Electronics, Volume 13, Issue 10 (May-2 2024) – 202 articles

This study introduces a steerable metasurface reflector designed for the Ka-band, enabling one-dimensional and two-dimensional beam steering. The paper elaborates on the design considerations, manufacturing process, and experimental findings. The unit cell design incorporates a Varactor diode as the tuning element, facilitating a dynamic phase range exceeding 300° with minimal metasurface beam steering losses. Notably, the experimental results are in good agreement with the simulation outcomes. The advantages of employing this metasurface reflector include rapid beam steering, cost-effective production implementation, support for both one-dimensional and two-dimensional beam steering, low reflection loss, high-resolution beam steering, and continuous beam steering capabilities. Full article

Brain tumor segmentation using Magnetic Resonance Imaging (MRI) is vital for clinical decision making. Traditional deep learning-based studies using convolutional neural networks have predominantly processed MRI data as two-dimensional slices, leading to the loss of contextual information. While three-dimensional (3D) convolutional layers represent an advancement, they have not fully exploited pathological information according to the three-axis nature of 3D MRI data—axial, coronal, and sagittal. Recognizing these limitations, we introduce a Tri-Axis based Context-Aware Reverse Network (TACA-RNet). This innovative approach leverages the unique 3D spatial orientations of MRI, learning crucial information on brain anatomy and pathology. We incorporated three specialized modules: a Tri-Axis Channel Reduction module for optimizing feature dimensions, a MultiScale Contextual Fusion module for aggregating multi-scale features and enhancing spatial discernment, and a 3D Axis Reverse Attention module for the precise delineation of tumor boundaries. The TACA-RNet leverages three specialized modules to enhance the understanding of tumor characteristics and spatial relationships within MRI data by fully utilizing its tri-axial structure. Validated on the Brain Tumor Segmentation Challenge 2018 and 2020 datasets, the TACA-RNet demonstrated superior performances over contemporary methodologies. This underscores the critical role of leveraging the three-axis structure of MRI to enhance segmentation accuracy. Full article

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve. Full article

3D point cloud registration is a crucial technology for 3D scene reconstruction and has been successfully applied in various domains, such as smart healthcare and intelligent transportation. With theoretical analysis, we find that geometric structural relationships are essential for 3D point cloud registration. The 3D point cloud registration method achieves excellent performance only when fusing local and global features with geometric structure information. Based on these discoveries, we propose a 3D point cloud registration method based on geometric structure embedding into the attention mechanism (GraM), which can extract the local features of the non-critical point and global features of the corresponding point containing geometric structure information. According to the local and global features, the simple regression operation can obtain the transformation matrix of point cloud pairs, thereby eliminating the semantics that ignores the geometric structure relationship. GraM surpasses the state-of-the-art results by 0.548° and 0.915° regarding the relative rotation error on ModelNet40 and LowModelNet40, respectively. Full article

Underwater wireless sensor networks play an important role in underwater communication systems. Communication through collaborative communication is an effective way to solve critical problems in underwater communication systems. Underwater sensors are often deployed in spaces that overlap with those of marine mammals, which can adversely affect them. For this reason, in this paper, a marine mammal conflict avoidance method that can be dynamically adjusted according to the channel idle time duration and sensor node demand is designed, and the derivation of the maximum occupancy time duration is performed. Meanwhile, in addition, combining the potential of reinforcement learning in adaptive management, efficient resource optimization, and solving complex problems, this study also proposes a reinforcement learning-based relay-assisted spectrum switching method (R2S), which aims to achieve a reasonable allocation of spectrum resources in relay collaborative communication systems. The experimental results show that the method proposed in this study can effectively reduce the disturbance to marine mammals while performing well in terms of conflict probability, interruption probability, and quality of service. Full article

Aspect-level sentiment analysis is used to predict the sentiment polarity of a specific aspect in a sentence. However, most current research cannot fully utilize semantic information, and the models lack robustness. Therefore, this article proposes a model for aspect-level sentiment analysis based on a combination of adversarial training and dependency syntax analysis. First, BERT is used to transform word vectors and construct adjacency matrices with dependency syntactic relationships to better extract semantic dependency relationships and features between sentence components. A multi-head attention mechanism is used to fuse the features of the two parts, simultaneously perform adversarial training on the BERT embedding layer to enhance model robustness, and, finally, to predict emotional polarity. The model was tested on the SemEval 2014 Task 4 dataset. The experimental results showed that, compared with the baseline model, the model achieved significant performance improvement after incorporating adversarial training and dependency syntax relationships. Full article

