Sensors, Volume 22, Issue 15 (August-1 2022) – 465 articles

Apache Spark is a popular open-source distributed data processing framework that can efficiently process massive amounts of data. It provides more than 180 configuration parameters for users to manually select the appropriate parameter values according to their own experience. However, due to the large number of parameters and the inherent correlation between them, manual tuning is very tedious. To solve the problem of tuning through personal experience, we designed and implemented a reinforcement-learning-based Spark configuration parameter optimizer. First, we trained a Spark application performance prediction model with deep neural networks, and verified the accuracy and effectiveness of the model from multiple perspectives. Second, in order to improve the search efficiency of better configuration parameters, we improved the Q-learning algorithm, and automatically set start and end states in each iteration of training, which effectively improves the agent’s poor performance in exploring better configuration parameters. Lastly, comparing our proposed configuration with the default configuration as the baseline, experimental results show that the optimized configuration gained an average performance improvement of 47%, 43%, 31%, and 45% for four different types of Spark applications, which indicates that our Spark configuration parameter optimizer could efficiently find the better configuration parameters and improve the performance of various Spark applications. Full article

Non-specific binding (NSB) is one of the important issues in biosensing performance. Herein, we designed a strategy for removing non-specific binding including anti-mouse IgG antibody and bovine serum albumin (BSA) by utilizing anisotropic cadmium selenide tetrapods (CdSe TPs) in a vortex flow. The shear force on the tetrapod nanoparticles was increased by controlling the rotation rate of the vortex flow from 0 rpm to 1000 rpm. As a result, photoluminescence (PL) signals of fluorescein (FITC)-conjugated protein, anti-mouse IgG antibody-FITC and bovine serum albumin (BSA)-FITC, were reduced by 35% and 45%, respectively, indicating that NSB can be removed under vortex flow. In particular, simultaneous NSB removal and protein capture can be achieved even with mixture solutions of target antibodies and anti-mouse IgG antibodies by applying cyclic mode vortex flow on anisotropic CdSe TPs. These results demonstrate successfully that NSB can be diminished by rotating CdSe TPs to generate shear force under vortex flow. This study opens up new research protocols for utilization of anisotropic nanoparticles under vortex flow, which increases the feasibility of protein capture and non-specific proteins removal for biosensors. Full article

Hydrogen sulfide (H₂S) is known to participate in bacteria-induced inflammatory response in periodontal diseases. Therefore, it is necessary to quantify H₂S produced by oral bacteria for diagnosis and treatment of oral diseases including halitosis and periodontal disease. In this study, we introduce a paper-based colorimetric assay for detecting bacterial H₂S utilizing silver/Nafion/polyvinylpyrrolidone membrane and a 96-well microplate. This H₂S-sensing paper showed a good sensitivity (8.27 blue channel intensity/μM H₂S, R² = 0.9996), which was higher than that of lead acetate paper (6.05 blue channel intensity/μM H₂S, R² = 0.9959). We analyzed the difference in H₂S concentration released from four kinds of oral bacteria (Eikenella corrodens, Streptococcus sobrinus, Streptococcus mutans, and Lactobacillus casei). Finally, the H₂S level in Eikenella corrodens while varying the concentration of cysteine and treatment time was quantified. This paper-based colorimetric assay can be utilized as a simple and effective tool for in vitro screening of H₂S-producing ability of many bacteria as well as salivary H₂S analysis. Full article

