Showing papers in "IEEE Sensors Journal in 2019"
TL;DR: The aim is to comprehensively investigate the channel specific nature of EEG signals and to provide an effective method based on flexible analytic wavelet transform (FAWT) for recognition of emotion and to show better performance for human emotion classification.
Abstract: Human emotion is a physical or psychological process which is triggered either consciously or unconsciously due to perception of any object or situation. The electroencephalogram (EEG) signals can be used to record ongoing neuronal activities in the brain to get the information about the human emotional state. These complicated neuronal activities in the brain cause non-stationary behavior of the EEG signals. Thus, emotion recognition using EEG signals is a challenging study and it requires advanced signal processing techniques to extract the hidden information of emotions from EEG signals. Due to poor generalizability of features from EEG signals across subjects, recognizing cross-subject emotion has been difficult. Thus, our aim is to comprehensively investigate the channel specific nature of EEG signals and to provide an effective method based on flexible analytic wavelet transform (FAWT) for recognition of emotion. FAWT decomposes the EEG signal into different sub-band signals. Furthermore, we applied information potential to extract the features from the decomposed sub-band signals of EEG signal. The extracted feature values were smoothed and fed to the random forest and support vector machine classifiers that classified the emotions. The proposed method is applied to two different publicly available databases which are SJTU emotion EEG dataset and database for emotion analysis using physiological signal. The proposed method has shown better performance for human emotion classification as compared to the existing method. Moreover, it yields channel specific subject classification of emotion EEG signals when exposed to the same stimuli.
187 citations
TL;DR: Results show that the proposed CNN method has better reconstruction results than LBP, Tikhonov, and Landweber, and the network has good generalization ability.
Abstract: Image reconstruction is a key problem for electrical resistance tomography (ERT). Because of the soft-field nature and the ill-posed problem in solving inverse problem, traditional image reconstruction methods cannot achieve high accuracy and the process is usually time consuming. Since deep learning is good at mapping complicated nonlinear function, a deep learning method based on convolutional neural network (CNN) is proposed for image reconstruction of ERT. To establish the database, 41122 samples were generated with numerical simulations. 10-fold cross validation was used to divide all samples into training set and validation set. The network structure was based on LeNet, and refined by applying dropout layer and moving average. After 346 training epochs, the image correlation coefficient (ICC) on validation set was 0.95. When white Gaussian noise with a signal-to-noise ratio of 30, 40, and 50 were added to validation set, the ICC was 0.79, 0.89, and 0.93, respectively, which proved the anti-noise capability of the network. The reconstruction results on samples which have more inclusions, different conductivity, and other shapes explained the network has good generalization ability. Furthermore, experimental data from a 16-electrode industrial ERT system was used to compare the accuracy of the proposed model with some typical reconstruction methods. Results show that the proposed CNN method has better reconstruction results than LBP, Tikhonov, and Landweber.
172 citations
TL;DR: In this paper, the authors used a miniature radar sensor to capture Doppler signatures of 14 different hand gestures and trained a deep convolutional neural network (DCNN) to classify these captured gestures.
Abstract: Low-cost consumer radar integrated circuits combined with recent advances in machine learning have opened up a range of new possibilities in smart sensing. In this paper, we use a miniature radar sensor to capture Doppler signatures of 14 different hand gestures and train a deep convolutional neural network (DCNN) to classify these captured gestures. We utilize two receiving antennas of a continuous-wave Doppler radar capable of producing the in-phase and quadrature components of the beat signals. We map these two beat signals into three input channels of a DCNN as two spectrograms and an angle of arrival matrix. The classification results of the proposed architecture show a gesture classification accuracy exceeding 95% and a very low confusion between different gestures. This is almost 10% improvement over the single-channel Doppler methods reported in the literature.
157 citations
TL;DR: In this paper, a nearly perfect metamaterial absorber is proposed and analyzed for terahertz sensing applications, which is based on increasing the confinement of both electric and magnetic fields simultaneously at the resonance frequency.
Abstract: A novel design of nearly perfect metamaterial absorber is proposed and analyzed for terahertz sensing applications. The full vectorial finite element method is used to simulate and analyze the reported design. The suggested structure is based on increasing the confinement of both electric and magnetic fields simultaneously at the resonance frequency. Therefore, an absorptivity of 0.99 is achieved at 2.249 THz with a narrow resonant peak and a $Q$ -factor of 22.05. The resonance frequency is sensitive to the surrounding medium refractive index at fixed analyte thickness. Consequently, the reported metamaterial design can be used as a refractive index (RI) sensor with the high sensitivity of 300 GHz/RIU and the figure of merit (FoM) of 2.94 through an RI range from 1.0 to 1.39 at the analyte thickness of $1.0~ \mu \text{m}$ . Furthermore, the proposed sensor has a sensitivity of 23.7 GHz/ $\mu \text{m}$ for the detection of the sensing layer thickness variation at the fixed analyte RI of 1.35. It is worth noting that most of the biomedical samples have a refractive index range from 1.3 to 1.39. Therefore, the reported sensor can be used for biomedical applications with high sensitivity.