This brief presents a comprehensive analysis of the output-dependent modulation (ODM) in a current-steering digital-to-analog converter (CS-DAC) based on the differential-quad switching (DQS) structure. A mathematical model is proposed to accurately describe ODM, which is categorized into two types: output transition errors and boundary effect errors. A novel approach of adding isolation devices is introduced and reinterpreted to mitigate the effect of ODM. The simulation results indicate that the inclusion of isolation devices efficiently suppresses the odd harmonics at mid-to-high frequency by a value that is 13 dB lower than before. Experimental validation is conducted on a 16-bit 250 MS/s CS-DAC fabricated in a 180 nm process. Full article

This paper introduces a novel natural language processing (NLP) model as an original approach to sentiment analysis, with a focus on understanding emotional responses during major disasters or conflicts. The model was created specifically for Croatian and is based on unigrams, but it can be used with any language that supports the n-gram model and expanded to multiple word sequences. The presented model generates a sentiment score aligned with discrete and dimensional emotion models, reliability metrics, and individual word scores using affective datasets Extended ANEW and NRC WordEmotion Association Lexicon. The sentiment analysis model incorporates different methodologies, including lexicon-based, machine learning, and hybrid approaches. The process of preprocessing includes translation, lemmatization, and data refinement, utilized automated translation services as well as the CLARIN Knowledge Centre for South Slavic languages (CLASSLA) library, with a particular emphasis on diacritical mark correction and tokenization. The presented model was experimentally evaluated on three simultaneous major natural crises that recently affected Croatia. The study’s findings reveal a significant shift in emotional dimensions during the COVID-19 pandemic, particularly a decrease in valence, arousal, and dominance, which corresponded with the two-month recovery period. Furthermore, the 2020 Croatian earthquakes elicited a wide range of negative discrete emotions, including anger, fear, and sadness, with the recuperation period much longer than in the case of COVID-19. This study represents an advancement in sentiment analysis, particularly in linguistically specific contexts, and provides insights into the emotional landscape shaped by major societal events. Full article

The scope of complex dynamical networks (CDNs) with dynamic edges is very wide, as it is composed of a class of realistic networks including web-winding systems, communication networks, neural networks, etc. However, a classic research topic in CDNs, the synchronization control problem, has not been effectively solved for CDNs with dynamic edges. This paper will investigate the emergence mechanism of synchronization from the perspective of large-scale systems. Firstly, a CDN with dynamic edges is conceptualized as an interconnected coupled system composed of an edge subsystem (ES) and a node subsystem (NS). Then, based on the proposed improved directed matrix ES model and expanded matrix inequality, this paper overcomes the limitations of coupling term design in node models and the strong correlation of tracking targets between nodes and edges. Due to the effect of the synthesized node controller and the auxiliary effect of the ES, state synchronization can be realized in the CDN. Finally, through simulation examples, the validity and advantages of our work compared to existing methods are demonstrated. Full article

Mainstream pedestrian recognition algorithms have problems such as low accuracy and insufficient real-time performance. In this study, we developed an improved pedestrian recognition algorithm named YOLO-MSP (multiscale parallel) based on residual network ideas, and we improved the network architecture based on YOLOv5s. Three pooling layers were used in parallel in the MSP module to output multiscale features and improve the accuracy of the model while ensuring real-time performance. The Swin Transformer module was also introduced into the network, which improved the efficiency of the model in image processing by avoiding global calculations. The CBAM (Convolutional Block Attention Module) attention mechanism was added to the C3 module, and this new module was named the CBAMC3 module, which improved model efficiency while ensuring the model was lightweight. The WMD-IOU (weighted multidimensional IOU) loss function proposed in this study used the shape change between the recognition frame and the real frame as a parameter to calculate the loss of the recognition frame shape, which could guide the model to better learn the shape and size of the target and optimize recognition performance. Comparative experiments using the INRIA public data set showed that the proposed YOLO-MSP algorithm outperformed state-of-the-art pedestrian recognition methods in accuracy and speed. Full article

