Electronics, Volume 12, Issue 13 (July-1 2023) – 247 articles

The existing expert weight determination method for multi-attribute decision making based on the Pythagorean fuzzy number approach does not make sufficient use of the hesitation involved with the decision information, which may cause biased weight assignment. Therefore, to address the issue of unknown expert weights and attribute evaluation based on Pythagorean fuzzy numbers in multi-attribute group decision-making problems, a weight determination method is proposed that improves the treatment of hesitation in Pythagorean fuzzy sets. Firstly, the proximity of experts and similarity of the modified ones are determined according to the evaluation matrix. Then, the expert weights are integrated from the aspects of proximity and corrected similarity to obtain an assembled comprehensive evaluation matrix. Finally, the alternatives are ranked using the PF-TOPSIS method. The results of expert weight analysis and data verification demonstrate that the proposed method fully utilizes expert decision-making information, leading to a significant improvement in the rationality and accuracy of multi-attribute group decision-making problems. Full article

This paper examines the flocking control issue of the Cucker–Smale model in the presence of denial-of-service (DoS) attacks and communication delays. In the setting of DoS attacks, the attacker only obstructs the information communication between agents during the activation phases, while it concentrates on supplying its own energy during the dormancy phases. Furthermore, the communication delays are assumed to be time-varying and heterogeneous. Firstly, a general control input scheme that defends against DoS network attacks and communication delays is constructed. Secondly, on the basis of the presented control input and the properties of graph theory, the flocking control issue is equivalently transformed into a products convergence issue of infinite sub-stochastic matrices. Finally, an algebraic condition is obtained to formulate all the agents that asymptotically achieve the flocking behavior. Moreover, the obtained theoretical results are verified by a numerical example. Full article

In this paper, a dual-mode step-down DC-DC converter with an automatic mode-switching circuit is implemented in a 28 nm digital CMOS process and embedded in an RF transceiver chip to power the digital part. The proposed automatic mode-switching circuit includes a frequency-voltage conversion circuit that is designed according to the principle of charge redistribution on capacitance. The converter can switch modes according to the load without external intervention. This converter, along with a PMU sequencer, can also provide a solution for low-power design for system-on-chip applications. The IC occupies a total die area of 0.378 mm². The input voltage of the converter is 3.3 V, the output voltage is 1.05 V, and the maximum load current can reach 1 A. The converter shows a conversion efficiency of not less than 81% at a full load range and can achieve a peak conversion efficiency of 91% when the load current is 100 mA. The load range of the PWM mode is 1 A to 50 mA, and that of the PFM mode is 100 mA to 1 mA. The combination of zero-crossing detection circuitry and freewheel switches can reduce energy loss and eliminate additional electromagnetic interference. Full article

Three current paths are proposed, and theoretical analysis and laboratory tests are carried out to investigate the root causes of bearing failure in IGBT inverter-fed locomotives and EMUs. The three types of current paths that run through the drive unit bearings and axle box bearings used on EMUs and electric locomotives are classified as the primary side current path, the main traction system current path, and the current path between the vehicles of the EMU or electric locomotive and the vehicles it hauls. The research found that the EDM current path in the main traction system caused by common mode voltage is distinguished as the main cause resulting in the failure of the bogie motor bearings or the bearings of the load connected to the motor shaft. The cause of common mode voltage is analyzed, and the thresholds of current density and voltage without causing bearing damage are analyzed and presented. The lab tests carried out on the bearings on the main traction system’s current path verified that the current path does exist. The proof to identify electric erosion, such as craters and washboards, and corresponding measures to prevent the failure of bogie bearings are proposed. Further research about the other two current paths is urgent and necessary. Full article

The Internet of Things (IoT) faces significant challenges in the requirements of sensitive task latency, reasonable resource allocation and reliability for resource transactions. This paper introduces a novel method for road resource allocation in the IoT context of connected and autonomous electric vehicles (CAEVs). The proposed algorithm leverages the ant colony algorithm (ACA) to effectively allocate and coordinate road resources within groups of CAEVs. By considering the energy consumption and pheromone volatilization, the allocation and coordination process of road resources are optimized. To improve the linear packet loss of RED, we adopt the advanced ACA and CRED in the NS2 platform. The experimental results demonstrate that the proposed method outperforms the RED algorithm in packet loss rate and delay time, significantly enhancing system efficiency and performance. Furthermore, the combination of the CRED algorithm and ant colony algorithm successfully mitigates short-term congestion and identifies optimized paths with minimal delay. Full article