151 citations
TL;DR: In this article, the application of a Ru-doped InN (Ru-InN) monolayer as a novel gas adsorbent scavenging SF6 decomposed species based on a first-principles theory was investigated.
Abstract: SF6 insulation devices are important components in the power system, wherein the SF6 acts as the insulating gas protecting the operation state of devices effectively. However, the inevitable decomposition of SF6 under partial discharge in a long-running device would deteriorate the insulation property of SF6 largely. In this paper, we investigate the application of a Ru-doped InN (Ru-InN) monolayer as a novel gas adsorbent scavenging SF6 decomposed species based on a first-principles theory. Results indicate that the Ru-InN monolayer possesses quite strong adsorption behaviors upon three SF6 decomposed gases: SO2, SOF2, and SO2F2, wherein chemisorption can be identified. This allows exploration of the Ru-InN monolayer-based adsorbent for removing pollutant gases from SF6 insulation devices. Meanwhile, giving the obvious changes in conductivity of the Ru-InN monolayer caused by gas adsorption, the exploration of gas sensor using the Ru-InN monolayer would also be a means to evaluate the operation status of SF6 insulation devices. Our investigation indicates that the Ru-InN monolayer can be a good candidate for sensing or adsorbing to prevent paralysis of a power system caused by SF6 decomposition.
147 citations
TL;DR: In this paper, a differential microwave sensor, based on a pair of uncoupled microstrip lines each one loaded with a split ring resonator (SRR), is applied to the measurement of electrolyte concentration in deionized (DI) water.
Abstract: A differential microwave sensor, based on a pair of uncoupled microstrip lines each one loaded with a split ring resonator (SRR), is applied to the measurement of electrolyte concentration in deionized (DI) water. For that purpose, fluidic channels are added on top of the SRR gaps, the most sensitive parts of the structure. The operating principle is based on the measurement of the cross-mode insertion loss, highly sensitive to small asymmetries caused by differences between the reference liquid and the liquid under test (LUT). In this paper, the reference liquid is pure DI water (the solvent), whereas the solution, DI water with electrolyte content, is injected to the LUT channel. The proposed sensor is able to detect electrolyte concentrations as small as 0.25 g/L, with maximum sensitivity of 0.033 (g/L)–1. The sensor is validated by measuring the concentration of three types of electrolytes, i.e., NaCl, KCl, and CaCl2. Finally, the sensor is applied to monitor variations of total electrolyte concentration in urine samples.
143 citations
TL;DR: A discussion of the main aspects of RPL and the advantages and disadvantages of using it in different IoT applications, and a comparison of related RPL-based protocols in terms of energy efficiency, reliability, flexibility, robustness, and security.
Abstract: In the last few years, the Internet of Things (IoT) has proved to be an interesting and promising paradigm that aims to contribute to countless applications by connecting more physical “things” to the Internet. Although it emerged as a major enabler for many next-generation applications, it also introduced new challenges to already saturated networks. The IoT is already coming to life especially in healthcare and smart environment applications adding a large number of low-powered sensors and actuators to improve lifestyle and introduce new services to the community. The Internet Engineering Task Force (IETF) developed RPL as the routing protocol for low-power and lossy networks (LLNs) and standardized it in RFC6550 in 2012. RPL quickly gained interest, and many research papers were introduced to evaluate and improve its performance in different applications. In this paper, we present a discussion of the main aspects of RPL and the advantages and disadvantages of using it in different IoT applications. We also review the available research related to RPL in a systematic manner based on the enhancement area and the service type. In addition to that, we compare related RPL-based protocols in terms of energy efficiency, reliability, flexibility, robustness, and security. Finally, we present our conclusions and discuss the possible future directions of RPL and its applicability in the Internet of the future.
138 citations
IMEC1
TL;DR: A comprehensive review of state-of-the-art research on heart rate estimation from wrist-worn PPG signals and brief theoretical details about PPG sensing and other potential applications–biometric identification, disease diagnosis using wrist PPG are presented.
