Electronics, Volume 13, Issue 2 (January-2 2024) – 223 articles

Patient decontamination is the act of removing or neutralising hazardous substances from an affected individual. To ensure adequate emergency preparedness, regulations require hospitals to train personnel in decontamination procedures regularly. To supplement in-person training, a virtual reality (VR) system is being developed for the training of hospital staff members in the mass decontamination of hazardous and toxic materials (HAZMAT) and/or radioactively contaminated casualties. As a demonstration of the concept, a primary VR prototype is designed to help users familiarize themselves with a chemical scanner tool, intended for examining victims for residual chemical hazards. This initial prototype showcases the benefits of using VR to create training simulations, complementing existing decontamination training methods in a secure and cost-effective manner. The proposed approach features a modularized user-centric design, a novel scanning simulation, and a high-realism virtual environment and workflow to enhance training effectiveness. A pilot user study and assessment suggest that new users were able to achieve a significant level of competency with VR, compared to users who underwent traditional training. Full article

The precise detection of small lesions on grape leaves is beneficial for early detection of diseases. In response to the high missed detection rate of small target diseases on grape leaves, this paper adds a new prediction branch and combines an improved channel attention mechanism and an improved E-ELAN (Extended-Efficient Long-range Attention Network) to propose an improved algorithm for the YOLOv7 (You Only Look Once version 7) model. Firstly, to address the issue of low resolution for small targets, a new detection head is added to detect smaller targets. Secondly, in order to increase the feature extraction ability of E-ELAN components in YOLOv7 for small targets, the asymmetric convolution is introduced into E-ELAN to replace the original 3 × 3 convolution in E-ELAN network to achieve multi-scale feature extraction. Then, to address the issue of insufficient extraction of information from small targets in YOLOv7, a channel attention mechanism was introduced and improved to enhance the network’s sensitivity to small-scale targets. Finally, the CIoU (Complete Intersection over Union) in the original YOLOv7 network model was replaced with SIoU (Structured Intersection over Union) to optimize the loss function and enhance the network’s localization ability. In order to verify the effectiveness of the improved YOLOv7 algorithm, three common grape leaf diseases were selected as detection objects to create a dataset for experiments. The results show that the average accuracy of the algorithm proposed in this paper is 2.7% higher than the original YOLOv7 algorithm, reaching 93.5%. Full article

In verifying programs for embedded systems, it is essential to reduce the verification time because state explosion may occur during model checking. One solution is to reduce the number of interrupt handler executions. In particular, when periodic interrupts such as timer interrupts are incorporated, it is necessary to know the physical time. In this paper, we define a control flow automaton (CFA) that can handle time and propose an algorithm based on interrupt handler execution reduction (IHER). The proposed method reduces the number of interrupt executions, including timer interrupts. A case study verified the effectiveness of this algorithm. Full article

Wind power is a crucial direction for new energy transition technology in response to the challenges of global warming. However, the potential for collisions between the blades and the tower barrel remains a significant concern. To address this issue, a large number of sensors, such as lasers and cameras, are attached to the structure, but they struggle to operate in complex weather and at night. This paper presents a method of employing a 79 GHz FMCW (frequency-modulated continuous wave) mmWave (millimeter-wave) radar with circularly polarization on the top of the tower. During the design, two main considerations are raised: (1) Since the small-RCS (radar cross-section) blade experiences an oblique incidence from more than 70 m away, the channel SNR (signal-to-noise ratio) is low, so high-gain antennas and SIMO (single-input multiple-output) radar configurations are designed to increase the P_t (transmitting power). (2) Wind turbines are often located in offshore or mountainous areas with a high level of weather interference, so a pair of circularly polarized antenna is used to reduce the interference of meteorological particles to the radar. Finally, test results from a practical wind turbine in different weather conditions prove its practicality. During tests, the wind turbine operates at a rotor speed of 6 to 12 rounds per minute, and the clearance range has an obvious inverse relationship with it, ranging from 6 to 12 m. This technology enhances safety, maximizes efficiency, and enables optimal length and weight determination during design for improved power generation. Full article

