Internet of Things (IoT) refers to the interconnection of everyday objects and sharing of information through the Internet. Congestion in networks leads to transmission delays and packet loss and causes wastage of time and energy on recovery. The routing protocols are adaptive to the congestion status of the network, which can greatly improve the network performance. In this research, collision-aware routing using the multi-objective seagull optimization algorithm (CAR-MOSOA) is designed to meet the efficiency of a scalable WSN. The proposed protocol exploits the clustering process to choose cluster heads to transfer the data from source to endpoint, thus forming a scalable network, and improves the performance of the CAR-MOSOA protocol. The proposed CAR-MOSOA is simulated and examined using the NS-2.34 simulator due to its modularity and inexpensiveness. The results of the CAR-MOSOA are comprehensively investigated with existing algorithms such as fully distributed energy-aware multi-level (FDEAM) routing, energy-efficient optimal multi-path routing protocol (EOMR), tunicate swarm grey wolf optimization (TSGWO), and CoAP simple congestion control/advanced (CoCoA). The simulation results of the proposed CAR-MOSOA for 400 nodes are as follows: energy consumption, 33 J; end-to-end delay, 29 s; packet delivery ratio, 95%; and network lifetime, 973 s, which are improved compared to the FDEAM, EOMR, TSGWO, and CoCoA. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

15 pages, 2705 KiB

Open AccessArticle

Relative Pose Determination of Uncooperative Spacecraft Based on Circle Feature

by Yue Liu, Shijie Zhang and Xiangtian Zhao

Sensors 2021, 21(24), 8495; https://doi.org/10.3390/s21248495 - 20 Dec 2021

Cited by 5 | Viewed by 3082

Abstract

This paper investigates the problem of spacecraft relative navigation with respect to an unknown target during the close-proximity operations in the on-orbit service system. The serving spacecraft is equipped with a Time-of-Flight (ToF) camera for object recognition and feature detection. A fast and [...] Read more.

This paper investigates the problem of spacecraft relative navigation with respect to an unknown target during the close-proximity operations in the on-orbit service system. The serving spacecraft is equipped with a Time-of-Flight (ToF) camera for object recognition and feature detection. A fast and robust relative navigation strategy for acquisition is presented without any extra information about the target by using the natural circle features. The architecture of the proposed relative navigation strategy consists of three ingredients. First, a point cloud segmentation method based on the auxiliary gray image is developed for fast extraction of the circle feature point cloud of the target. Secondly, a new parameter fitting method of circle features is proposed including circle feature calculation by two different geometric models and results’ fusion. Finally, a specific definition of the coordinate frame system is introduced to solve the relative pose with respect to the uncooperative target. In order to validate the efficiency of the segmentation, an experimental test is conducted based on real-time image data acquired by the ToF camera. The total time consumption is saved by 94%. In addition, numerical simulations are carried out to evaluate the proposed navigation algorithm. It shows good robustness under the different levels of noises. Full article

(This article belongs to the Special Issue Instrument and Measurement Based on Sensing Technology in China)

► Show Figures

Figure 1

14 pages, 1108 KiB

Open AccessArticle

The Compact Support Neural Network

by Adrian Barbu and Hongyu Mou

Sensors 2021, 21(24), 8494; https://doi.org/10.3390/s21248494 - 20 Dec 2021

Cited by 2 | Viewed by 2895

Abstract

Neural networks are popular and useful in many fields, but they have the problem of giving high confidence responses for examples that are away from the training data. This makes the neural networks very confident in their prediction while making gross mistakes, thus [...] Read more.

Neural networks are popular and useful in many fields, but they have the problem of giving high confidence responses for examples that are away from the training data. This makes the neural networks very confident in their prediction while making gross mistakes, thus limiting their reliability for safety-critical applications such as autonomous driving and space exploration, etc. This paper introduces a novel neuron generalization that has the standard dot-product-based neuron and the radial basis function (RBF) neuron as two extreme cases of a shape parameter. Using a rectified linear unit (ReLU) as the activation function results in a novel neuron that has compact support, which means its output is zero outside a bounded domain. To address the difficulties in training the proposed neural network, it introduces a novel training method that takes a pretrained standard neural network that is fine-tuned while gradually increasing the shape parameter to the desired value. The theoretical findings of the paper are bound on the gradient of the proposed neuron and proof that a neural network with such neurons has the universal approximation property. This means that the network can approximate any continuous and integrable function with an arbitrary degree of accuracy. The experimental findings on standard benchmark datasets show that the proposed approach has smaller test errors than the state-of-the-art competing methods and outperforms the competing methods in detecting out-of-distribution samples on two out of three datasets. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

16 pages, 3400 KiB

Open AccessArticle

Thermal Drift Correction for Laboratory Nano Computed Tomography via Outlier Elimination and Feature Point Adjustment

by Mengnan Liu, Yu Han, Xiaoqi Xi, Siyu Tan, Jian Chen, Lei Li and Bin Yan

Sensors 2021, 21(24), 8493; https://doi.org/10.3390/s21248493 - 20 Dec 2021

Cited by 4 | Viewed by 2830

Abstract

Thermal drift of nano-computed tomography (CT) adversely affects the accurate reconstruction of objects. However, feature-based reference scan correction methods are sometimes unstable for images with similar texture and low contrast. In this study, based on the geometric position of features and the structural [...] Read more.