Abstract: Photoplethysmography (PPG) is a low-cost, non-invasive, and optical technique used to detect blood volume changes in the microvascular tissue bed, measured from the skin surface. It has traditionally been used in commercial medical devices for oxygen saturation, blood pressure monitoring, and cardiac activity for assessing peripheral vascular disease and autonomic function. There has been a growing interest to incorporate PPG sensors in daily life, capable of use in ambulatory settings. However, inferring cardiac information (e.g. heart rate) from PPG traces in such situations is extremely challenging, because of interferences caused by motion. Following the IEEE Signal Processing Cup in 2015, numerous methods have been proposed for estimating particularly the average heart rate using wrist-worn PPG during physical activity. Details on PPG technology, sensor development, and applications have been well documented in the literature. Hence, in this paper, we have presented a comprehensive review of state-of-the-art research on heart rate estimation from wrist-worn PPG signals. Our review also encompasses brief theoretical details about PPG sensing and other potential applications–biometric identification, disease diagnosis using wrist PPG. This paper will set a platform for future research on pervasive monitoring using wrist PPG.
138 citations
TL;DR: This paper introduces a methodology based on deep convolutional neural networks (DCNN) for motor imagery (MI) tasks recognition in the brain-computer interface (BCI) system and obtained results show that the CWT approach yields better results than the STFT approach.
Abstract: This paper introduces a methodology based on deep convolutional neural networks (DCNN) for motor imagery (MI) tasks recognition in the brain-computer interface (BCI) system. More specifically, the DCNN is used for classification of the right hand and right foot MI-tasks based electroencephalogram (EEG) signals. The proposed method first transforms the input EEG signals into images by applying the time-frequency (T-F) approaches. The used T-F approaches are short-time-Fourier-transform (STFT) and continuous-wavelet-transform (CWT). After T-F transformation the images of MI-tasks EEG signals are applied to the DCNN stage. The pre-trained DCNN model, AlexNet is explored for classification. The efficiency of the proposed method is evaluated on IVa dataset of BCI competition-III. The evaluation metrics such as accuracy, sensitivity, specificity, F1-score, and kappa value are used for measuring the proposed method results quantitatively. The obtained results show that the CWT approach yields better results than the STFT approach. In addition, the proposed method obtained 99.35% accuracy score is the best one among the existing methods accuracy scores.
131 citations
TL;DR: In this article, a flexible sensor based on an FBG encapsulated into Dragon skin 20 silicone rubber was used for developing a wearable system for respiratory and cardiac rates' monitoring, which was evaluated on healthy volunteers to evaluate its suitability for monitoring respiratory frequency and heart rate.
Abstract: There is a growing demand for strain sensors that can be embedded into wearables for several potential applications. Among others, respiratory and cardiac rates’ monitoring from chest wall displacements have driven the development of strain sensors based on fiber Bragg gratings (FBGs) coupled with polymers. In this paper, we addressed the fabrication of a flexible sensor based on an FBG encapsulated into Dragon skin 20 silicone rubber. The sensor is intended to be used for developing a wearable system for respiratory and cardiac rates’ monitoring. The sensor’s response to strain, temperature changes, and relative humidity variations has been experimentally assessed. By considering the repetitive strains induced on the chest wall by the phenomena of interest, the hysteresis response has also been analyzed. Then, an elastic band was equipped with the flexible sensor. The feasibility of this wearable system has been preliminarily assessed on healthy volunteers to evaluate its suitability for monitoring respiratory frequency ( $f_{\mathbf {R}}$ ) and heart rate (HR). The interesting results suggest that the proposed system is easy to be worn, non-invasive, stretchy, and seems to be suitable to well-match the chest wall displacements for monitoring $f_{\mathbf {R}}$ and HR. Such findings call for further investigation targeted to evaluate the accuracy of the FBG-based wearable system in monitoring respiratory and cardiac activities and the system usability in both clinical and sports sciences.
128 citations
TL;DR: In this paper, the shape of a flexible instrument is reconstructed using Frenet-Serret equations in conjunction with the calculated curvature and torsion of the instrument, and the results show that shape sensing for flexible medical instruments is feasible with FBG sensors in multi-core fibers.
Abstract: This paper presents a technique to reconstruct the shape of a flexible instrument in three-dimensional Euclidean space based on data from fiber Bragg gratings (FBGs) that are inscribed in multi-core fibers. Its main contributions are the application of several multi-core fibers with FBGs as shape sensor for medical instruments and a thorough presentation of the reconstruction technique. The data from the FBG sensors are first converted to strain measurements, which is then used to calculate the curvature and torsion of the fibers. The shape of the instrument is reconstructed using Frenet–Serret equations in conjunction with the calculated curvature and torsion of the instrument. The reconstruction technique is validated with a catheter sensorized with four multi-core fibers that have FBG sensors. The catheter is placed in eight different configurations and the reconstruction is compared to the ground truth. The maximum reconstruction error among all the configurations is found to be 1.05 mm. The results show that shape sensing for flexible medical instruments is feasible with FBG sensors in multi-core fibers.
