scispace - formally typeset
Search or ask a question

Showing papers in "IEEE Sensors Journal in 2023"


Journal ArticleDOI
TL;DR: This paper proposes a situation-aware mechanism to detect Covid-19 systems early and alert the user to be self-aware regarding the situation to take precautions if the situation seems unlikely to be normal.
Abstract: Ambient intelligence plays a crucial role in healthcare situations. It provides a certain way to deal with emergencies to provide the essential resources such as nearest hospitals and emergency stations promptly to avoid deaths. Since the outbreak of Covid-19, several artificial intelligence techniques have been used. However, situation awareness is a key aspect to handling any pandemic situation. The situation-awareness approach gives patients a routine life where they are continuously monitored by caregivers through wearable sensors and alert the practitioners in case of any patient emergency. Therefore, in this paper, we propose a situation-aware mechanism to detect Covid-19 systems early and alert the user to be self-aware regarding the situation to take precautions if the situation seems unlikely to be normal. We provide Belief-Desire-Intention intelligent reasoning mechanism for the system to analyze the situation after acquiring the data from the wearable sensors and alert the user according to their environment. We use the case study for further demonstration of our proposed framework. We model the proposed system by temporal logic and map the system illustration into a simulation tool called NetLogo to determine the results of the proposed system.

24 citations


Peer ReviewDOI
TL;DR: In this paper , surface plasmon resonance (SPR)-based photonic crystal fibers (PCF) are used to detect chemical and biological (such as antibodies, cells, bacteria, enzymes, viruses, nucleic acids, etc.) substances.
Abstract: The promising properties of photonic crystal fibers (PCFs) have sparked the interest of a number of research organizations. Due to the PCF’s air holes, liquid or gas samples can be inserted into them. This permits a well-controlled interaction between confined light and sensing samples, enabling the development of novel sensing applications. That was never conceivable with conventional optical fibers. PCF applications in sensing fields can be divided into physical sensors and biochemical sensors based on the parameter being measured. Physical sensors measure pressure, temperature, refractive index (RI), curvature, vibration, torsion, electric field, and displacement, among other physical characteristics. Biochemical sensors can detect chemical and biological (such as antibodies, cells, bacteria, enzymes, viruses, nucleic acids, etc.) substances. The measurement of the chemical RI is a crucial component of biochemical sensors. Due to their close relationship with biosensors, chemical sensors are commonly referred to as biochemical sensors. This article covers the detecting capabilities of surface plasmon resonance (SPR)-based PCF biochemical and physical sensors in addition to a variety of ways to enhance their sensing capacities.

16 citations


DOI
TL;DR: In this paper , an intelligent Passive Thermography (PTG) based fault diagnosis technique for detection of bearing faults using Convolutional Neural Network (CNN) with Transfer Learning (TL) under varying working conditions.
Abstract: Bearing is one of the core components of any rotating machine, and its failure is widespread. This reason drives continuous monitoring and detecting bearing faults during machine operation to warn operators and prevent unforeseen damage. This paper proposes an intelligent Passive Thermography (PTG) based fault diagnosis technique for detection of bearing faults using Convolutional Neural Network (CNN) with Transfer Learning (TL) under varying working conditions. The validation of the proposed method has been done on three different datasets; bearing test rig dataset has been taken as a source domain data while Induction Motor (IM), and Machine Fault Simulator (MFS) datasets have been taken as target domain data. The proposed method enables and speeds up the training process of CNN towards accurate adaptation for fault diagnosis approach in the escalated time frame. The experimental results demonstrated that the suggested approach could successfully learn transferable characteristics from the source domain model, which can cope with the issue of limited availability of training data required for the target domain. The classification accuracy on the target domain dataset were varied in the range of 89 -95.4 % in the case of the IM dataset and 96.5-97.5% in the case of the MFS dataset. Moreover, it shows the benefits of the suggested method, which may be utilized as an effective non-invasive diagnostic tool for rotating machines to avoid unexpected system shutdowns.

15 citations


DOI
TL;DR: In this paper , a robust method that can automatically detect and remove eyeblink and muscular artifacts from EEG using a k-nearest neighbor classifier and a long short-term memory (LSTM) network is proposed.
Abstract: Electroencephalogram (EEG) is often corrupted with artifacts originating from sources such as eyes and muscles. Hybrid artifact removal methods often require human intervention for the adjustment of different parameters. We propose a robust method that can automatically detect and remove eyeblink and muscular artifacts from EEG using a k-nearest neighbor (kNN) classifier and a long short-term memory (LSTM) network. Our method adopts a sliding window of 0.5 s to detect and remove the artifacts from EEG. Features, such as the variance, peak-to-peak amplitude, and average rectified value, are calculated for each EEG segment to identify corrupted segments using the kNN classifier. The kNN classifier detects the presence of artifacts, after which the corresponding EEG window is forwarded to the LSTM network for artifact removal. The LSTM network is trained with the corrupted segments of 0.5 s as input and clean segments of 0.5 s as output. Our method achieved an accuracy of 97.4% in identifying corrupted EEG segments and an average correlation coefficient, structural similarity, signal-to-artifact ratio, and normalized mean squared error of 0.69, 0.76, 1.52 dB, and 0.0013, respectively, in cleaning the EEG. Our results outperformed other hybrid methods reported in the literature based on a combination of ensemble empirical mode decomposition and canonical correlation analysis, a combination of independent component analysis and wavelet decomposition, and tensor decomposition. The mean absolute error of our method is also better in comparison to other methods. Our method can be applied to single and multiple channels and does not require any tuning of parameters.