Thermal drift of nano-computed tomography (CT) adversely affects the accurate reconstruction of objects. However, feature-based reference scan correction methods are sometimes unstable for images with similar texture and low contrast. In this study, based on the geometric position of features and the structural similarity (SSIM) of projections, a rough-to-refined rigid alignment method is proposed to align the projection. Using the proposed method, the thermal drift artifacts in reconstructed slices are reduced. Firstly, the initial features are obtained by speeded up robust features (SURF). Then, the outliers are roughly eliminated by the geometric position of global features. The features are refined by the SSIM between the main and reference projections. Subsequently, the SSIM between the neighborhood images of features are used to relocate the features. Finally, the new features are used to align the projections. The two-dimensional (2D) transmission imaging experiments reveal that the proposed method provides more accurate and robust results than the random sample consensus (RANSAC) and locality preserving matching (LPM) methods. For three-dimensional (3D) imaging correction, the proposed method is compared with the commonly used enhanced correlation coefficient (ECC) method and single-step discrete Fourier transform (DFT) algorithm. The results reveal that proposed method can retain the details more faithfully. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

12 pages, 1421 KiB

Open AccessArticle

Assessing Post-Driving Discomfort and Its Influence on Gait Patterns

by Marko M. Cvetkovic, Denise Soares and João Santos Baptista

Sensors 2021, 21(24), 8492; https://doi.org/10.3390/s21248492 - 20 Dec 2021

Cited by 1 | Viewed by 4788

Abstract

Professional drivers need constant attention during long driving periods and sometimes perform tasks outside the truck. Driving discomfort may justify inattention, but it does not explain post-driving accidents outside the vehicle. This study aims to study the discomfort developed during driving by analysing [...] Read more.

Professional drivers need constant attention during long driving periods and sometimes perform tasks outside the truck. Driving discomfort may justify inattention, but it does not explain post-driving accidents outside the vehicle. This study aims to study the discomfort developed during driving by analysing modified preferred postures, pressure applied at the interface with the seat, and changes in pre- and post-driving gait patterns. Each of the forty-four volunteers drove for two hours in a driving simulator. Based on the walking speed changes between the two gait cycles, three homogeneous study groups were identified. Two groups performed faster speeds, while one reduced it in the post-steering gait. While driving, the pressure at the interface and the area covered over the seat increased throughout the sample. Preferred driving postures differed between groups. No statistical differences were found between the groups in the angles between the segments (flexed and extended). Long-time driving develops local or whole-body discomfort, increasing interface pressure over time. While driving, drivers try to compensate by modifying their posture. After long steering periods, a change in gait patterns can be observed. These behaviours may result from the difficulties imposed on blood circulation by increasing pressure at this interface. Full article

(This article belongs to the Special Issue Environmental and Workplace Monitoring for the Assessment of Occupational Risks and Worker Comfort)

► Show Figures

Figure 1

24 pages, 5342 KiB

Open AccessReview

Recent Advances in Aptasensor for Cytokine Detection: A Review

by Jinmyeong Kim, Seungwoo Noh, Jeong Ah Park, Sang-Chan Park, Seong Jun Park, Jin-Ho Lee, Jae-Hyuk Ahn and Taek Lee

Sensors 2021, 21(24), 8491; https://doi.org/10.3390/s21248491 - 20 Dec 2021

Cited by 22 | Viewed by 5598

Abstract

Cytokines are proteins secreted by immune cells. They promote cell signal transduction and are involved in cell replication, death, and recovery. Cytokines are immune modulators, but their excessive secretion causes uncontrolled inflammation that attacks normal cells. Considering the properties of cytokines, monitoring the [...] Read more.

