Electronics, Volume 13, Issue 5 (March-1 2024) – 194 articles

This study proposes a solution for Active Simultaneous Localization and Mapping (Active SLAM) of robots in unknown indoor environments using a combination of Deep Deterministic Policy Gradient (DDPG) path planning and the Cartographer algorithm. To enhance the convergence speed of the DDPG network and minimize collisions with obstacles, we devised a unique reward function that integrates exploration and exploitation strategies. The exploration strategy allows the robot to achieve the shortest running time and movement trajectory, enabling efficient traversal of unmapped environments. Moreover, the exploitation strategy introduces active closed loops to enhance map accuracy. We conducted experiments using the simulation platform Gazebo to validate our proposed model. The experimental results demonstrate that our model surpasses other Active SLAM methods in exploring and mapping unknown environments, achieving significant grid completeness of 98.7%. Full article

A robust explicit model predictive control (EMPC)-based frequency-adaptive grid voltage sensorless control is developed for a grid-connected inverter (GCI) via a linear matrix inequality (LMI) approach under the model parametric uncertainties as well as distorted and imbalanced grid voltages. In order to ensure the quality of grid currents injected into the utility grid even when the system model parameters vary, the proposed control scheme is accomplished by an enhanced prediction model rather than the conventional prediction model obtained by fixed parameters. Furthermore, an LMI-based observer is integrated with the disturbance observer to improve the reference tracking performance and to reject disturbances. The proposed observer is employed for the grid frequency-adaptive control without the need for grid voltage sensors. The proposed current controller and observer employ the LMI scheme to maintain a stable and robust operation of the GCI. The discrete-time frequency response and pole-zero map analyses are utilized to examine the system performance including the stability and robustness against parametric uncertainties. Comprehensive simulation and experimental tests as well as theoretical analyses clearly validate the robustness of the proposed control scheme under various harsh test conditions with non-ideal and unexpected grid and system parametric uncertainties. Full article

A compact high-power four-port circulator aiming to simplify the conventional, complex, and bulky injection-locking magnetron system is proposed. To reduce the performance deterioration and the risk of ferrite rupture under long-term high-microwave-power condition, the method of breaking a monolithic ferrite into three discrete ferrites in a conventional three-port circulator is proposed. To miniaturize the size and cost of the four-port circulator, a butterfly-shaped waveguide structure is proposed, with a stub inserted into the cavity at the central point and with no connecting waveguide. Multiphysics simulation results show that the temperature coefficient of variation (COV) at the surface of the discrete ferrites is 12.4% lower than that of a monolithic ferrite circulator, with input microwave power of 10 kW. The size of the proposed four-port waveguide circulator is 27% less than the assembly of two three-port circulators, and way smaller than a conventional differential phase shift circulator (DPSC). The simulated and measured S-parameters match well, and the measured power capacity of the fabricated circulator is higher than 3 kW (limited by the experimental condition). A magnetron is successfully locked using only one designed compact circulator. The research in this paper promotes the development of injection-locking magnetron and provides a design example for the compact, high-power circulator. Full article

Accurate fault simulation and failure prediction have long been challenges for SiC MOSFETs users. This paper presents a behavior model of Silicon Carbide (SiC) double-implanted MOSFET (DMOSFET), considering thermal-runaway failures in short-circuit and avalanche breakdown faults on the basis of cell-level physical processes. The proposed model can simulate the faults with extremely high accuracy and precisely predict SiC DMOSFET’s short-circuit withstand time and critical avalanche energy. By finite-element simulations, cell-level physical processes of short-circuit and avalanche breakdown faults are clarified. The mechanisms of thermal-runaway failures are deeply discussed with references to existing studies. Based on semiconductor and device physics mechanisms, the proposed model is constructed upon a traditional behavior model of SiC MOSFET with several parallel branches that are proposed to describe the thermal-runaway failures during both faults. The Cauer thermal network model is used for estimating junction temperature within it. The proposed model is constructed in Simulink, and it is validated using short-circuit and unclamped inductive switching (UIS) tests. Full article