12 citations


DOI
TL;DR: In this article, a multitask CNN was proposed for bolt loosening, which consists of a temperature compensation subnetwork to compensate for the temperature effect, and a lightweight damage identification sub-network to identify bolt loosens states.
Abstract: Bolts are frequently subjected to loosening due to time varying external loads during service. The electromechanical impedance (EMI) technique based on piezoelectric ceramic wafers (PZT) is sensitive to the initial bolt preload looseness. However, the change in environmental temperature has a great effect on EMI monitoring. Deep convolutional neural network (CNN) is a promising technique for EMI monitoring. Nevertheless, it is difficult to train a deep CNN with limited training data to accurately identify damages under a wide range of temperature variations. To this end, this study proposes a multitask CNN for identifying bolts loosening. The network consists of a temperature compensation subnetwork to compensate for the temperature effect, and a lightweight damage identification subnetwork to identify bolt loosening states. The temperature compensation subnetwork is a modified Unet, and both the impedance and temperature are used as its input. The damage identification subnetwork is connected in series behind the temperature compensation subnetwork. A multiloss function is proposed in which a TV regularizer is used. Experimental results show that the validation accuracy of the multitask network is 97.71% when the network is trained by only about 30 samples from each loosening state. Moreover, the generalization abilities of the proposed multitask model to unexpected temperatures and bolt torques are investigated. The model is interpreted by the integrated gradients method, and is also compared with single-task damage identification CNNs. It is proved that the multitask network trained by limited samples can achieve accurate damage identification in temperature varying environments.

12 citations


DOI
TL;DR: In this article , a multiframe 4D millimeter-wave radar point cloud point cloud is used to detect 3D objects in a complex traffic environment, where the ego vehicle velocity information is estimated by the millimeterwave radar, and the relative velocity information of the mmWave radar point clouds is compensated for the absolute velocity information.
Abstract: Object detection is a crucial task in autonomous driving. Currently, object-detection methods for autonomous driving systems are primarily based on information from cameras and light detection and ranging (LiDAR), which may experience interference from complex lighting or poor weather. At present, the 4-D ( ${x}$ , ${y}$ , ${z}$ , ${v}$ millimeter-wave radar can provide a denser point cloud to achieve 3-D object-detection tasks that are difficult to complete with traditional millimeter-wave radar. Existing 3-D object point-cloud-detection algorithms are mostly based on 3-D LiDAR; these methods are not necessarily applicable to millimeter-wave radars, which have sparser data and more noise and include velocity information. This study proposes a 3-D object-detection framework based on a multiframe 4-D millimeter-wave radar point cloud. First, the ego vehicle velocity information is estimated by the millimeter-wave radar, and the relative velocity information of the millimeter-wave radar point cloud is compensated for the absolute velocity. Second, by matching between millimeter-wave radar frames, the multiframe millimeter-wave radar point cloud is matched to the last frame. Finally, the object is detected by the proposed multiframe millimeter-wave radar point-cloud-detection network. Experiments are performed using our newly recorded TJ4DRadSet dataset in a complex traffic environment. The results showed that the proposed object-detection framework outperformed the comparison methods based on the 3-D mean average precision. The experimental results and methods can be used as the baseline for other multiframe 4-D millimeter-wave radar-detection algorithms.

7 citations


Journal ArticleDOI
TL;DR: In this paper, a comprehensive assessment of the QoS of Internet of Medical Things (IoMT) applications used in this pandemic from 2019 to 2021 to identify their requirements and current challenges by taking into account various network components and communication metrics is presented.
Abstract: Smart Sensing has shown notable contributions in the healthcare industry and revamps immense advancement. With this, the present smart sensing applications such as the Internet of Medical Things (IoMT) applications are elongated in the COVID-19 outbreak to facilitate the victims and alleviate the extensive contamination frequency of this pathogenic virus. Although, the existing IoMT applications are utilized productively in this pandemic, but somehow, the Quality of Service (QoS) metrics are overlooked, which is the basic need of these applications followed by patients, physicians, nursing staff, etc. In this review article, we will give a comprehensive assessment of the QoS of IoMT applications used in this pandemic from 2019 to 2021 to identify their requirements and current challenges by taking into account various network components and communication metrics. To claim the contribution of this work, we explored layer-wise QoS challenges in the existing literature to identify particular requirements, and set the footprint for future research. Finally, we compared each section with the existing review articles to acknowledge the uniqueness of this work followed by the answer of a question why this survey paper is needed in the presence of current state-of-the-art review papers.