Track processing is the foundation of radar multi-target tracking, and the processing performance for jamming has particular research significance when it comes to protecting high-value targets. At present, passive jamming using a modulated metasurface exhibits a fast response and a flexible operation mode. However, most research in this area has been carried out at the radar signal processing level and less at the data processing level. In this paper, a range of false target track deception method based on a phase-switched screen (PSS) is proposed, and the relationship between the matched filtering output, radar detection, and track processing is derived. This method uses PSS to generate multiple false targets with controlled spatial distribution and magnitude, which can form high-fidelity false tracking tracks. The number of false tracking tracks can be flexibly altered by controlling the modulation parameters. The simulation results validate the effectiveness of the proposed method. Full article

High-quality space target images are important for space surveillance and space attack defense confrontation. To obtain space target images with higher resolution and sharpness, this paper proposes an image super-resolution reconstruction network based on dual regression and a deformable convolutional attention mechanism (DCAM). Firstly, the mapping space is constrained by dual regression; secondly, deformable convolution is used to expand the perceptual field and extract the high-frequency features of the image; finally, the convolutional attention mechanism is used to calculate the saliency of the channel domain and the spatial domain of the image to enhance the useful features and suppress the useless feature responses. The experimental results show that the method outperforms the comparison algorithm in both objective quality evaluation index and localization accuracy on the space target image dataset compared with the current mainstream image super-resolution algorithms. Full article

It is well known that the fluctuations in experimentally obtained characteristic impedance versus frequency curves are associated with resonances originated by standing waves bouncing back and forth between the transitions at the transmission line terminations. In fact, microwave engineers are aware of the difficulty to completely remove the parasitic effect of these transitions, which makes obtaining smooth and physically expected frequency-dependent curves for the characteristic impedance a tough task. Here, we point out for the first time that these curves exhibit additional fluctuations within the microwave range due to standing waves taking place within the transition itself. Experimental verification of this fact was carried out by extracting this fundamental parameter from measurements performed on on-chip and printed circuit board (PCB) lines using probe pad adapters and coaxial connectors. We demonstrate that the lumped circuit approach to represent the transitions lacks validity when the additional fluctuations due to the connectors become apparent, and we propose a new model including transmission line effects within the transition. Full article

All electric vehicles are the only way to decarbonize transport quickly and substantially. Although multilevel inverters have already been used in some transportation modes, they are rarely used in road transportation, especially in light-duty passenger BEVs. With the transition to a high 800-V DC link to extend the driving range and enable extreme fast charging, the possibility of using multilevel inverters in commercial light-duty passenger BEVs becomes feasible. Higher efficiency, higher power density, better waveform quality, lower switching frequency, the possibility of using low-rated switches, and inherent fault tolerance are known advantages of multilevel inverters that make them an efficient option for replacing 2-level inverters in high DC link passenger BEVs. This paper discusses high DC link voltage benefits in light-duty passenger BEVs, presents the state-of-the-art of different conventional multilevel inverter topologies used in BEVs, and compares them with conventional 2-level inverters from different aspects and limitations. Based on commercial upper-class passengers’ BEV data and a review of multilevel inverters on the market, future trends and possible research areas are identified. Full article