Cytokines are proteins secreted by immune cells. They promote cell signal transduction and are involved in cell replication, death, and recovery. Cytokines are immune modulators, but their excessive secretion causes uncontrolled inflammation that attacks normal cells. Considering the properties of cytokines, monitoring the secretion of cytokines in vivo is of great value for medical and biological research. In this review, we offer a report on recent studies for cytokine detection, especially studies on aptasensors using aptamers. Aptamers are single strand nucleic acids that form a stable three-dimensional structure and have been receiving attention due to various characteristics such as simple production methods, low molecular weight, and ease of modification while performing a physiological role similar to antibodies. Full article

(This article belongs to the Special Issue Field Effect Transistor (FET)-Based Biosensors)

► Show Figures

Figure 1

11 pages, 14656 KiB

Open AccessArticle

Limitations of Muscle Ultrasound Shear Wave Elastography for Clinical Routine—Positioning and Muscle Selection

by Alyssa Romano, Deborah Staber, Alexander Grimm, Cornelius Kronlage and Justus Marquetand

Sensors 2021, 21(24), 8490; https://doi.org/10.3390/s21248490 - 20 Dec 2021

Cited by 27 | Viewed by 5242

Abstract

Shear wave elastography (SWE) is a clinical ultrasound imaging modality that enables non-invasive estimation of tissue elasticity. However, various methodological factors—such as vendor-specific implementations of SWE, mechanical anisotropy of tissue, varying anatomical position of muscle and changes in elasticity due to passive muscle [...] Read more.

Shear wave elastography (SWE) is a clinical ultrasound imaging modality that enables non-invasive estimation of tissue elasticity. However, various methodological factors—such as vendor-specific implementations of SWE, mechanical anisotropy of tissue, varying anatomical position of muscle and changes in elasticity due to passive muscle stretch—can confound muscle SWE measurements and increase their variability. A measurement protocol with a low variability of reference measurements in healthy subjects is desirable to facilitate diagnostic conclusions on an individual-patient level. Here, we present data from 52 healthy volunteers in the areas of: (1) Characterizing different limb and truncal muscles in terms of inter-subject variability of SWE measurements. Superficial muscles with little pennation, such as biceps brachii, exhibit the lowest variability whereas paravertebral muscles show the highest. (2) Comparing two protocols with different limb positioning in a trade-off between examination convenience and SWE measurement variability. Repositioning to achieve low passive extension of each muscle results in the lowest SWE variability. (3) Providing SWE shear wave velocity (SWV) reference values for a specific ultrasound machine/transducer setup (Canon Aplio i800, 18 MHz probe) for a number of muscles and two positioning protocols. We argue that methodological issues limit the current clinical applicability of muscle SWE. Full article

(This article belongs to the Special Issue Ultrasound Imaging and Sonoelastography for Measuring Mechanical Properties of Human Tissues)

► Show Figures

Figure 1

Figure 1
Representation of the muscle measurement locations with the average SWV in m/s and the corresponding standard deviation (±) of Protocol 1 (A) and 2 (B) and comparison of the variance between them (C): The variances of measurements acquired using Protocol 2 (optimized, rigid SWE-protocol) were significantly lower (p < 0.001) than under Protocol 1 (clinical feasibility). DE = deltoideus. BB = biceps brachii. ECR = extensor carpi radialis. FDP = flexor digitorum profundus. TR = triceps brachii. MU (C8) = multifidus (C8). ES (Th10) = erector spinae (Th10). ES (L3) = erector spinae (L3). VA = vastus lateralis. BF = biceps femoris (caput longum). TA = tibialis anterior. GCM = gastrocnemius (caput mediale). Full article ">Figure A1
SWE images of the examination of a 32-year-old male in Protocol 2 (optimized, rigid SWE-protocol): SWE pictures of the deltoid (DE), flexor digitorum profundus (FDP), tibialis anterior (TA), biceps brachii (BB) and vastus lateralis (VA) muscle, triceps brachii (TR), biceps femoris caput longum (BF), extensor carpi radialis (ECR) and gastrocnemius caput mediale (GCM) muscle are shown. On the left side of each picture, the B-mode images in gray scale are overlaid with SWV data in color. The cooler colors, such as the blue in these pictures, depict slower shear wave speeds, typically ranging from 0–6 m/s. As predicted, in Protocol 2 (optimized, rigid SWE-protocol), the muscles were positioned in optimally relaxed states, to avoid strain, which was demonstrated by the consistent blue coloring within the SWE pictures. On the right side of each picture, the shape of the shear waves is displayed with lines. The blue lines represent the origin of the shear waves and the red lines represent the change in the shear waves as they propagate accordingly through the muscle. In these pictures, the greater depth of acquisition required for FDP and DE can be seen. The layer of subcutaneous fat above the DE was typically thicker than for TA, BB and VA. Additionally, the greater pennation angle of DE is illustrated in that the muscle fibers could not be completely optimally displayed to parallel in the longitudinal plane. Alternatively, the path of the muscle fibers of FDP, TA, BB and VA could be displayed well in the longitudinal plane. Full article ">

19 pages, 12740 KiB

Open AccessArticle

Design of a New Seismoelectric Logging Instrument

by Liangchen Zhang, Xiaodong Ju, Junqiang Lu, Baiyong Men and Weiliang He

Sensors 2021, 21(24), 8489; https://doi.org/10.3390/s21248489 - 20 Dec 2021

Cited by 1 | Viewed by 2298

Abstract

To increase the accuracy of reservoir evaluation, a new type of seismoelectric logging instrument was designed. The designed tool comprises the invented sonde-structured array complex. The tool includes several modules, including a signal excitation module, data acquisition module, phased array transmitting module, impedance [...] Read more.