7 citations


Peer ReviewDOI
TL;DR: In this paper , the authors summarized the efforts made in the last five years to leverage AI-aided noncontact sensing techniques for applications in structural health monitoring (SHM), with an emphasis on image-based methods.
Abstract: Engineering structures and infrastructure continue to be used despite approaching or having reached their design lifetime. While contact-based measurement techniques are challenging to implement at a large scale and provide information at discrete locations only, noncontact methods are more user-friendly and offer accurate, robust, and continuous spatial information to quantify the structural conditions of the targeted systems. Advancements in optical sensors and image-processing algorithms increased the applicability of image-based noncontact techniques, such as photogrammetry, infrared thermography, and laser imaging for structural health monitoring (SHM). In addition, with the incorporation of artificial intelligence (AI) algorithms, the assessment process is expedited and made more efficient. This article summarizes the efforts made in the last five years to leverage AI-aided noncontact sensing techniques for applications in SHM with an emphasis on image-based methods. Future directions to advance AI-aided image-based sensing techniques for SHM of engineering structures are also discussed.

7 citations


Journal ArticleDOI
TL;DR: In this article , a terahertz (THz) microfluidic electromagnetic-induced transparency (EIT) meta-sensors were used to detect volatile organic compounds (VOCs) in liquid phase and soil.
Abstract: Volatile organic compounds (VOCs) are directly associated with human health concerns and environmental safety. Therefore, it is urgent to achieve accurate detection of VOCs both qualitatively and quantitatively. In this work, the qualitative detection of ethyl benzene (EB), isopropyl alcohol (IPA), and ethyl acetate (EA)—three pure VOCs in liquid phase—was discussed using terahertz (THz) microfluidic electromagnetic-induced transparency (EIT) meta-sensors. The THz response illustrated that with an increase in VOCs’ volumes (1– $6~\mu \text{L}$ ), resonant frequencies of dual transmission dips (0.855 and 1.724 THz) and the EIT peak (1.213 THz) exhibited redshift. The limit of detections (LODs) for pure IPA, EA, and EB can achieve 5.45, 13.46, and $4.35~\mu \text{g}$ , respectively. The multivariate fusion (MF) model based on the EIT responses to VOCs was utilized to improve the accuracy of trace detection and classification of VOCs. Furthermore, the above method combined with principal component analysis with the Gaussian mixture model (PCA-GMM) and the neural network classification algorithm support vector machine (SVM) was applied to the recognition of VOCs. In addition, the THz method is not feasible to detect trace amounts of VOCs (typically 0.3 mg/L) in wastewater because water is highly absorbable in the THz band and VOCs will evaporate if water is removed. Here, IPA, EA, and EB in soil were detected and classified by PCA-GMM combined with MF. Our results provide a new THz meta-sensor platform to trace the detection of VOCs in the liquid phase and soil and may be used to identify hazardous wastes in illegal dumping.

7 citations


DOI
TL;DR: In this article , a support vector machine (SVM) classifier was proposed to identify fault severity levels in the outer bearing's raceway from the measurement of motor dynamic strain signals collected from sensors based on fiber Bragg grating (FBG).
Abstract: Due to its robustness and cost-effectiveness, the three-phase induction motor (TIM) has become the most widespread electric machine today. However, like any other equipment, it is vulnerable to a fault, and about 52% of these are related to bearings. This work presents the detection of flaws in the outer bearing’s raceway from the measurement of motor dynamic strain signals collected from sensors based on fiber Bragg grating (FBG). Three different degrees of severity were considered for faults in the outer bearing’s raceway. The tests were carried out on the motor operating under no-load conditions, with 47 different power supply frequencies. This work proposes a support vector machine (SVM) classifier to identify fault severity levels. Feature extraction was performed using two techniques: selecting the four highest peaks in the frequency spectrum and principal component analysis (PCA). The supervised SVM classifiers show that the dataset formed from the PCA presented a higher hit rate than the dataset constituted by the four highest peaks, with 99.82% and 92.73%, respectively. Based on the methodology presented in this work, it was possible to validate the use of FBG to detect bearing faults. Regardless of the degree of severity of the fault analyzed, the sensor detected its characteristic frequency. Based on the methodology presented in this work, it was possible to validate the use of FBG to detect bearing faults. Regardless of the degree of severity of the flaw analyzed, the sensor detected its characteristic frequency.

6 citations


Peer ReviewDOI
TL;DR: In this paper , the most recent advancements in thermal imaging technology, key performance parameters, an overview of its applications, and machine-learning techniques applied to thermal images for various tasks are discussed.
Abstract: Recent advancements in thermal imaging sensor technology have resulted in the use of thermal cameras in a variety of applications, including automotive, industrial, medical, defense and space, agriculture, and other related fields. Thermal imaging, unlike RGB imaging, does not rely on background light, and the technique is nonintrusive while also protecting privacy. This review article focuses on the most recent advancements in thermal imaging technology, key performance parameters, an overview of its applications, and machine-learning techniques applied to thermal images for various tasks. This article begins with the most recent advancements in thermal imaging, followed by a classification of thermal cameras and their key specifications, and finally a review of machine-learning techniques used on thermal images for various applications. This detailed review article is highly useful for designing thermal imaging-based applications using various machine-learning techniques.