To effectively suppress the effects of uncertainties including unmodeled dynamics and external disturbances in the vehicle stabilization system, a nonlinear robust control strategy based on a multilayer neural network is proposed in this paper. First, the mechanical and electrical coupling dynamics model of the vehicle stabilization system, considering model uncertainty and actuator dynamics, is refined. Second, the lumped uncertainty of the vehicle stabilization system is estimated by a multi-layer neural network and compensated by feedforward control. The high robustness of the system is ensured by constructing the sliding mode feedback control law. The proposed control method overcomes the limitations of sliding mode technology and the neural network and is naturally applied to the vehicle stabilization system, avoiding the adverse effects of high-gain feedback. Based on Lyapunov theory, it is demonstrated that the proposed controller is able to achieve the desired stability tracking performance. Finally, the effectiveness of the proposed control strategy is verified by co-simulation and comparative experiments. Full article

Data mining technology is the process of extracting hidden knowledge and potentially useful information from a large number of incomplete, noisy, and random practical application data. The clustering algorithm based on multi-objective evolution has obvious advantages compared with the traditional single-objective method. In order to further improve the performance of evolutionary multi-objective clustering algorithms, this paper proposes a multi-objective automatic clustering model based on evolutionary multi-task optimization. Based on the multi-objective clustering algorithm that automatically determines the value of k, evolutionary multi-task optimization is introduced to deal with multiple clustering tasks simultaneously. A set of non-dominated solutions for clustering results is obtained by concurrently optimizing the overall deviation and connectivity index. Multi-task adjacency coding based on a locus adjacency graph was designed to encode the clustered data. Additionally, an evolutionary operator based on relevance learning was designed to facilitate the evolution of individuals within the population. It also facilitates information transfer between individuals with different tasks, effectively avoiding negative transfer. Finally, the proposed algorithm was applied to both artificial datasets and UCI datasets for testing. It was then compared with traditional clustering algorithms and other multi-objective clustering algorithms. The results verify the advantages of the proposed algorithm in clustering accuracy and algorithm convergence. Full article

This paper examines the quantitative and qualitative situation of the current fixed and mobile Internet and its expected future. It provides a detailed insight into the past, present, and future of the Internet along with the development of technology and the problems that have arisen in accessing and using broadband Internet. First, the number of users and penetration rate of the Internet, the various types of services in different countries, the ranking of countries in terms of the mean and median download and upload Internet data speeds, Internet data volume, and number and location of data centers in the world are presented. The second task introduces and details twelve performance evaluation metrics for broadband Internet access. Third, different wired and wireless Internet technologies are introduced and compared based on data rate, coverage, type of infrastructure, and their advantages and disadvantages. Based on the technical and functional criteria, in the fourth work, two popular wired and wireless Internet platforms, one based on optical fiber and the other based on the 5G cellular network, are compared in the world in general and Australia in particular. Moreover, this paper has a look at Starlink as the latest satellite Internet candidate, especially for rural and remote areas. The fifth task outlines the latest technologies and emerging broadband Internet-based services and applications in the spotlight. Sixthly, it focuses on three problems in the future Internet in the world, namely the digital divide due to the different qualities of available Internet and new Internet-based services and applications of emerging technologies, the impact of the Internet on social interactions, and hacking and insecurity on the Internet. Finally, some solutions to these problems are proposed. Full article

ChatGPT (GPT-3.5), an intelligent Web-based tool capable of conducting text-based conversations akin to human interaction across various subjects, has recently gained significant popularity. This surge in interest has led researchers to examine its impact on numerous fields, including education. The aim of this paper is to investigate the perceptions of undergraduate students regarding ChatGPT’s utility in academic environments, focusing on its strengths, weaknesses, opportunities, and threats. It responds to emerging challenges in educational technology, such as the integration of artificial intelligence in teaching and learning processes. The study involved 257 students from two university departments in Greece—namely primary and early childhood education pre-service teachers. Data were collected using a structured questionnaire. Various methods were employed for data analysis, including descriptive statistics, inferential analysis, K-means clustering, and decision trees. Additional insights were obtained from a subset of students who undertook a project in an elective course, detailing the types of inquiries made to ChatGPT and their reasons for recommending (or not recommending) it to their peers. The findings offer valuable insights for tutors, researchers, educational policymakers, and ChatGPT developers. To the best of the authors’ knowledge, these issues have not been dealt with by other researchers. Full article