To increase the accuracy of reservoir evaluation, a new type of seismoelectric logging instrument was designed. The designed tool comprises the invented sonde-structured array complex. The tool includes several modules, including a signal excitation module, data acquisition module, phased array transmitting module, impedance matching module and a main system control circuit, which are interconnected through high-speed tool bus to form a distributed architecture. UC/OS-II was used for the real-time system control. After constructing the experimental measurement system prototype of the seismoelectric logging detector, its performance was verified in the laboratory. The obtained results showed that the consistency between the multi-channel received waveform amplitude and benchmark spectrum was more than 97%. The binary phased linear array transmitting module of the instrument can realize 0° to 20° deflection and directional radiation. In the end, a field test was conducted to verify the tool’s performance in downhole conditions. The results of this test proved the effectiveness of the developed seismoelectric logging tool. Full article

(This article belongs to the Special Issue Sensors in Electronic Measurement Systems)

► Show Figures

Figure 1

17 pages, 9511 KiB

Open AccessArticle

Autonomous UAV System for Cleaning Insulators in Power Line Inspection and Maintenance

by Ricardo Lopez Lopez, Manuel Jesus Batista Sanchez, Manuel Perez Jimenez, Begoña C. Arrue and Anibal Ollero

Sensors 2021, 21(24), 8488; https://doi.org/10.3390/s21248488 - 20 Dec 2021

Cited by 28 | Viewed by 6092

Abstract

The inspection and maintenance tasks of electrical installations are very demanding. Nowadays, insulator cleaning is carried out manually by operators using scaffolds, ropes, or even helicopters. However, these operations involve potential risks for humans and the electrical structure. The use of Unmanned Aerial [...] Read more.

The inspection and maintenance tasks of electrical installations are very demanding. Nowadays, insulator cleaning is carried out manually by operators using scaffolds, ropes, or even helicopters. However, these operations involve potential risks for humans and the electrical structure. The use of Unmanned Aerial Vehicles (UAV) to reduce the risk of these tasks is rising. This paper presents an UAV to autonomously clean insulators on power lines. First, an insulator detection and tracking algorithm has been implemented to control the UAV in operation. Second, a cleaning tool has been designed consisting of a pump, a tank, and an arm to direct the flow of cleaning liquid. Third, a vision system has been developed that is capable of detecting soiled areas using a semantic segmentation neuronal network, calculating the trajectory for cleaning in the image plane, and generating arm trajectories to efficiently clean the insulator. Fourth, an autonomous system has been developed to land on a charging pad to charge the batteries and potentially fill the tank with cleaning liquid. Finally, the autonomous system has been validated in a controlled outdoor environment. Full article

(This article belongs to the Special Issue Advanced Sensors Technologies Applied in Mobile Robot)

► Show Figures

Figure 1

27 pages, 3549 KiB

Open AccessArticle

Divergence-Based Segmentation Algorithm for Heavy-Tailed Acoustic Signals with Time-Varying Characteristics

by Aleksandra Grzesiek, Karolina Gąsior, Agnieszka Wyłomańska and Radosław Zimroz

Sensors 2021, 21(24), 8487; https://doi.org/10.3390/s21248487 - 20 Dec 2021

Cited by 5 | Viewed by 2685

Abstract

Many real-world systems change their parameters during the operation. Thus, before the analysis of the data, there is a need to divide the raw signal into parts that can be considered as homogeneous segments. In this paper, we propose a segmentation procedure that [...] Read more.

Many real-world systems change their parameters during the operation. Thus, before the analysis of the data, there is a need to divide the raw signal into parts that can be considered as homogeneous segments. In this paper, we propose a segmentation procedure that can be applied for the signal with time-varying characteristics. Moreover, we assume that the examined signal exhibits impulsive behavior, thus it corresponds to the so-called heavy-tailed class of distributions. Due to the specific behavior of the data, classical algorithms known from the literature cannot be used directly in the segmentation procedure. In the considered case, the transition between parts corresponding to homogeneous segments is smooth and non-linear. This causes that the segmentation algorithm is more complex than in the classical case. We propose to apply the divergence measures that are based on the distance between the probability density functions for the two examined distributions. The novel segmentation algorithm is applied to real acoustic signals acquired during coffee grinding. Justification of the methodology has been performed experimentally and using Monte-Carlo simulations for data from the model with heavy-tailed distribution (here the stable distribution) with time-varying parameters. Although the methodology is demonstrated for a specific case, it can be extended to any process with time-changing characteristics. Full article