Journal ArticleDOI
TL;DR: In this paper , the authors make full use of the target imaging prior information and take the minimum dimension of the measurement matrix and the maximum similarity between the obtained image and expected image as the goal of measurement matrix optimization.
Abstract: Radar target imaging can provide important information for target monitoring and recognition. In order to reduce the data amount and save radar resources, the target imaging methods based on compressed sensing (CS) have received extensive attention. In these methods, the measurement matrix will directly affect the target imaging quality and data down-sampling rate. However, most of the existing research works on measurement matrix optimization did not take into account the full use of target characteristic information and the internal consistency between the measurement matrix structure and the data sampling process, which makes it difficult to obtain the optimal imaging quality and down-sampling rate. To solve the above problems, this article makes full use of the target imaging prior information and takes the minimum dimension of the measurement matrix and the maximum similarity between the obtained image and expected image as the goal of measurement matrix optimization. On this basis, aims at the kind of signal which is composed of a group of sub-pulses with stepped frequency, a joint optimization model of measurement matrix and imaging performance based on the target imaging prior is established with the consideration of the 0–1 constraint of the measurement matrix structure caused by the physical observation process of the sparse-stepped frequency signals. Then, the corresponding sparse reconstruction algorithm is proposed. Thus, the optimal measurement matrix and high-resolution imaging results can be obtained, and the radar data down-sampling rate can be improved significantly. Simulation results indicate the effectiveness of the proposed method.

DOI
TL;DR: In this article , a redundant MEMS gyroscope system with an optimal configuration structure is constructed, and an optimal KF algorithm for multi-signal fusion is designed to estimate the three-dimensional orthogonal angular rate.
Abstract: Data fusion of redundant MEMS inertial sensors has become a new method for reducing sensor drift error and enhancing the accuracy of navigation systems. In this paper, a redundant MEMS gyroscope system having an optimal configuration structure is constructed. Firstly, the evaluation index of a redundant gyroscope system configuration is established, and the influencing factors of the configuration are analyzed under the condition of noise correlation in the component gyroscopes. Then redundant 4,5,6-gyro systems are designed. Secondly, the optimal KF algorithm for multi-signal fusion of the redundant gyroscope system is designed to estimate the three-dimensional orthogonal angular rate. Finally, a redundant 4-IMU system is designed. The simulation results showed that the input rate signal in the body coordinate ${X}_{b} {Y}_{b}{Z}_{b}$ can be accurately estimated and the drift error in single gyroscope can be remarkably reduced by fusing the redundant measurements. The experimental results illustrated that the ARW and RRW noise on the ${X}_{b}$ , ${Y}_{b}$ and ${Z}_{b}$ axes were reduced by a factor about 3.2 and 3.7 compared to the single gyroscope. In the swing test, the ${X}_{b}$ and ${Y}_{b}$ axes’ $1\sigma $ estimated error was reduced by a factor about 4.7 using the optimal KF algorithm compared to the single gyroscope, while on the ${Z}_{b}$ axis there was a decrease by a factor about 2.6.

DOI
TL;DR: In this paper , the authors investigated the characteristics of impedance signals induced by debris at different positions in planar coil under different frequencies, debris sizes and velocities, and they demonstrated that the double peaks generated in the induced signals can be eliminated without sacrificing the sensitivity by placing the sensor channel at the coil inner wall, and the sensitivity can be improved by observing resistance signals, increasing the frequencies and reducing debris velocity.
Abstract: The uneven radial magnetic field distribution in the planar coil will lead to debris detection errors, especially for inductive debris sensors with high throughput and sensitivity, so the effect of debris position on the detection sensitivity should be addressed. In this study, based on spatial magnetic field analysis of planar coil, the characteristics of impedance signals induced by debris at different positions in planar coil were investigated under different frequencies, debris sizes and velocities. The experimental results demonstrated that the double peaks generated in the induced signals can be eliminated without sacrificing the sensitivity by placing the sensor channel at the coil inner wall, and the sensitivity can be improved by observing resistance signals, increasing the frequencies and reducing debris velocities.

DOI
TL;DR: In this paper , a fiber Bragg grating (FBG) is embedded inside a patch made of silicone rubber, which allows to make the FBG sensitive to the force variations, obtain a flexible patch having a moldable shape, and protect the most fragile areas of the optical fiber.
Abstract: Force sensing is a key enabler for getting haptic feedback, useful in a variety of applications, especially in the fields of robotics, automation, and health. Indeed, equipping machines, vehicles, robots, and even humans with force sensors provides controlled processes and production, safe and enhanced external interaction, and capability to perform efficient manipulation and precise movements. Aiming to develop an alternative solution to electrical force sensors, in this work a fiber Bragg grating (FBG) is embedded inside a patch made of silicone rubber. Such embedding strategy allows to make the FBG sensitive to the force variations, obtain a flexible patch having a moldable shape, and protect the most fragile areas of the optical fiber. Moreover, due to its high flexibility and stretchability, the sensing patch can be easily employed as portable and wearable device. Besides reporting fabrication process and results of the performed force tests, this work provides a systematic study of the FBG embedding in a silicone matrix. Indeed, for this purpose, three sensing patches having different thicknesses are developed and tested in temperature, strain, and force, finding that the patch thickness influences the sensing performances of the device. The resulting force sensitivity varies in the range from 9.2 to 19.0 pm/N, based on the sensor thickness. Temperature sensitivity, instead, is comparable with respect to bare FBGs, while strain sensitivity is enormously reduced, obtaining a patch able to insulate the FBG from the strain variations.

