Electronics, Volume 13, Issue 9 (May-1 2024) – 195 articles

Remote passive sonar detection with underwater acoustic vector sensor (UAVS) has attracted increasing attention due to its merit in measuring the full sound field information. However, the accurate estimation of the direction-of-arrival (DOA) remains a challenging problem, especially under low signal-to-noise ratio (SNR) conditions. In this paper, a novel convolution (COV)-based single-vector acoustic preprocessing method is proposed on the basis of the single-vector acoustic preprocessing model. In view of the theoretical analysis of the classical single-vector acoustic DOA estimation method, the principle of preprocessing can be described as “to achieve an improved denoising performance in the constraint of equivalent amplitude gain and phase response.” This can be naturally guaranteed by our proposed COV method. In addition, the upper bound with matched filtering (MF) preprocessing is provided in the consideration of the optimal linear signal processing for weak signal detection under Gaussian noise. Numerical analyses demonstrate the effectiveness of our proposed preprocessing method with both vector array signal processing-based and intensity-based methods. Experimental verification conducted in South China Sea further verifies the effectiveness of our approach for practical applications. This work can lay a solid foundation in improving underwater remote vector acoustic DOA estimation under low SNR, and can provide important guidance for future research work. Full article

This experimental study investigates the damage effects of nanosecond pulse laser irradiation on silicon solar cells. It encompasses the analysis of transient pulse signal waveform characteristics at the cells’ output and changes in electrical parameters, such as I–V curves before and after laser irradiation under varying laser fluence and background light intensities, and explores the underlying action mechanisms of laser irradiation. The study reveals that as the laser fluence increases up to 4.0 J/cm², the peak value of the transient pulse signal increases by 47.5%, while the pulse width augments by 88.2% compared to the initial transient pulse signal. Furthermore, certain parameters, such as open-circuit voltage, short-circuit current, and peak power obtained, from the measured I–V curve indicate a threshold laser fluence for functional degradation of the solar cell at approximately 1.18 ± 0.42 J/cm². Results obtained from laser irradiation under different background light intensities underscore the significant influence of background light on laser irradiation of silicon cells, with the most severe damage occurring in the absence of light. Moreover, findings from laser irradiation at multiple locations on the silicon cell demonstrate a linear decrease in the output voltage of the silicon cell with an increase in the number of irradiation points. Full article

For hybrid direct sequence/frequency hopping (DS/FH) spread spectrum signals, even if the relative motion speed between the transmitter and receiver remains constant, the Doppler frequency will vary due to the continuous hopping of the carrier frequency. Under high dynamic conditions, the first-order and second-order change rates of the Doppler frequency attached to the received signal further increase the Doppler frequency agility, making it difficult for the carrier tracking loop to maintain steady-state tracking. To address these issues, a high dynamic velocity locked loop (HD-VLL) is proposed in this paper. Specifically, the accumulated phase tracking error caused by acceleration and jerk is first analyzed. Subsequently, to compensate for this phase tracking error with the system clock, the proposed loop adds an acceleration compensation module and a jerk compensation module. However, this results in the output of the high dynamic loop filter being updated with the system clock, which contradicts the multiplexing design of a traditional loop filter for parallel signal processing, making the hardware implementation of an HD-VLL impractical. Therefore, this contradiction leads us to design an HD-VLL-based multi-carrier NCO (HD-VLL-NCO). The HD-VLL and HD-VLL-NCO are simulated, revealing the HD-VLL’s superior dynamic adaptability and steady-state tracking, while the HD-VLL-NCO achieves comparable accuracy with the appropriate truncation bit width. Full article