Background: Despite extensive literature regarding laboratory-based balance perturbations, there is no up-to-date systematic review of methods. This systematic review aimed to assess current perturbation methods and outcome variables used to report participant biomechanical responses during walking. Methods: Web of Science, CINAHL, and PubMed online databases were searched, for records from 2015, the last search was on 30th of May 2022. Studies were included where participants were 18+ years, with or without clinical conditions, conducted in non-hospital settings. Reviews were excluded. Participant descriptive, perturbation method, outcome variables and results were extracted and summarised. Bias was assessed using the Appraisal tool for Cross-sectional Studies risk of bias assessment tool. Qualitative analysis was performed as the review aimed to investigate methods used to apply perturbations. Results: 644 records were identified and 33 studies were included, totaling 779 participants. The most frequent method of balance perturbation during gait was by means of a treadmill translation. The most frequent outcome variable collected was participant step width, closely followed by step length. Most studies reported at least one spatiotemporal outcome variable. All included studies showed some risk of bias, generally related to reporting of sampling approaches. Large variations in perturbation type, duration and intensity and outcome variables were reported. Conclusions: This review shows the wide variety of published laboratory perturbation methods. Moreover, it demonstrates the significant impact on outcome measures of a study based on the type of perturbation used. Registration: PROSPERO ID: CRD42020211876. Full article

The development of Wireless Underground Sensor Networks (WUSNs) is a recent research axis based on sensor nodes buried a few dozen centimeters deep. The communication ranges are, however, highly reduced due to the high attenuation of electromagnetic waves in soil, leading to issues of data collection. This paper proposes to embed a data collector on an Unmanned Aerial Vehicle (UAV) coming close to each buried sensor node. The whole system was developed (sensor nodes, data collector, gateway) and experimentations were carried out in real conditions. In hovering mode, the measurements on the RSSI levels with respect to the position of the UAV highlight the interest in maintaining a high altitude when the UAV is far from the node. In dynamic mode, the experimental results demonstrate the feasibility of carrying out the data collection task while the UAV is moving. The speed of the UAV has, however, to be adapted to the required time to collect the data. In the case of numerous buried sensor nodes, evolutionary algorithms are implemented to plan the trajectory of the UAV optimally. To the best of our knowledge, this paper is the first one that reports experiment results combining WUSN and UAV technologies. Full article

In this paper, we proposed an accurate and robust method for absolute pose estimation with UAV (unmanned aerial vehicle) using RANSAC (random sample consensus). Because the artificial 3D control points with high accuracy are time-consuming and the small point set may lead low measuring accuracy, we designed a customized UAV to efficiently obtain mass 3D points. A light source was mounted on the UAV and used as a 3D point. The position of the 3D point was given by RTK (real-time kinematic) mounted on the UAV, and the position of the corresponding 2D point was given by feature extraction. The 2D–3D point correspondences exhibited some outliers because of the failure of feature extraction, the error of RTK, and wrong matches. Hence, RANSAC was used to remove the outliers and obtain the coarse pose. Then, we proposed a method to refine the coarse pose, whose procedure was formulated as the optimization of a cost function about the reprojection error based on the error transferring model and gradient descent to refine it. Before that, normalization was given for all the valid 2D–3D point correspondences to improve the estimation accuracy. In addition, we manufactured a prototype of a UAV with RTK and light source to obtain mass 2D–3D point correspondences for real images. Lastly, we provided a thorough test using synthetic data and real images, compared with several state-of-the-art perspective-n-point solvers. Experimental results showed that, even with a high outlier ratio, our proposed method had better performance in terms of numerical stability, noise sensitivity, and computational speed. Full article

Mobile communication has achieved enormous technology innovations over many generations of progression. New cellular technology, including 5G cellular systems, is being deployed and making use of higher frequencies, including the Millimetre Wave (MMW) range (30–300 GHz) of the electromagnetic spectrum. Numerical computational techniques such as the Finite Difference Time Domain (FDTD) method have been used extensively as an effective approach for assessing electromagnetic fields’ biological impacts. This study demonstrates the variation of the accuracy of the FDTD computational simulation system when different meshing sizes are used, by using the interaction of the critically sensitive human cornea with EM in the 30 to 100 GHz range. Different approaches of base cell size specifications were compared. The accuracy of the computation is determined by applying planar sensors showing the detail of electric field distribution as well as the absolute values of electric field collected by point sensors. It was found that manually defining the base cell sizes reduces the model size as well as the computation time. However, the accuracy of the computation decreases in an unpredictable way. The results indicated that using a cloud computing capacity plays a crucial role in minimizing the computation time. Full article