(This article belongs to the Special Issue Sensing Technology and Data Interpretation in Machine Diagnosis and Systems Condition Monitoring: Volume 2)

► Show Figures

Figure 1

8 pages, 3286 KiB

Open AccessCommunication

Plasma Generator with Dielectric Rim and FSS Electrode for Enhanced RCS Reduction Effect

by Taejoo Oh, Changseok Cho, Wookhyun Ahn, Jong-Gwan Yook, Jangjae Lee, Shinjae You, Jinwoo Yim, Jungje Ha, Gihun Bae, Heung-Cheol You and Yongshik Lee

Sensors 2021, 21(24), 8486; https://doi.org/10.3390/s21248486 - 20 Dec 2021

Cited by 10 | Viewed by 2708

Abstract

In this study, a method was experimentally verified for further reducing the radar cross-section (RCS) of a two-dimensional planar target by using a dielectric rim in a dielectric barrier discharge (DBD) plasma generator using a frequency selective surface (FSS) as an electrode. By [...] Read more.

In this study, a method was experimentally verified for further reducing the radar cross-section (RCS) of a two-dimensional planar target by using a dielectric rim in a dielectric barrier discharge (DBD) plasma generator using a frequency selective surface (FSS) as an electrode. By designing the frequency selective surface such that the passbands of the radar signal match, it is possible to minimize the effect of the conductor electrode, in order to maximize the RCS reduction effect due to the plasma. By designing the FSS to be independent of the polarization, the effect of RCS reduction can be insensitive to the polarization of the incoming wave. Furthermore, by introducing a dielectric rim between the FSS electrode and the target, an additional RCS reduction effect is achieved. By fabricating the proposed plasma generator, an RCS reduction effect of up to 6.4 dB in X-band was experimentally verified. Full article

(This article belongs to the Section Remote Sensors)

► Show Figures

Figure 1

Figure 1
Components of the proposed dielectric barrier discharge (DBD) structure plasma generator: (a) frequency selective surface (FSS) electrode, (b) dielectric rim, (c) three-dimensional (3D) layer structure. Full article ">Figure 2
Fabricated DBD structure plasma generator. Full article ">Figure 3
Monostatic radar cross-section (RCS) experimental environment: (a) block diagram, (b) photograph. Full article ">Figure 4
Plasma generation form of the fabricated generator. Full article ">Figure 5
Voltage and current value of optimal plasma. Full article ">Figure 6
Measured (thick) and simulated (thin) RCS results: target (20 × 20 cm2 copper plate), target with DBD (plasma off), target with DBD (plasma on with and without dielectric rim). Simulated results are those of the target. Full article ">Figure 7
Comparison of RCS reduction effect of proposed DBD: with and without dielectric rim. Measured (thick) and simulated (thin) results based on the Drude model using CST [<a href="#B14-sensors-21-08486" class="html-bibr">14</a>]. Full article ">

34 pages, 2666 KiB

Open AccessReview

Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review

by Rabindra Gandhi Thangarajoo, Mamun Bin Ibne Reaz, Geetika Srivastava, Fahmida Haque, Sawal Hamid Md Ali, Ahmad Ashrif A. Bakar and Mohammad Arif Sobhan Bhuiyan

Sensors 2021, 21(24), 8485; https://doi.org/10.3390/s21248485 - 20 Dec 2021

Cited by 23 | Viewed by 4298

Abstract

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their [...] Read more.

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of ‘3N’ biosignals—nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result. Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

15 pages, 1408 KiB

Open AccessArticle

Sagittal and Vertical Growth of the Maxillo–Mandibular Complex in Untreated Children: A Longitudinal Study on Lateral Cephalograms Derived from Cone Beam Computed Tomography

by Leah Yi, Hyeran Helen Jeon, Chenshuang Li, Normand Boucher and Chun-Hsi Chung

Sensors 2021, 21(24), 8484; https://doi.org/10.3390/s21248484 - 20 Dec 2021

Cited by 5 | Viewed by 2995

Abstract

The aim of this longitudinal study was to evaluate the sagittal and vertical growth of the maxillo–mandibular complex in untreated children using orthogonal lateral cephalograms compressed from cone beam computed tomography (CBCT). Two sets of scans, on 12 males (mean 8.75 years at [...] Read more.

