Showing papers in "IEEE Sensors Journal in 2021"

A Review on Soft Sensors for Monitoring, Control, and Optimization of Industrial Processes

Abstract: Over the past twenty years, numerous research outcomes have been published, related to the design and implementation of soft sensors. In modern industrial processes, various types of soft sensors are used, which play essential roles in process monitoring, control and optimization. Emerging new theories, advanced techniques and the information infrastructure have enabled the elevation of the performance of soft sensing. However, novel opportunities are accompanied by novel challenges. This work is motivated by these observations and aims to present a comprehensive review of the developments since the start of the millennium. While a few books and review articles are published on the related topics, more focus on the most up-to-the-date advancement is put in this work, from the perspective of systems and control.

Unmanned Aerial Vehicles in Smart Agriculture: Applications, Requirements, and Challenges

Abstract: In the next few years, smart farming will reach each and every nook of the world. The prospects of using unmanned aerial vehicles (UAV) for smart farming are immense. However, the cost and the ease in controlling UAVs for smart farming might play an important role for motivating farmers to use UAVs in farming. Mostly, UAVs are controlled by remote controllers using radio waves. There are several technologies such as Wi-Fi or ZigBee that are also used for controlling UAVs. However, Smart Bluetooth (also referred to as Bluetooth Low Energy) is a wireless technology used to transfer data over short distances. Smart Bluetooth is cheaper than other technologies and has the advantage of being available on every smart phone. Farmers can use any smart phone to operate their respective UAVs along with Bluetooth Smart enabled agricultural sensors in the future. However, certain requirements and challenges need to be addressed before UAVs can be operated for smart agriculture-related applications. Hence, in this article, an attempt has been made to explore the types of sensors suitable for smart farming, potential requirements and challenges for operating UAVs in smart agriculture. We have also identified the future applications of using UAVs in smart farming.

Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging

Abstract: With the increase of COVID-19 cases worldwide, an effective way is required to diagnose COVID-19 patients. The primary problem in diagnosing COVID-19 patients is the shortage and reliability of testing kits, due to the quick spread of the virus, medical practitioners are facing difficulty in identifying the positive cases. The second real-world problem is to share the data among the hospitals globally while keeping in view the privacy concerns of the organizations. Building a collaborative model and preserving privacy are the major concerns for training a global deep learning model. This paper proposes a framework that collects a small amount of data from different sources (various hospitals) and trains a global deep learning model using blockchain-based federated learning. Blockchain technology authenticates the data and federated learning trains the model globally while preserving the privacy of the organization. First, we propose a data normalization technique that deals with the heterogeneity of data as the data is gathered from different hospitals having different kinds of Computed Tomography (CT) scanners. Secondly, we use Capsule Network-based segmentation and classification to detect COVID-19 patients. Thirdly, we design a method that can collaboratively train a global model using blockchain technology with federated learning while preserving privacy. Additionally, we collected real-life COVID-19 patients’ data open to the research community. The proposed framework can utilize up-to-date data which improves the recognition of CT images. Finally, we conducted comprehensive experiments to validate the proposed method. Our results demonstrate better performance for detecting COVID-19 patients.

Applications, Deployments, and Integration of Internet of Drones (IoD): A Review

Abstract: The Internet of Drones (IoD) has become a hot research topic in academia, industry, and management in current years due to its wide potential applications, such as aerial photography, civilian, and military. This paper presents a comprehensive survey of IoD and its applications, deployments, and integration. We focused in this review on two main sides; IoD Applications include smart cities surveillance, cloud and fog frameworks, unmanned aerial vehicles, wireless sensor networks, networks, mobile computing, and business paradigms; integration of IoD includes privacy protection, security authentication, neural network, blockchain, and optimization based-method. A discussion highlights the hot research topics and problems to help researchers interested in this area in their future works. The keywords that have been used in this paper are Internet of Drones.