A micro-expression (ME), as a spontaneous facial expression, usually occurs instantaneously and is difficult to disguise after an emotion-evoking event. Numerous convolutional neural network (CNN)-based models have been widely explored to recognize MEs for their strong local feature representation ability on images. However, the main drawback of the current methods is their inability to fully extracting holistic contextual information from ME images. To achieve efficient ME learning representation from diverse perspectives, this paper uses Transformer variants as the main backbone and the dual-branch architecture as the main framework to extract meaningful multi-modal contextual features for ME recognition (MER). The first branch leverages an optical flow operator to facilitate the motion information extraction between ME sequences, and the corresponding optical flow maps are fed into the Swin Transformer to acquire motion–spatial representation. The second branch directly sends the apex frame in one ME clip to Mobile ViT (Vision Transformer), which can capture the local–global features of MEs. More importantly, to achieve the optimal feature stream fusion, a CAB (cross attention block) is designed to interact the feature extracted by each branch for adaptive learning fusion. The extensive experimental comparisons on three publicly available ME benchmarks show that the proposed method outperforms the existing MER methods and achieves an accuracy of 81.6% on the combined database. Full article

All kinds of vessels consist of dozens of complex machineries with rotating parts and electric motors that operate continuously in harsh environments with excess temperature, humidity, vibration, fatigue, and load. A breakdown or malfunction in one of these machineries can significantly impact a vessel’s operation and safety and, consequently, the safety of the crew and the environment. To maintain operational efficiency and seaworthiness, the shipping industry invests substantial resources in preventive maintenance and repairs. This study presents the economic and technical benefits of predictive maintenance over traditional preventive maintenance and repair by replacement approaches in the maritime domain. By leveraging modern technology and artificial intelligence, we can analyze the operating conditions of machinery by obtaining measurements either from sensors permanently installed on the machinery or by utilizing portable measuring instruments. This facilitates the early identification of potential damage, thereby enabling efficient strategizing for future maintenance and repair endeavors. In this paper, we propose and develop a convolutional neural network that is fed with raw vibration measurements acquired in a laboratory environment from the ball bearings of a motor. Then, we investigate whether the proposed network can accurately detect the functional state of ball bearings and categorize any possible failures present, contributing to improved maintenance practices in the shipping industry. Full article

Deep-learning-based breast cancer image diagnosis is currently a prominent and growingly popular area of research. Existing convolutional-neural-network-related methods mainly capture breast cancer image features based on spatial domain characteristics for classification. However, according to digital signal processing theory, texture images usually contain repeated patterns and structures, which appear as intense energy at specific frequencies in the frequency domain. Motivated by this, we make an attempt to explore a breast cancer histopathology classification application in the frequency domain and further propose a novel multi-branch spectral channel attention network, i.e., the MbsCANet. It expands the interaction of frequency domain attention mechanisms from a multi-branch perspective via combining the lowest frequency features with selected high frequency information from two-dimensional discrete cosine transform, thus preventing the loss of phase information and gaining richer context information for classification. We thoroughly evaluate and analyze the MbsCANet on the publicly accessible BreakHis breast cancer histopathology dataset. It respectively achieves the optimal image-level and patient-level classification results of 99.01% and 98.87%, averagely outperforming the spatial-domain-dominated models by a large margin, and visualization results also demonstrate the effectiveness of the MbsCANet for this medical image application. Full article

IEEE 1588, also known as the Precision Time Protocol (PTP), is a standard protocol for clock synchronization in distributed systems. While it is not architecture-specific, implementing IEEE 1588 on Reduced Instruction Set Computer-V (RISC-V) low-power embedded devices demands considering the system requirements and available resources. This paper explores various approaches and techniques to achieve accurate time synchronization in such instruments. The analysis covers software and hardware implementations, discussing each method’s challenges, benefits, and trade-offs. By examining the state-of-the-art in this field, this paper provides valuable insights and guidance for researchers and engineers working on time-critical applications in RISC-V-based embedded systems, aiding in selecting the most-suitable stack for their designs. Full article