In this paper, a W-band waveguide bandpass filter with a standard fourth-order Chebyshev response is proposed based on the computer numerical control (CNC)-milling technology. The harmonics-staggered technique and orthogonal coupling method are incorporated into this waveguide filter design without increasing the complexity of the filter structure in order to suppress the intrinsic spurious responses near the passband. Furthermore, the proposed filter design maintains a simple construction, which can be conveniently fabricated using CNC milling. The fabricated waveguide filter exhibits an average insertion loss of 0.9 dB and a return loss of above 20 dB in a 3 dB fractional bandwidth (FBW) of 5.5% centered at 85 GHz. The excellent spurious suppression property can reach better than −25 dB up to 165 GHz. The wide stopband performance of the proposed W-band filter is very competitive compared with the reported waveguide filters. Full article

With the construction and development of the smart grid, the power business puts higher requirements on the communication capability of the network. In order to improve the energy efficiency of the space–air–ground-integrated power three-dimensional fusion communication network, we establish an optimization problem for joint air platform (AP) flight path selection, ground power facility (GPF) association, and power control. In solving the problem, we decompose the problem into two subproblems, one is the AP flight path selection subproblem and the other is the GPF association and power control subproblem. Firstly, based on the GPF distribution and throughput weights, we model the AP flight path selection subproblem as a Markov Decision Process (MDP) and propose a multi-agent iterative optimization algorithm based on the comprehensive judgment of GPF positions and workload. Secondly, we model the GPF association and power control subproblem as a multi-agent, time-varying K-armed bandit model and propose an algorithm based on multi-agent Temporal Difference (TD) learning. Then, by alternately iterating between the two subproblems, we propose a reinforcement learning (RL)-based joint optimization algorithm. Finally, the simulation results indicate that compared to the three baseline algorithms (random path, average transmit power, and random device association), the proposed algorithm improves an overall energy efficiency of the system of 16.23%, 86.29%, and 5.11% under various conditions (including different noise power levels, GPF bandwidth, and GPF quantities), respectively. Full article

This study aims to evaluate leg movement by integrating gait analysis with surface electromyography (sEMG) and accelerometer (ACC) data from the lower limbs. We employed a wireless, self-made, and multi-channel measurement system in combination with commercial GaitUp Physilog^® 5 shoe-worn inertial sensors to record the walking patterns and muscle activations of 17 participants. This approach generated a comprehensive dataset comprising 1452 samples. To accurately predict gait parameters, a machine learning model was developed using features extracted from the sEMG signals of thigh and calf muscles, and ACCs from both legs. The study utilized evaluation metrics including accuracy (R²), Pearson correlation coefficient (PCC), root mean squared error (RMSE), mean absolute percentage error (MAPE), mean squared error (MSE), and mean absolute error (MAE) to evaluate the performance of the proposed model. The results highlighted the superiority of the CatBoost model over alternatives like XGBoost and Decision Trees. The CatBoost’s average PCCs for 17 temporospatial gait parameters of the left and right legs are 0.878 ± 0.169 and 0.921 ± 0.047, respectively, with MSE of 7.65, RMSE of 1.48, MAE of 1.00, MAPE of 0.03, and Accuracy (R²-Score) of 0.91. This research marks a significant advancement by providing a more comprehensive method for detecting and analyzing gait statuses. Full article

In this paper, a novel weighted block sparse method based on the signal subspace is proposed to realize the Direction-of-Arrival (DOA) estimation under unknown mutual coupling in the uniform linear array. Firstly, the signal subspace is obtained by decomposing the eigenvalues of the sampling covariance matrix. Then, a block sparse model is established based on the deformation of the product of the mutual coupling matrix and the steering vector. Secondly, a suitable set of weighted coefficients is calculated to enhance sparsity. Finally, the optimization problem is transformed into a second-order cone (SOC) problem and solved. Compared with other algorithms, the simulation results of this paper have better performance on DOA accuracy estimation. Full article