The Metaverse promises to change our lives and how we usually interact with the world. However, it can only evolve with technological development and entertainment engagement advances. To investigate more leads regarding this concept, we have a main search question: How are the Metaverse, gaming, and digital twins represented in Academia? To answer it, we need to verify and determine how the Metaverse is defined, how gaming, as an entertainment industry, is represented, and how Digital Twins are defined by scientific knowledge. It will also be important to analyze how these concepts are intercorrelated. Here, we present a documental study—meta-analysis—of the most relevant indexed scientific papers published in the last ten years, according to predefined inclusion and exclusion criteria. Leximancer software will help us determine the main concepts and themes extracted from these articles—namely from the Keywords, Abstracts, Methodologies, and Conclusions sections. This study allows us to understand how these concepts are perceived, contribute to a scientific discussion, and give suggestions for future research and new leads on approaching these concepts. Full article

One of the major challenges in designing a wireless indoor–outdoor communication network operating in tunnels and long corridors is to identify the optimal location of the outside station for attaining a proper coverage. It is required to formulate a combined model, describing the propagation along the tunnel and the resulting diffracted outdoor pattern from its exit. An integrated model enables estimations of the radiation patterns at the rectangular tunnel exit, as well as in the free space outside of the tunnel. The tunnel propagation model is based on a ray-tracing image model, while the free-space diffraction model is based on applying the far-field Fraunhofer diffraction equation. The model predictions of sensing the radiation intensity at the tunnel end and at a plane located at a distance ahead were compared with experimental data obtained using a down-scaled tunnel model and shorter radiation wavelength correspondingly. This down-scaling enabled detailed measurements of the radiation patterns at the tunnel exit and at the far field. The experimental measurements for the scaled tunnel case fit the theoretical model predictions. The presented model accurately described the multi-path effects emerging from inside the tunnel and the resulting outdoor diffracted pattern at a distance from the tunnel exit. Full article

In the context of strong electromagnetic interference environments, the measurement accuracy of the capacitance parameters of transmission lines under power frequency measurement methods is not high. In this paper, a capacitance parameter anti-interference measurement method for transmission lines based on harmonic components is proposed to overcome the impact of power frequency interference. When applying this method, it is first necessary to open-circuit the end of the line under test. Subsequently, apply voltage to the head end of the tested line through a step-up transformer. Due to the saturation of the transformer during no-load conditions, a large number of harmonics are generated, primarily third harmonic. The third harmonic components of voltage and current on the tested transmission line are extracted using the Fourier transform. The proposed method addresses the influence of line distribution effects by establishing a distributed parameter model for long-distance transmission lines. The relevant transmission matrix for the zero-sequence distributed parameters is obtained by combining Laplace transform and similarity transform to solve the transmission line equations. Using synchronous measurement data from the third harmonic components of voltage and current at both ends of the transmission line, combined with the transmission matrix, this method accurately measures the zero-sequence capacitance parameters. The PSCAD/EMTDC simulation results and field test outcomes have demonstrated the feasibility and accuracy of the proposed method for measuring line capacitance parameters under strong electromagnetic interference. Full article

Traditional video frame interpolation methods based on deep convolutional neural networks face challenges in handling large motions. Their performance is limited by the fact that convolutional operations cannot directly integrate the rich temporal and spatial information of inter-frame pixels, and these methods rely heavily on additional inputs such as optical flow to model motion. To address this issue, we develop a novel framework for video frame interpolation that uses Transformer to efficiently model the long-range similarity of inter-frame pixels. Furthermore, to effectively aggregate spatio-temporal features, we design a novel attention mechanism divided into temporal attention and spatial attention. Specifically, spatial attention is used to aggregate intra-frame information, integrating both attention and convolution paradigms through the simple mapping approach. Temporal attention is used to model the similarity of pixels on the timeline. This design achieves parallel processing of these two types of information without extra computational cost, aggregating information in the space–time dimension. In addition, we introduce a context extraction network and multi-scale prediction frame synthesis network to further optimize the performance of the Transformer. Our method and state-of-the-art methods are extensively quantitatively and qualitatively experimented on various benchmark datasets. On the Vimeo90K and UCF101 datasets, our model achieves improvements of 0.09 dB and 0.01 dB in the PSNR metrics over UPR-Net-large, respectively. On the Vimeo90K dataset, our model outperforms FLAVR by 0.07 dB, with only 40.56% of its parameters. The qualitative results show that for complex and large-motion scenes, our method generates sharper and more realistic edges and details. Full article