A modular Sigma DC/DC converter with wide input voltage range is proposed in this paper. The proposed converter is combined with a traditional LLC converter and two multi-resonant converters via Sigma architecture. Among them, the traditional LLC converter operates as a DC transformer (DCX) at resonant frequency to achieve maximum efficiency. Meanwhile, one of the multi-resonant converters, the DC to DC (D2D) part of the Sigma structure, is responsible for voltage regulation over a wide input voltage range. In addition, the other multi-resonant converter has two operation modes, including DCX and D2D. When it operates in the DCX mode, the Sigma converter has better performance and higher efficiency. When it operates in the D2D mode, the Sigma converter can handle a wider input voltage range. For each submodule, the operation principle and characteristics of the proposed Sigma converter are analyzed in detail. In addition, some key points of the parameter design for each part are also demonstrated. Finally, an experimental prototype with an input voltage of 540~1100 V is built to verify the effectiveness of the proposed converter. Full article

This paper provides a comprehensive survey of the integration of graph neural networks (GNN) and deep reinforcement learning (DRL) in end-to-end (E2E) networking solutions. We delve into the fundamentals of GNN, its variants, and the state-of-the-art applications in communication networking, which reveal the potential to revolutionize access, transport, and core network management policies. This paper further explores DRL capabilities, its variants, and the trending applications in E2E networking, particularly in enhancing dynamic network (re)configurations and resource management. By fusing GNN with DRL, we spotlight novel approaches, ranging from radio access networks to core management and orchestration, across E2E network layers. Deployment scenarios in smart transportation, smart factory, and smart grids demonstrate the practical implications of our survey topic. Lastly, we point out potential challenges and future research directions, including the critical aspects for modelling explainability, the reduction in overhead consumption, interoperability with existing schemes, and the importance of reproducibility. Our survey aims to serve as a roadmap for future developments in E2E networking, guiding through the current landscape, challenges, and prospective breakthroughs in the algorithm modelling toward network automation using GNN and DRL. Full article

Photovoltaic (PV) power prediction plays a significant role in supporting the stable operation and resource scheduling of integrated energy systems. However, the randomness and volatility of photovoltaic power generation will greatly affect the prediction accuracy. Focusing on this issue, a prediction framework is proposed in this research by developing an improved sparrow search algorithm (ISSA) to optimize the hyperparameters of long short-term memory (LSTM) neural networks. The ISSA is specially designed from the following three aspects to support a powerful search performance. Firstly, the initial population variety is enriched by using an enhanced sine chaotic mapping. Secondly, the relative position of neighboring producers is introduced to improve the producer position-updating strategy to enhance the global search capabilities. Then the Cauchy–Gaussian variation is utilized to help avoid the local optimal solution. Numerical experiments on 20 test functions indicate that ISSA could identify the optimal solution with better precision compared to SSA and PSO algorithms. Furthermore, a comparative study of PV power prediction methods is provided. The ISSA-LSTM algorithm developed in this paper and five benchmark models are implemented on a real dataset gathered from the Alice Springs area in Australia. In contrast to the SSA-LSTM model, most MAE, MAPE, and RMSE values of the proposed model are reduced by 20∼60%, demonstrating the superiority of the proposed model under various weather conditions and typical seasons. Full article

It is well known that the recursive least squares (RLS) algorithm is renowned for its rapid convergence and excellent tracking capability. However, its performance is significantly compromised when the system is sparse or when the input signals are contaminated by impulse noise. Therefore, in this paper, the minimum error entropy (MEE) criterion is introduced into the cost function of the RLS algorithm in this paper, with the aim of counteracting the interference from impulse noise. To address the sparse characteristics of the system, we employ a universally applicable convex function to regularize the cost function. The resulting new algorithm is named the convex regularization recursive minimum error entropy (CR-RMEE) algorithm. Simulation results indicate that the performance of the CR-RMEE algorithm surpasses that of other similar algorithms, and the new algorithm excels not only in scenarios with sparse systems but also demonstrates strong robustness against pulse noise. Full article