Visual tracking is a key research area in computer vision, as tracking technology is increasingly being applied in daily life, it has high-research significance. Visual tracking technology usually faces various challenging interference factors, among which, a similar background is one of the factors that has a greater impact on the tracking process. Kernelized Correlation Filter (KCF) tracking algorithm can track targets quickly by using circulant matrix, and has good tracking effect, so it is widely used in the tracking field. However, when the target is interfered by similar objects, the filter template in KCF cannot effectively distinguish between the target and the interfering object. This is because the filter only uses the texture gradient feature as the description object of the target, which will make the KCF algorithm extremely sensitive to the change of the target; therefore, the filter has difficultly making a judgment in the unstable scene, cannot accurately describe the target state, and finally leads to tracking failure. Therefore, this paper fuses Color Names (CN) on the basis of the original Histogram of Oriented Gradients (HOG) feature of KCF, which can obtain a more comprehensive feature representation, and realize the application of combined features to improve the anti-interference ability of KCF in complex scenes. In addition, this paper also uses the peak response of correlation filtering as the judgment condition to determine whether the current tracking result is stable. When the filter is in an unstable tracking state, the proposed algorithm will select the value with high confidence from its multiple responses as the candidate target of the Siamese network, and the deep learning network is used as the incremental learning method of the filter. The Channel Attention is introduced into the network layer, so that the network can adaptively reason and adjust the extracted universal features, and the enhanced feature information is used as the final discriminant basis. Finally, according to the response, the target with the smallest error compared with the target template is selected from multiple candidate targets as the final tracking result. The experimental results show that the average accuracy and average success rate of the proposed algorithm are significantly improved compared with the classical tracking algorithm, especially in dealing with similar target interference. Full article

Hyperspectral images (HSIs) have abundant spectral and spatial information, which shows bright prospects in the application industry of urban–rural. Thus, HSI classification has drawn much attention from researchers. However, the spectral and spatial information-extracting method is one of the research difficulties in HSI classification tasks. To meet this tough challenge, we propose an efficient channel attentional feature fusion dense network (CA-FFDN). Our network has two structures. In the feature extraction structure, we utilized a novel bottleneck based on separable convolution (SC-bottleneck) and efficient channel attention (ECA) to simultaneously fuse spatial–spectral features from different depths, which can make full use of the dual-scale shallow and deep spatial–spectral features of the HSI and also significantly reduce the parameters. In the feature enhancement structure, we used 3D convolution and average pooling to further integrate spatial–spectral features. Many experiments on Indian Pines (IP), University of Pavia (UP), and Kennedy Space Center (KSC) datasets demonstrated that our CA-FFDN outperformed the other five state-of-the-art networks, even with small training samples. Meanwhile, our CA-FFDN achieved classification accuracies of 99.51%, 99.91%, and 99.89%, respectively, in the case where the ratio of the IP, UP, and KSC datasets was 2:1:7, 1:1:8, and 2:1:7. It provided the best classification performance with the highest accuracy, fastest convergence, and slightest training and validation loss fluctuations. Full article

The maritime sector employs the Internet of Things (IoT) to exploit many of its benefits to maintain a competitive advantage and keep up with the growing demands of the global economy. The maritime IoT (MIoT) not only inherits similar security threats as the general IoT, it also faces cyber threats that do not exist in the traditional IoT due to factors such as the support for long-distance communication and low-bandwidth connectivity. Therefore, the MIoT presents a significant concern for the sustainability and security of the maritime industry, as a successful cyber attack can be detrimental to national security and have a flow-on effect on the global economy. A common component of maritime IoT systems is Radio Frequency Identification (RFID) technology. It has been revealed in previous studies that current RFID authentication protocols are insecure against a number of attacks. This paper provides an overview of vulnerabilities relating to maritime RFID systems and systematically reviews lightweight RFID authentication protocols and their impacts if they were to be used in the maritime sector. Specifically, this paper investigates the capabilities of lightweight RFID authentication protocols that could be used in a maritime environment by evaluating those authentication protocols in terms of the encryption system, authentication method, and resistance to various wireless attacks. Full article

Driving behavior analysis has become crucial for traffic safety. In addition, more abundant driving data are needed to analyze driving behavior more comprehensively and thus improve traffic safety. This paper proposes an approach to image data extraction and driving behavior analysis that uses geographic information and driving data. Information derived from geographic and global positioning systems was used for image data extraction. In addition, we used an onboard diagnostic II and a controller area network bus logger to record driving data for driving behavior analysis. Driving behavior was analyzed using sparse automatic encoders and data exploration to detect abnormal and aggressive behavior. A regression analysis was performed to derive the relationship between aggressive driving behavior and road facilities. The results indicated that lane ratios, no lane markings, and straight lane markings are important features that affect aggressive driving behaviors. Several traffic improvements were proposed for specific intersections and roads to make drivers and pedestrians safer. Full article