The wheel–rail adhesion is one of the key factors limiting the traction performance of railway vehicles. To meet the adhesion optimization needs and rapidly obtain wheel–rail creep characteristics under specific operating conditions, an engineering identification method for wheel–rail adhesion characteristics based on a nonlinear model is proposed. The proposed method, built upon the traditional Teaching-Learning-Based Optimization (TLBO) algorithm, has been adapted to the specific nature of nonlinear wheel–rail adhesion model parameters identification, enhancing both the search speed in the early stages and the search accuracy in the later stages of the algorithm. The proposed identification algorithm is validated using experimental data from the South African 22E dual-flow locomotive. The validation results demonstrate that the proposed identification algorithm can obtain a nonlinear wheel–rail adhesion characteristics model with an average adhesion coefficient error of around 0.01 within 50 iteration steps. These validation results indicate promising prospects for the engineering practice of the proposed algorithm. Full article

In recent years, multi-view graph clustering algorithms based on representations learning have received extensive attention. However, existing algorithms are still limited in two main aspects, first, most algorithms employ graph convolution networks to learn the local representations, but the presence of high-frequency noise in these representations limits the clustering performance. Second, in the process of constructing a global representation based on the local representations, most algorithms focus on the consistency of each view while ignoring complementarity, resulting in lower representation quality. To address the aforementioned issues, a local-global representation enhancement for multi-view graph clustering algorithm is proposed in this paper. First, the low-frequency signals in the local representations are enhanced by a low-pass graph encoder, which yields smoother and more suitable local representations for clustering. Second, by introducing an attention mechanism, the local embedded representations of each view can be weighted and fused to obtain a global representation. Finally, to enhance the quality of the global representation, it is jointly optimized using the neighborhood contrastive loss and reconstruction loss. The final clustering results are obtained by applying the k-means algorithm to the global representation. A wealth of experiments have validated the effectiveness and robustness of the proposed algorithm. Full article

A novel 3D auto-drum machine system for the generation and recording of percussion sounds is developed and presented. The capabilities of the machine, along with a calibration, sound production, and collection protocol are demonstrated. The sounds are generated by a drumstick at pre-defined positions and by known impact forces from the programmable 3D auto-drum machine. The generated percussion sounds are accompanied by the spatial excitation coordinates and the correspondent impact forces, allowing for large databases to be built, which are required by machine learning models. The recordings of the radiated sound by a microphone are analyzed using a pre-trained deep learning model, evaluating the consistency of the physical sample generation method. The results demonstrate the ability to perform regression and classification tasks when fine tuning the deep learning model with the gathered data. The produced databases can properly train machine learning models, aiding in the investigation of alternative and cost-effective materials and geometries with relevant sound characteristics and in the development of accurate vibroacoustic numerical models for studying percussion instruments sound synthesis. Full article

In the great majority of cases, the design of resonant photoacoustic cells is based on the use of resonators excited at the frequencies of their main resonances. This work presents a solution in which the use of a multi-cavity structure with the appropriate selection of the mechanical parameters of the cavities and the interconnecting ducts allows for the shaping of the frequency response of the cell. Such solutions may be particularly useful when the purpose of the designed cells is operation at multiple frequencies, e.g., in applications with the simultaneous detection of multiple gaseous compounds. The concept is tested with cells made using 3D printing technology. The measured frequency responses of the tested cells show very good agreement with the simulation results. This allows for an approach in which the development of a cell with the desired frequency response can be initially based on modeling, without the need for the time-consuming and expensive process of manufacturing and measuring numerous modifications of the cell. Full article

In the DC-6 GHz band, low-insertion-loss packaging materials were investigated to effectively reduce the heat generated during the working process of the attenuation chip. Based on the working principle of the attenuation chip, when the signal passes through the attenuation chip resistor network, it results in energy loss. This means that the insertion loss of the chip generates heat, which leads to an uneven heat dissipation of the chip and thus functional failure. The microwave characteristics of the packaged joints were investigated using different packaging techniques. The results show that the S21 and S11 of the attenuation chip after nano-silver and Au80Sn20 packaging are optimal in the frequency band of DC-6 GHz, and the insertion loss is low compared with the commonly used packaging materials Sn60Pb40 and Sn96.5Ag3.5, which reduces the heat loss and improves the reliability of the attenuation chip packaging. Full article