Person re-identification (Re-ID) networks are often affected by factors such as pose variations, changes in viewpoint, and occlusion, leading to the extraction of features that encompass a considerable amount of irrelevant information. However, most research has struggled to address the challenge of simultaneously endowing features with both attentive and diversified information. To concurrently extract attentive yet diverse pedestrian features, we amalgamated the strengths of convolutional neural network (CNN) attention and self-attention. By integrating the extracted latent features, we introduced a Hybrid Attention/Diversity Network (MIX-Net), which adeptly captures attentive but diverse information from personal images via a fusion of attention branches and attention suppression branches. Additionally, to extract latent information from secondary important regions to enrich the diversity of features, we designed a novel Discriminative Part Mask (DPM). Experimental results establish the robust competitiveness of our approach, particularly in effectively distinguishing individuals with similar attributes. Full article

This paper describes the design, operation and test results of a simple microprocessor-based device for measuring slow liquid flows. The device uses a module of 30 digital optical sensors to track the movement of a single air bubble inserted into a tube of flowing liquid. During a measurement session, the air bubble remains within the sensor module at all times, allowing the instrument to take measurements for any length of time. The liquid whose flow rate is being measured moves only in the closed tube system, without contact with other components of the device. The test of the device itself was carried out using a tube with an inner diameter of less than 1 mm, where the device is capable of measuring flow rates on the order of microliters per minute. Tests of the device showed good agreement between the measured volumetric flow rate and the reference flow rates of the infusion pump over the entire measurement range. The advantages and limitations of the device are discussed, as well as the prospects for developing the method. Full article

The development of new processor capabilities which enable hardware-based memory encryption, capable of isolating and encrypting application code and data in memory, have led to the rise of confidential computing techniques that protect data when processed on untrusted computing resources (e.g., cloud). Before confidential computing technologies, applications that needed data-in-use protection, like outsourced or secure multiparty computation, used purely cryptographic techniques, which had a large negative impact on the processing performance. Processing data in trusted enclaves protected by confidential computing technologies promises to protect data-in-use while possessing a negligible performance penalty. In this paper, we have analyzed the state-of-the-art in the field of confidential computing and present a Confidential Computing System for Artificial Intelligence (CoCoS.ai), a system for secure multiparty computation, which uses virtual machine-based trusted execution environments (in this case, AMD Secure Encrypted Virtualization (SEV)). The security of the proposed solution, as well as its performance, have been formally analyzed and measured. The paper reveals many gaps not reported previously that still exist in the current confidential computing solutions for the secure multiparty computation use case, especially in the processes of creating new secure virtual machines and their attestation, which are tailored for single-user use cases. Full article

Optimal control techniques such as model predictive control (MPC) have been widely studied and successfully applied across a diverse field of applications. However, the large computational requirements for these methods result in a significant challenge for embedded applications. While event-triggered MPC (eMPC) is one solution that could address this issue by taking advantage of the prediction horizon, one obstacle that arises with this approach is that the event-trigger policy is complex to design to fulfill both throughput and control performance requirements. To address this challenge, this paper proposes to design the event trigger by training a deep Q-network reinforcement learning agent (RLeMPC) to learn the optimal event-trigger policy. This control technique was applied to an active-cell-balancing controller for the range extension of an electric vehicle battery. Simulation results with MPC, eMPC, and RLeMPC control policies are presented along with a discussion of the challenges of implementing RLeMPC. Full article

Deep-learning-based malware-detection models are threatened by adversarial attacks. This paper designs a robust and secure convolutional neural network (CNN) for malware classification. First, three CNNs with different pooling layers, including global average pooling (GAP), global max pooling (GMP), and spatial pyramid pooling (SPP), are proposed. Second, we designed an executable adversarial attack to construct adversarial malware by changing the meaningless and unimportant segments within the Portable Executable (PE) header file. Finally, to consolidate the GMP-based CNN, a header-aware loss algorithm based on the attention mechanism is proposed to defend the executive adversarial attack. The experiments showed that the GMP-based CNN achieved better performance in malware detection than other CNNs with around $98.61\%$ accuracy. However, all CNNs were vulnerable to the executable adversarial attack and a fast gradient-based attack with a $46.34\%$ and $34.65\%$ accuracy decline on average, respectively. Meanwhile, the improved header-aware CNN achieved the best performance with an evasion ratio of less than $5.0\%$. Full article