This paper introduces a Hexa parallel robot and obstacle collision detection method based on dynamic modeling and a computer vision system. The processes to deal with the collision issues refer to collision detection, collision isolation, and collision identification applied to the Hexa robot, respectively, in this paper. Initially, the configuration, kinematic and dynamic characteristics during movement trajectories of the Hexa parallel robot are analyzed to perform the knowledge extraction for the method. Next, a virtual force sensor is presented to estimate the collision detection signal created as a combination of the solution to the inverse dynamics and a low-pass filter. Then, a vision system consisting of dual-depth cameras is designed for obstacle isolation and determining the contact point location at the end-effector, an arm, and a rod of the Hexa robot. Finally, a recursive Newton-Euler algorithm is applied to compute contact forces caused by collision cases with the real-Hexa robot. Based on the experimental results, the force identification is compared to sensor forces for the performance evaluation of the proposed collision detection method. Full article

Many studies on alpine skiing are limited to a few gates or collected data in controlled conditions. In contrast, it is more functional to have a sensor setup and a fast algorithm that can work in any situation, collect data, and distinguish alpine skiing activities for further analysis. This study aims to detect alpine skiing activities via smartphone inertial measurement units (IMU) in an unsupervised manner that is feasible for daily use. Data of full skiing sessions from novice to expert skiers were collected in varied conditions using smartphone IMU. The recorded data is preprocessed and analyzed using unsupervised algorithms to distinguish skiing activities from the other possible activities during a day of skiing. We employed a windowing strategy to extract features from different combinations of window size and sliding rate. To reduce the dimensionality of extracted features, we used Principal Component Analysis. Three unsupervised techniques were examined and compared: KMeans, Ward’s methods, and Gaussian Mixture Model. The results show that unsupervised learning can detect alpine skiing activities accurately independent of skiers’ skill level in any condition. Among the studied methods and settings, the best model had 99.25% accuracy. Full article

Nowadays, in a world full of uncertainties and the threat of digital and cyber-attacks, blockchain technology is one of the major critical developments playing a vital role in the creative professional world. Along with energy, finance, governance, etc., the healthcare sector is one of the most prominent areas where blockchain technology is being used. We all are aware that data constitute our wealth and our currency; vulnerability and security become even more significant and a vital point of concern for healthcare. Recent cyberattacks have raised the questions of planning, requirement, and implementation to develop more cyber-secure models. This paper is based on a blockchain that classifies network participants into clusters and preserves a single copy of the blockchain for every cluster. The paper introduces a novel blockchain mechanism for secure healthcare sector data management, which reduces the communicational and computational overhead costs compared to the existing bitcoin network and the lightweight blockchain architecture. The paper also discusses how the proposed design can be utilized to address the recognized threats. The experimental results show that, as the number of nodes rises, the suggested architecture speeds up ledger updates by 63% and reduces network traffic by 10 times. Full article

The accurate and timely identification of the degree of building damage is critical for disaster emergency response and loss assessment. Although many methods have been proposed, most of them divide damaged buildings into two categories—intact and damaged—which is insufficient to meet practical needs. To address this issue, we present a novel convolutional neural network—namely, the earthquake building damage classification net (EBDC-Net)—for assessment of building damage based on post-disaster aerial images. The proposed network comprises two components: a feature extraction encoder module, and a damage classification module. The feature extraction encoder module is employed to extract semantic information on building damage and enhance the ability to distinguish between different damage levels, while the classification module improves accuracy by combining global and contextual features. The performance of EBDC-Net was evaluated using a public dataset, and a large-scale damage assessment was performed using a dataset of post-earthquake unmanned aerial vehicle (UAV) images. The results of the experiments indicate that this approach can accurately classify buildings with different damage levels. The overall classification accuracy was 94.44%, 85.53%, and 77.49% when the damage to the buildings was divided into two, three, and four categories, respectively. Full article