Reducing the impact of underwater disturbance targets and improving the ability to recognize real moving targets underwater are important directions of active sonar research. In this paper, the highlight model of underwater targets was improved and a method was proposed to acquire highlight images of the echoes of these targets. A classification convolutional neural network called HasNet-5 was designed to extract the global features and local highlight features of the echo highlight images of underwater targets, which achieved the true/false recognition of targets via multi-classification. Five types of target highlight models were used to generate simulation data to complete the training, validation and testing of the network. Tests were performed using experimental data. The results indicate that the proposed method achieves 92% accuracy in real target recognition and 94% accuracy in two-dimensional disturbance target recognition. This study provides a new approach for underwater target recognition using active sonar. Full article

Cross -project defect prediction (CPDP) is a promising technical means to solve the problem of insufficient training data in software defect prediction. As a special case of CPDP, heterogeneous defect prediction (HDP) has received increasing attention in recent years due to its ability to cope with different metric sets in projects. Existing studies have proven that using mixed-project data is a potential way to improve HDP performance, but there remain several challenges, including the negative impact of noise modules and the insufficient utilization of unlabeled modules. To this end, we propose a landmark-based domain adaptation and selective pseudo-labeling (LDASP) approach for mixed-project HDP. Specifically, we propose a novel landmark-based domain adaptation algorithm considering marginal and conditional distribution alignment and a class-wise locality structure to reduce the heterogeneity between both projects while reweighting modules to alleviate the negative impact brought by noise ones. Moreover, we design a progressive pseudo-label selection strategy exploring the underlying discriminative information of unlabeled target data to further improve the prediction effect. Extensive experiments are conducted based on 530 heterogeneous prediction combinations that are built from 27 projects using four datasets. The experimental results show that (1) our approach improves the F1-score and AUC over the baselines by 9.8–20.2% and 4.8–14.4%, respectively and (2) each component of LDASP (i.e., the landmark weights and selective pseudo-labeling strategy) can promote the HDP performance effectively. Full article

In response to the shortcomings of the traditional A-star algorithm, such as excessive node traversal, long search time, unsmooth path, close proximity to obstacles, and applicability only to static maps, a path planning method that integrates an adaptive A-star algorithm and an improved Dynamic Window Approach (DWA) is proposed. Firstly, an adaptive weight value is added to the heuristic function of the A-star algorithm, and the Douglas–Pucker thinning algorithm is introduced to eliminate redundant points. Secondly, a trajectory point estimation function is added to the evaluation function of the DWA algorithm, and the path is optimized for smoothness based on the B-spline curve method. Finally, the adaptive A-star algorithm and the improved DWA algorithm are integrated into the fusion algorithm of this article. The feasibility and effectiveness of the fusion algorithm are verified through obstacle avoidance experiments in both simulation and real environments. Full article

The continuous advancement of electronic technology has led to the gradual integration of automated intelligent devices into various aspects of human life. Motion gesture-based human–computer interaction systems offer abundant information, user-friendly functionalities, and visual cues. Surface electromyography (sEMG) signals enable the decoding of muscle movements, facilitating the realization of corresponding control functions. Considering the inherent instability and minuscule nature of sEMG signals, this thesis proposes the integration of a dynamic time regularization algorithm to enhance gesture recognition detection accuracy and real-time system performance. The application of the dynamic time warping algorithm allows the fusion of three sEMG signals, enabling for the calculation of similarity between the sample and the model. This process facilitates gesture recognition and ensures effective communication between individuals and the 3D printed prosthesis. Utilizing this algorithm, the best feature model was generated by amalgamating six types of gesture classification model. A total of 600 training and evaluation experiments were performed, with each movement recognized 100 times. The experimental tests demonstrate that the accuracy of gesture recognition and prosthetic limb control using the temporal dynamic regularization algorithm achieves an impressive 93.75%, surpassing the performance of the traditional threshold control switch. Full article

Based on the original deep network architecture, this paper replaces the deep integrated network by integrating shallow FastText, a bidirectional gated recurrent unit (GRU) network and the convolutional neural networks (CNNs). In FastText, word embedding, 2-grams and 3-grams are combined to extract text features. In recurrent neural networks (RNNs), a bidirectional GRU network is used to lessen information loss during the process of transmission. In CNNs, text features are extracted using various convolutional kernel sizes. Additionally, three optimization algorithms are utilized to improve the classification capabilities of each network architecture. The experimental findings using the social network news dataset demonstrate that the integrated model is effective in improving the accuracy of text classification. Full article