A Review of Deep Learning Models for Time Series Prediction

Abstract: In order to approximate the underlying process of temporal data, time series prediction has been a hot research topic for decades. Developing predictive models plays an important role in interpreting complex real-world elements. With the sharp increase in the quantity and dimensionality of data, new challenges, such as extracting deep features and recognizing deep latent patterns, have emerged, demanding novel approaches and effective solutions. Deep learning, composed of multiple processing layers to learn with multiple levels of abstraction, is, now, commonly deployed for overcoming the newly arisen difficulties. This paper reviews the state-of-the-art developments in deep learning for time series prediction. Based on modeling for the perspective of conditional or joint probability, we categorize them into discriminative, generative, and hybrids models. Experiments are implemented on both benchmarks and real-world data to elaborate the performance of the representative deep learning-based prediction methods. Finally, we conclude with comments on possible future perspectives and ongoing challenges with time series prediction.

Human Activity Recognition With Smartphone and Wearable Sensors Using Deep Learning Techniques: A Review

Abstract: Human Activity Recognition (HAR) is a field that infers human activities from raw time-series signals acquired through embedded sensors of smartphones and wearable devices. It has gained much attraction in various smart home environments, especially to continuously monitor human behaviors in ambient assisted living to provide elderly care and rehabilitation. The system follows various operation modules such as data acquisition, pre-processing to eliminate noise and distortions, feature extraction, feature selection, and classification. Recently, various state-of-the-art techniques have proposed feature extraction and selection techniques classified using traditional Machine learning classifiers. However, most of the techniques use rustic feature extraction processes that are incapable of recognizing complex activities. With the emergence and advancement of high computational resources, Deep Learning techniques are widely used in various HAR systems to retrieve features and classification efficiently. Thus, this review paper focuses on providing profound concise of deep learning techniques used in smartphone and wearable sensor-based recognition systems. The proposed techniques are categorized into conventional and hybrid deep learning models described with its uniqueness, merits, and limitations. The paper also discusses various benchmark datasets used in existing techniques. Finally, the paper lists certain challenges and issues that require future research and improvements.

Smart Secure Sensing for IoT-Based Agriculture: Blockchain Perspective

Abstract: Agriculture is a vital area for the sustenance of mankind engulfing manufacturing, security, traceability, and sustainable resource management. With the resources receding expeditiously, it is of utmost significance to innovate techniques that help in the subsistence of agriculture. The growth of Internet of Things (IoT) and Blockchain technology as two rapidly emerging fields can ameliorate the state of food chain today. This paper provides a rigorous literature review to inspect the state-of-the-art development of the schemes that provide information security using blockchain technology. After identifying the core requirements in smart agriculture, a generalized blockchain-based security architecture has been proposed. A detailed cost analysis has been conducted on the studied schemes. A meticulous comparative analysis uncovered the drawbacks in existing research. Furthermore, detailed analysis of the literature has also revealed the security goals towards which the research has been directed and helped to identify new avenues for future research using artificial intelligence.

Gold-Immobilized Photonic Crystal Fiber-Based SPR Biosensor for Detection of Malaria Disease in Human Body

Abstract: This article presents the photonic crystal fiber (PCF) based surface plasmon resonance (SPR) biosensor for early detection of malaria disease in humans by measurement of the variation of red blood cells (RBCs). In the proposed PCF, two layers of air holes are arranged in a hexagonal lattice structure and a thin film of gold-coating is used over PCF for the occurrence of SPR phenomena. It occurs when surface plasmon polariton (SPP)-mode coupled with the core-mode during phase-matching conditions. Malaria infected RBCs samples are filled into the PCF, which have own refractive index (RI) that shift the SPR resonance wavelength during confinement loss measurement. The resonance wavelength of malaria-infected RBCs samples is different from their normal RBCs samples due to the difference in RI of infected and normal RBCs samples. The proposed work is helpful in the detection of different stages of malaria-infected RBCs such as ring phase, trophozoite phase and Schizont phase by measuring the shift in resonance wavelength. The calculated wavelength sensitivities of the proposed sensor for the ring phase, trophozoite phase and Schizont phase RBCs are 13714.29 nm/RIU, 9789.47 nm/RIU, and 8068.97 nm/RIU, respectively in x-polarized direction and 14285.71 nm/RIU, 10000 nm/RIU, and 8206.9 nm/RIU, respectively in y-polarized direction with the maximum detection limit of 0.029. The proposed PCF-based SPR biosensor is suitable for the early diagnosis of malaria disease due to its enhanced sensing performance (low detection limit and high sensitivity).