Currently, the escalating integration of renewable energy sources is causing a steady weakening of grid strength. When grid strength is weak, interactions between inverters or those between inverters and grid line impedance can provoke widespread oscillations in the power system. Additionally, the diverse DC voltage application characteristics of power converter systems (PCS) may lead to over-modulation, generating narrow pulse issues that further impact control of the midpoint potential balance. Existing dead-time elimination methods are highly susceptible to current polarity judgments, rendering them ineffective in practical use. PCS, due to inherent dead-time effects, midpoint potential imbalances in three-level topologies, and narrow pulses, can elevate low-order harmonic content in the output voltage, ultimately distorting grid-connected currents. This is particularly susceptible to causing resonance in weak grids. To enhance the output voltage waveform of PCS, this article introduces a comprehensive compensation control strategy that combines dead-time elimination, midpoint potential balance, and narrow pulse suppression, all based on an active neutral point clamped (ANPC) three-level topology. This strategy gives precedence to dead-time elimination and calculates the upper and lower limits of the zero-sequence available for midpoint potential balance while fully compensating for narrow pulses. By prioritizing dead-time elimination, followed by narrow pulse suppression and finally midpoint potential balance, this method decouples the coupling between these three factors. The effectiveness of the proposed method is validated through semi-physical simulations. Full article

The future generation of mobile networks envision Artificial Intelligence (AI) and the Internet of Things (IoT) as key enabling technologies that will foster the emergence of sophisticated use cases, with the industrial sector being one to benefit the most. This survey reviews related works in this field, with a particular focus on the specific role of network softwarization. Furthermore, the survey delves into their context and trends, categorizing works into several types and comparing them based on their contribution to the advancement of the state of the art. Since our analysis yields a lack of integrated practical implementations and a potential desynchronization with current standards, we finalize our study with a summary of challenges and future research ideas. Full article

Embedded computers are ubiquitous in products across various industries, including the automotive and medical industries, and in consumer goods such as appliances and entertainment devices. These specialized computing systems utilize Systems on Chips (SoCs), devices that are made up of one or more main microprocessor cores. SoCs are augmented with sub-blocks that perform dedicated tasks to support the system. Sub-blocks contain custom logic or small-footprint microprocessors, depending upon their complexity, and perform support functions such as clock generation, device testing, phase-locked loop synchronization and peripheral management for interfaces such as a Universal Serial Bus (USB) or Serial Peripheral Interface (SPI). SoC designers have traditionally obtained sub-blocks from commercial vendors. While these sub-blocks have well-defined interfaces, their internal implementations are opaque. Without visibility of the specifics of the implementation, SoC designers are limited to the degree to which they can optimize these off-the-shelf sub-blocks. The result is that power and area constraints are dictated by the design of a third-party vendor. This work introduces a novel idea: using an open-source, small, multitasking, real-time operating system inside an SoC sub-block to manage multiple processes, thereby conserving code space. This OS is TurbOS, a new operating system whose primary goal is to provide the highest performance using the least amount of space. It is written in the assembly language of a new pipelined 16-bit microprocessor developed at the University of Florida, the Turbo9. TurbOS is derived from and incorporates the design benefits of an existing operating system called NitrOS-9, and reduces the code size from its progenitor by nearly 20%. Furthermore, it is over 80% smaller than the popular FreeRTOS operating system. TurbOS delivers a rich feature set for managing memory and process resources that are useful in SoC sub-block applications in an extremely small footprint of only 3 kilobytes. Full article

Generalized zero-shot learning (GZSL) aims to simultaneously recognize both seen classes and unseen classes by training only on seen class samples and auxiliary semantic descriptions. Recent state-of-the-art methods infer unseen classes based on semantic information or synthesize unseen classes using generative models based on semantic information, all of which rely on the correct alignment of visual–semantic features. However, they often overlook the inconsistency between original visual features and semantic attributes. Additionally, due to the existence of cross-modal dataset biases, the visual features extracted and synthesized by the model may also mismatch with some semantic features, which could hinder the model from properly aligning visual–semantic features. To address this issue, this paper proposes a GZSL framework that enhances the consistency of visual–semantic features using a self-distillation and disentanglement network (SDDN). The aim is to utilize the self-distillation and disentanglement network to obtain semantically consistent refined visual features and non-redundant semantic features to enhance the consistency of visual–semantic features. Firstly, SDDN utilizes self-distillation technology to refine the extracted and synthesized visual features of the model. Subsequently, the visual–semantic features are then disentangled and aligned using a disentanglement network to enhance the consistency of the visual–semantic features. Finally, the consistent visual–semantic features are fused to jointly train a GZSL classifier. Extensive experiments demonstrate that the proposed method achieves more competitive results on four challenging benchmark datasets (AWA2, CUB, FLO, and SUN). Full article