To improve the accuracy of steel surface defect detection, an improved model of multi-directional optimization based on the YOLOv8 algorithm was proposed in this study. First, we innovate the CSP Bottleneck with the two convolutions (C2F) module in YOLOv8 by introducing deformable convolution (DCN) technology to enhance the learning and expression ability of complex texture and irregular shape defect features. Secondly, the advanced Bidirectional Feature Pyramid Network (BiFPN) structure is adopted to realize the weight distribution learning of input features of different scales in the feature fusion stage, allowing for more effective integration of multi-level feature information. Next, the BiFormer attention mechanism is embedded in the backbone network, allowing the model to adaptively allocate attention based on target features, such as flexibly and efficiently skipping non-critical areas, and focusing on identifying potentially defective parts. Finally, we adjusted the loss function from Complete-Intersection over Union (CIoU) to Wise-IoUv3 (WIoUv3) and used its dynamic non-monotony focusing property to effectively solve the problem of overfitting the low quality target bounding box. The experimental results show that the mean Average Precision (mAP) of the improved model in the task of steel surface defect detection reaches 84.8%, which depicts a significant improvement of 6.9% compared with the original YOLO8 model. The improved model can quickly and accurately locate and classify all kinds of steel surface defects in practical applications and meet the needs of steel defect detection in industrial production. Full article

In the current era, energy resources from the environment via piezoelectric materials are not only used for self-powered electronic devices, but also play a significant role in creating a pleasant living environment. Piezoelectric materials have the potential to produce energy from micro to milliwatts of power depending on the ambient conditions. The energy obtained from these materials is used for powering small electronic devices such as sensors, health monitoring devices, and various smart electronic gadgets like watches, personal computers, and cameras. These reviews explain the comprehensive concepts related to piezoelectric (classical and non-classical) materials, energy harvesting from the mechanical vibration of piezoelectric materials, structural modelling, and their optimization. Non-conventional smart materials, such as polyceramics, polymers, or composite piezoelectric materials, stand out due to their slender actuator and sensor profiles, offering superior performance, flexibility, and reliability at competitive costs despite their susceptibility to performance fluctuations caused by temperature variations. Accurate modeling and performance optimization, employing analytical, numerical, and experimental methodologies are imperative. This review also furthers research and development in optimizing piezoelectric energy utilization, suggesting the need for continued experimentation to select optimal materials and structures for various energy applications. Full article

To ensure precise phase estimation within the q-axis of the phase-locked loop (PLL), integrating a filter into the q-axis loop is essential to mitigate grid-voltage harmonics. Nevertheless, the intrinsic delay characteristics of this filter impede PLL synchronization during significant grid disturbances. This study begins by developing mathematical models for three types of filters—moving-average filter (MAF) for eliminating odd harmonic components, dq-frame cascaded delayed signal cancellation (dqCDSC) filter, and notch filter (NF). Following the reduction in filter orders, a third-order nonlinear large-signal model of the PLL, incorporating an additional q-axis internal filter, is formulated. Using phase plane analysis, this study investigates the transient synchronism of the grid-following converter (GFL) and explores the influence of delay time constants from the three PLL filters on its behavior while delineating the boundaries of their basins of attraction. Theoretical findings indicate that, relative to the traditional SRF-PLL, incorporating an internal filter into the PLL compromises the transient synchronous stability of GFL. Specifically, greater filter delay time constants exacerbate the GFL’s vulnerability to transient instability amid substantial grid disturbances. Hence, careful consideration is essential when using MAF-PLL and NF-PLL in situations demanding high synchronization stability. The theoretical analyses are validated using Matlab/Simulink to verify their accuracy. Full article

This paper introduces a Python framework for developing Deep Reinforcement Learning (DRL) in an open-source Godot game engine to tackle sim-to-real research. A framework was designed to communicate and interface with the Godot game engine to perform the DRL. With the Godot game engine, users will be able to set up their environment while defining the constraints, motion, interactive objects, and actions to be performed. The framework interfaces with the Godot game engine to perform defined actions. It can be further extended to perform domain randomization and enhance overall learning by increasing the complexity of the environment. Unlike other proprietary physics or game engines, Godot provides extensive developmental freedom under an open-source licence. By incorporating Godot’s built-in powerful node-based environment system, flexible user interface, and the proposed Python framework, developers can extend its features to develop deep learning applications. Research performed on Sim2Real using this framework has provided great insight into the factors that affect the gap in reality. It also demonstrated the effectiveness of this framework in Sim2Real applications and research. Full article