DOI
TL;DR: Wang et al. as mentioned in this paper constructed copper nanoclusters with strong luminescence capable of rapid, sensitive, and visual detection of formaldehyde, which was self-assembled using D-penicillamine (DPA) as the protecting ligand.
Abstract: Highly sensitive detection of formaldehyde (FA) is of great importance to protect human health against its adverse effect. Herein, we constructed copper nanoclusters (Cu NCs) with strong luminescence capable of rapid, sensitive, and visual detection of FA, which was self-assembled using D-penicillamine (DPA) as the protecting ligand. Common physical measurements were carried out to analyze the as-fabricated samples (DPA-Cu NCs). Experimental results revealed its strong red fluorescence (FL), large Stokes shift, and a long fluorescence lifetime. Furthermore, DPA-Cu NCs presented self-assembled aggregation-induced emission (SAIE) property and achieved a fluorescence quantum yield (FLQY) as high as 76.26% in the solid state. Notably, FA could quench the fluorescence of Cu NCs effectively. The possible quenching mechanism was attributed to static quenching. Moreover, a paper-based visual sensor was built by immobilizing the DPA-Cu NCs probe on the filter paper, which can achieve on-site detection of FA.

DOI
TL;DR: In this article , a humidity sensor based on a bacterial nanocellulose membrane (BNC) produced from Komagataeibacter xylinus is presented. But the results of the measurements showed a combined sensitivity of −4.13 nF/°C in relation to the temperature, and +492 nF/(%RH) and +66.8 nA/(% RH) in relation with the relative humidity.
Abstract: This article presents the development of a humidity sensor based on bacterial nanocellulose membrane (BNC) produced from Komagataeibacter xylinus. BNC has a porous surface that absorbs water and therefore it changes the mechanical and electrical properties of the membrane. As the amount of water inside the membrane increases the capacitance of the membrane also increases. The capacitance of the BNC was measured in different values of temperature (from 30° to 100°) and relative humidity (from 30% to 100%). Chronoamperometry was used as a reproducibility test and the result was a linear and more precise variation for RH over 50% and a temperature of 30°. The measurements showed a combined sensitivity of −4.13 nF/°C in relation to the temperature, and +492 nF/(%RH) and +66.8 nA/(%RH) in relation to the relative humidity.

DOI
TL;DR: In this article , a concatenated microfiber interferometer and an artificial molecular receptor-based imprinting technique was used to develop an imprinted polymer functionalized optical sensor for precise determination of water pollutant 4-nitrophenol (4-NP) in aqueous media with a dynamic detection range of $10^{-{12}}$
Abstract: Optical interferometry integrated with molecularly imprinting polymer (MIP) can be an advanced futuristic approach for developing ultrasensitive and selective remote detection technology. This cohesive strategy has enormous potential for developing next-generation online biomolecule detection systems riding on the benefits of artificial complementary polymeric nanostructure with outstanding durability, easy synthesis process, and sustainability in harsh environmental conditions. Here, we have reported a label-free, hypersensitive, online, and selective biodetection method by combining a concatenated microfiber interferometer and an artificial molecular receptor-based imprinting technique to develop an imprinted polymer functionalized optical sensor for precise determination of water pollutant 4-nitrophenol (4-NP) in aqueous media with a dynamic detection range of $10^{-{12}}$ $10^{-{4}}$ M. The proposed imprinted polymer functionalized optical sensor exhibits a hypersensitivity of $6.14\times 10^{{11}}$ nm/M and a minimum detection limit of 1.628 fM. The compact size, fast response, repeatable behavior, and highly selective label-free detection nature of the developed system will pave a new path for selective biosensing, water quality monitoring, and environmental research applications.

Peer ReviewDOI
TL;DR: In this paper , a review of state-of-the-art studies on on-device DL for mobile and wearable devices, particularly from the sensor data analytics perspective, is presented.
Abstract: Although running deep-learning (DL) algorithms is challenging due to resource constraints on mobile and wearable devices, they provide performance improvements compared to lightweight or shallow architectures. The widespread application areas for on-device DL include computer vision, image processing, natural language processing, and audio classification. However, mobile and wearable sensing applications are also gaining attention. They can benefit from on-device DL, given that these devices are integrated with various sensors and produce large amounts of data. This article reviews state-of-the-art studies on on-device DL for mobile and wearable devices, particularly from the sensor data analytics perspective. We first discuss the general optimization techniques of DL algorithms to meet the resource limitations of the devices. Then, we elaborate on model update and personalization techniques and review the studies by classifying them according to several aspects, including application areas, sensors, types of devices, utilized DL algorithms, mode of implementation, methods for optimizing DL algorithms for the target devices, training method, implementation toolkit/platform, performance metrics, and resource consumption analysis. Finally, we discuss the open issues and future research directions about on-device DL for mobile and wearable sensing applications.