TL;DR: This review paper has discussed the existing state-of-the-art practices of improved intelligent features, controlling parameters and Internet of things (IoT) infrastructure required for smart building, focusing on sensing, controlling the IoT infrastructure which enables the cloud clients to use a virtual sensing infrastructure using communication protocols.
Abstract: In this review paper, we have discussed the existing state-of-the-art practices of improved intelligent features, controlling parameters and Internet of things (IoT) infrastructure required for smart building. The main focus is on sensing, controlling the IoT infrastructure which enables the cloud clients to use a virtual sensing infrastructure using communication protocols. The following are some of the intelligent features that usually make building smart such as privacy and security, network architecture, health services, sensors for sensing, safety, and overall management in smart buildings. As we know, the Internet of Things (IoT) describes the ability to connect and control the appliances through the network in smart buildings. The development of sensing technology, control techniques, and IoT infrastructure give rise to a smart building more efficient. Therefore, the new and problematic innovation of smart buildings in the context of IoT is to a great extent and scattered. The conducted review organized in a scientific manner for future research direction which presents the existing challenges, and drawbacks.
TL;DR: This paper proposes DQ-RSS, a deep-reinforcement-learning-based relay selection scheme in WSNs and uses DQN to process high-dimensional state spaces and accelerate the learning rate, and compares the network performance on the basis of three aspects: outage probability, system capacity, and energy consumption.
Abstract: Cooperative communication technology has become a research hotspot in wireless sensor networks (WSNs) in recent years, and will become one of the key technologies for improving spectrum utilization in wireless communication systems in the future. It leverages cooperation among multiple relay nodes in the wireless network to realize path transmission sharing, thereby improving the system throughput. In this paper, we model the process of cooperative communications with relay selection in WSNs as a Markov decision process and propose DQ-RSS, a deep-reinforcement-learning-based relay selection scheme, in WSNs. In DQ-RSS, a deep-Q-network (DQN) is trained according to the outage probability and mutual information, and the optimal relay is selected from a plurality of relay nodes without the need for a network model or prior data. More specifically, we use DQN to process high-dimensional state spaces and accelerate the learning rate. We compare DQ-RSS with the Q-learning-based relay selection scheme and evaluate the network performance on the basis of three aspects: outage probability, system capacity, and energy consumption. Simulation results indicate that DQ-RSS can achieve better performance on these elements and save the convergence time compared with existing schemes.
TL;DR: In this article, a novel partial type-b crystalline core with more compact cladding in hexagonal packing photonic crystal fiber (CC-PCF)-based optical sensor has been proposed for sensing different blood components.
Abstract: In this paper, a novel partial type-b crystalline core with more compact cladding in hexagonal packing photonic crystal fiber (CC-PCF)-based optical sensor has been proposed for sensing different blood components. This fiber has investigated in terahertz (THz) region from 1.5 to 3.50 THz, intending to superior relative sensitivity with low confinement loss (CL). Circular air holes have been employed in the formation of the partial type-b crystalline core in a symmetric manner. A significant relative sensitivity response of 80.93%, 80.56%, 80.13%, 79.91%, and 79.39% are achieved for the targeted analytes such as RBCs, hemoglobin, WBCs, plasma, and water at frequency ${f} = 1.5$ THz. In X-polarization mode, a negligible CL of $1.23\times 10^{-11}$ dB/m, $8.63\times 10^{-12}$ dB/m, $4.93\times 10^{-12}$ dB/m, $2.93\times 10^{-12}$ dB/m, and $1.13\times 10^{-12}$ dB/m are also gained, respectively, for same analytes and at same THz frequency. Moreover, effective area ( A eff), V-Parameter ( $V_{\mathrm{ eff}}$ ), dispersion ( $\beta _{2}$ ), spot size ( $W_{\mathrm{ eff}}$ ), and beam divergence ( $\theta $ ) have been determined over the investigated region. The improved outcomes are anticipated that the proposed CC-PCF sensor will be opened a new epoch in biomedical sensing purposes.
TL;DR: A comprehensive classification of different energy sources that can be capitalized to power wearable devices is presented, which deals with the key challenges that must be considered in the development of autonomous wearable devices for telemedicine applications.
Abstract: In recent years, wearable devices have attracted attention because of their ability to enhance the quality of life. This disruptive technology has helped healthcare professionals with intervening early in chronic diseases, especially amongst independently living patients, and has facilitated real-time monitoring of patients’ vital signs remotely. One of the major bottlenecks that hamper the adoption of wearable device is the continuous power supply. Most wearable devices solely depend on battery supply. When the energy stored in the battery is depleted, the operation of wearable devices is affected. To overcome this limitation, efficient energy harvesters for wearable devices are crucial. The paper primarily aims to present a comprehensive classification of different energy sources that can be capitalized to power wearable devices. In addition, this research paper deals with the key challenges that must be considered in the development of autonomous wearable devices for telemedicine applications with a proposed system design for wearable device that uses energy harvesting technology.