With the rapid development of the Internet of Things (IoT), ensuring secure communication between devices has become a crucial challenge. This paper proposes a novel secure communication solution by extracting wireless channel state information (CSI) features from IoT devices to generate a device identity. Due to the instability of the wireless channel, the CSI features are fuzzy and time-varying; thus, we a employ locally sensitive hashing (LSH) algorithm to ensure the stability of the generated identity in a dynamically changing wireless channel environment. Furthermore, zero-knowledge proofs are utilized to guarantee the authenticity and effectiveness of the generated identity. Finally, the identity generated using the aforementioned approach is integrated into an IBE communication scheme, which involves the fuzzy extraction of channel state information from IoT devices, stable identity extraction for fuzzy IoT devices using LSH, and the use of zero-knowledge proofs to ensure the authenticity of the generated identity. This identity is then employed as the identity information in identity-based encryption (IBE), constructing the device’s public key for achieving confidential communication between devices. Full article

As a commonly used plasma diagnostic method, the spectral analysis methodology generates a large amount of data and has a complex quantitative relationship with discharge parameters, which result in low accuracy and time-consuming operation of traditional manual spectral recognition methods. To quickly and efficiently recognize the discharge parameters based on the collected spectral data, a one-dimensional (1D) deep convolutional neural network was constructed, which can learn the data features of different classes of ethylene plasma spectra to obtain the corresponding discharge parameters. The results show that this method has a higher recognition accuracy of higher than 98%. This model provides a new idea for plasma spectral diagnosis and its related application. Full article

With the exploration of subterranean scenes, determining how to ensure the safety of subterranean pedestrians has gradually become a hot research topic. Considering the poor illumination and lack of annotated data in subterranean scenes, it is essential to explore the LiDAR-based domain adaptive detectors for localizing the spatial location of pedestrians, thus providing instruction for evacuation and rescue. In this paper, a novel domain adaptive subterranean 3D pedestrian detection method is proposed to adapt pre-trained detectors from the annotated road scenes to the unannotated subterranean scenes. Specifically, an instance transfer-based scene updating strategy is designed to update the subterranean scenes by transferring instances from the road scenes to the subterranean scenes, aiming to create sufficient high-quality pseudo labels for fine-tuning the pre-trained detector. In addition, a pseudo label confidence-guided learning mechanism is constructed to fully utilize pseudo labels of different qualities under the guidance of confidence scores. Extensive experiments validate the superiority of our proposed domain adaptive subterranean 3D pedestrian detection method. Full article

Optical interconnects are being discussed as a replacement for conventional electrical interconnects and are expected to be applied for future generations of high-performance supercomputers and data centers. Benes networks have attracted much attention because they require only 2 × 2 optical switches, which reduce the cost of rearrangeable nonblocking. However, optical power imbalances can significantly challenge receiver sensitivity. In this work, insertion loss (IL) fairness has been proposed and applied to the field of switches to achieve a relative balance of optical path data transmission in Benes networks. Fairness can be achieved when the port count is small (4 × 4) if the IL between ports is balanced. When the number of ports is moderate (8 × 8), we must use a suitable algorithm or determine the appropriate operating wavelength to minimize the power imbalance. An efficient two-step algorithm (ETS) has particular advantages in solving the path fairness problem and mitigating the power imbalance. As the number of ports increases, the switch states and topology jointly deteriorate the power imbalance. Finally, the ETS algorithm narrows the dynamic range requirement to 13.66 dB, with a 2 dB improvement. It achieves an extinction ratio of 24 dB and a bandwidth of 375 GHz, which outperforms the conventional 32 × 32 Benes network, respectively. Full article