DOI
TL;DR: In this article , a modified PROfile energy (Pro-energy) prediction technique is proposed to control unnecessary errors in solar-based harvesting systems related to the sensing devices, which estimates the most similar profile-based energy observation in previous time slots.
Abstract: Solar energy harvesting (EH) is one of the best promising approaches toward perpetual network operation, and it is implemented in various regions of interest (RoIs). However, saving external energy is the essential prime factor in any embedded sensor with finite storage capacity. Generally, the energy conversion rate of the solar system is too fast due to various environmental conditions. Besides, ambient resource energy is noncontrollable, and rechargeable battery only operates in outdoor ecological systems. Frequent environmental fluctuation in their prediction is imperative for initial energy control. Considering the challenges mentioned above, in this article, we propose a modified PROfile energy (Pro-energy) prediction technique to control unnecessary errors in solar-based harvesting systems related to the sensing devices, which estimates the most similar profile-based energy observation in previous time slots. Our proposed method uses prior energy measurements to show future energy status in the respective time slots. Experimental observations on various performance matrices validate that the modified Pro-energy prediction technique exhibits more promising and superior performance than existing EMWA, weather-conditioned moving average (WCMA), and Pro-energy methods.

DOI
TL;DR: In this paper , the authors highlight the current state of thin-film magnetoelectric (ME) sensor development based on a magnetocardiography (MCG) pilot study involving a healthy volunteer in a magnetically shielded chamber.
Abstract: In principle, electrode-based bioelectrical signal acquisition can be complemented by biomagnetic sensing and therefore requires a more detailed assessment, especially because of the availability of novel noncryogenic sensor technologies. The current development of thin-film magnetoelectric (ME) sensors ensures that ME technology is becoming a prospective candidate for biomagnetometry. The main obstacle for large-scale usage is the lack of extremely low noise floors at the final sensor system output. This article highlights the current state of ME sensor development based on a magnetocardiography (MCG) pilot study involving a healthy volunteer in a magnetically shielded chamber. For assessment, an ME prototype (converse ME thin-film sensors) will be applied for the first time. This sensor type ensures a noise amplitude spectral density below 20 pT / $\sqrt {\text {Hz}}$ at 10 Hz by using a sophisticated magnetic layer system. The main aim of this pilot study is to evaluate the applicability of this promising sensor for the detection of a human heart signal and to evaluate the sensor output with competitive optical magnetometry technology. A magnetic equivalent of a human R wave could be successfully detected within a 1-min measurement period with the sensor presented here. Finally, the article will provide an outlook on future ME perspectives and challenges, especially for cardiovascular applications.

Peer ReviewDOI
TL;DR: In this article , a survey of 3D bounding box encoding techniques and evaluation metrics for object detection in autonomous driving has been presented, where the image-based methods are categorized based on the technique used to estimate an image's depth information.
Abstract: An accurate and robust perception system is key to understanding the driving environment of autonomous driving and robots. Autonomous driving needs 3-D information about objects, including the object’s location and pose, to understand the driving environment clearly. A camera sensor is widely used in autonomous driving because of its richness in color and texture, and low price. The major problem with the camera is the lack of 3-D information, which is necessary to understand the 3-D driving environment. In addition, the object’s scale change and occlusion make 3-D object detection more challenging. Many deep learning-based methods, such as depth estimation, have been developed to solve the lack of 3-D information. This survey presents the image 3-D object detection 3-D bounding box encoding techniques and evaluation metrics. The image-based methods are categorized based on the technique used to estimate an image’s depth information, and insights are added to each method. Then, state-of-the-art (SOTA) monocular and stereo camera-based methods are summarized. We also compare the performance of the selected 3-D object detection models and present challenges and future directions in 3-D object detection.

DOI
TL;DR: A new edge-centric healthcare framework for remote health monitoring and disease prediction using Wearable Sensors and advanced Machine Learning (ML) model, namely Bag-of-Neural Network (BoNN), respectively is developed.
Abstract: Considering the increasing growth of communicable diseases worldwide such as COVID-19, it is recommended to stay at home for patients with fewer chronic health problems. In recent times, the high chance of COVID-19 spread and the lack of an excellent remote monitoring system make the situation challenging for hospital administrators. Inspired by these challenges, in this paper, we develop a new edge-centric healthcare framework for remote health monitoring and disease prediction using Wearable Sensors (WSs) and advanced Machine Learning (ML) model, namely Bag-of-Neural Network (BoNN), respectively. The epidemic model collects the health symptoms of the patient using various a set of WSs and preprocesses the data in distributed edge devices for preparing a useful dataset. Finally, the proposed BoNN model is applied over the refined dataset for detecting COVID-19 disease at centralized cloud servers using a set of random neural networks. To demonstrate the efficiency of the proposed BoNN model over the standard ML models, the system is fine-tuned and trained over a synthetic COVID-19 dataset before being evaluated on a benchmark Brazil COVID-19 dataset using various performance metrics. The experimental results demonstrate that the proposed BoNN model achieves 99.8% accuracy while analyzing the Brazil dataset.