In modern warfare, frequency-hopping communication serves as the primary method for battlefield information transmission, with its significance continuously growing. Fighting for the control of electromagnetic power on the battlefield has become an important factor affecting the outcome of war. As communication electronic warfare evolves, jammers employing deep neural networks (DNNs) to decode frequency-hopping communication parameters for smart jamming pose a significant threat to communicators. This paper proposes a method to generate adversarial samples of frequency-hopping communication signals using adaptive whitening and feature gradient smoothing. This method targets the DNN cognitive link of the jammer, aiming to reduce modulation recognition accuracy and counteract smart interference. First, the frequency-hopping signal is adaptively whitened. Subsequently, rich spatiotemporal features are extracted from the hidden layer after inputting the signal into the deep neural network model for gradient calculation. The signal’s average feature gradient replaces the single-point gradient for iteration, enhancing anti-disturbance capabilities. Simulation results show that, compared with the existing gradient symbol attack algorithm, the attack success rate and migration rate of the adversarial samples generated by this method are greatly improved in both white box and black box scenarios. Full article

Electric vehicles (EVs) are becoming more and more popular as they provide significant environmental benefits compared to fossil-fuel vehicles. However, they represent substantial loads on the power grid, and the scheduling of EV charging can be a challenge, especially in large parking lots. This paper presents a metaheuristic-based approach parallelized on multicore processors (CPU) and graphics processing units (GPU) to optimize the scheduling of EV charging in a single smart parking lot. The proposed method uses a particle swarm optimization algorithm that takes as input the arrival time, the departure time, and the power demand of the vehicles and produces an optimized charging schedule for all vehicles in the parking lot, which minimizes the overall charging cost while respecting the chargers’ capacity and the parking lot feeder capacity. The algorithm exploits task-level parallelism for the multicore CPU implementation and data-level parallelism for the GPU implementation. The proposed algorithm is tested in simulation on parking lots containing 20 to 500 EVs. The parallel implementation on CPUs provides a speedup of 7.1x, while the implementation on a GPU provides a speedup of up to 247.6x. The parallel implementation on a GPU is able to optimize the charging schedule for a 20-EV parking lot in 0.87 s and a 500-EV lot in just under 30 s. These runtimes allow for real-time computation when a vehicle arrives at the parking lot or when the electricity cost profile changes. Full article

Predicting sound sources in reverberant environments is a challenging task because reverberation causes reflection and scattering of sound waves, making it difficult to accurately determine the position of the sound source. Due to the characteristics of overcoming multipath effects and adaptive focusing of the time reversal technology, this paper focuses on the application of the time reversal operator decomposition method for sound source localization in reverberant environments and proposes the image-source time reversal multiple signals classification (ISTR-MUSIC) method. Firstly, the time reversal operator is derived, followed by the proposal of a subspace method to achieve sound source localization. Meanwhile, the use of the image-source method is proposed to calculate and construct the transfer matrix. To validate the effectiveness of the proposed method, simulations and real-data experiments were performed. In the simulation experiments, the performance of the proposed method under different array element numbers, signal-to-noise ratios, reverberation times, frequencies, and numbers of sound sources were studied and analyzed. A comparison was also made with the traditional time reversal method and the MUSIC algorithm. The experiment was conducted in a reverberation chamber. Simulation and experimental results show that the proposed method has good localization performance and robustness in reverberant environments. Full article

Track fastener defect detection is an essential component in ensuring railway safety operations. Traditional manual inspection methods no longer meet the requirements of modern railways. The use of deep learning image processing techniques for classifying and recognizing abnormal fasteners is faster, more accurate, and more intelligent. With the widespread use of unmanned aerial vehicles (UAVs), conducting railway inspections using lightweight, low-power devices carried by UAVs has become a future trend. In this paper, we address the characteristics of track fastener detection tasks by improving the YOLOv4-tiny object detection model. We improved the model to output single-scale features and used the K-means++ algorithm to cluster the dataset, obtaining anchor boxes that were better suited to the dataset. Finally, we developed the FPGA platform and deployed the transformed model on this platform. The experimental results demonstrated that the improved model achieved an mAP of 95.1% and a speed of 295.9 FPS on the FPGA, surpassing the performance of existing object detection models. Moreover, the lightweight and low-powered FPGA platform meets the requirements for UAV deployment. Full article