This study investigated the reliability of Zener diodes subjected to a gradually increasing DC switching surge amplitude with delay internals between surges to avoid thermal degradation from different manufacturers with similar specifications. The analysis involved applying occasional 3 ms direct current (DC) switching surges with a gradual increasing surge voltage, followed by a constant current test to verify device functionality for three different selected manufacturer 5.1 V Zener diodes. This experimental approach was used to identify the maximum surge current that each Zener diode could handle before failing to clamp the surge voltage at the specified Zener reference voltage. Statistical analysis revealed significant differences in the maximum average surge current between different manufacturers. The maximum average surge current findings just before failure were 1.98 A, 3.18 A, and 3.33 A, respectively, and associated 95% confidence interval ranges can be used as a reliable metric to compare Zener diode population reliability against occasional DC switching surges. The findings revealed variations in the DC switching surge current handling capabilities between Zener diodes from different manufacturers with similar electrical specifications. The statistically measured maximum average surge current just before device failure can be considered an effective metric to compare the reliability of Zener diodes against DC switching surge degradation. Full article

This research paper introduces a new topology for multilevel inverters, emphasizing the reduction of harmonic distortion and the optimization of the component count. The complexity of an inverter is determined by the number of power switches, which is significantly reduced in the presented topology, as fewer switches require fewer driver circuits. In this proposed topology, a new single-phase generalized multilevel inverter is analyzed with an equal magnitude of voltage supply. A 9-level, 11-level, or 13-level symmetrical inverter with RL load is analyzed in MATLAB/Simulink 2019b and then experimentally validated using the dSPACE-1103 controller. The experimental verification of the load voltage and current with different modulation indices is also presented. The analysis of the proposed topology concludes that the total required number of components is lower than that necessary for the classical inverter topologies, as well as for some new proposed multilevel inverters that are also compared with the proposed topology in terms of gate driver circuits, power switches, and DC sources, which thereby enhances the goodness of the proposed topology. Thus, a comparison of this inverter with the other topologies validates its acceptance. Full article

For the vibration of automobile powertrain, this paper designs electro–hydraulic composite engine mounts. Subsequently, the dynamic characteristics of the hydraulic mount and the electromagnetic actuator were analyzed and experimentally studied separately. Due to the strong nonlinearity of the hybrid electromechanical engine mount, a Fractional-Order Least-Mean-Square (FGO-LMS) algorithm was proposed to model its secondary path identification. To validate the vibration reduction effect, a rapid control prototype test platform was established, and vibration active control experiments were conducted based on the Multiple–Input Multiple–Output Filter-x Least-Mean-Square (MIMO-FxLMS) algorithm. The results indicate that, under various operating conditions, the vibration transmitted to the chassis from the powertrain was significantly suppressed. Full article

The integration of Artificial Intelligence (AI) in Energy Storage Systems (ESS) for Electric Vehicles (EVs) has emerged as a pivotal solution to address the challenges of energy efficiency, battery degradation, and optimal power management. The capability of such systems to differ from theoretical modeling enhances their applicability across various domains. The vast amount of data available today has enabled AI to be trained and to predict the behavior of complex systems with a high degree of accuracy. As we move towards a more sustainable future, the electrification of vehicles and integrating electric systems for energy storage are becoming increasingly important and need to be addressed. The synergy of AI and ESS enhances the overall efficiency of electric vehicles and plays a crucial role in shaping a sustainable and intelligent energy ecosystem. To the best of the authors’ knowledge, AI applications in energy storage systems for the integration of electric vehicles have not been explicitly reviewed. The research investigates the importance of AI advancements in energy storage systems for electric vehicles, specifically focusing on Battery Management Systems (BMS), Power Quality (PQ) issues, predicting battery State-of-Charge (SOC) and State-of-Health (SOH), and exploring the potential for integrating Renewable Energy Sources with EV charging needs and optimizing charging cycles. This study examined all topics to identify the most commonly used methods, which were analyzed based on their characteristics and potential. Future trends were identified by exploring emerging techniques introduced in recent literature contributions published since 2017. Full article