The important problem of selecting the predictors in a high-dimensional case where the number of candidates is larger than the sample size is often solved by the researchers from the signal processing community using the orthogonal matching pursuit algorithm or other greedy algorithms. In this work, we show how the same problem can be solved by applying methods based on the concept of stability. Even if it is not a new concept, the stability is less known in the signal processing community. We illustrate the use of stability by presenting a relatively new algorithm from this family. As part of this presentation, we conduct a simulation study to investigate the effect of various parameters on the performance of the algorithm. Additionally, we compare the stability-based method with more than eighty variants of five different greedy algorithms in an experiment with air pollution data. The comparison demonstrates that the use of stability leads to promising results in the high-dimensional case. Full article

The security of Industrial Internet of Things (IIoT) systems is a challenge that needs to be addressed immediately, as the increasing use of new communication paradigms and the abundant use of sensors opens up new opportunities to compromise these types of systems. In this sense, technologies such as Trusted Execution Environments (TEEs) and Hardware Security Modules (HSMs) become crucial for adding new layers of security to IIoT systems, especially to edge nodes that incorporate sensors and perform continuous measurements. These technologies, coupled with new communication paradigms such as Blockchain, offer a high reliability, robustness and good interoperability between them. This paper proposes the design of a secure sensor incorporating the above mentioned technologies—HSMs and a TEE—in a hardware device based on a dual-core architecture. Through this combination of technologies, one of the cores collects the data extracted by the sensors and implements the security mechanisms to guarantee the integrity of these data, while the remaining core is responsible for sending these data through the appropriate communication protocol. This proposed approach fits into the Blockchain networks, which act as an Oracle. Finally, to illustrate the application of this concept, a use case applied to wine logistics is described, where this secure sensor is integrated into a Blockchain that collects data from the storage and transport of barrels, and a performance evaluation of the implemented prototype is provided. Full article

Multimodal sentiment analysis (MSA) has attracted more and more attention in recent years. This paper focuses on the representation learning of multimodal data to reach higher prediction results. We propose a model to assist in learning modality representations with multitask learning and contrastive learning. In addition, our approach obtains dynamic weights by considering the homoscedastic uncertainty of each task in multitask learning. Specially, we design two groups of subtasks, which predict the sentiment polarity of unimodal and bimodal representations, to assist in learning representation through a hard parameter-sharing mechanism in the upstream neural network. A loss weight is learned according to the homoscedastic uncertainty of each task. Moreover, a training strategy based on contrastive learning is designed to balance the inconsistency between training and inference caused by the randomness of the dropout layer. This method minimizes the MSE between two submodels. Experimental results on the MOSI and MOSEI datasets show our method achieves better performance than the current state-of-the-art methods by comprehensively considering the intramodality and intermodality interaction information. Full article

Diffusion magnetic resonance imaging (dMRI) is an indispensable technique in today’s neurological research, but its signal acquisition time is extremely long due to the need to acquire signals in multiple diffusion gradient directions. Supervised deep learning methods often require large amounts of complete data to support training, whereas dMRI data are difficult to obtain. We propose a deep learning model for the fast reconstruction of high angular resolution diffusion imaging in data-unpaired scenarios. Firstly, two convolutional neural networks were designed for the recovery of k-space and q-space signals, while training with unpaired data was achieved by reducing the uncertainty of the prediction results of different reconstruction orders. Then, we enabled the model to handle noisy data by using graph framelet transform. To evaluate the performance of our model, we conducted detailed comparative experiments using the public dataset from human connectome projects and compared it with various state-of-the-art methods. To demonstrate the effectiveness of each module of our model, we also conducted reasonable ablation experiments. The final results showed that our model has high efficiency and superior reconstruction performance. Full article