Sensor-Fault Detection, Isolation and Accommodation for Digital Twins via Modular Data-Driven Architecture

Abstract: Sensor technologies empower Industry 4.0 by enabling integration of in-field and real-time raw data into digital twins. However, sensors might be unreliable due to inherent issues and/or environmental conditions. This article aims at detecting anomalies in measurements from sensors, identifying the faulty ones and accommodating them with appropriate estimated data, thus paving the way to reliable digital twins. More specifically, we propose a general machine-learning-based architecture for sensor validation built upon a series of neural-network estimators and a classifier. Estimators correspond to virtual sensors of all unreliable sensors (to reconstruct normal behaviour and replace the isolated faulty sensor within the system), whereas the classifier is used for detection and isolation tasks. A comprehensive statistical analysis on three different real-world data-sets is conducted and the performance of the proposed architecture validated under hard and soft synthetically-generated faults.

Infrared Thermography-Based Fault Diagnosis of Induction Motor Bearings Using Machine Learning

Abstract: Bearing is one of the most crucial parts in induction motor (IM) as a result there is a constant call for effective diagnosis of bearing faults for reliable operation. Infrared thermography (IRT) is appreciably used as a non-destructive and non-contact method to detect the bearing defects in a rotary machine. However, its performance is limited by insignificant information and string noise present in the infrared thermal image. To address this issue, an emergent two dimensional discrete wavelet transform (2D-DWT) based IRT method has been proposed in this article for diagnosing the different bearing faults in IM, namely, inner and outer race defects, and lack of lubrication. The dimensionality of the extracted features was reduced using principal component analysis (PCA) and thereafter the selected features were ranked in the order of most relevant features using the Mahalanobis distance (MD) method to achieve the optimal feature set. Finally these selected features have been passed to the complex decision tree (CDT), linear discriminant analysis (LDA) and support vector machine (SVM) for fault classification and performance evaluation. The classification results reveal that the SVM outperformed CDT and LDA. The proposed strategy can be used for self-adaptive recognition of bearing faults in IM which helps to avoid the unplanned and unwanted system shutdowns due to the bearing failure.

Survey of Authentication and Privacy Schemes in Vehicular ad hoc Networks

Abstract: Vehicular ad hoc networks (VANETs) have become increasingly common in recent years due to their critical role in the field of smart transportation by supporting Vehicle-to-Vehicle and Vehicle-to-Infrastructure communication. The security and privacy of VANET are of the utmost importance due to the use of an open wireless communication medium where messages are exchanged in plain text, something which allows attackers to intercept, tamper, replay, and delete them. Hence, there is a high probability that the safety of a VANET-based smart transportation system could be compromised. Nowadays, securing and safeguarding the exchange of messages in VANETs is the focus of many security research teams, as reflected by the number of authentication and privacy schemes that have been proposed. However, these schemes have not fulfilled all aspects of the security and privacy requirements. The present paper is an effort to provide a thorough background on VANETs and their components; various types of attacks on them; and all the security and privacy requirements for authentication and privacy schemes for VANETs. This paper is among the first to provide a comprehensive survey of the existing authentication and privacy schemes and compare them based on all security and privacy requirements, computational and communicational overheads, and the level of resistance to different types of attacks. It also provides a qualitative comparison with the existing surveys. This paper could serve as a guide and reference in the design and development of any new security and privacy techniques for VANETs.

Fault Diagnosis of Rolling Bearings Based on an Improved Stack Autoencoder and Support Vector Machine

Abstract: In recent years, autoencoder has been widely used for the fault diagnosis of mechanical equipment because of its excellent performance in feature extraction and dimension reduction; however, the original autoencoder only has limited feature extraction ability due to the lack of label information. To solve this issue, this study proposes a feature distance stack autoencoder (FD-SAE) for rolling bearing fault diagnosis. Compared with the existing methods, FD-SAE has stronger feature extraction ability and faster network convergence speed. By analyzing the characteristics of original rolling bearing data, it is found that there are evident differences between normal data and faulty data. Therefore, a simple linear support vector machine (SVM) is used to classify normal data and faulty data, and then the proposed FD-SAE is used for fault classification. The novel combination of SVM and FD-SAE has simple structure and little computational complexity. Finally, the proposed method is verified on the rolling bearing data set of Case Western Reserve University (CWRU).