Given the difficulty of explaining the unwrapping process through traditional teaching methodologies, this article presents the design, development, and validation of an immersive Virtual Reality (VR) serious game, named Unwrap 3D Virtual: Ready (UVR), aimed at facilitating the learning of unwrapping 3D models. The game incorporates animations to aid users in understanding the unwrapping process, following Mayer’s Cognitive Theory of Multimedia Learning and Gamification principles. Structured into four levels of increasing complexity, users progress through different aspects of 3D model unwrapping, with the final level allowing for result review. A sample of 53 students with experience in 3D modeling was categorized based on device (PC or VR) and previous experience (XP) in VR, resulting in Low-XP, Mid-XP, and High-XP groups. Hierarchical clustering identified three clusters, reflecting varied user behaviors. Results from surveys assessing game experience, presence, and satisfaction show higher immersion reported by VR users despite greater satisfaction being observed in the PC group due to a bug in the VR version. Novice users exhibited higher satisfaction, which was attributed to the novelty effect, while experienced users demonstrated greater control and proficiency. Full article

With the advancement of power systems, the integration of a substantial portion of renewable energy often leads to frequent voltage surges and increased fluctuations in distribution networks (DNs), significantly affecting the safety of DNs. Active distribution networks (ADNs) can address voltage issues arising from a high proportion of renewable energy by regulating distributed controllable resources. However, the conventional mathematical optimization-based approach to voltage reactive power control has certain limitations. It heavily depends on precise DN parameters, and its online implementation requires iterative solutions, resulting in prolonged computation time. In this study, we propose a Volt-VAR control (VVC) framework in ADNs based on multi-agent reinforcement learning (MARL). To simplify the control of photovoltaic (PV) inverters, the ADNs are initially divided into several distributed autonomous sub-networks based on the electrical distance of reactive voltage sensitivity. Subsequently, the Multi-Agent Soft Actor-Critic (MASAC) algorithm is employed to address the partitioned cooperative voltage control problem. During online deployment, the agents execute distributed cooperative control based on local observations. Comparative tests involving various methods are conducted on IEEE 33-bus and IEEE 141-bus medium-voltage DNs. The results demonstrate the effectiveness and versatility of this method in managing voltage fluctuations and mitigating reactive power loss. Full article

In this study, we present a novel approach to derive hand poses from data input via a haptic controller, leveraging machine learning techniques. The input values received from the haptic controller correspond to the movement of five fingers, each assigned a value between 0.0 and 1.0 based on the applied pressure. The wide array of possible finger movements requires a substantial amount of motion capture data, making manual data integration difficult. This challenge is primary due to the need to process and incorporate large volumes of diverse movement information. To tackle this challenge, our proposed method automates the process by utilizing machine learning algorithms to convert haptic controller inputs into hand poses. This involves training a machine learning model using supervised learning, where hand poses are matched with their corresponding input values, and subsequently utilizing this trained model to generate hand poses in response to user input. In our experiments, we assessed the accuracy of the generated hand poses by analyzing the angles and positions of finger joints. As the quantity of training data increased, the margin of error decreased, resulting in generated poses that closely emulated real-world hand movements. Full article

The motion planning task of the manipulator in a dynamic environment is relatively complex. This paper uses the improved Soft Actor Critic Algorithm (SAC) with the maximum entropy advantage as the benchmark algorithm to implement the motion planning of the manipulator. In order to solve the problem of insufficient robustness in dynamic environments and difficulty in adapting to environmental changes, it is proposed to combine Euclidean distance and distance difference to improve the accuracy of approaching the target. In addition, in order to solve the problem of non-stability and uncertainty of the input state in the dynamic environment, which leads to the inability to fully express the state information, we propose an attention network fused with Long Short-Term Memory (LSTM) to improve the SAC algorithm. We conducted simulation experiments and present the experimental results. The results prove that the use of fused neural network functions improved the success rate of approaching the target and improved the SAC algorithm at the same time, which improved the convergence speed, success rate, and avoidance capabilities of the algorithm. Full article