In pursuit of advancing fault diagnosis in electromechanical systems, this research focusses on vibration analysis through innovative techniques. The study unfolds in a structured manner, beginning with an introduction that situates the research question in a broader context, emphasising the critical role of fault diagnosis. Subsequently, the methods section offers a concise summary of the primary techniques employed, highlighting the utilisation of short-time Fourier transform (STFT) and continuous wavelet transform (CWT) for extracting time–frequency components from the signal. The results section succinctly summarises the main findings of the article, showcasing the results of features extraction by CWT and subsequently utilising a convolutional neural network (CNN) for fault diagnosis. The proposed method, named CWTx6-CNN, was compared with the STFTx6-CNN method of the previous stage of the investigation. Visual insights into the time–frequency characteristics of the inertial measurement unit (IMU) data are presented for various operational classes, offering a clear representation of fault-related features. Finally, the conclusion section underscores the advantages of the suggested method, particularly the concentration of single-frequency components for enhanced fault representation. The research demonstrates commendable classification performance, highlighting the efficiency of the suggested approach in real-time scenarios of fault analysis in less than 50 ms. Calculation by CWT with a complex Morlet wavelet of six time–frequency images and combining them into a single colour image took less than 35 ms. In this study, interpretability techniques have been employed to address the imperative need for transparency in intricate neural network models, particularly in the context of the case presented. Notably, techniques such as Grad-CAM (gradient-weighted class activation mapping), occlusion, and LIME (locally interpretable model-agnostic explanation) have proven instrumental in elucidating the inner workings of the model. Through a comparative analysis of the proposed CWTx6-CNN method and the reference STFTx6-CNN method, the application of interpretability techniques, including Grad-CAM, occlusion, and LIME, has played a pivotal role in revealing the distinctive spectral representations of these methodologies. Full article

In this paper, we propose an optimized device structure to address issues in 3D NAND flash memory devices, which encounter difficulties when using the hole erase method due to the unfavorable hole characteristics of indium gallium zinc oxide (IGZO). The proposed structure mitigated the erase operation problem caused by the low hole mobility of IGZO by introducing a filler inside the IGZO channel. It facilitated the injection of holes into the IGZO channel through the filler, while the existing P-type doped polysilicon filler material was replaced by a P-type oxide semiconductor. In contrast to polysilicon (band gap: 1.1 eV), this P-type oxide semiconductor has a band gap similar to that of the IGZO channel (2.5 to 3.0 eV). Consequently, it was confirmed through device simulation that there was no barrier due to the difference in band gaps, enabling the seamless supply of holes to the IGZO channel. Based on these results, we conducted a simulation to determine the optimal parameters for the P-type oxide semiconductor to be used as a filler, demonstrating improved erase operation when the P-type carrier density was 10¹⁹ cm⁻³ or higher and the band gap was 3.0 eV or higher. Full article

The ZX Spectrum was a popular 8-bit home computer by Sinclair Research in the 1980s. Even though some of these computers may still work, the audio tapes, the TV with an analog tuner, and the micro-switch joystick that were used with the original ZX Spectrum are outdated and hard to find in good working order or to replicate. As many other old closed systems are also very difficult to update to support modern peripherals there is a necessity to provide a methodology to adapt such systems to support new peripherals while being compatible with existing software. This implementation is a means by which to validate the methodology before applying it to a physical system. The work proposed in this paper focused on recreating a ZX Spectrum+/48K computer and interfacing it with modern peripherals on an FPGA. This was accomplished by adding a co-processor to assist with the control of the more complex peripherals. Otherwise, the original system would require complex architectural changes and would perform poorly due to the low performance of the Z80 CPU. This work distanced itself from previous works on emulating a ZX Spectrum, as it focused on the use of different upgraded peripherals and the use of a NIOS II soft processor as a co-processor to manage the SD card accesses and save-state functionality. A demonstration of the proposed modernized architecture was made by successfully running a diagnostics ROM and playing original ZX Spectrum games from an SD card for games with a PS/2 keyboard and a pair of joysticks. Full article