Matrix multiplication plays a crucial role in various engineering and scientific applications. Cannon’s algorithm, executed within two-dimensional systolic arrays, significantly enhances computational efficiency through parallel processing. However, as the matrix size increases, reliability issues become more prominent. Although the previous work has proposed a fault-tolerant mechanism, it is only suitable for scenarios with a limited number of faulty processing elements (PEs). This paper introduces a pair-matching mechanism, assigning a fault-free PE as a proxy for each faulty PE to execute its tasks. Our fault-tolerant mechanism comprises two stages: in the first stage, each fault-free PE completes its designated computations; in the second stage, computations intended for each faulty PE are executed by its assigned fault-free PE proxy. The experimental results demonstrate that compared to the previous work, our approach not only significantly improves the fault tolerance of systolic arrays (applicable to scenarios with a higher number of faulty PEs) but also reduces circuit areas. Therefore, the proposed approach proves effective in practical applications. Full article

The deployment of wireless communication networks in the E band (60–90 GHz) requires highly flexible, real-time, and precise tunability to optimize power transmission amidst diffraction, obstacles, and scattering challenges. This paper proposes an innovative reconfigurable metasurface reflect array design capable of achieving a dynamic phase range of 312 degrees with less than 1 dB of loss. The design integrates two types of unit cells and employs piezoelectric crystal as the tuning element. Simulation results illustrate the feasibility of beam focusing and accurate beam steering within a range of ±3 degrees. Furthermore, the proposed reconfigurable metasurface reflector demonstrates an antenna gain comparable to that of a dish antenna with the same aperture size. Full article

Aiming at a series of limitations of the Adam algorithm, such as hyperparameter sensitivity and unstable convergence, in this paper, an improved optimization algorithm, the Cycle-Norm-Adam (CN-Adam) algorithm, is proposed. The algorithm integrates the ideas of a cyclic exponential decay learning rate (CEDLR) and gradient paradigm constraintsand accelerates the convergence speed of the Adam model and improves its generalization performance by dynamically adjusting the learning rate. In order to verify the effectiveness of the CN-Adam algorithm, we conducted extensive experimental studies. The CN-Adam algorithm achieved significant performance improvementsin both standard datasets. The experimental results show that the CN-Adam algorithm achieved 98.54% accuracy in the MNIST dataset and 72.10% in the CIFAR10 dataset. Due to the complexity and specificity of medical images, the algorithm was tested in a medical dataset and achieved an accuracy of 78.80%, which was better than the other algorithms. The experimental results show that the CN-Adam optimization algorithm provides an effective optimization strategy for improving model performance and promoting medical research. Full article

In coal-fired power plants, coal piles serve as the fundamental management units. Acquiring point clouds of coal piles facilitates the convenient measurement of daily coal consumption and combustion efficiency. When using servo motors to drive Light Detection and Ranging (LiDAR) scanning of large-scale coal piles, the motors are subject to rotational errors due to gravitational effects. As a result, the acquired point clouds often contain significant noise. To address this issue, we proposes a Rapid Point Cloud Stitching–Constrained Particle Filter (RPCS-CPF) method. By introducing random noise to simulate servo motor rotational errors, both local and global point clouds are sequentially subjected to RPCS-CPF operations, resulting in smooth and continuous coal pile point clouds. Moreover, this paper presents a coal pile boundary detection method based on gradient region growing clustering. Experimental results demonstrate that our proposed RPCS-CPF method can generate smooth and continuous coal pile point clouds, even in the presence of servo motor rotational errors. Full article