The limited coverage extension of mobile edge computing (MEC) necessitates exploring cooperation with unmanned aerial vehicles (UAV) to leverage advanced features for future computation-intensive and mission-critical applications. Moreover, the workflow for task offloading in software-defined networking (SDN)-enabled 5G is significant to tackle in UAV-MEC networks. In this paper, deep reinforcement learning (DRL) SDN control methods for improving computing resources are proposed. DRL-based SDN controller, termed DRL-SDNC, allocates computational resources, bandwidth, and storage based on task requirements, upper-bound tolerable delays, and network conditions, using the UAV system architecture for task exchange between MECs. DRL-SDNC configures rule installation based on state observations and agent evaluation indicators, such as network congestion, user equipment computational capabilities, and energy efficiency. This paper also proposes the training deep network architecture for the DRL-SDNC, enabling interactive and autonomous policy enforcement. The agent learns from the UAV-MEC environment through experience gathering and updates its parameters using optimization methods. DRL-SDNC collaboratively adjusts hyperparameters and network architecture to enhance learning efficiency. Compared with baseline schemes, simulation results demonstrate the effectiveness of the proposed approach in optimizing resource efficiency and achieving satisfied quality of service for efficient utilization of computing and communication resources in UAV-assisted networking environments. Full article

This paper presents two optimization methods of an interior permanent magnetic motor (IPM). The first method is based on the non-dominated sorting genetic algorithm II (NSGA-II), while the second one is based on the NSGA-III algorithm. The focus is on the reduction of the cogging torque (CT), which acts upon the rotor when the IPM is not powered, and the current that flows through the three windings is 0. The influence of the CT over the motor operation is a negative one, inducing vibrations that are not desired. The limitation of these influences is the desired way for improvement. The optimizations applied entailed the change of the geometrical configuration of the stator whilst maintaining the exterior dimensions unaltered. Through this simple but robust approach, the performance of the IPM proposed was improved. Full article

As one of foundation technologies for massive data processing for AI, event mining is attracting more and more attention, mainly including event detection (event trigger identification and event classification) and argument extraction. At present, EE-GCN is one of the most effective methods for event detection. However, since EE-GCN only focuses on event detection, complete event multi-tuple extraction needs to be improved. Inspired by the EE-GCN event detection method, this paper proposes an effective event extraction method via graph convolutional network indication with a hierarchical argument selection strategy. The method mainly includes the following steps. (1) Based on the ACE2005 argument extraction template, a new argument extraction template is established for the Baidu event extraction dataset. (2) The trigger events and event classification detected by EE-GCN are used as indicators to determine the argument extraction template, and the alternative arguments are extracted via named entity recognition based on the determined template. (3) Making full use of the side information of EE-GCN graph to solve the local and global correlation degree, and based on the local and global correlation degrees, the final argument multi-tuple is determined. (4) Finally, several experiments are conducted on the Baidu event extraction dataset to compare the proposed method with other methods. The experimental results show that the proposed method has improved the accuracy and completeness of the event extraction compared to other existing methods. Full article

Non-autoregressive neural machine translation (NAMT) has received increasing attention recently in virtue of its promising acceleration paradigm for fast decoding. However, these splendid speedup gains are at the cost of accuracy, in comparison to its autoregressive counterpart. To close this performance gap, many studies have been conducted for achieving a better quality and speed trade-off. In this paper, we survey the NAMT domain from two new perspectives, i.e., target dependency management and training strategies arrangement. Proposed approaches are elaborated at length, involving five model categories. We then collect extensive experimental data to present abundant graphs for quantitative evaluation and qualitative comparison according to the reported translation performance. Based on that, a comprehensive performance analysis is provided. Further inspection is conducted for two salient problems: target sentence length prediction and sequence-level knowledge distillation. Accumulative reinvestigation of translation quality and speedup demonstrates that non-autoregressive decoding may not run fast as it seems and still lacks authentic surpassing for accuracy. We finally prospect potential work from inner and outer facets and call for more practical and warrantable studies for the future. Full article