For brain diseases, e.g., autism spectrum disorder (ASD), with unclear biological characteristics, the detection of imaging-based biomarkers is a critical task for diagnosis. Several landmark-based categorization approaches have been developed for the computer-aided diagnosis of brain diseases, such as Alzheimer’s disease (AD), utilizing structural magnetic resonance imaging (sMRI). With the automatic detection of the landmarks of brain disease, more detailed brain features were identified for clinical diagnosis. Multi-instance learning is an effective technique for classifying brain diseases based on landmarks. The multiple-instance learning approach relies on the assumption of independent distribution hypotheses and is mostly focused on local information, thus the correlation among different brain regions may be ignored. However, according to previous research on ASD and AD, the abnormal development of different brain regions is highly correlated. Vision Transformers, with self-attention modules to capture the relationship between embedded patches from a whole image, have recently demonstrated superior performances in many computer vision tasks. Nevertheless, the utilization of 3D brain MRIs imposes a substantial computational load, especially while training with Vision Transformer. To address the challenges mentioned above, in this research, we proposed a landmark-based multi-instance Conv-Transformer (LD-MILCT) framework as a solution to the aforementioned issues in brain disease diagnosis. In this network, a two-stage multi-instance learning strategy was proposed to explore both spatial and morphological information between different brain regions; the Vision Transformer utilizes a multi-instance learning head (MIL head) to fully utilize the features that are not involved in the ultimate classification. We assessed our proposed framework using T1-weighted MRI images from both AD and ASD databases. Our method outperformed existing deep learning and landmark-based methods in terms of brain MRI classification tasks. Full article

With the global trend of carbon reduction, high-speed maglevs are going to use a large percentage of the electricity generated from renewable energy. However, the fluctuating characteristics of renewable energy can cause voltage disturbance in the traction power system, but high-speed maglevs have high requirements for power quality. This paper presents a novel scheme of a high-speed maglev power system using superconducting magnetic energy storage (SMES) and distributed renewable energy. It aims to solve the voltage sag caused by renewable energy and achieve smooth power interaction between the traction power system and maglevs. The working principle of the SMES power compensation system for topology and the control strategy were analyzed. A maglev train traction power supply model was established, and the results show that SMES effectively alleviated voltage sag, responded rapidly to the power demand during maglev acceleration and braking, and maintained voltage stability. In our case study of a 10 MW high-speed maglev traction power system, the SMES system could output/absorb power to compensate for sudden changes within 10 ms, stabilizing the DC bus voltage with fluctuations of less than 0.8%. Overall, the novel SMES power compensation system is expected to become a promising solution for high-speed maglevs to overcome the power quality issues from renewable energy. Full article

Circular planar spiral coils are the most important parts of wireless power transfer systems. This paper presents the optimization of wireless power transfer coils used for wireless power transfer, which is a problem when designing wireless power transfer systems. A single transmitter coil transfers power to a single receiving side. The performance of the wireless power transfer system depends greatly on the size and shape of the wireless power transfer system. Therefore, the optimization of the coils is of the utmost importance. The main optimization parameter was the coupling coefficient between the transmitter and the receiver coil in the horizontally aligned and misaligned position. A genetic evolutionary algorithm was used to optimize the coil, according to the developed cost function. The algorithm was implemented using the MATLAB programming language. The constraints regarding the design of the coils are also presented for the problem to be analyzed correctly. The results obtained using the genetic algorithm were first verified using FEM simulations. The optimized coils were later fabricated and measured to confirm the theory. Full article

Vietnamese is an under-resourced language. The requirement for a large-scale and high-quality Vietnamese speech corpus increases on demand. We introduce a new large-scale Vietnamese speech corpus with 100.5 h collected from various audio sources in the Internet. The raw collected audio was processed to obtain clean speech. Transcription of the clean speech was made manually. The new corpus was analyzed in terms of gender, topic and regional dialect. Results shows that the new corpus has good diversity of genders, topics and regional dialects. We also evaluated the new corpus using state-of-the-art automatic speech recognition models like LAS and Speech-Transformer for multiple scenarios. This is the first time that these models have been applied to Vietnamese speech recognition and obtained reasonable results. Simulation results showed that the new corpus would be a good dataset for the Vietnamese ASR tasks because it reflected correctly difficulties in recognizing speech from different dialects and topic domains. Full article

Recent technological advancements such as IoT and Big Data have granted industries extensive access to data, opening up new opportunities for integrating artificial intelligence (AI) across various applications to enhance production processes. We cite two critical areas where AI can play a key role in industry: product quality control and predictive maintenance. This paper presents a survey of AI applications in the domain of Industry 4.0, with a specific focus on product quality control and predictive maintenance. Experiments were conducted using two datasets, incorporating different machine learning and deep learning models from the literature. Furthermore, this paper provides an overview of the AI solution development approach for product quality control and predictive maintenance. This approach includes several key steps, such as data collection, data analysis, model development, model explanation, and model deployment. Full article