DOI
TL;DR: Wang et al. as discussed by the authors designed a wearable piezoelectric ring based on PEG material, which can be easily integrated into the bolt connection as a washer to verify the feasibility of wearable PEG ring.
Abstract: As a safe and reliable connection, bolted connection is widely used in various structural systems. Monitoring the bolted connection is beneficial to ensure the safety of the whole structure. In this study, a wearable piezoelectric ring based on piezoelectric material is designed and it can be easily integrated into the bolt connection as a washer. To verify the feasibility of wearable piezoelectric ring, single-bolt looseness experiment based on wearable piezoelectric ring was carried out. Firstly, the wearable piezoelectric ring was installed on the bolted joint, acting as a piezoelectric sensor, and multiple piezoelectric actuators were installed in different location of the plate surface. Then, different torque level was applied to the bolt and the stress wave signals were obtained by piezoelectric active sensing technique. Finally, the recursive analysis method was introduced to extract nonlinear recursive features of the stress wave signals. The experimental results showed that the change of the bolt looseness could be qualitatively characterized by the phase space trajectory and the recurrence plots. Moreover, the recursive entropy could quantitatively characterize the bolt looseness, showing a bright prospect in monitoring the bolt looseness using the wearable piezoelectric ring.

DOI
TL;DR: In this article , the steering vector (SV) estimation for robust adaptive beamforming (RAB) is introduced via steering vector estimation, and a vertical error vector is constructed based on the property of subspace in the proposed method, and the SV error neighborhood table is built in advance to lower the computational complexity.
Abstract: The performance of the sample matrix inverse (SMI) beamformer degrades greatly when the signal-to-noise ratio (SNR) increases because the signal of interest (SOI) is mistaken as interferences and suppressed. To avoid this situation, the interference-plus-noise covariance matrix (INCM) is introduced via steering vector (SV) estimation for robust adaptive beamforming (RAB). To avoid the convex optimization for the SV estimation, a vertical error vector is constructed based on the property of subspace in the proposed method, and the SV error neighborhood table is built in advance to lower the computational complexity. Through the Capon spectrum search, the initial directions of the SOI and interference signals are estimated, and more accurate SVs are confirmed through neighborhood optimization in the table. Next, the interference covariance matrix (ICM) is generated by the estimated SVs and the noise covariance matrix (NCM) is obtained by the least-square (LS) solution based on the corrected SVs. Finally, INCM is reconstructed and the weight vector is computed for RAB. The main advantage of the proposed method is robust against unknown arbitrary-type mismatches. Simulation results demonstrate the effectiveness and robustness of the proposed method.

DOI
TL;DR: In this paper , a high-precision fusion strategy for a hierarchical WSN is proposed to improve the performance of temperature monitoring in aquaculture ponds, which not only reduces external interference but also improves the accuracy of global optimal temperature state estimation while ensuring the stability and accuracy of data fusion.
Abstract: In aquaculture ponds, wireless sensor networks (WSNs) with uneven temperature distribution and low collection efficiency may lead to poor monitoring effects. To improve the performance of temperature monitoring, a high-precision fusion strategy for a hierarchical WSN is proposed. In the bottom layer, the temperature data collected by the sensors are preprocessed by an improved unscented Kalman filter. In the middle layer, each cluster head sensor, as a local fusion center, is used to fuse the data collected from the sensors by a sequential analysis and fast inverse covariance intersection (ICI) algorithm. In the top layer, a global fusion center is utilized to fuse the temperature data from the middle layer to reflect the global temperature by an improved seagull algorithm to optimize the extreme learning machine (ELM) algorithm. Through calculation and simulation, the results show that the fusion strategy not only reduces external interference but also improves the accuracy of global optimal temperature state estimation while ensuring the stability and accuracy of data fusion.

DOI
TL;DR: In this paper , the authors evaluated the use of a non-destructive technology, equipment including a mechanical-portable sampler with a hardware device and sensors for real-time monitoring of temperature, relative humidity (RH), and intergranular carbon dioxide (CO2) to predict the quality of soybean in the function of different moisture contents (11, 14, and 18% w.b.).
Abstract: Grain moisture content and shipping time can interfere with postharvest logistics on soybean quality. Thus, the study aimed to evaluate the use of a nondestructive technology, equipment including a mechanical-portable sampler with a hardware device and sensors for real-time monitoring of temperature, relative humidity (RH), and intergranular carbon dioxide (CO2) to predict the quality of soybean in the function of different moisture contents (11%, 14%, and 18% w.b.), sampling positions in the grain mass profile, and shipping time (0, 60, 480, and 1440 min). The monitoring of indirect quality measurement variables associated with the application of machine-learning (ML) models satisfactorily predicted the physical quality of the grain mass, over the shipping time, for the different conditions tested. The moisture content associated with time was the factor with the greatest influence on the quality of transported grains. The shipping time is the determining factor for controlling the quality of grains. Lots of soybeans harvested from crops with moisture content between 14% and 18% must not exceed 120 min of shipping time to maintain quality. It is recommended that the shipping time of grains shipped from storage units to processing industries, with moisture contents between 11% and 14%, should not exceed 840 min. The M5P and reduced error pruning tree (REPTree) algorithms were the ones that best performed the prediction of grain quality. The monitoring system and grain quality prediction has application in grain-producing farms, grain storage, the grain-processing industry, and companies providing services in grain transport. The technology contributes to grain loss reduction and conservation in the context of logistics, sustainability, and food security.