Wearable Sensors for Real-Time Kinematics Analysis in Sports: A Review

Abstract: Wearable Inertial sensors have revolutionised the way kinematics analysis is performed in sports. This paper aims to present a comprehensive review of the literature related to the use of wearable inertial sensors for performance analysis in various games. Kinematics analysis using wearable sensors can provide real-time feedback to the players about their adopted techniques in their respective sports and thus help them to perform efficiently. This article reviews the key technologies (IMU sensors, communication technology, data fusion and data analysis techniques) that enable the implementation of wearable sensors for performance analysis in sports. The review focuses on research papers, commercial sports sensors and 3D motion tracking products to provide a holistic and systematic categorisation & analysis of the wearable sensors in sports. The review identifies the importance of sensors classification, applications and performance parameters in sports for structured analysis. The survey also reviews the technology concerning sensor architecture, network and communication protocols, covers various data fusion algorithms and their accuracy while throwing light on essential performance matrices for an athlete. This review paper will assist both end-users and the researchers to have a comprehensive glimpse of the wearable technology pertaining to designing sensors and solutions for athletes in different sports.

Fault Diagnosis for Electrical Systems and Power Networks: A Review

Abstract: In this paper, we review the state of the art in the detection, location, and diagnosis of faults in electrical wiring interconnection systems (EWIS) including in the electric power grid and vehicles and machines. Most electrical test methods rely on measurements of either currents and voltages or on high frequency reflections from impedance discontinuities. Of these high frequency test methods, we review phasor, travelling wave and reflectometry methods. The reflectometry methods summarized include time domain reflectometry (TDR), sequence time domain reflectometry (STDR), spread spectrum time domain reflectometry (SSTDR), orthogonal multi-tone reflectometry (OMTDR), noise domain reflectometry (NDR), chaos time domain reflectometry (CTDR), binary time domain reflectometry (BTDR), frequency domain reflectometry (FDR), multicarrier reflectometry (MCR), and time-frequency domain reflectometry (TFDR). All of these reflectometry methods result in complex data sets (reflectometry signatures) that are the result of reflections in the time/frequency/spatial domains. Automated analysis techniques are needed to detect, locate, and diagnose the fault including genetic algorithm (GA), neural networks (NN), particle swarm optimization, teaching–learning-based optimization, backtracking search optimization, inverse scattering, and iterative approaches. We summarize several of these methods including electromagnetic time-reversal (TR) and the matched-pulse (MP) approach. We also discuss the issue of soft faults (small impedance changes) and methods to augment their signatures, and the challenges of branched networks. We also suggest directions for future research and development.

Automated Vehicle Sideslip Angle Estimation Considering Signal Measurement Characteristic

Abstract: Vehicle slip angle (VSA) estimation is of paramount importance for connected automated vehicle dynamic control, especially in critical lateral driving scenarios. In this paper, a novel kinematic-model-based VSA estimation method is proposed by fusing information from a global navigation satellite system (GNSS) and an inertial measurement unit (IMU). First, to reject the gravity components induced by the vehicle roll and pitch, a vehicle attitude angle observer based on the square-root cubature Kalman filter (SCKF) is designed to estimate the roll and pitch. A novel feedback mechanism based on the vehicle intrinsic information (the steering angle and wheel speed) for the pitch and roll is designed. Then, the integration of the reverse smoothing and grey prediction is adopted to compensate for the cumulative velocity errors during the relatively low sampling interval of the GNSS. Moreover, the GNSS signal delay has been addressed by an estimation-prediction integrated framework. Finally, the results confirm that the proposed method can estimate the VSA under both the slalom and double lane change (DLC) scenarios.