A novel patch phased array antenna with improved scanning performance is presented in this paper. The active element pattern is changed as desired through a modified SIW cavity, resulting in an extension of the phased array’s 3 dB scanning range. Furthermore, sequential rotation is used to reduce the cross-polarization level of the array, which also improves the scanning gain at ±45°. Without altering the element size or profile, the array has the merits of low cost, low complexity, and a simple feed structure. The presented phased array antenna (PAA) exhibits a gain fluctuation of less than 2.2 dB when steering to 45°. Furthermore, the cross-polarization levels are below −68.1 dB when scanning to 45° in a E-/H-plane over the whole working band. To validate the proposed design, a prototype of a 24 × 16 active PAA is designed, fabricated, and measured. A good agreement between the simulated and measured results is achieved, Thus, this paper offers a viable solution to enhance the scanning performance of a PAA with fixed interelement spacing. Full article

In this study, we introduce a stagger-stacked DDR module that comprises one IPD chip (top die) along with four memory chips initially. The steady-state thermal characteristics of this configuration were empirically assessed using a dedicated thermal test vehicle. The purpose of this research is to investigate the module’s junction temperature by adjusting four factors: the thermal conductivity of the molding plastic, chip thickness, chip misalignment length, and the thermal conductivity of the adhesive film. We observed that the junction temperature decreases with an increase in the chip staggered length. An improved orthogonal experimental method was utilized to achieve the optimal design of the module. The optimal junction temperature has decreased by 4.74% compared to the initial value. Additionally, three alternative packaging technologies—cantilever, pyramid, and a combination of cantilever and pyramid—were evaluated for the benchmarking of the thermal performance. Ultimately, the stagger-stacked package demonstrated a reduction in the junction temperature by 3.62%, 7.95%, and 5.63%, respectively, when compared to the three traditional stacked packages. Full article

This paper presents a Simultaneous Lightwave Information and Power Transfer (SLIPT) system for implantable biomedical applications composed of an external and internal (i.e., implantable) unit designed at a transistor level in TMSC 0.18 µm standard CMOS Si technology, requiring Si areas of 200 × 260 µm² and 615 × 950 µm², respectively. The SLIPT external unit employs a semiconductor laser to transmit data and power to the SLIPT internal unit, which contains an Optical Wireless Power Transfer (OWPT) module to supply its circuitry and, in particular, the data receiver module. To enable these operations, the transmitter module of the SLIPT external unit uses a novel reverse multilevel synchronized pulse position modulation technique based on dropping the laser driving current to zero so it produces laser pulses with a reversed intensity profile. This modulation technique allows: (i) the SLIPT external unit to code and transmit data packages of 6-bit symbols received and decoded by the SLIPT internal unit; and (ii) to supply the OWPT module also in the period between the transmission of two consecutive data packages. The receiver module operates for a time window of 12.5 µs every 500 µs, this being the time needed for the OWPT module to fully recover the energy to power the SLIPT internal unit. Post-layout simulations demonstrate that the proposed SLIPT system provides a final data throughput of 6 Mbps, an energy efficiency of 7 pJ/bit, and an OWPT module power transfer efficiency of 40%. Full article

This paper addresses the tracking control for an n-link flexible-joint robot system with full-state constraints and external disturbances. First, a nonlinear disturbance observer (NDO) is introduced to asymptotically estimate and suppress the influence of the related disturbances. Next, the constrained system under consideration is transformed into a new unconstrained system using state-dependent function (SDF) transformations. Subsequently, a NDO-based tracking controller that combines the backstepping method and filter technique is proposed in this work. Based on stability analysis, it can be proven that the tracking error converges to a predefined compact set, which can be arbitrarily small without violating the full-state constraints. Finally, simulation results are presented to demonstrate the validity of the suggested control algorithm. Full article