In the process of vehicles transitioning from conventional means of transportation to mobile computing platforms, ensuring secure communication and data exchange is of paramount importance. Consequently, identity authentication has emerged as a crucial security measure. Specifically, effective authentication is required prior to the communication between the On-Board Unit (OBU) and Roadside Unit (RSU). To address vehicle identity authentication challenges in the Internet of Vehicles (VANETs), this paper proposes a three-party identity authentication and key agreement protocol based on elliptic curve public key cryptography. Considering issues such as vehicle impersonation attacks, RSU impersonation attacks, and vehicle privacy breaches in existing schemes within wireless mobile environments, this protocol introduces a trusted registry center that successfully enables mutual authentication between OBU and RSU. The proposed protocol not only enhances the VANETs system’s ability to withstand security threats but also improves the credibility and efficiency of the authentication process. Full article

3D (Three-Dimensional) scene inpainting aims to remove objects from scenes and generate visually plausible regions to fill the hollows. Leveraging the foundation of NeRF (Neural Radiance Field), considerable advancements have been achieved in the realm of 3D scene inpainting. However, prevalent issues persist: primarily, the presence of inconsistent 3D details across different viewpoints and occlusion losses of real background details in inpainted regions. This paper presents a NeRF-based inpainting approach using uncertainty estimation that formulates mask and uncertainty branches for consistency enhancement. In the initial training, the mask branch learns a 3D-consistent representation from inaccurate input masks, and after background rendering, the background regions can be fully exposed to the views. The uncertainty branch learns the visibility of spatial points by modeling them as Gaussian distributions, generating variances to identify regions to be inpainted. During the inpainting training phase, the uncertainty branch measures 3D consistency in the inpainted views and calculates the confidence from the variance as dynamic weights, which are used to balance the color and adversarial losses to achieve 3D-consistent inpainting with both the structure and texture. The results were evaluated on datasets such as Spin-NeRF and NeRF-Object-Removal. The proposed approach outperformed the baselines in inpainting metrics of LPIPS and FID, and preserved more spatial details from real backgrounds in multi-scene settings, thus achieving 3D-consistent restoration. Full article

With the support of deep neural networks, the existing image manipulation detection (IMD) methods can detect manipulated regions within a suspicious image effectively. In general, manipulation operations (e.g., splicing, copy-move, and removal) tend to leave manipulation artifacts in the high-frequency domain of the image, which provides rich clues for locating manipulated regions. Inspired by this phenomenon, in this paper, we propose a High-Frequency Component Enhancement Network, short for HFCE-Net, for image manipulation detection, which aims to fully explore the manipulation artifacts left in the high-frequency domain to improve the localization performance in IMD tasks. Specifically, the HFCE-Net consists of two parallel branches, i.e., the main stream and high-frequency auxiliary branch (HFAB). The HFAB is introduced to fully explore high-frequency artifacts within manipulated images. To achieve this goal, the input image of the HFAB is filtered out of the low-frequency component by the Sobel filter. Furthermore, the HFEB is supervised with the edge information of the manipulated regions. The main stream branch takes the RGB image as input, and aggregates the features learned from the HFAB by the proposed multi-layer fusion (MLF) in a hierarchical manner. We conduct extensive experiments on widely used benchmarks, and the results demonstrate that our HFCE-Net exhibits a strong ability to capture high-frequency information within the manipulated image. Moreover, the proposed HFCE-Net achieves comparable performance (57.3%, 90.9%, and 73.8% F1 on CASIA, NIST, and Coverage datasets) and achieves 1.9%, 9.0%, and 1.5% improvement over the existing method. Full article