Application of bio-based fertilizers is considered a practical solution to enhance soil fertility and maintain soil quality. However, the composition of bio-based fertilizers needs to be quantified before their application to the soil. Non-destructive techniques such as near-infrared (NIR) and mid-infrared (MIR) are generally used to quantify the composition of bio-based fertilizers in a speedy and cost-effective manner. However, the prediction performances of these techniques need to be quantified before deployment. With this motive, this study investigates the potential of these techniques to characterize a diverse set of bio-based fertilizers for 25 different properties including nutrients, minerals, heavy metals, pH, and EC. A partial least square model with wavelength selection is employed to estimate each property of interest. Then a model averaging, approach is tested to examine if combining model outcomes of NIR with MIR could improve the prediction performances of these sensors. In total, 17 of the 25 elements could be predicted to have a good performance status using individual spectral methods. Combining model outcomes of NIR with MIR resulted in an improvement, increasing the number of properties that could be predicted from 17 to 21. Most notably the improvement in prediction performance was observed for Cd, Cr, Zn, Al, Ca, Fe, S, Cu, Ec, and Na. It was concluded that the combined use of NIR and MIR spectral methods can be used to monitor the composition of a diverse set of bio-based fertilizers. Full article

Digital twins (DTs) play a vital role in revolutionising the healthcare industry, leading to more personalised, intelligent, and proactive healthcare. With the evolution of personalised healthcare, there is a significant need to represent a virtual replica for individuals to provide the right type of care in the right way and at the right time. Therefore, in this paper, we surveyed the concept of a personal digital twin (PDT) as an enhanced version of the DT with actionable insight capabilities. In particular, PDT can bring value to patients by enabling more accurate decision making and proper treatment selection and optimisation. Then, we explored the progression of PDT as a revolutionary technology in healthcare research and industry. However, although several research works have been performed for smart healthcare using DT, PDT is still at an early stage. Consequently, we believe that this work can be a step towards smart personalised healthcare industry by guiding the design of industrial personalised healthcare systems. Accordingly, we introduced a reference framework that empowers smart personalised healthcare using PDTs by bringing together existing advanced technologies (i.e., DT, blockchain, and AI). Then, we described some selected use cases, including the mitigation of COVID-19 contagion, COVID-19 survivor follow-up care, personalised COVID-19 medicine, personalised osteoporosis prevention, personalised cancer survivor follow-up care, and personalised nutrition. Finally, we identified further challenges to pave the PDT paradigm toward the smart personalised healthcare industry. Full article

In the Long Term Evolution (LTE) system, the Signal Propagation Model (SPM) and the location information of the base stations are required for positioning a smartphone. To this end, this paper proposes a technique for estimating the SPM and the location of the base station at the same time using location-based Reference Signal Received Power (RSRP) information acquired in a limited area. In the proposed technique, multiple Virtual Locations (VLs) for a base station are set within the service area. Signal propagation modelling is performed based on the assumptions that a base station is in each VL and the RSRP measurements are obtained from the corresponding base station. The residuals between the outputs of the estimated SPM and the RSRP measurements are then calculated. The VL with the minimum sum of the squared residuals is determined as the location of the base station. At the same time, the SPM estimated based on the corresponding VL is selected as the SPM of the base station. As a result of the experiment in Seoul, it was confirmed that the positions of seven base stations were estimated with an average accuracy of 40.2 m. Full article

Vehicle seats have a significant impact on the comfort of passengers. The development of seats is a field in which scholars are widely concerned. In this study, we add an electromagnetic levitation structure and design a new active seat suspension based on the passive seat suspension. Then, simulation research is carried out based on a C-level road surface combined with integral sliding mode control and state feedback control. The results show that both state feedback control and integral sliding mode control positively affect vehicle seat vibration reduction, and integral sliding mode control has a better anti-interference effect than state feedback control. At the same time, it is proved that the seat suspension has good working characteristics and economy. Full article