The automotive industry’s focus on driver-oriented issues underscores the critical importance of driver safety. This paper presents the development of advanced driver assistance system (ADAS) algorithms specifically tailored for an electric bus (e-bus) to enhance safety. The proposed approach incorporates two key components: a 360-degree surround-view system and driver behavior recognition utilizing the You Only Look Once V5 (YOLO_V5) method. The adoption of YOLO_V5 in ADASs enables rapid response by processing multiple class probabilities and region proposals within an image instantaneously. Additionally, ADAS implementation includes an image processing-based surround-view system utilizing OpenCV. In order to evaluate the performance of the proposed algorithms regarding a smart e-bus, comprehensive experimental studies were conducted. The driver behavior recognition system underwent rigorous testing using various images captured by an onboard camera. Similarly, the surround-view system’s performance was verified in diverse driving scenarios, including regular driving, parking, and parking in near-to-line situations. The results demonstrate the viability and effectiveness of the proposed system, validating its potential to significantly improve driver safety in electric buses. This paper provides a comprehensive overview of the work accomplished by emphasizing the specific contributions of the 360-degree surround-view system, driver behavior recognition using YOLO_V5, and the experimental validation conducted for an e-bus. Full article

The reliability and lifetime of systems-on-chip (SoCs) are being seriously threatened by thermal issues. In modern SoCs, dynamic thermal management (DTM) uses the thermal data captured by thermal sensors to constantly track the hot spots and thermal peak locations in real time. Estimating peak temperatures and the location of these peaks can play a crucial role for DTM systems, as temperature underestimation can cause SoCs to fail and have shortened lifetime. In this paper, a novel sensor allocation algorithm (called thermal gradient tracker, TGT), based on the recursive elimination of regions that likely do not contain any thermal peaks, is proposed for determining regions that potentially contain thermal peaks. Then, based on an empirical source temperature detection technique called GDS (gradient direction sensor), a hybrid algorithm for detecting the position and temperature of thermal peaks is also proposed to increase the accuracy of temperature sensing while trying to keep the number of thermal sensors to a minimum. The essential parameters, H and R, of the GDS technique are determined using an automated search algorithm based on simulated annealing. The proposed algorithm has been applied in a system-on-chip (SoC) in which four heat sources are present, and for temperatures ranging between 45 °C and 115 °C, in a chip area equal to 25 mm². The simulation results show that our proposed sensor allocation scheme can detect on-chip peaks with a maximum error of 1.48 °C and an average maximum error of 0.49 °C by using 15 thermal sensors. Full article

This paper proposes and simulates research on the reverse recovery characteristics of two novel superjunction (SJ) MOSFETs by adjusting the doping profile. In the manufacturing process of the SJ MOSFET using multilayer epitaxial deposition (MED), the position and concentration of each Boron bubble can be adjusted by designing different doping profiles to adjust the resistance of the upper half P-pillar. A higher P-pillar resistance can slow down the sweep out speed of hole carriers when the body diode is turned off, thus resulting in a smoother reverse recovery current and reducing the current recovery rate (d${}_{ir}$/d${}_t$) from a peak to zero. The simulation results show that the reverse recovery peak current (I${}_{rrm}$) of the two proposed devices decreased by 5% and 3%, respectively, compared to the conventional SJ. Additionally, the softness factor (S) increased by 64% and 55%, respectively. Furthermore, this study also demonstrates a trade-off relationship between static and reverse recovery characteristics with the adjustable doping profile, thus providing a guideline for actual application scenarios. Full article

The imaging performance of a semiconductor radiation imaging detector critically depends on its photoconductor layer thickness. The conventional detector structure (i.e., a photoconductor layer is sandwiched between two parallel electrodes) needs a strict design criterion on photoconductor thickness as compared to folded detector structure for optimizing the detective quantum efficiency (DQE), which is the most important imaging performance. In this paper, the DQE performance of both folded and conventional detector structures is analyzed by incorporating the quantum noise due to random charge carrier trapping in the photoconductor layer in the cascaded linear system model. An analytical expression for the variance of incomplete charge collection in folded structure is also developed. The optimum values of photoconductor layer thickness and spacing between electrodes for maximizing the DQE under various combinations of exposure, electronic noise and charge carrier transport parameters are investigated. The folded structure provides a design flexibility for achieving DQE higher than 0.7 by adjusting the distance between electrodes without compromising the quantum efficiency while the maximum possible DQE in conventional structure can be even below 0.3 for certain values of material and detector parameters. Full article