Singlemode-Multimode-Singlemode Fiber Structures for Sensing Applications—A Review

Abstract: A singlemode-multimode-singlemode (SMS) fiber structure consists of a short section of multimode fiber fusion- spliced between two SMS fibers. The mechanism underpinning the operation of an SMS fiber structure is multimode interference and associated self-imaging. SMS structures can be used in a variety of optical fiber systems but are most commonly used as sensors for a variety of parameters, ranging from macro-world measurands such as temperature, strain, vibration, flow rate, RI and humidity to the micro-world with measurands such as proteins, pathogens, DNA and specific molecules. While traditional SMS structures employ a short section of standard multimode fiber, a large number of structures have been investigated and demonstrated over the last decade involving the replacement of the multimode fiber section with alternatives such as a hollow core fiber or a tapered fiber. The objective of replacing the multimode fiber has most often been to allow sensing of different measurands or to improve sensitivity. In this paper, several different categories of SMS fiber structures, including traditional SMS, modified SMS and tapered SMS fiber structures are discussed with some theoretical underpinning and reviews of a wide variety of sensing examples and recent advances. The paper then summarizes and compares the performances of a variety of sensors which have been published under a number of headings. The paper concludes by considering the challenges faced by SMS based sensing schemes in terms of their deployment in real world applications and discusses possible future developments of SMS fiber sensors.

Multi-Modal Sensor Fusion-Based Deep Neural Network for End-to-End Autonomous Driving With Scene Understanding

Abstract: This study aims to improve the performance and generalization capability of end-to-end autonomous driving with scene understanding leveraging deep learning and multimodal sensor fusion techniques. The designed end-to-end deep neural network takes as input the visual image and associated depth information in an early fusion level and outputs the pixel-wise semantic segmentation as scene understanding and vehicle control commands concurrently. The end-to-end deep learning-based autonomous driving model is tested in high-fidelity simulated urban driving conditions and compared with the benchmark of CoRL2017 and NoCrash. The testing results show that the proposed approach is of better performance and generalization ability, achieving a 100% success rate in static navigation tasks in both training and unobserved situations, as well as better success rates in other tasks than the prior models. A further ablation study shows that the model with the removal of multimodal sensor fusion or scene understanding pales in the new environment because of the false perception. The results verify that the performance of our model is improved by the synergy of multimodal sensor fusion with scene understanding subtask, demonstrating the feasibility and effectiveness of the developed deep neural network with multimodal sensor fusion.

Towards Precision Agriculture: IoT-Enabled Intelligent Irrigation Systems Using Deep Learning Neural Network

Abstract: Recently, precision agriculture has gained substantial attention due to the ever-growing world population demands for food and water. Consequently, farmers will need water and arable land to meet this demand. Due to the limited availability of both resources, farmers need a solution that changes the way they operate. Precision irrigation is the solution to deliver bigger, better, and more profitable yields with fewer resources. Several machine learning-based irrigation models have been proposed to use water more efficiently. Due to the limited learning ability of these models, they are not well suited to unpredictable climates. In this context, this paper proposes a deep learning neural network-based Internet of Things (IoT)-enabled intelligent irrigation system for precision agriculture (DLiSA). This is a feedback integrated system that keeps its functionality better in the weather of any region for any period of time. DLiSA utilizes a long short-term memory network (LSTM) to predict the volumetric soil moisture content for one day ahead, irrigation period, and spatial distribution of water required to feed the arable land. It is evident from the simulation results that DLiSA uses water more wisely than state-of-the-art models in the experimental farming area.

Layer-Wise Training Convolutional Neural Networks With Smaller Filters for Human Activity Recognition Using Wearable Sensors