Convolutional neural networks have been widely applied in the field of computer vision. In convolutional neural networks, convolution operations account for more than 90% of the total computational workload. The current mainstream approach to achieving high energy-efficient convolution operations is through dedicated hardware accelerators. Convolution operations involve a significant amount of weights and input feature data. Due to limited on-chip cache space in accelerators, there is a significant amount of off-chip DRAM memory access involved in the computation process. The latency of DRAM access is 20 times higher than that of SRAM, and the energy consumption of DRAM access is 100 times higher than that of multiply–accumulate (MAC) units. It is evident that the “memory wall” and “power wall” issues in neural network computation remain challenging. This paper presents the design of a hardware accelerator for convolutional neural networks. It employs a dataflow optimization strategy based on on-chip data reordering. This strategy improves on-chip data utilization and reduces the frequency of data exchanges between on-chip cache and off-chip DRAM. The experimental results indicate that compared to the accelerator without this strategy, it can reduce data exchange frequency by up to 82.9%. Full article

As mobile communications transform, 5G technology can potentially change many industries and businesses. The change will have a great influence across many fields, such as the automotive, healthcare, and manufacturing sectors. This paper aims to review the existing applications of blockchain technology in providing 5G network security and identify new possibilities for such security solutions. We consider different aspects of blockchain in 5G, particularly data transmission, access control, and applications including vertical industry-oriented applications and specific solutions supporting such sectors of economic activity. The paper briefly describes modern technologies in 5G networks and introduces blockchain’s properties and different aspects of using such technology in practical applications. It also presents access control management with blockchain applied in 5G and related problems, reviews other blockchain-enforced network technologies, and shows how blockchain can help in services dedicated to vertical industries. Finally, it presents our vision of new blockchain applications in modern 5G networks and beyond. The new-generation networks use two fundamental technologies, slicing and virtualization, and attackers attempt to execute new types of attacks on them. In the paper, we discuss one of the possible scenarios exhibiting the shortcomings of the slicing technology architecture. We propose using blockchain technology to create new slices and to connect new or existing subscribers to slices in the 5G core network. Blockchain technology should solve these architectural shortcomings. Full article

Insider threats are one of the most costly and difficult types of attacks to detect due to the fact that insiders have the right to access an organization’s network systems and understand its structure and security procedures, making it difficult to detect this type of behavior through traditional behavioral auditing. This paper proposes a method to leverage unsupervised outlier scores to enhance supervised insider threat detection by integrating the advantages of supervised and unsupervised learning methods and using multiple unsupervised outlier mining algorithms to extract from the underlying data useful representations, thereby enhancing the predictive power of supervised classifiers on the enhanced feature space. This novel approach provides superior performance, and our method provides better predictive power compared to other excellent abnormal detection methods. Using only 20% of the computing budget, our method achieved an accuracy of 86.12%. Compared with other anomaly detection methods, the accuracy increased by up to 12.5% under the same computing budget. Full article

Aiming at the problem of difficult obstacle avoidance for unmanned ground vehicles (UGVs) in complex dynamic environments, an improved A*-APF algorithm (BA*-MAPF algorithm) is proposed in this paper. Addressing the A* algorithm’s challenges of lengthy paths, excess nodes, and lack of smoothness, the BA*-MAPF algorithm integrates a bidirectional search strategy, applies interpolation to remove redundant nodes, and uses cubic B-spline curves for path smoothing. To rectify the traditional APF algorithm’s issues with local optimization and ineffective dynamic obstacle avoidance, the BA*-MAPF algorithm revises the gravitational field function by incorporating a distance factor, and fine-tunes the repulsive field function to vary with distance. This adjustment ensures a reduction in gravitational force as distance increases and moderates the repulsive force near obstacles, facilitating more effective local path planning and dynamic obstacle navigation. Through our experimental analysis, the BA*-MAPF algorithm has been validated to significantly outperform existing methods in achieving optimal path planning and dynamic obstacle avoidance, thereby markedly boosting path planning efficiency in varied scenarios. Full article