Single-image super-resolution (SISR) is an important task in image processing, aiming to achieve enhanced image resolution. With the development of deep learning, SISR based on convolutional neural networks has also gained great progress, but as the network deepens and the task of SISR becomes more complex, SISR networks become difficult to train, which hinders SISR from achieving greater success. Therefore, to further promote SISR, many challenges have emerged in recent years. In this review, we briefly review the SISR challenges organized from 2017 to 2022 and focus on the in-depth classification of these challenges, the datasets employed, the evaluation methods used, and the powerful network architectures proposed or accepted by the winners. First, depending on the tasks of the challenges, the SISR challenges can be broadly classified into four categories: classic SISR, efficient SISR, perceptual extreme SISR, and real-world SISR. Second, we introduce the datasets commonly used in the challenges in recent years and describe their characteristics. Third, we present the image evaluation methods commonly used in SISR challenges in recent years. Fourth, we introduce the network architectures used by the winners, mainly to explore in depth where the advantages of their network architectures lie and to compare the results of previous years’ winners. Finally, we summarize the methods that have been widely used in SISR in recent years and suggest several possible promising directions for future SISR. Full article

In this work, sub-micron-thick AlN/GaN transistors (HEMTs) grown on a silicon substrate for high-frequency power applications are reported. Using molecular beam epitaxy, an innovative ultrathin step-graded buffer with a total stack thickness of 450 nm enables one to combine an excellent electron confinement, as reflected by the low drain-induced barrier lowering, a low leakage current below 10 µA/mm and low trapping effects up to a drain bias V_DS = 30 V while using sub-150 nm gate lengths. As a result, state-of-the-art GaN-on-silicon power performances at 40 GHz have been achieved, showing no degradation after multiple large signal measurements in deep class AB up to V_DS = 30 V. Pulsed-mode large-signal characteristics reveal a combination of power-added efficiency (PAE) higher than 35% with a saturated output power density (P_OUT) of 2.5 W/mm at V_DS = 20 V with a gate-drain distance of 500 nm. To the best of our knowledge, this is the first demonstration of high RF performance achieved with sub-micron-thick GaN HEMTs grown on a silicon substrate. Full article

With the flourishing development of wireless communication, further challenges will be introduced by the future demands of emerging applications. However, in the face of more complex communication scenarios, favorable decoding results may not be yielded by conventional channel decoding schemes based on mathematical models. The remarkable contributions of deep neural networks (DNNs) in various fields have garnered widespread recognition, which has ignited our enthusiasm for their application in wireless communication systems. Therefore, a reliable DNN-based decoding scheme designed for wireless communication systems is proposed. This scheme comprises efficient local decoding using linear and nonlinear operations. To be specific, linear operations are carried out on the edges connecting neurons, while nonlinear operations are performed on each neuron. After forward propagation through the DNN, the loss value is estimated based on the output, and backward propagation is employed to update the weights and biases. This process is performed iteratively until a near-optimal message sequence is recovered. Various factors within the DNN are considered in the simulation and the potential impacts of each factor are analyzed. Simulation results indicate that our proposed DNN-based decoding scheme is superior to the conventional hard decision. Full article

This paper presents a novel DQ-based multicarrier pulse width modulation PWM for a single-phase, three-level PV-powered grid-connected F-type inverter. The main control objective in the proposed inverter is to regulate the grid current with low total harmonic distortion and load power components compensation. Despite the F-type inverter’s advanced advantages, there are only a few works addressing the control issue in the literature yet. The proposed control and switching methods aim to achieve both DC-side voltage balance and the lowest switching losses. The proposed scheme has been designed based on a modified multicarrier PWM switching algorithm. Consequently, the proposed control method is able to satisfy the requirements of DC-side voltage balance and achieve lower switching losses. A further advantage of the proposed control and switching methods is that they retain the main advantage of the F-Type inverter, which is that only 25% of the power switches are exposed to full DC voltage. This is an important advantage since it reduces the overall cost of the inverter and improves its reliability. Overall, the proposed modified multicarrier PWM switching algorithm appears to be a promising approach for controlling the F-Type inverter, offering improved performance and efficiency compared to other control methods. The theoretical model was verified through simulation using MATLAB/Simulink. According to the simulation results, the grid current and dc capacitor voltages are successfully managed in all operational situations. Full article