Federated learning has been a hot topic in the field of artificial intelligence in recent years due to its distributed nature and emphasis on privacy protection. To better align with real-world scenarios, federated class incremental learning (FCIL) has emerged as a new research trend, but it faces challenges such as heterogeneous data, catastrophic forgetting, and inter-client interference. However, most existing methods enhance model performance at the expense of privacy, such as uploading prototypes or samples, which violates the basic principle of only transmitting models in federated learning. This paper presents a novel selective knowledge fusion (FedSKF) model to address data heterogeneity and inter-client interference without sacrificing any privacy. Specifically, this paper introduces a PIT (projection in turn) module on the server side to indirectly recover client data distribution information through optimal transport. Subsequently, to reduce inter-client interference, knowledge of the global model is selectively absorbed via knowledge distillation and an incomplete synchronization classifier at the client side, namely an SKS (selective knowledge synchronization) module. Furthermore, to mitigate global catastrophic forgetting, a global forgetting loss is proposed to distill knowledge from the old global model. Our framework can easily integrate various CIL methods, allowing it to adapt to application scenarios with varying privacy requirements. We conducted extensive experiments on CIFAR100 and Tiny-ImageNet datasets, and the performance of our method surpasses existing works. Full article

Urban transportation systems are increasingly burdened by traffic congestion, a consequence of population growth and heightened reliance on private vehicles. This congestion not only disrupts travel efficiency but also undermines productivity and urban resident’s overall well-being. A critical step in addressing this challenge is the accurate prediction of bus travel times, which is essential for mitigating congestion and improving the experience of public transport users. To tackle this issue, this study introduces the Hybrid Temporal Forecasting Network (HTF-NET) model, a framework that integrates machine learning techniques. The model combines an attention mechanism with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) layers, enhancing its predictive capabilities. Further refinement is achieved through a Support Vector Regressor (SVR), enabling the generation of precise bus travel time predictions. To evaluate the performance of the HTF-NET model, comparative analyses are conducted with six deep learning models using real-world digital tachograph (DTG) data obtained from intracity buses in Cheonan City, South Korea. These models includes various architectures, including different configurations of LSTM and GRU, such as bidirectional and stacked architectures. The primary focus of the study is on predicting travel times from the Namchang Village bus stop to the Dongnam-gu Public Health Center, a crucial route in the urban transport network. Various experimental scenarios are explored, incorporating overall test data, and weekday and weekend data, with and without weather information, and considering different route lengths. Comparative evaluations against a baseline ARIMA model underscore the performance of the HTF-NET model. Particularly noteworthy is the significant improvement in prediction accuracy achieved through the incorporation of weather data. Evaluation metrics, including root mean squared error (RMSE), mean absolute error (MAE), and mean squared error (MSE), consistently highlight the superiority of the HTF-NET model, outperforming the baseline ARIMA model by a margin of 63.27% in terms of the RMSE. These findings provide valuable insights for transit agencies and policymakers, facilitating informed decisions regarding the management and optimization of public transportation systems. Full article

Detecting pedestrians in varying illumination conditions poses a significant challenge, necessitating the development of innovative solutions. In response to this, we introduce Prior-AttentionNet, a pedestrian detection model featuring a Prior-Attention mechanism. This model leverages the stark contrast between thermal objects and their backgrounds in far-infrared (FIR) images by employing saliency attention derived from FIR images via UNet. However, extracting salient regions of diverse scales from FIR images poses a challenge for saliency attention. To address this, we integrate Simple Linear Iterative Clustering (SLIC) superpixel segmentation, embedding the segmentation feature map as prior knowledge into UNet’s decoding stage for comprehensive end-to-end training and detection. This integration enhances the extraction of focused attention regions, with the synergy of segmentation prior and saliency attention forming the core of Prior-AttentionNet. Moreover, to enrich pedestrian details and contour visibility in low-light conditions, we implement multispectral image fusion. Experimental evaluations were conducted on the KAIST and OTCBVS datasets. Applying Prior-Attention mode to FIR-RGB images significantly improves the delineation and focus on multi-scale pedestrians. Prior-AttentionNet’s general detector demonstrates the capability of detecting pedestrians with minimal computational resources. The ablation studies indicate that the FIR-RGB+ Prior-Attention mode markedly enhances detection robustness over other modes. When compared to conventional multispectral pedestrian detection models, Prior-AttentionNet consistently surpasses them by achieving higher mean average precision and lower miss rates in diverse scenarios, during both day and night. Full article