Series-cascaded microgrids (SCMGs) indeed provide control flexibility and high-voltage synthesis capabilities. However, the power distribution in SCMGs based on distributed generation (DG) sources stays understudied. This paper proposes an SCMG topology using non-dispatchable DG sources and battery energy storage, with an integrated power-routing control. The objective is to address power distribution limitations and stabilize SCMG output voltages under varying conditions. A case study validates the control methodology, considering zero irradiation levels for photovoltaic (PV) and maximum power sharing. The battery modules play a crucial role by providing power, voltage support, and maintaining capacitor voltage at a reference value of a PV-integrated module. This is achieved through a third harmonic current injection in the fundamental frequency current, coupled with proportional power distribution using a third harmonic power signal. The effectiveness of the proposed SCMG topology and control is demonstrated through MATLAB/Simulink and hardware-in-loop analyses (Typhoon HIL). The results present an extended power distribution between series-cascaded DG sources-based units while ensuring stable SCMG output voltages, even in adverse conditions like PV module intermittency. Future work aims to extend the proposed topology to a ring/delta-connection SCMG, where third harmonic current aids power distribution among SCMG legs and between series-cascaded DG sources-based units. Full article

Active front-end (AFE) rectifiers have become widely employed in power systems to achieve unity power factor and harmonic mitigations. The typical modeling approaches applied for AFE rectifiers in the literature mostly relied on two baselines: the detailed model and the time-average model. The former approach deals with the switching element model (SEM), which leads to significant harmonics in currents with distorted waveforms. The latter approach uses the average-value model (AVM) to overcome the currents’ harmonics as well as provide fast responses. However, even the AVM baseline has shown problems during the starting stage (lack of control signals) and over the dead-time periods, which causes serious issues in the implementation process. This paper presents an improved dynamic AVM for AFE rectifiers by precisely considering the issues mentioned above, along with the practical starting procedure and desirable initialization. The studied AFE rectifier is developed using the voltage-oriented control (VOC) technique based on the different modeling methodologies, including SEM, Conventional AVM, and the proposed AVM. The performance of all models is analyzed and compared using simulation results with MATLAB/Simulink R2023a Function blocks for all the algorithm parts and SimScape elements for the electrical circuit model. The simulation results illustrate that the performance of the proposed AVM approach can closely resemble the behavior of the SEM baseline with low harmonic distortion. To evaluate the performance of the proposed model, several case studies are investigated to verify the AFE rectifier operation, regarding mostly the total harmonic distortion (THD) wherein the THD percentages are improved to 4.78 and 2.5 from 5.14 and 2.78 for low- and high-power loads, respectively. Full article

Compared with traditional anomaly analysis, intelligent connected vehicle (ICV) data validity analysis is faced with a variety of data anomalies, including sensor anomalies, driving behavior anomalies, malicious tampering, and so on, which eventually leads to anomalies in the data. How to integrate the vehicle moving characteristics, driving style, and traffic flow conditions to provide an effective data detection method has become a new problem in the field of intelligent networked vehicles. Based on ICV data, a particle swarm optimization data validity detection algorithm (TE-PSO-SVM) was proposed by combining driving style and traffic flow theory to realize the effective detection of driving data. In addition, aiming at the problem of mixed types of anomalies in complex scenes, a model pool is constructed, and a model selection algorithm based on reinforcement learning (RLBMS) is proposed. Experiments on the real data set HighD show that RLBMS has a better detection effect in complex scenes of mixed types of anomalies. Full article

Multispectral object detection is a crucial technology in remote sensing image processing, particularly in low-light environments. Most current methods extract features at a single scale, resulting in the fusion of invalid features and the failure to detect small objects. To address these issues, we propose a multispectral object detection network based on multilevel feature fusion and dual feature modulation (GMD-YOLO). Firstly, a novel dual-channel CSPDarknet53 network is used to extract deep features from visible-infrared images. This network incorporates a Ghost module, which generates additional feature maps through a series of linear operations, achieving a balance between accuracy and speed. Secondly, the multilevel feature fusion (MLF) module is designed to utilize cross-modal information through the construction of hierarchical residual connections. This approach strengthens the complementarity between different modalities, allowing the network to improve multiscale representation capabilities at a more refined granularity level. Finally, a dual feature modulation (DFM) decoupling head is introduced to enhance small object detection. This decoupled head effectively meets the distinct requirements of classification and localization tasks. GMD-YOLO is validated on three public visible-infrared datasets: DroneVehicle, KAIST, and LLVIP. DroneVehicle and LLVIP achieved [email protected] of 78.0% and 98.0%, outperforming baseline methods by 3.6% and 4.4%, respectively. KAIST exhibited an MR of 7.73% with an FPS of 61.7. Experimental results demonstrated that our method surpasses existing advanced methods and exhibits strong robustness. Full article