TL;DR: A modified long short-term memory (LSTM) model for continuous sequences of gestures or continuous SLR that recognizes a sequence of connected gestures based on splitting of continuous signs into sub-units and modeling them with neural networks is proposed.
Abstract: Sign language facilitates communication between hearing impaired peoples and the rest of the society. A number of sign language recognition (SLR) systems have been developed by researchers, but they are limited to isolated sign gestures only. In this paper, we propose a modified long short-term memory (LSTM) model for continuous sequences of gestures or continuous SLR that recognizes a sequence of connected gestures. It is based on splitting of continuous signs into sub-units and modeling them with neural networks. Thus, the consideration of a different combination of sub-units is not required during training. The proposed system has been tested with 942 signed sentences of Indian Sign Language (ISL). These sign sentences are recognized using 35 different sign words. The average accuracy of 72.3% and 89.5% has been recorded on signed sentences and isolated sign words, respectively.
TL;DR: This review discusses the recent innovative technologies developed for the visually impaired to aid them in walking with their merits and demerits and draws a schema for upcoming development in the field of sensors, computer vision, and smartphone-based walking assistants.
Abstract: The development of walking assistants for visually impaired people has become a prominent research area due to the rapid growth of these individuals in recent decades. Although numerous frameworks have been developed to aid visually impaired people, a considerable portion of these is limited in their scopes. In this review, we exhibit a similar review of walking assistants for visually impaired people to demonstrate the advancement of such technologies. This review discusses the recent innovative technologies developed for the visually impaired to aid them in walking with their merits and demerits. With the help of this review, a schema is drawn for upcoming development in the field of sensors, computer vision, and smartphone-based walking assistants. This review aims to present the majority of the issues of such frameworks to serve as a basis for different researchers to develop walking assistants that ensure movability and safety of visually impaired people.
TL;DR: A novel attention-based human activity recognition method to process the weakly labeled activity data that can greatly facilitate the process of sensor data annotation and makes data collection easier.
Abstract: Traditional methods of human activity recognition usually require a large amount of strictly labeled data for training classifiers. However, it is hard for one to keep a fixed activity when collecting desired activity data by wearable sensors, and the weakly labeled data inevitably occurs in the process of data collection. For now, human activity recognition methods have seldom been researched according to weakly labeled data, which deserves deep investigation. In this paper, we proposed a novel attention-based human activity recognition method to process the weakly labeled activity data. The traditional convolutional neural network (CNN)-based human activity recognition is modified by attention mechanism, which computes the compatibility between the global features extracted at the final fully connected layers and the local features extracted at a given convolutional layer. The attention-based CNN architecture can amplify the salient activity information and suppress the irrelevant and potentially confusing information by weighing up their compatibility. Our methods are compared with two state-of-the-art methods, CNN and DeepConvLSTM. The experimental results show that our model is comparably well on the traditional UCI HAR dataset and outperforms them on the weakly labeled dataset in accuracy. Our method can greatly facilitate the process of sensor data annotation and makes data collection easier.
TL;DR: A novel algorithm which combined the merits of the clustering strategy and the compressive sensing-based (CS-based) scheme was proposed in this paper and the effect of EECSR on improving energy efficiency and extending the lifespan of wireless sensor networks was verified.
Abstract: A novel algorithm which combined the merits of the clustering strategy and the compressive sensing-based (CS-based) scheme was proposed in this paper. The lemmas for the relationship between any two adjacent layers, the optimal size of clusters, the optimal distribution of the cluster head (CH), and the corresponding proofs were presented first. In addition, to alleviate the “hot spot problem” and reduce the energy consumption resulted from the rotation of the role of CHs, a third role of backup CH (BCH) as well as the corresponding mechanism to rotate the roles between the CH and BCH were proposed. Subsequently, the energy-efficient compressive sensing-based clustering routing (EECSR) protocol was presented in detail. Finally, extensive simulation experiments were conducted to evaluate its energy performance. Comparisons with the existing clustering algorithms and the CS-based algorithm verified the effect of EECSR on improving energy efficiency and extending the lifespan of wireless sensor networks.
TL;DR: A new method called N2-3DDV-Hop (non-dominated sorting genetic algorithm II with 3D distance-vector hop) that builds on the 3D-DV- Hop algorithm by adding multi-objective model and NSGA-II is proposed.