We developed and tested a microwave in situ salinity sensor (MiSSo) to simultaneously measure salinity and temperature within the same water sample over broad ranges of salinity (S) (3–50 psu) and temperature (T) (3–30 °C). Modern aquatic S sensors rely on measurements of conductivity (C) between a set of electrodes contained within a small volume of water. To determine water salt content or S, conductivity, or C, measurements must be augmented with concurrent T measurements from the same water volume. In practice, modern S sensors do not sample C and T within the same volume, resulting in the S determination characterized by measurement artifacts. These artifacts render processing vast amounts of available C and T data to derive S time-consuming and generally preclude automated processing. Our MiSSo approach eliminates the need for an additional T sensor, as it permits us to concurrently determine the sample S and T within the same water volume. Laboratory trials demonstrated the MiSSo accuracy of S and T measurements to be <0.1 psu and <0.1 °C, respectively, when using microwave reflections at 11 distinct frequencies. Each measurement took 0.1 $\mathsf{\mu }$s. Our results demonstrate a new physical method that permits the accurate S and T determination within the same water volume. Full article

Fragment kinetic energy is an important parameter to characterize the damage power of fragments. In this study, an acoustic emission technology-based method to evaluate fragment kinetic energy is proposed. The dynamic response of the fragment impacting an aluminum alloy target plate and the relationship between the initial kinetic energy of the fragment impact and the acoustic emission waveform were theoretically evaluated; the numerical simulation of typical spherical fragments (8 mm diameter) penetrating the aluminum alloy target plate was performed, the wavelet energy of the acoustic emission signal was obtained using wavelet packet theory, and a mathematical model of wavelet energy and fragment kinetic energy was constructed. A fragment kinetic energy test system was established, and a fragment penetration test was performed. The analysis showed that the wavelet energy mathematical models and the fragment kinetic energy exhibited favorable consistency, and the measurement errors of the three experiments were 3%, 3.7%, and 3%. This demonstrates the effectiveness of the typical acoustic emission fragment kinetic energy test methods proposed in this study and establishes a new method for the direct measurement of fragment kinetic energy. Full article

A multiscale modelling approach has been applied to the simulation of the electrical properties of oral tissue, for the purpose of informing an electrical impedance-based method of oral potential malignant disorder (OPMD) diagnosis. Finite element models of individual cell types, with geometry informed by histological analysis of human oral tissue (normal, hyperplastic and dysplastic), were generated and simulated to obtain electrical parameters. These were then used in a histology-informed tissue scale model, including the electrode geometry of the ZedScan tetrapolar impedance-measurement device. The simulations offer insight into the feasibility of distinguishing moderate dysplasia from severe dysplasia or healthy tissue. For some oral sites, simulated spectra agreed with real measurements previously collected using ZedScan. However, similarities between simulated spectra for dysplastic, keratinised and non-dysplastic but hyperkeratinised tissue suggest that significant keratinisation could cause some OPMD tissues to exhibit larger than expected impedance values. This could lead to misidentification of OPMD spectra as healthy. Sources of uncertainty within the models were identified and potential remedies proposed. Full article

The development of MEMS acoustic resonators meets the increasing demand for in situ detection with a higher performance and smaller size. In this paper, a lithium niobate film-based S₁ mode Lamb wave resonator (HF-LWR) for high-sensitivity gravimetric biosensing is proposed. The fabricated resonators, based on a 400-nm X-cut lithium niobate film, showed a resonance frequency over 8 GHz. Moreover, a PMMA layer was used as the mass-sensing layer, to study the performance of the biosensors based on HF-LWRs. Through optimizing the thickness of the lithium niobate film and the electrode configuration, the mass sensitivity of the biosensor could reach up to 74,000 Hz/(ng/cm²), and the maximum value of figure of merit (FOM) was 5.52 × 10⁷, which shows great potential for pushing the performance boundaries of gravimetric-sensitive acoustic biosensors. Full article