Adversarial attacks are more prevalent in Consumer Internet of Things (CIoT) devices (i.e., smart home devices, cameras, actuators, sensors, and micro-controllers) because of their growing integration into daily activities, which brings attention to their possible shortcomings and usefulness. Keeping protection in the CIoT and countering emerging risks require constant updates and monitoring of these devices. Machine learning (ML), in combination with Explainable Artificial Intelligence (XAI), has become an essential component of the CIoT ecosystem due to its rapid advancement and impressive results across several application domains for attack detection, prevention, mitigation, and providing explanations of such decisions. These attacks exploit and steal sensitive data, disrupt the devices’ functionality, or gain unauthorized access to connected networks. This research generates a novel dataset by injecting adversarial attacks into the CICIoT2023 dataset. It presents an adversarial attack detection approach named TXAI-ADV that utilizes deep learning (Mutli-Layer Perceptron (MLP) and Deep Neural Network (DNN)) and machine learning classifiers (K-Nearest Neighbor (KNN), Support Vector Classifier (SVC), Gaussian Naive Bayes (GNB), ensemble voting, and Meta Classifier) to detect attacks and avert such situations rapidly in a CIoT. This study utilized Shapley Additive Explanations (SHAP) techniques, an XAI technique, to analyze the average impact of each class feature on the proposed models and select optimal features for the adversarial attacks dataset. The results revealed that, with a 96% accuracy rate, the proposed approach effectively detects adversarial attacks in a CIoT. Full article

In this paper, we analyze the timeliness of a multi-user system in terms of the age of information (AoI) and the corresponding stability region in which the packet rates of users lead to finite queue lengths. Specifically, we consider a hybrid OFDMA-NOMA system where the users are partitioned into several groups. While users in each group share the same resource block using non-orthogonal multiple access (NOMA), different groups access the fading channel using orthogonal frequency division multiple access (OFDMA). For this system, we consider three decoding schemes at the service terminals: interfering decoding, which treats signals from other users as interference; serial interference cancellation, which removes signals from other users once they have been decoded; and the enhanced SIC strategy, where the receiver attempts to decode for another user if decoding for a previous user fails. We present the average AoI for each of the three decoding schemes in closed form. Under the constraint of the stable region, we find the minimum AoI of each decoding scheme efficiently. The numerical results show that by optionally choosing the decoding scheme and transmission rate, the hybrid OFDMA-NOMA outperforms conventional OFDMA in terms of both system timeliness and stability. Full article

The recently introduced Video Coding Standard, VVC, presents a novel Quadtree plus Nested Multi-Type Tree (QTMTT) block structure. This structure enables a more flexible block partition and demonstrates enhanced compression performance compared to its predecessor, HEVC. However, The introduction of the new structure has led to a more complex partition search process, resulting in a considerable increase in time complexity. The QTMTT structure yields diverse Coding Unit (CU) block sizes, posing challenges for CNN model inference. In this study, we propose a representation structure termed Block Segmentation and Block Connection (BSC), rooted in texture features. This ensures that partial CU blocks are uniformly represented in size. To address different-sized CUs, various levels of CNN models are designed for prediction. Moreover, we introduce a post-processing method and a multi-thresholding scheme to further mitigate errors introduced by CNNs. This allows for flexible and adjustable acceleration, achieving a trade-off between coding time complexity and performance. Experimental results indicate that, in comparison to VTM-10.0, our “Fast” scheme reduces the average complexity by 57.14% with a 1.86% increase in BDBR. Meanwhile, the “Moderate” scheme reduces average complexity by 50.14% with only a 1.39% increase in BDBR. Full article