DOI
TL;DR: In this article , a gas sensor based on poly(3hexylthiophene-2,5-diyl) (P3HT)/graphene quantum dot (GQD) nanocomposite as a sensing surface was demonstrated.
Abstract: This article demonstrates the highly selective and responsive room temperature (RT = 25 °C) operated hydrogen sulfide ( $\text{H}_{{2}}\text{S}$ ) gas sensor based on poly(3-hexylthiophene-2,5-diyl) (P3HT)/graphene quantum dot (GQD) nanocomposite as a sensing surface. The GQD has an average size of ~2 nm that is randomly distributed over the P3HT film and enhances the charge transfer mechanism and the surface area/volume ( ${S}/{V}$ ) ratio of the sensing surface, which incorporates quick and highly responsive $\text{H}_{{2}}\text{S}$ sensing. The sensing film has been developed on a SiO2-coated $\text{p}^{++}$ Si substrate by solution-processed floating-film transfer (FTM) method, and the multiparameters of the fabricated sensor have been investigated with varying $\text{H}_{{2}}\text{S}$ gas concentrations in the range of 0–25 ppm. To investigate the effect of the GQD in the polymer matrix, the sensing performance of the pristine P3HT-based organic thin-film transistor (OTFT) has been compared to P3HT/GQD nanocomposite-based OTFT. The P3HT/GQD-based OTFT has better sensing responses of ~91% at 25 ppm over pristine P3HT-based OTFT 30% at 25 ppm. The enhanced sensing performance of the nanocomposite matrix (P3HT/GQD) is attributed to an improved charge carrier transfer mechanism due to GQD over the pristine P3HT-based OTFT.

DOI
TL;DR: In this paper , a Geometric Appearance Awareness (GAA) module is proposed to obtain the geometry-guided appearance feature, which can be used to estimate reliable orientation, and a Sample-aware Feature Fusion (SFF) head is designed to deal with the uniqueness of different samples for learning 3D dimension.
Abstract: The object detection task in autonomous driving scenario is usually completed by a complex visual sensor system, such as the LiDAR sensor, the stereo sensor, and the monocular sensor. Recent progress in autonomous driving leverages a monocular sensor to achieve a highly efficient 3D object detection task with geometric constraints. These detectors improve with the explicit geometry projection, which can build the bridge between the 2D image plane and the 3D world space. However, they tend to focus on optimizing depth estimation and ignore the equally important 3D properties of orientation and 3D dimension. In this work, we propose a Geometric Appearance Awareness (GAA) module to improve the estimation of orientation. Specifically, a GAA module is proposed to obtain the geometry-guided appearance feature, which can be used to estimate reliable orientation. Furthermore, we design a Sample-aware Feature Fusion (SFF) head in the 3D dimension regression branch. This head dynamically deals with the uniqueness of different samples for learning 3D dimension. We evaluate our method on the KITTI dataset, and achieve significant improvements in the 3D object detection task. Compared with the latest method, our approach obtains a 1.08 improvement for the metric of ${\mathrm {AP}}_{{3}{D}}$ on the hard level and 1.53/3.41/5.79 improvements for the metric of APBEV under the easy/moderate/hard settings, respectively.

DOI
TL;DR: In this article , a YOLOv5-based satellite components recognition model (YSCRM) was proposed to handle the complex multimodal recognition problem of the components, improving the model's feature selection and representation capability.
Abstract: Recognizing typical components of the satellite is a challenging task for on-orbit services. This article proposes a YOLOv5-based satellite components recognition model (YSCRM) on a computationally limited platform. In particular, feature fusion layers and selective kernel networks (SK-Nets) are introduced to handle the complex multimodal recognition problem of the components, improving the model’s feature selection and representation capability and significantly increasing the recognition accuracy. The transformer encoder modules are used at the end of the Yolov5 Neck to explore the prediction potential with the self-attention mechanism. The channel sparseness training method is implemented to reduce the model size to deploy the model on an embedded platform. Moreover, for the purpose of enlarging the training datasets and their diversity, a data generation approach based on the synthetic images generated by 3ds Max and a data augmentation method based on cycle-consistent adversarial network (Cycle-GAN) are presented in this research. The proposed hybrid dataset is used for training and testing, and extensive qualitative and quantitative experiments are performed. The results demonstrate that the YSCRM has significant recognition performance, and the five typical components, solar panel, body, tripod, nozzle, and docking ring, can be recognized with high accuracy, which indicates that the proposed model can be used for real-world scenarios.