This work proposes a mono-axial piezoelectric energy harvester based on the innovative combination of magnetic plucking and indirect impacts, e.g., impacts happening on the package of the harvester. The harvester exploits a permanent magnet placed on a non-magnetic mass, free to move within a predefined bounded region located in front of a piezoelectric bimorph cantilever equipped with a magnet as the tip mass. When the harvester is subjected to a low-frequency external acceleration, the moving mass induces an abrupt deflection and release of the cantilever by means of magnetic coupling, followed by impacts of the same mass against the harvester package. The combined effect of magnetic plucking and indirect impacts induces a frequency up-conversion. A prototype has been designed, fabricated, fastened to the wrist of a person by means of a wristband, and experimentally tested for different motion levels. By setting the magnets in a repulsive configuration, after 50 s of consecutive impacts induced by shaking, an energy of 253.41 μJ has been stored: this value is seven times higher compared to the case of harvester subjected to indirect impacts only, i.e., without magnetic coupling. This confirms that the combination of magnetic plucking and indirect impacts triggers the effective scavenging of electrical energy even from low-frequency non-periodical mechanical movements, such as human motion, while preserving the reliability of piezoelectric components. Full article

How to generate the path planning of mobile robots quickly is a problem in the field of robotics. The Q-learning(QL) algorithm has recently become increasingly used in the field of mobile robot path planning. However, its selection policy is blind in most cases in the early search process, which slows down the convergence of optimal solutions, especially in a complex environment. Therefore, in this paper, we propose a continuous local search Q-Learning (CLSQL) algorithm to solve these problems and ensure the quality of the planned path. First, the global environment is gradually divided into independent local environments. Then, the intermediate points are searched in each local environment with prior knowledge. After that, the search between each intermediate point is realized to reach the destination point. At last, by comparing other RL-based algorithms, the proposed method improves the convergence speed and computation time while ensuring the optimal path. Full article

Body to body networks (BBNs) are a kind of large-scaled sensor network that are composed of several wireless body area networks (WBANs) in the distributed structure, and in recent decades, BBNs have played a key role in medical, aerospace, and military applications. Compared with the traditional WBANs, BBNs have larger scales and longer transmission distances. The sensors within BBNs not only transmit the data they collect, but also forward the data sent by other nodes as relay nodes. Therefore, BBNs have high requirements in energy efficiency, data security, and privacy protection. In this paper, we propose a secure and efficient data transmission method for sensor nodes within BBNs that is based on the perception of chaotic compressive sensing. This method can simultaneously accomplish data compression, encryption, and critical information concealment during the data sampling process and provide various levels of reconstruction qualities according to the authorization level of receivers. Simulation and experimental results demonstrate that the proposed method could realize data compression, encryption, and critical information concealment for images that are transmitted within BBNs. Specifically, the proposed method could enhance the security level of data transmission by breaking the statistical patterns of original data, providing large key space and sensitivity of the initial values, etc. Full article

In a reconfigurable intelligent surface (RIS) assisted millimeter Wave (mmWave) communication system, the channel coefficient increases exponentially with the number of RIS elements which results in expensive pilot overhead. Most previous works have proposed some channel estimation algorithms for the estimation accuracy of cascaded channels, which have improved the estimation accuracy, but the pilot overhead is discouraging in the estimation process. To improve the channel estimation accuracy with reduced pilot overhead, we propose a two-stage channel estimation protocol by exploiting semi-passive elements and the coherent time difference of the channel, where the quasi-static channel between the base stations (BS) and RIS is estimated at the RIS, and the user (UE)-RIS time-varying channel is estimated at the BS. In the first stage, we formulate the BS-RIS channel estimation as a mathematical optimization problem by an iterative weighting method and then propose a gradient descent (GD)-based algorithm to solve it. In the second stage, we first transform the received the UE-RIS signal model into an equivalent parallel factor (PARAFAC) tensor model and estimate the UE-RIS channel by the least-squares (LS) algorithm. The simulation results show that the proposed method has better estimation accuracy than the LS, compression sensing (CS) and minimum mean square error (MMSE) methods with less pilot overhead, and the spectral efficiency is improved by at least 10.5% compared to the other three methods. Full article