The aim of this longitudinal study was to evaluate the sagittal and vertical growth of the maxillo–mandibular complex in untreated children using orthogonal lateral cephalograms compressed from cone beam computed tomography (CBCT). Two sets of scans, on 12 males (mean 8.75 years at T1, and 11.52 years at T2) and 18 females (mean 9.09 years at T1, and 10.80 years at T2), were analyzed using Dolphin 3D imaging. The displacements of the landmarks and rotations of both jaws relative to the cranial base were measured using the cranial base, and the maxillary and mandibular core lines. From T1 to T2, relative to the cranial base, the nasion, orbitale, A-point, and B-point moved anteriorly and inferiorly. The porion moved posteriorly and inferiorly. The ANB and mandibular plane angle decreased. All but one subject had forward rotation in reference to the cranial base. The maxillary and mandibular superimpositions showed no sagittal change on the A-point and B-point. The U6 and U1 erupted at 0.94 and 1.01 mm/year (males) and 0.82 and 0.95 mm/year (females), respectively. The L6 and L1 erupted at 0.66 and 0.88 mm/year (males), and at 0.41 mm/year for both the L6 and the L1 (females), respectively. Full article

(This article belongs to the Special Issue New Frontier in Advanced Dentistry: CBCT, Intraoral Scanner, Sensors, and Artificial Intelligence in Dentistry)

► Show Figures

Figure 1

Figure 1
CBCT Orientation: (A) roll and yaw, and (B) pitch, as previously published in [<a href="#B25-sensors-21-08484" class="html-bibr">25</a>]. Full article ">Figure 2
The cranial base, maxillary, and mandibular core lines. (A) Landmarks were placed on the CBCT image to facilitate the identification of certain structures. (B) The cranial base core line is drawn on the T1 lateral cephalograms and transferred onto the T2 tracing on a cranial base superimposition. (C) The maxillary core lines. (D) The mandibular core lines. Black: T1, and red: T2. Full article ">Figure 3
Angular measurements: (A) CB line-A, CB line-B, and A-CB point-B.; (B) CB line-GoGn.; (C) CB line-Mx point, CB line-Md point, and Mx point-CB line-Md point.; (D) CB line-Mx line and CB line-Md line; (E) Co-Md line.; (F) Md line-Md border. Full article ">Figure 4
Sagittal (x) and vertical (y) movements of cephalometric points in males (mm/year). The average annual sagittal (x) and vertical (y) movements of cephalometric points on cranial base, maxillary, and mandibular superimpositions of the T1 and T2 lateral cephalograms in males. Full article ">Figure 5
Sagittal (x) and vertical (y) movements of cephalometric points in females (mm/year). The average annual sagittal (x) and vertical (y) movements of cephalometric points on cranial base, maxillary, and mandibular superimpositions of the T1 and T2 lateral cephalograms in females. Full article ">Figure 6
The annual average changes in the linear and angular measurements in males (gray) and females (white). Full article ">

9 pages, 3414 KiB

Open AccessArticle

Estimation of Fluor Emission Spectrum through Digital Photo Image Analysis with a Water-Based Liquid Scintillator

by Ji-Won Choi, Ji-Young Choi and Kyung-Kwang Joo

Sensors 2021, 21(24), 8483; https://doi.org/10.3390/s21248483 - 20 Dec 2021

Cited by 2 | Viewed by 2224

Abstract

In this paper, we performed a feasibility study of using a water-based liquid scintillator (WbLS) for conducting imaging analysis with a digital camera. The liquid scintillator (LS) dissolves a scintillating fluor in an organic base solvent to emit light. We synthesized a liquid [...] Read more.

In this paper, we performed a feasibility study of using a water-based liquid scintillator (WbLS) for conducting imaging analysis with a digital camera. The liquid scintillator (LS) dissolves a scintillating fluor in an organic base solvent to emit light. We synthesized a liquid scintillator using water as a solvent. In a WbLS, a suitable surfactant is needed to mix water and oil together. As an application of the WbLS, we introduced a digital photo image analysis in color space. A demosaicing process to reconstruct and decode color is briefly described. We were able to estimate the emission spectrum of the fluor dissolved in the WbLS by analyzing the pixel information stored in the digital image. This technique provides the potential to estimate fluor components in the visible region without using an expensive spectrophotometer. In addition, sinogram analysis was performed with Radon transformation to reconstruct transverse images with longitudinal photo images of the WbLS sample. Full article

(This article belongs to the Special Issue Sensors and Advanced Sensing Techniques for Signal, Image and Computer Vision Applications)