Abstract: Location information is generally considered to be indispensable information in wireless sensor networks, but existing algorithms have notable limitations in their positioning accuracy in 3-dimensional (3D) spaces To improve the positioning accuracy of nodes in a 3D scenario, this paper proposes a new method called N2-3DDV-Hop (non-dominated sorting genetic algorithm II with 3D distance-vector hop) that builds on the 3D-DV-Hop algorithm by adding multi-objective model and NSGA-II In this paper, it is analyzed that the limitations of the traditional single-objective positioning model and showed the relationship among the average hop distance, the number of sensor nodes, and the theoretical average distance In addition then, the multi-objective positioning model incorporating the NSGA-II algorithm is presented To evaluate its performance relative to other current methods, we compared our method by testing all of the methods with three different complex network topologies Simulation results demonstrate that the N2-3DDV-Hop offered the best overall positioning performance compared with other algorithms and better robustness than the 3DDV-Hop algorithm
TL;DR: A deep-learning-based fault classification method in small current grounding power distribution systems is presented and has the characteristics of high accuracy and adaptability in fault classification of power Distribution systems.
Abstract: Fault classification is important for the fault cause analysis and faster power supply restoration. A deep-learning-based fault classification method in small current grounding power distribution systems is presented in this paper. The current and voltage signals are sampled at a substation when a fault occurred. The time-frequency energy matrix is constructed via applying Hilbert–Huang transform (HHT) band-pass filter to those sampled fault signals. Regarding the time-frequency energy matrix as the pixel matrix of digital image, a method for image similarity recognition based on convolution neural network (CNN) is used for fault classification. The presented method can extract the features of fault signals and accurately classify ten types of short-circuit faults, simultaneously. Two simulation models are established in the PSCAD/EMTDC and physical system environment, respectively. The performance of the presented method is studied in the MATLAB environment. Various kinds of fault conditions and factors including asynchronous sampling, different network structures, distribution generators access, and so on are considered to verify the adaptability of the presented method. The results of investigation show that the presented method has the characteristics of high accuracy and adaptability in fault classification of power distribution systems.
TL;DR: This paper reviews recent onboard condition monitoring sensors, systems, methods and techniques, aiming to define the present state of the art and its potential application for freight wagons without onboard electric power.
Abstract: Given the constant demand for heavier, longer, faster, and more efficient rail freight vehicles, onboard fault detection systems appear as a good approach for enhanced railway asset exploitation. Real-time condition monitoring reduces inefficient preventive and reactive maintenance actions, decreases waste from replacing parts that still have a useful life, and improves availability and safety by real-time rolling stock diagnosis. There have been considerable advances in wayside monitoring applications, but these cannot achieve real-time continuous monitoring. With the price reduction and miniaturization trends of electronic devices, the cost of deploying wireless sensor networks onboard freight trains continues to become more feasible and accessible. On the other hand, the lack of onboard electric power availability on freight wagons appears as the major limitation for the implementation of these technologies. This paper reviews recent onboard condition monitoring sensors, systems, methods and techniques, aiming to define the present state of the art and its potential application for freight wagons without onboard electric power.
TL;DR: In this article, the authors compared the sensitivities of TFETs and uniform gate Heterojunction (HJ) TFET as label-free biosensors based on dielectric modulation.
Abstract: This paper compares circular gate (CG) tunnel field effect transistor (TFET) and uniform gate Heterojunction (HJ) TFET as label-free biosensors based on dielectric modulation. Neutral and charged biomolecules with different values of dielectric constant are considered. Sensitivities of partially filled nanogaps arising out of steric hindrance in both the biosensors for concave, convex, increasing and decreasing step profiles of biomolecules are compared. The effect of probe position on sensitivities of the two biosensors is reported for various cases. A status map is presented, plotting the sensitivities of some of the most significant works in applications of FET as label-free biosensors along with sensitivities of the proposed devices. CG TFET exhibits higher sensitivity than HJ TFET due to its non-uniform gate architecture. The sensitivities of the TFETs are highly dependent on the position of biomolecules (steric hindrance and probe position) with respect to the tunnel junction. A maximum sensitivity of $1.31\times 10^{8}$ ( $3.382\times 10^{6}$ ) is achieved for fully filled nanogap in CG TFET (HJ TFET) for dielectric constant 12.
TL;DR: A wearable sensor-based continuous fall monitoring system is proposed in this paper, which is capable of detecting a fall and identifying the falling pattern and the activity associated with the fall incident.