The development of synthetic biology has enabled massive progress in biotechnology and in approaching research questions from a brand-new perspective. In particular, the design and study of gene regulatory networks in vitro, in vivo, and in silico have played an increasingly indispensable role in understanding and controlling biological phenomena. Among them, it is of great interest to understand how associative learning is formed at the molecular circuit level. Mathematical models are increasingly used to predict the behaviours of molecular circuits. Fernando’s model, which is one of the first works in this line of research using the Hill equation, attempted to design a synthetic circuit that mimics Hebbian learning in a neural network architecture. In this article, we carry out indepth computational analysis of the model and demonstrate that the reinforcement effect can be achieved by choosing the proper parameter values. We also construct a novel circuit that can demonstrate forced dissociation, which was not observed in Fernando’s model. Our work can be readily used as reference for synthetic biologists who consider implementing circuits of this kind in biological systems. Full article

Hyperspectral image (HSI) clustering is a challenging task, whose purpose is to assign each pixel to a corresponding cluster. The high-dimensionality and noise corruption are two main problems that limit the performance of HSI clustering. To address those problems, this paper proposes a projected clustering with a spatial–spectral constrained adaptive graph (PCSSCAG) method for HSI clustering. PCSSCAG first constructs an adaptive adjacency graph to capture the accurate local geometric structure of HSI data adaptively. Then, a spatial–spectral constraint is employed to simultaneously explore the spatial and spectral information for reducing the negative influence on graph construction caused by noise. Finally, projection learning is integrated into the spatial–spectral constrained adaptive graph construction for reducing the redundancy and alleviating the computational cost. In addition, an alternating iteration algorithm is designed to solve the proposed model, and its computational complexity is theoretically analyzed. Experiments on two different scales of HSI datasets are conducted to evaluate the performance of PCSSCAG. The associated experimental results demonstrate the superiority of the proposed method for HSI clustering. Full article

In this research, a microfluid-based extended gate field-effect transistor (EGFET) biosensor with an on-chip sensing window (OCSW) was fabricated. The detection window was composed of six metal layers, and a ruthenium dioxide (RuO₂) film was spattered on the surface and functionalized with lactase to detect lactic acid (LA). To detect LA in a more diversified way, a microfluidic system was integrated with the biosensor. Moreover, a special package was used to seal the sensing window and microfluidic tube and insulate it from other parts to prevent water molecule invasion and chip damage. The sensitivity analysis of the EGFET biosensor was studied by a semiconductor parameter analyzer (SPA). The static and dynamic measurements of the EGFET with sensing windows on a chip were analyzed. The sensing characteristics of the EGFET biosensor were verified by the experimental results. The proposed biosensor is suitable for wearable applications due to the advantages of its low weight, low voltage, and simple manufacturing process. Full article

This paper presents a method to monitor the thermal peaks that are major concerns when designing Integrated Circuits (ICs) in various advanced technologies. The method aims at detecting the thermal peak in Systems on Chip (SoC) using arrays of oscillators distributed over the area of the chip. Measured frequencies are mapped to local temperatures that are used to produce a chip thermal mapping. Then, an indication of the local temperature of a single heat source is obtained in real-time using the Gradient Direction Sensor (GDS) technique. The proposed technique does not require external sensors, and it provides a real-time monitoring of thermal peaks. This work is performed with Field-Programmable Gate Array (FPGA), which acts as a System-on-Chip, and the detected heat source is validated with a thermal camera. A maximum error of 0.3 °C is reported between thermal camera and FPGA measurements. Full article