Multi-person pose tracking is a challenging task. It requires identifying the human poses in each frame and matching them across time. This task still faces two main challenges. Firstly, sudden camera zooming and drastic pose changes between adjacent frames may result in mismatched poses between them. Secondly, the time relationships modeled by most existing methods provide insufficient information in scenarios with long-term occlusion. In this paper, to address the first challenge, we propagate the bounding boxes of the current frame to the previous frame for pose estimation, and match the estimated results with the previous ones, which we call the Backward Temporal Pose-Matching (BTPM) module. To solve the second challenge, we design an Association Across Multiple Frames (AAMF) module that utilizes long-term temporal relationships to supplement tracking information lost in the previous frames as a Re-identification (Re-id) technique. Specifically, we select keyframes with a fixed step size in the videos and label other frames as general frames. In the keyframes, we use the BTPM module and the AAMF module to perform tracking. In the general frames, we propagate poses in the previous frame to the current frame for pose estimation and association, which we call the Forward Temporal Pose-Matching (FTPM) module. If the pose association fails, the current frame will be set as a keyframe, and tracking will be re-performed. In the PoseTrack 2018 benchmark tests, our method shows significant improvements over the baseline methods, with improvements of 2.1 and 1.1 in mean Average Precision (mAP) and Multi-Object Tracking Accuracy (MOTA), respectively. Full article

The article focuses on the use of short-time Fourier transform (STFT) to detect the unbalance of a drive with a flexible connection between the driving machine and the load. The authors present the unbalance model and justify, through subsequent experiments, why the STFT-based approach is appropriate. The effectiveness of the presented method of analyzing signals from acceleration sensors was confirmed experimentally by designing an artificial neural network for detecting the unbalance. Full article

This paper displays a voltage-controlled oscillator (VCO) with high performance implemented in 0.18 µm CMOS. The proposed CMOS VCO adopts a current-reused method, analog coarse and fine tuning mechanisms, and an adaptive overdrive voltage control structure to increase the overall performance, such as the power dissipation, phase noise, and tuning range, and has a robust start-up condition. The current-reused complementary structure with higher transistor transconductances is to save power consumption; the analog coarse and fine tuning mechanisms are to effectively widen the tuning range; and the adaptive overdrive voltage control technique is to change the transconductances of the transistors to improve power consumption by reasonably biasing the gate and body terminals in a class-AB mode to adjust the threshold voltage of the NMOS transistors. The proposed CMOS VCO adopts the class-AB mode to improve the overall performance and the start-up condition. The figure-of-merit (FOM) and FOM with tuning range (FOM_T) are used in evaluating the CMOS VCO performance. The measured phase noise at 1 MHz and 10 MHz offsets is –130.34 dBc/Hz and –150.96 dBc/Hz at the 3.38 GHz operating frequency, respectively. The proposed CMOS VCO has a tuning range between 2.85 and 3.62 GHz corresponding to 23.8% for the fifth-generation (5G) wireless communication applications. The proposed CMOS VCO core using a 1.4-V supply consumes 7.5 mW DC power. The FOMs and FOM_Ts at 1- and 10-MHz offsets are −192.2, −192.8, −199.7, and −200.3 dBc/Hz, respectively, from the 3.38 GHz output frequency. Full article

A quantum Pauli noise is a nonunitary process that alters the state of a qubit by random application of the four Pauli operators. We investigate a four-qubit quantum circuit, consisting of a pipeline of three independently controlled Pauli gates, for simulating the general class of qubit Pauli noises. The circuit with a fixed architecture is controllable by three separable quantum states from three auxiliary qubits in order to adjust the parameters of the targeted Pauli noise on the principal qubit. Important Pauli noises such as bit flip, phase flip, bit phase flip, and depolarizing noise are readily simulated, along with an infinite subset of other Pauli noises. However, the quantum circuit with its simple and fixed architecture cannot simulate all conceivable Pauli noises, and a characterization is proposed, in the parameter space of the Pauli noises, denoting those that are simulable by the circuit and those that are not. The circuit is a useful tool to contribute to controlled simulation, on current or future quantum processors, of nonunitary processes of noise and decoherence. Full article