► Show Figures

Figure 1

Figure 1
A workflow example of CFA arrangement and the demosaicing process for an interpolated full color image. (a) Repetitive patterns consisting of R, G, and B are called mosaics. (b) Demosaicing according to each RGB color component. Input raw (mosaiced) image from CFA. (c) Spatial arrangement (lowercase of rgb) of each pixel is assigned based on neighboring pixel color information. The result of red, green and blue channel interpolation at white locations. (d) The final result of RGB interpolation of each pixel. The final result of red, green, and blue channel interpolation at red, green and blue locations. Full article ">Figure 2
(a) Experimental setting for taking digital image photographs. The camera was placed approximately 50 cm in front of the WbLS sample. Because there was a wall between the camera and the WbLS sample the UV lamp light did not directly enter the camera. Only the desired light reached the camera. A cylindrical quartz container with a diameter of 4 cm and a height of 7 cm was filled with WbLS using IGEPAL CO-630 surfactant. It was placed on top of the rotating disk. UV light illuminated the sample from the top of the container. The camera was remotely controlled. (b) Rectangular boxes represent regions of interest. Only those pixel regions whose V value in the HSV model was greater than 60% were selected and their boundary lines were displayed as a rectangular box. The fourth box was selected for the background rejection. Full article ">Figure 3
(a) Red, (b) Green, and (c) Blue components extracted from the photographed images in <a href="#sensors-21-08483-f002" class="html-fig">Figure 2</a>b taken by a CMOS digital camera (Canon EOS 450D). RGB values of PPO, PPO+POPOP, PPO+bis-MSB as a function of pixel intensity are listed. Among R, G, and B values, blue values are dominant in each fluor case. (d) Extracted emission spectrum of PPO, POPOP, and bis-MSB from hue value after background subtraction as a function of wavelength. Full article ">Figure 3 Cont.
(a) Red, (b) Green, and (c) Blue components extracted from the photographed images in <a href="#sensors-21-08483-f002" class="html-fig">Figure 2</a>b taken by a CMOS digital camera (Canon EOS 450D). RGB values of PPO, PPO+POPOP, PPO+bis-MSB as a function of pixel intensity are listed. Among R, G, and B values, blue values are dominant in each fluor case. (d) Extracted emission spectrum of PPO, POPOP, and bis-MSB from hue value after background subtraction as a function of wavelength. Full article ">Figure 4
(a) UV light was illuminated from above the WbLS sample. An initial front view digital image of the WbLS sample using HCO-60 surfactant placed on a rotating disk before rotation. Then, the disk rotated at a constant speed. (b) A horizontal dashed line is shown passing through the air bubble in the container. Its pixel number of z-axis is 542. The tomographic image was extracted and reconstructed based on this line. The camera was focused on the center of the container and a picture was taken after rotating the disk every 0.25°. Only a portion of the 1,400 projected images is shown. Full article ">Figure 5
(a) A 360° sinogram reconstructed from the image of the small air bubble created in WbLS sample. The x-axis is 1 to 360° (1 to 1400 pixel labels), depending on how much the cylindrical circle is divided. The y-axis is the pixel label of the y-axis (height) of the yz-plane image. The color represents the brightness of the surroundings including the bottle when we reconstruct it with an arbitrary color. Each pixel number band on the y-axis means 700–800 (outer wall), 800–900 (air layer between sample container and outer wall), 900–1000 (inside WbLS sample container), 1000–1100 (air layer between sample container and outer wall, same as 800–900 pixel numbers), 1100–1200 (outer wall, same as 700–800 pixel numbers). (b) Tomographic top view image after inverse Radon transformation from (a). The pixel number of z-axis is 542. The x(y)-axis is the pixel label of the x(y) coordinate seen from the top. Two air bubbles in the center of the WbLS sample container can be seen. The ring shape surrounding the air bubbles represents the container. The outermost circle-shaped image represents a virtual image created by light reflected from the outside of the WbLS sample container. Full article ">

19 pages, 7344 KiB

Open AccessArticle

Highly Configurable 100 Channel Recording and Stimulating Integrated Circuit for Biomedical Experiments

by Piotr Kmon

Sensors 2021, 21(24), 8482; https://doi.org/10.3390/s21248482 - 20 Dec 2021

Viewed by 3017

Abstract

This paper presents the design results of a 100-channel integrated circuit dedicated to various biomedical experiments requiring both electrical stimulation and recording ability. The main design motivation was to develop an architecture that would comprise not only the recording and stimulation, but would [...] Read more.

This paper presents the design results of a 100-channel integrated circuit dedicated to various biomedical experiments requiring both electrical stimulation and recording ability. The main design motivation was to develop an architecture that would comprise not only the recording and stimulation, but would also block allowing to meet different experimental requirements. Therefore, both the controllability and programmability were prime concerns, as well as the main chip parameters uniformity. The recording stage allows one to set their parameters independently from channel to channel, i.e., the frequency bandwidth can be controlled in the (0.3 Hz–1 kHz)–(20 Hz–3 kHz) (slow signal path) or (0.3 Hz–1 kHz)–4.7 kHz (fast signal path) range, while the voltage gain can be set individually either to 43.5 dB or 52 dB. Importantly, thanks to in-pixel circuitry, main system parameters may be controlled individually allowing to mitigate the circuitry components spread, i.e., lower corner frequency can be tuned in the 54 dB range with approximately 5% precision, and the upper corner frequency spread is only 4.2%, while the voltage gain spread is only 0.62%. The current stimulator may also be controlled in the broad range (69 dB) with its current setting precision being no worse than 2.6%. The recording channels’ input-referred noise is equal to 8.5 µV_RMS in the 10 Hz–4.7 kHz bandwidth. The single-pixel occupies 0.16 mm² and consumes 12 µW (recording part) and 22 µW (stimulation blocks). Full article