Abstract: Recently, convolutional neural networks (CNNs) have set latest state-of-the-art on various human activity recognition (HAR) datasets. However, deep CNNs often require more computing resources, which limits their applications in embedded HAR. Although many successful methods have been proposed to reduce memory and FLOPs of CNNs, they often involve special network architectures designed for visual tasks, which are not suitable for deep HAR tasks with time series sensor signals, due to remarkable discrepancy. Therefore, it is necessary to develop lightweight deep models to perform HAR. As filter is the basic unit in constructing CNNs, it deserves further research whether re-designing smaller filters is applicable for deep HAR. In the article, inspired by the idea, we proposed a lightweight CNN using Lego filters for HAR. A set of lower-dimensional filters is used as Lego bricks to be stacked for conventional filters, which does not rely on any special network structure. The local loss function is used to train model. To our knowledge, this is the first paper that proposes lightweight CNN for HAR in ubiquitous and wearable computing arena. The experiment results on five public HAR datasets, UCI-HAR dataset, OPPORTUNITY dataset, UNIMIB-SHAR dataset, PAMAP2 dataset, and WISDM dataset collected from either smartphones or multiple sensor nodes, indicate that our novel Lego CNN with local loss can greatly reduce memory and computation cost over CNN, while achieving higher accuracy. That is to say, the proposed model is smaller, faster and more accurate. Finally, we evaluate the actual performance on an Android smartphone.

Cortisol In-Fiber Ultrasensitive Plasmonic Immunosensing

Abstract: Cortisol is a stress biomarker whose chronic elevated levels are associated with higher risk of metabolic syndromes, anxiety, and cardiovascular diseases, among other medical conditions. A new immunosensor based on plasmonic tilted fiber Bragg grating (TFBG) has been developed and tested for rapid and ultrasensitive cortisol detection. The gold coated TFBG was characterized to surrounding refractive index (SRI) changes and functionalized with anti-cortisol antibodies via cysteamine. The functionalization was monitored, allowing to verify the SRI alteration at the fiber surface by the respective molecular adhesion. In this work, an alternative method to the monitoring of the most sensitive surface plasmon resonance mode was explored, based on tracking the local maximum of the plasmonic signature of the lower envelope of the spectra. With this interrogation method, the sensor achieved a sensitivity to cortisol detection of 0.275 ± 0.028 nm/ng.mL−1, for the detection range of 0.1-10 ng/mL, with a total wavelength shift of around 3 nm, which is higher several orders of magnitude than the usually reported TFBG plasmonic immunosensors. The proposed biosensor provides a rapid, highly sensitive, label-free, low-volume consumption method for cortisol detection, with a working range suitable to monitor different biological samples.

Deep ConvLSTM With Self-Attention for Human Activity Decoding Using Wearable Sensors

Abstract: Decoding human activity accurately from wearable sensors can aid in applications related to healthcare and context awareness. The present approaches in this domain use recurrent and/or convolutional models to capture the spatio-temporal features from time-series data from multiple sensors. We propose a deep neural network architecture that not only captures the spatio-temporal features of multiple sensor time-series data but also selects, learns important time points by utilizing a self-attention mechanism. We show the validity of the proposed approach across different data sampling strategies on six public datasets and demonstrate that the self-attention mechanism gave a significant improvement in performance over deep networks using a combination of recurrent and convolution networks. We also show that the proposed approach gave a statistically significant performance enhancement over previous state-of-the-art methods for the tested datasets. The proposed methods open avenues for better decoding of human activity from multiple body sensors over extended periods of time. The code implementation for the proposed model is available at https://github.com/isukrit/encodingHumanActivity

Grape Disease Detection Network Based on Multi-Task Learning and Attention Features

Abstract: The disease-free growth of a plant is highly influential for both environment and human life. However, there are numerous plant diseases such as viruses, fungus, and micro-organisms that affect the growth and agricultural production of a plant. Grape esca, black-rot, and isariopsis are multi-symptomatic soil-borne diseases. Often, these diseases may cause leaves drop or sometimes even vanishes the plant/plant vicinity. Hence, early detection and prevention becomes necessary and must be treated on time for better grape growth and productivity. The state-of-the-art either involve classical computer vision techniques such as edge detection/segmentation or regression-based object detection applied over UAV images. In addition, the treatment is not viable until detected leaves are classified for actual disease/symptoms. This results in increased time and cost consumption. Therefore, in this paper, a grape leaf disease detection network (GLDDN) is proposed that utilizes dual attention mechanisms for feature evaluation, detection, and classification. At evaluation stage, the experimentation performed over benchmark dataset confirms that disease detection network could be fairly befitting than the existing methods since it recognizes as well as detects the infected/diseased regions. With the proposed disease detection mechanism, we achieved an overall accuracy of 99.93% accuracy for esca, black-rot and isariopsis detection.