Abstract: Falling is a severe hazard among older adults. Fall treatment is considered to be one of the most costly treatments, which usually extends to a long time. One bad fall can cause severe injuries that may lead to permanent disability or even death. Therefore, an efficient and cost-effective fall monitoring system is exceptionally indispensable. With the advancement in technology, wearable sensors and systems provide a lucrative way to continuously monitor the elderly people for detecting any fall incident that may occur. Most of these wearable fall monitoring systems focus only on detecting a fall incident. However, to avoid the risk of any future fall, it is essential to be aware of the cause of a fall incident also. Therefore, to address this challenge, a wearable sensor-based continuous fall monitoring system is proposed in this paper, which is capable of detecting a fall and identifying the falling pattern and the activity associated with the fall incident. The performance of the proposed scheme is investigated with a series of experiments using three machine learning algorithms, namely, $k$ -nearest neighbors (KNNs), support vector machine, and random forest (RF). The proposed methodology achieved the highest accuracy for fall detection, i.e., 99.80%, using KNNs classifier, whereas the highest accuracy achieved in recognizing different falling activities is 96.82% using RF classifier.
TL;DR: A novel approach, namely physics-based convolutional neural network (PCNN), for fault diagnosis of rolling element bearings is proposed and the performance of PCNN in machinery fault diagnosis is compared with that of traditional machine learning- and deep learning-based approaches reported in the literature.
Abstract: During the past few years, deep learning has been recognized as a useful tool in condition monitoring and fault detection of rolling element bearings. Although existing deep learning approaches are able to intelligently detect and classify the faults in bearings, they still face one or both of the following challenges: 1) most of these approaches rely exclusively on data and do not incorporate physical knowledge into the learning and prediction processes and 2) the approaches often focus on the fault diagnosis of a single bearing in a rotating machine, while in reality, a rotating machine may contain multiple bearings. To address these challenges, this paper proposes a novel approach, namely physics-based convolutional neural network (PCNN), for fault diagnosis of rolling element bearings. In PCNN, an exclusively data-driven deep learning approach, called CNN, is carefully modified to incorporate useful information from physical knowledge about bearings and their fault characteristics. To this end, the proposed approach 1) utilizes spectral kurtosis and envelope analysis to extract sidebands from raw sensor signals and minimize non-transient components of the signals and 2) feeds the information about the fault characteristics into the CNN model. With the capability to process signals from multiple sensors, the proposed PCNN approach is capable of concurrently monitoring multiple bearings and detecting faults in these bearings. The performance of PCNN in machinery fault diagnosis is compared with that of traditional machine learning- and deep learning-based approaches reported in the literature.
TL;DR: CellinDeep is a deep learning-based localization system that achieves fine-grained accuracy using the ubiquitous cellular technology and leverages a deep network to model the inherent dependency between the signals of the different cell towers in the area of interest.
Abstract: The demand for a ubiquitous and accurate indoor localization service is continuously growing. Current solutions for indoor localization usually depend on using the embedded sensors on high-end phones or provide coarse-grained accuracy. We present CellinDeep : a deep learning-based localization system that achieves fine-grained accuracy using the ubiquitous cellular technology. Specifically, CellinDeep captures the non-linear relation between the cellular signal heard by a mobile phone and its location. To do that, it leverages a deep network to model the inherent dependency between the signals of the different cell towers in the area of interest, allowing it achieve high localization accuracy. As part of the design of CellinDeep , we introduce modules to address a number of practical challenges such as handling the noise in the input wireless signal, reducing the amount of data required for the deep learning model, as avoiding over-training. Implementation of CellinDeep on different Android phones shows that it can achieve a median localization accuracy of 0.78m. This accuracy is better than the state-of-the-art indoor cellular-based systems by at least 350%. In addition, CellinDeep provides at least 93.45% savings in power compared to the WiFi-based techniques.
TL;DR: In this paper, a microwave microfluidic sensor based on improved split ring resonator (SRR) for detecting glucose concentration in aqueous glucose solutions is proposed, which incorporates inter-digital capacitor (IDC) in the gap of the resonator for enhanced electric field concentration over a larger surface area.
Abstract: A high-sensitive microwave microfluidic sensor based on improved split ring resonator (SRR) for detecting glucose concentration in aqueous glucose solutions is proposed. The novel SRR design of the proposed sensor incorporates inter-digital capacitor (IDC) in the gap of the resonator for enhanced electric field concentration over a larger surface area, which provides higher sensitivity for testing of dielectric liquids. In order to facilitate the measurement of lossy fluids using the proposed sensor, a microfluidic channel is appropriately positioned over the IDC region of the SRR, through which the glucose solutions are made to pass. The microfluidic channel, made of polydimethylsiloxane (PDMS) is biocompatible, economical, which is customized to preserve the sample from external contamination. Aqueous solutions with glucose concentrations ranging from 0 to 5000 mg/dl are characterized based on the shift in the resonant frequency and the normalized peak attenuation of the SRR sensor. The measured sensitivity of the proposed PDMS integrated novel SRR sensor for glucose testing is found to be 2.60E-02 MHz/mgdl−1, which is a fair improvement compared to earlier proposed sensors employing similar sensing methodologies. The applicability of the proposed sensor for quantitative analysis of aqueous glucose solutions is verified using both simulation and experimental procedures.