In the era of Industry 4.0 and beyond, ball bearings remain an important part of industrial systems. The failure of ball bearings can lead to plant downtime, inefficient operations, and significant maintenance expenses. Although conventional preventive maintenance mechanisms like time-based maintenance, routine inspections, and manual data analysis provide a certain level of fault prevention, they are often reactive, time-consuming, and imprecise. On the other hand, machine learning algorithms can detect anomalies early, process vast amounts of data, continuously improve in almost real time, and, in turn, significantly enhance the efficiency of modern industrial systems. In this work, we compare different machine learning and deep learning techniques to optimise the predictive maintenance of ball bearing systems, which, in turn, will reduce the downtime and improve the efficiency of current and future industrial systems. For this purpose, we evaluate and compare classification algorithms like Logistic Regression and Support Vector Machine, as well as ensemble algorithms like Random Forest and Extreme Gradient Boost. We also explore and evaluate long short-term memory, which is a type of recurrent neural network. We assess and compare these models in terms of their accuracy, precision, recall, F1 scores, and computation requirement. Our comparison results indicate that Extreme Gradient Boost gives the best trade-off in terms of overall performance and computation time. For a dataset of 2155 vibration signals, Extreme Gradient Boost gives an accuracy of 96.61% while requiring a training time of only 0.76 s. Moreover, among the techniques that give an accuracy greater than 80%, Extreme Gradient Boost also gives the best accuracy-to-computation-time ratio. Full article

Recently, a data-driven approach has been widely used at various stages of the system development lifecycle thanks to its ability to extract knowledge from historical data. However, despite its superiority over other conventional approaches, e.g., approaches that are model-based and signal-based, the availability of representative datasets poses a major challenge. Therefore, for various engineering applications, new solutions to generate representative faulty data that reflect the real world operating conditions should be explored. In this study, a novel approach based on a hardware-in-the-loop (HIL) simulation and automated real-time fault injection (FI) method is proposed to generate, analyse and collect data samples in the presence of single and concurrent faults. The generated dataset is employed for the development of machine learning (ML)-assisted test strategies during the system verification and validation phases of the V-cycle development model. The developed framework can generate not only time series data but also a textual data including fault logs in an automated manner. As a case study, a high-fidelity simulation model of a gasoline engine system with a dynamic entire vehicle model is utilised to demonstrate the capabilities and benefits of the proposed framework. The results reveal the applicability of the proposed framework in simulating and capturing the system behaviour in the presence of faults occurring within the system’s components. Furthermore, the effectiveness of the proposed framework in analysing system behaviour and acquiring data during the validation phase of real-time systems under realistic operating conditions has been demonstrated. Full article

In the field of remote sensing image segmentation, achieving high accuracy and efficiency in diverse and complex environments remains a challenge. Additionally, there is a notable imbalance between the underlying features and the high-level semantic information embedded within remote sensing images, and both global and local recognition improvements are also limited by the multi-scale remote sensing scenery and imbalanced class distribution. These challenges are further compounded by inaccurate local localization segmentation and the oversight of small-scale features. To achieve balance between visual space and semantic space, to increase both global and local recognition accuracy, and to enhance the flexibility of input scale features while supplementing global contextual information, in this paper, we propose a U-shaped hierarchical structure called ResU-Former. The incorporation of the Swin Residual Transformer block allows for the efficient segmentation of objects of varying sizes against complex backgrounds, a common scenario in remote sensing datasets. With the specially designed Swin Residual Transformer block as its fundamental unit, ResU-Former accomplishes the full utilization and evolution of information, and the maximum optimization of semantic segmentation in complex remote sensing scenarios. The standard experimental results on benchmark datasets such as Vaihingen, Overall Accuracy of 81.5%, etc., show the ResU-Former’s potential to improve segmentation tasks across various remote sensing applications. Full article