Multi-Object Detection and Tracking, Based on DNN, for Autonomous Vehicles: A Review

Abstract: Multi-object detection and multi-object-tracking in diverse driving situations is the main challenge in autonomous vehicles. Vehicle manufacturers and research organizations are addressing this problem, with multiple sensors such as camera, LiDAR, RADAR, ultrasonic-sensors, GPS, and Vehicle-to-Everything-technology. Deep Neural Networks (DNN) are playing a predominant role to solve this. Fusing the sensing modalities with DNN will be the leading solution to this challenge. This paper evaluates the state-of-the-art techniques that address this challenge, with three primary sensors camera, LiDAR, and RADAR with DNN, and fusion of sensor data with DNN. The analysis shows that there exists an excellent potential to design a more optimized solution to address this challenge. This work proposes a perception model for autonomous vehicles.

Advances in Optical Fiber Sensors Based on Multimode Interference (MMI): A Review

Abstract: In recent years, optical fiber sensors based on multimode interference (MMI) have attracted increasing interest and developed into various sensors used in many practical applications. This review presents MMI-based fiber sensors with a specific focus on the probe structures, measurement methods, and sensing properties of different structures. The fundamentals of MMI-based fiber sensors are briefly described. Further, five main categories of SMS structure-based fiber sensors are reviewed, including conventional SMS fiber sensors, MMI-based sensors with no-core fiber (NCF), MMI-based sensors with etched/polished fiber, MMI-based sensors with tapered fiber, and cascades of MMI-based fiber sensors. Besides, their probe structures, sensing properties, practical fields, and measurement sensitivities are summarized. Finally, the current challenges and technique outlook of the MMI-based fiber sensors are pointed out, which gives the potential solutions for the existing problems and future development. This work indicates that the MMI-based fiber sensors bring the possibilities of applying multi-mode fiber (MMF) in different measurement fields with high sensitivities, easy fabrication, and low cost. With the appearance and development of new SMS fiber sensors, it will contribute significant value to scientific research and industrial applications.

Human Fall Detection in Surveillance Videos Using Fall Motion Vector Modeling

Abstract: Representation of spatio-temporal properties of human body silhouette and human-to-ground relationship, significantly contribute to the fall detection process. So, we propose an approach to efficiently model the spatio-temporal features using fall motion vector. First, we construct a Gaussian mixture model (GMM) called fall motion mixture model (FMMM) using histogram of optical flow and motion boundary histogram features to implicitly capture motion attributes in both the fall and non-fall videos. The FMMM contains both fall and non-fall attributes resulting in a high-dimensional representation. In order to extract only the relevant attributes for a particular fall or non-fall videos, we perform factor analysis on FMMM to get a low dimensional representation known as fall motion vector. Using fall motion vector, we are able to efficiently identify fall events in varieties of scenarios, such as the narrow angle camera (Le2i dataset), wide angle camera (URFall dataset), and multiple cameras (Montreal dataset). In all these scenarios, we show that the proposed fall motion vector achieves better performance than the existing methods.

Smart Irrigation System for Precision Agriculture—The AREThOU5A IoT Platform

Abstract: Agriculture 4.0, as the future of farming technology, includes several key enabling technologies towards sustainable agriculture. The use of state-of-the-art technologies, such as the Internet of Things, transform traditional cultivation practices, like irrigation, to modern solutions of precision agriculture. In this paper, we present in detail the subsystems and the architecture of an intelligent irrigation system for precision agriculture, the AREThOU5A IoT platform. We describe the operation of the IoT node that is utilized in the platform. Moreover, we apply the radiofrequency energy harvesting technique to the presented IoT platform, as an alternative technique to deliver power to the IoT node of the platform. To this end, we fabricate and validate a rectenna module for radiofrequency energy harvesting. Experimental results of the fabricated rectenna exhibit a satisfactory performance as a harvester of ambient sources in an outdoor environment.

Shallow 3D CNN for Detecting Acute Brain Hemorrhage From Medical Imaging Sensors

Abstract: Successive layers in convolutional neural networks (CNN) extract different features from input images. Applications of CNNs to detect abnormalities in the 2D images or 3D volumes of body organs have recently become popular. However, computer-aided detection of diseases using deep CNN is challenging due to the absence of a large set of training medical images/scans and the relatively small and hard to detect abnormalities. In this paper, we propose a method for normalizing 3D volumetric scans using the intensity profile of the training samples. This aids the CNN by creating a higher contrast around the abnormal region of interest in the scan. We use the CQ500 head CT dataset to demonstrate the validity of our method for detecting different acute brain hemorrhages such as subarachnoid hemorrhage (SAH), intraparenchymal hemorrhage (IPH), subdural hematoma (SDH), and intraventricular hemorrhage (IVH). We compare the proposed method with a baseline, two variants of the 3D VGGNet architectures, Resnet, and show that the proposed method achieves significant improvement in classification performance. For binary classification, we achieved the best F1 score of 0.96 (normal vs SAH), 0.93 (normal vs IPH), 0.98 (normal vs SDH), and 0.99 (normal vs IVH), and for four-class classification, we obtained an average F1 score of 0.77. Finally, we show a limitation of the proposed method while detecting varied abnormalities. The proposed method has applications for abnormality detection for different organs.

Contactless Methods For Measuring Respiratory Rate: A Review

Abstract: Recent advances in understanding the importance of respiratory frequency ( ${ f}_{ R}$ ) as a sensitive marker of a variety of physiopathological stressors are fostering growing interest in respiratory monitoring. This interest is further stimulated by the ever-increasing efforts that companies are devoting to the development of systems measuring ${ f}_{ R}$ . There are a variety of techniques based on different sensors and technologies for ${ f}_{ R}$ monitoring. These techniques are commonly classified as contact-based or contactless, depending on whether the system which embeds the sensor is in contact with the body or not. This review is focused on the contactless methods for ${ f}_{ R}$ monitoring. We have introduced the main fields of use where contactless respiratory monitoring is important and provided a taxonomy to classify the most popular contactless techniques for ${ f}_{ R}$ monitoring. Finally, we have described the performances of the most popular methods, the main open challenges, and the main perspectives.

FPDP: Flexible Privacy-Preserving Data Publishing Scheme for Smart Agriculture

Abstract: The development of the Internet of Things (IoT) and 5th generation wireless network (5G) is set to push the smart agriculture to the next level since the massive and real-time data can be collected to monitor the status of crops and livestock, logistics management, and other important information. Recently, COVID-19 has attracted more human attention to food safety, which also has a positive impact on smart agriculture market share. However, the security and privacy concern for smart agriculture has become more prominent. Since smart agriculture implies working with large sets of data, which usually sensitive, some are even confidential, and once leakage it can expose user privacy. Meanwhile, considering the data publishing of smart agriculture helps the public or investors to real-timely anticipate risks and benefits, these data are also a public resource. To balance the data publishing and data privacy, in this article, a privacy-preserving data aggregation scheme with a flexibility property uses ElGamal Cryptosystem is proposed. It is proved to be secure, private, and flexible with the analysis and performance simulation.

Coupled GAN With Relativistic Discriminators for Infrared and Visible Images Fusion

Abstract: Infrared and visible images are a pair of multi-source multi-sensors images. However, the infrared images lack structural details and visible images are impressionable to the imaging environment. To fully utilize the meaningful information of the infrared and visible images, a practical fusion method, termed as RCGAN, is proposed in this paper. In RCGAN, we introduce a pioneering use of the coupled generative adversarial network to the field of image fusion. Moreover, the simple yet efficient relativistic discriminator is applied to our network. By doing so, the network converges faster. More importantly, different from the previous works in which the label for generator is either infrared image or visible image, we innovatively put forward a strategy to use a pre-fused image as the label. This is a technical innovation, which makes the process of generating fused images no longer out of thin air, but from “existence” to “excellent.” The extensive experiments demonstrate the proposed RCGAN can produce a faithful fused image, which can efficiently persevere the rich texture from visible images and thermal radiation information from infrared images. Compared with traditional methods, it successfully avoids the complex manual designed fusion rules, and also shows a clear advantages over other deep learning-based fusion methods.