TL;DR: Electroencephalogram signals are used for the detection of drowsiness, with the proposed method being composed of three main building blocks, and it is shown that this method’s achievement was found to be better than the compared results.
Abstract: Early detection of driver drowsiness and the development of a functioning driver alertness system may support the prevention of numerous vehicular accidents worldwide. Wearable sensors and camera-based systems are generally employed in the driver drowsiness detection. Electroencephalogram (or EEG) is considered another effective option for the driver drowsiness detection. Various EEG-based drowsiness detection systems have been proposed to date. In this paper, EEG signals are also used for the detection of drowsiness, with the proposed method being composed of three main building blocks. Both raw EEG signals and their corresponding spectrograms are used in the proposed building blocks. In the first building block, while energy distribution and zero-crossing distribution features are calculated from the raw EEG signals, spectral entropy and instantaneous frequency features are extracted from the EEG spectrogram images. In the second building block, deep feature extraction is employed directly on the EEG spectrogram images using pre-trained AlexNet and VGGNet. In the third building block, the tunable Q-factor wavelet transform (TQWT) is used to decompose the EEG signals into related sub-bands. The spectrogram images of the obtained sub-bands and statistical features, such as mean and standard deviation of the sub-bands’ instantaneous frequencies, are then calculated. Each feature group from each building block is fed to a long-short term memory (LSTM) network for the purposes of classification. The obtained results from the LSTM networks are then fused with a majority voting layer. The MIT-BIH Polysomnographic database was used in the experimental works. The evaluation of the proposed method was carried out with ten-fold cross validation test and the average accuracy represented accordingly. The obtained average accuracy score was 94.31%. The obtained result was also compared with other results to be found in the literature. The comparison shows that the proposed method’s achievement was found to be better than the compared results.
TL;DR: In this paper, a simple, highly sensitive, and compact footprint biosensor for cancer detection based on metamaterial containing structure utilizing theoretical model is presented, which includes array of split ring resonators on a dielectric substrate.
Abstract: In the present paper, we aim to report a simple, highly sensitive, and compact footprint biosensor for cancer detection based on metamaterial containing structure utilizing theoretical model. This model includes of array of split ring resonators on a dielectric substrate. The proposed structure is simulated using three-dimensional finite-element method. To achieve the appropriate operation, the effects of the physical properties including dielectric material, and different cells on the performance of the proposed sensor are considered. For this purpose, three types of dielectrics, including silicon dioxide (SiO2), titanium dioxide (TiO2), and polymethyl methacrylate (PMMA) substrates have been used to evaluate the biosensor. Calculated sensitivity values for SiO2, TiO2, and the PMMA are 658, 653, and 633, respectively, while the figure of merit for these three sub-layers are 258, 2431, and 225. According to the simulation results, when the refractive index of a sub-layer is closer to the refractive index of the samples, the sensor is more sensitive. Also, due to the nanometer size of SSRs, it is easy to detect nanometer-sized specimens. The biosensor has a very high resolution so that the capability of measurement and the detection of cancer cells are enhanced.
TL;DR: This paper proposes a classification for crowd-powered indoor localization solutions to clarify which crowds-based approach is utilized in each indoor localization solution because in many cases the distinction is not clear and often leads to misconception.
Abstract: Among the emerging concepts in the context of IoT, crowdsourcing, and crowdsensing are known as two critical building blocks on the intersection point of things and human-based techniques. Although contribution and involvement of people is a key factor in both crowdsensing and crowdsourcing systems which provides reliability and data quality, level of human contribution is what makes crowd-powered systems different. To scrutinize this difference it is considered that user intervention in crowd-based schemes can be either implicit or explicit. Since one of the most important applications of crowdsourcing and crowdsensing systems is providing location services in indoor environments, in this paper, we study the level of user contribution in available crowd-powered techniques and propose a classification for crowd-powered indoor localization solutions to clarify which crowds-based approach is utilized in each indoor localization solution because in many cases the distinction is not clear and often leads to misconception. Dependency on site survey process is considered as another distinction point in our proposed classification. Hence, we consider indoor localization solutions with implicit user participation and latent mobile utilization as crowdsensing indoor localization systems. Respectively, indoor localization solutions with explicit user participation and manifest mobile utilization are classified as crowdsourcing indoor localization systems.