In response to the dangerous behavior of pedestrians roaming freely on unsupervised train tracks, the real-time detection of pedestrians is urgently required to ensure the safety of trains and people. Aiming to improve the low accuracy of railway pedestrian detection, the high missed-detection rate of target pedestrians, and the poor retention of non-redundant boxes, YOLOv5 is adopted as the baseline to improve the effectiveness of pedestrian detection. First of all, L1 regularization is deployed before the BN layer, and the layers with smaller influence factors are removed through sparse training to achieve the effect of model pruning. In the next moment, the context extraction module is applied to the feature extraction network, and the input features are fully extracted using receptive fields of different sizes. In addition, both the context attention module CxAM and the content attention module CnAM are added to the FPN part to correct the target position deviation in the process of feature extraction so that the accuracy of detection can be improved. What is more, DIoU_NMS is employed to replace NMS as the prediction frame screening algorithm to improve the problem of detection target loss in the case of high target coincidence. Experimental results show that compared with YOLOv5, the AP of our YOLOv5-AC model for pedestrians is 95.14%, the recall is 94.22%, and the counting frame rate is 63.1 FPS. Among them, AP and recall increased by 3.78% and 3.92%, respectively, while the detection speed increased by 57.8%. The experimental results verify that our YOLOv5-AC is an effective and accurate method for pedestrian detection in railways. Full article

The essential factors of information-aware systems are heterogeneous multi-sensory devices. Because of the ambiguity and contradicting nature of multi-sensor data, a data-fusion method based on the cloud model and improved evidence theory is proposed. To complete the conversion from quantitative to qualitative data, the cloud model is employed to construct the basic probability assignment (BPA) function of the evidence corresponding to each data source. To address the issue that traditional evidence theory produces results that do not correspond to the facts when fusing conflicting evidence, the three measures of the Jousselme distance, cosine similarity, and the Jaccard coefficient are combined to measure the similarity of the evidence. The Hellinger distance of the interval is used to calculate the credibility of the evidence. The similarity and credibility are combined to improve the evidence, and the fusion is performed according to Dempster’s rule to finally obtain the results. The numerical example results show that the proposed improved evidence theory method has better convergence and focus, and the confidence in the correct proposition is up to 100%. Applying the proposed multi-sensor data-fusion method to early indoor fire detection, the method improves the accuracy by 0.9–6.4% and reduces the false alarm rate by 0.7–10.2% compared with traditional and other improved evidence theories, proving its validity and feasibility, which provides a certain reference value for multi-sensor information fusion. Full article

The Industrial Internet of Things (IIoT) connects industrial assets to ubiquitous smart sensors and actuators to enhance manufacturing and industrial processes. Data-driven condition monitoring is an essential technology for intelligent manufacturing systems to identify anomalies from malfunctioning equipment, prevent unplanned downtime, and reduce the operation costs by predictive maintenance without interrupting normal machine operations. However, data-driven condition monitoring requires massive data collected from smart sensors to be transmitted to the cloud for further processing, thereby contributing to network congestion and affecting the network performance. Furthermore, unbalanced training data with very few labelled anomalies limit supervised learning models because of the lack of sufficient fault data for the training process in anomaly detection algorithms. To address these issues, we proposed an IIoT-based condition monitoring system with an edge-to-cloud architecture and computed the relative wavelet energy as feature vectors on the edge layer to reduce the network traffic overhead. We also proposed an unsupervised deep long short-term memory (LSTM) network module for anomaly detection. We implemented the proposed IIoT condition monitoring system for a manufacturing machine in a real shop site to evaluate our proposed solution. Our experimental results verify the effectiveness of our approach which can not only reduce the network traffic overhead for the IIoT but also detect anomalies accurately. Full article