(This article belongs to the Section Biomedical Sensors)

► Show Figures

Figure 1

21 pages, 5726 KiB

Open AccessArticle

Efficient Online Object Tracking Scheme for Challenging Scenarios

by Khizer Mehmood, Ahmad Ali, Abdul Jalil, Baber Khan, Khalid Mehmood Cheema, Maria Murad and Ahmad H. Milyani

Sensors 2021, 21(24), 8481; https://doi.org/10.3390/s21248481 - 20 Dec 2021

Cited by 10 | Viewed by 3670

Abstract

Visual object tracking (VOT) is a vital part of various domains of computer vision applications such as surveillance, unmanned aerial vehicles (UAV), and medical diagnostics. In recent years, substantial improvement has been made to solve various challenges of VOT techniques such as change [...] Read more.

Visual object tracking (VOT) is a vital part of various domains of computer vision applications such as surveillance, unmanned aerial vehicles (UAV), and medical diagnostics. In recent years, substantial improvement has been made to solve various challenges of VOT techniques such as change of scale, occlusions, motion blur, and illumination variations. This paper proposes a tracking algorithm in a spatiotemporal context (STC) framework. To overcome the limitations of STC based on scale variation, a max-pooling-based scale scheme is incorporated by maximizing over posterior probability. To avert target model from drift, an efficient mechanism is proposed for occlusion handling. Occlusion is detected from average peak to correlation energy (APCE)-based mechanism of response map between consecutive frames. On successful occlusion detection, a fractional-gain Kalman filter is incorporated for handling the occlusion. An additional extension to the model includes APCE criteria to adapt the target model in motion blur and other factors. Extensive evaluation indicates that the proposed algorithm achieves significant results against various tracking methods. Full article

(This article belongs to the Special Issue Sensors for Object Detection, Classification and Tracking)

► Show Figures

Figure 1

11 pages, 3912 KiB

Open AccessArticle

Detecting Teeth Defects on Automotive Gears Using Deep Learning

by Abdelrahman Allam, Medhat Moussa, Cole Tarry and Matthew Veres

Sensors 2021, 21(24), 8480; https://doi.org/10.3390/s21248480 - 19 Dec 2021

Cited by 11 | Viewed by 5171

Abstract

Gears are a vital component in many complex mechanical systems. In automotive systems, and in particular vehicle transmissions, we rely on them to function properly on different types of challenging environments and conditions. However, when a gear is manufactured with a defect, the [...] Read more.

Gears are a vital component in many complex mechanical systems. In automotive systems, and in particular vehicle transmissions, we rely on them to function properly on different types of challenging environments and conditions. However, when a gear is manufactured with a defect, the gear’s integrity can become compromised and lead to catastrophic failure. The current inspection process used by an automotive gear manufacturer in Guelph, Ontario, requires human operators to visually inspect all gear produced. Yet, due to the quantity of gears manufactured, the diverse array of defects that can arise, the time requirements for inspection, and the reliance on the operator’s inspection ability, the system suffers from poor scalability, and defects can be missed during inspection. In this work, we propose a machine vision system for automating the inspection process for gears with damaged teeth defects. The implemented inspection system uses a faster R-CNN network to identify the defects, and combines domain knowledge to reduce the manual inspection of non-defective gears by 66%. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

Figure 1
Damaged Teeth defect on the Tooth Edge (top row), and Top Land (bottom row). Full article ">Figure 2
Faster R-CNN deep learning network for defect detection. Full article ">Figure 3
The same damaged teeth defect remains visible to the camera as the gear is rotated during inspection starting from the left most image to the right most image. Full article ">Figure 4
Inspection cell and sample camera images. Left: inspection cell, Top Right: image from the first camera, Bottom Right: image from the second camera. Full article ">Figure 5
Average precision and recall of the 10-folds for the damaged teeth defects. Full article ">Figure 6
Precision and recall values for 306 images of damaged teeth defects. Full article ">Figure 7
A false positive was not considered a defect since it was detected by the algorithm only on the first and second images (surrounded by blue and yellow bounding boxes), and was not detected on the third image (red circle). Full article ">

Journal Menu

Journal Browser

Sensors, Volume 21, Issue 24 (December-2 2021) – 347 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI