Next Issue
Volume 12, July-1
Previous Issue
Volume 12, June-1
 
 

Electronics, Volume 12, Issue 12 (June-2 2023) – 203 articles

Cover Story (view full-size image): The rise of the metaverse holds the promise of bridging the gap between the physical and virtual realms, offering users immersive experiences. As interactions within the metaverse increase, the ability to experience physical touch, such as handshakes, can greatly enhance virtual interactions. In this research, we propose the design and implementation of digital twin robotic arms which enable individuals to engage in realistic remote handshakes. The findings demonstrate a strong interest among participants in utilizing this system to partake in meaningful handshakes. Furthermore, we have identified correlations between handshake characteristics and participants' personality traits. These digital twin robotic arms serve as a bridge between the physical and digital worlds, heightening the sense of immersion in the metaverse. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
19 pages, 5966 KiB  
Article
Fabric–Metal Barrier for Low Specific Absorption Rate and Wide-Band Felt Substrate Antenna for Medical and 5G Applications
by Fatimah Fawzi Hashim, Wan Nor Liza Binti Wan Mahadi, Tarik Bin Abdul Latef and Mohamadariff Bin Othman
Electronics 2023, 12(12), 2754; https://doi.org/10.3390/electronics12122754 - 20 Jun 2023
Cited by 3 | Viewed by 1154
Abstract
This study proposed the dimensions of 55 mm × 34 mm × 1 mm for wearable antenna; the copper Y-slot patch and copper partial ground are attached to a felt substrate. The partial ground has the higher impact in antenna gain enhancement compared [...] Read more.
This study proposed the dimensions of 55 mm × 34 mm × 1 mm for wearable antenna; the copper Y-slot patch and copper partial ground are attached to a felt substrate. The partial ground has the higher impact in antenna gain enhancement compared with the full ground, making it the most suitable candidate for wearable applications and suitable for embedding in fabrics for use in medical applications. In addition, the proposed antenna design combined a fabric–metal barrier operated at 2.4 GHz 65.4% with a low specific absorption rate (SAR) of 0.01 watts per kilogramme (W/kg) and 0.006 W/kg per 10 g and a gain of 6.48 dBi. The proposed antenna has an omnidirectional radiation pattern. The two-layer barrier is designed to achieve high electromagnetic (EM) absorption and reduce the antenna’s absorption coefficient (SAR) for safe use in applications involving human activities. Simulation and measurement results on the arm and the head of the human body indicated that the antenna has excellent performance. In addition, the measurement results agreed well with the simulation results, making the proposed wearable antenna reliable for medical and 5G applications. Full article
(This article belongs to the Section Microwave and Wireless Communications)
Show Figures

Figure 1

18 pages, 1029 KiB  
Article
Virtual Network Function Migration Considering Load Balance and SFC Delay in 6G Mobile Edge Computing Networks
by Yi Yue, Xiongyan Tang, Zhiyan Zhang, Xuebei Zhang and Wencong Yang
Electronics 2023, 12(12), 2753; https://doi.org/10.3390/electronics12122753 - 20 Jun 2023
Viewed by 1303
Abstract
With the emergence of Network Function Virtualization (NFV) and Software-Defined Networks (SDN), Service Function Chaining (SFC) has evolved into a popular paradigm for carrying and fulfilling network services. However, the implementation of Mobile Edge Computing (MEC) in sixth-generation (6G) mobile networks requires efficient [...] Read more.
With the emergence of Network Function Virtualization (NFV) and Software-Defined Networks (SDN), Service Function Chaining (SFC) has evolved into a popular paradigm for carrying and fulfilling network services. However, the implementation of Mobile Edge Computing (MEC) in sixth-generation (6G) mobile networks requires efficient resource allocation mechanisms to migrate virtual network functions (VNFs). Deep learning is a promising approach to address this problem. Currently, research on VNF migration mainly focuses on how to migrate a single VNF while ignoring the VNF sharing and concurrent migration. Moreover, most existing VNF migration algorithms are complex, unscalable, and time-inefficient. This paper assumes that each placed VNF can serve multiple SFCs. We focus on selecting the best migration location for concurrently migrating VNF instances based on actual network conditions. First, we formulate the VNF migration problem as an optimization model whose goal is to minimize the end-to-end delay of all influenced SFCs while guaranteeing network load balance after migration. Next, we design a Deep Learning-based Two-Stage Algorithm (DLTSA) to solve the VNF migration problem. Finally, we combine previous experimental data to generate realistic VNF traffic patterns and evaluate the algorithm. Simulation results show that the SFC delay after migration calculated by DLTSA is close to the optimal results and much lower than the benchmarks. In addition, it effectively guarantees the load balancing of the network after migration. Full article
(This article belongs to the Special Issue Edge AI for 6G and Internet of Things)
Show Figures

Figure 1

19 pages, 11048 KiB  
Article
An Ultrathin Low-Profile Tightly Coupled Dipole Array Fed by Compact Zigzagging Baluns
by Weiwei Wu, Yuchen Yan, Shaozhi Wang, Yuhong Ma and Naichang Yuan
Electronics 2023, 12(12), 2752; https://doi.org/10.3390/electronics12122752 - 20 Jun 2023
Viewed by 943
Abstract
In this paper, we propose for the first time a novel feed approach to a tightly coupled dipole array (TCDA). Firstly, compact zigzagging microstrip feedlines are utilized as baluns to feed our array elements to obtain wideband impedance-matching characteristics. Secondly, this array is [...] Read more.
In this paper, we propose for the first time a novel feed approach to a tightly coupled dipole array (TCDA). Firstly, compact zigzagging microstrip feedlines are utilized as baluns to feed our array elements to obtain wideband impedance-matching characteristics. Secondly, this array is designed on ultrathin substrates aiming at obtaining ultra-tight coupling between the dipole arms of two neighboring elements. Some irreplaceable parasitic pads are developed and added to the radiating arms to improve both the impedance and radiation characteristics of the TCDA. With these technologies, a 12 × 12 TCDA prototype is designed, fabricated and measured for verification. The array achieves an impressive impedance bandwidth spanning of 4–18 GHz for S11<10 dB. Its radiation patterns and realized gain are measured to verify its stable electromagnetic characteristics. Its realized gain is from 15 dB to 25 dB within the operating frequency band. Its efficiency is around 91%. Its measured results show good agreement with simulations. Full article
(This article belongs to the Special Issue Advanced Technologies in Antennas and Their Applications)
Show Figures

Figure 1

15 pages, 3566 KiB  
Article
Robust Adaptive Beamforming Based on a Convolutional Neural Network
by Zhipeng Liao, Keqing Duan, Jinjun He, Zizhou Qiu and Binbin Li
Electronics 2023, 12(12), 2751; https://doi.org/10.3390/electronics12122751 - 20 Jun 2023
Cited by 1 | Viewed by 1143
Abstract
To address the advancements in jamming technology, it is imperative to consider robust adaptive beamforming (RBF) methods with finite snapshots and gain/phase (G/P) errors. This paper introduces an end-to-end RBF approach that utilizes a two-stage convolutional neural network. The first stage includes convolutional [...] Read more.
To address the advancements in jamming technology, it is imperative to consider robust adaptive beamforming (RBF) methods with finite snapshots and gain/phase (G/P) errors. This paper introduces an end-to-end RBF approach that utilizes a two-stage convolutional neural network. The first stage includes convolutional blocks and residual blocks without downsampling; the blocks assess the covariance matrix precisely using finite snapshots. The second stage maps the first stage’s output to an adaptive weight vector employing a similar structure to the first stage. The two stages are pre-trained with different datasets and fine-tuned as end-to-end networks, simplifying the network training process. The two-stage structure enables the network to possess practical physical meaning, allowing for satisfying performance even with a few snapshots in the presence of array G/P errors. We demonstrate the resulting beamformer’s performance with numerical examples and compare it to various other adaptive beamformers. Full article
Show Figures

Figure 1

17 pages, 5201 KiB  
Article
LPE-Unet: An Improved UNet Network Based on Perceptual Enhancement
by Suwei Wang, Chenxun Yuan and Caiming Zhang
Electronics 2023, 12(12), 2750; https://doi.org/10.3390/electronics12122750 - 20 Jun 2023
Cited by 1 | Viewed by 1032
Abstract
In Computed Tomography (CT) images of the coronary arteries, the segmentation of calcified plaques is extremely important for the examination, diagnosis, and treatment of coronary heart disease. However, one characteristic of the lesion is that it has a small size, which brings two [...] Read more.
In Computed Tomography (CT) images of the coronary arteries, the segmentation of calcified plaques is extremely important for the examination, diagnosis, and treatment of coronary heart disease. However, one characteristic of the lesion is that it has a small size, which brings two difficulties. One is the class imbalance when computing loss function and the other is that small-scale targets are prone to losing details in the continuous downsampling process, and the blurred boundary makes the segmentation accuracy less satisfactory. Therefore, the segmentation of calcified plaques is a very challenging task. To address the above problems, in this paper, we design a framework named LPE-UNet, which adopts an encoder–decoder structure similar to UNet. The framework includes two powerful modules named the low-rank perception enhancement module and the noise filtering module. The low-rank perception enhancement module extracts multi-scale context features by increasing the receptive field size to aid target detection and then uses an attention mechanism to filter out redundant features. The noise filtering module suppresses noise interference in shallow features to high-level features in the process of multi-scale feature fusion. It computes a pixel-wise weight map of low-level features and filters out useless and harmful information. To alleviate the problem of class imbalance caused by small-sized lesions, we use a weighted cross-entropy loss function and Dice loss to perform mixed supervised training on the network. The proposed method was evaluated on the calcified plaque segmentation dataset, achieving a high F1 score of 0.941, IoU of 0.895, and Dice of 0.944. This result verifies the effectiveness and superiority of our approach for accurately segmenting calcified plaques. As there is currently no authoritative publicly available calcified plaque segmentation dataset, we have constructed a new dataset for coronary artery calcified plaque segmentation (Calcified Plaque Segmentation Dataset, CPS Dataset). Full article
(This article belongs to the Special Issue Deep Learning for Computer Vision)
Show Figures

Figure 1

20 pages, 7392 KiB  
Article
Three-Dimensional Point Cloud-Filtering Method Based on Image Segmentation and Absolute Phase Recovery
by Jianmin Zhang, Jiale Long, Zihao Du, Yi Ding, Yuyang Peng and Jiangtao Xi
Electronics 2023, 12(12), 2749; https://doi.org/10.3390/electronics12122749 - 20 Jun 2023
Viewed by 966
Abstract
In three-dimensional (3D) shape measurement based on fringe projection, various factors can degrade the quality of the point cloud. Existing point cloud filtering methods involve analyzing the geometric relationship between 3D space and point cloud, which poses challenges such as complex calculation and [...] Read more.
In three-dimensional (3D) shape measurement based on fringe projection, various factors can degrade the quality of the point cloud. Existing point cloud filtering methods involve analyzing the geometric relationship between 3D space and point cloud, which poses challenges such as complex calculation and low efficiency. To improve the accuracy and speed of point cloud filtering, this paper proposes a new point cloud filtering method based on image segmentation and the absolute phase for the 3D imaging obtained by fringe projection. Firstly, a two-dimensional (2D) point cloud mapping image is established based on the 3D point cloud obtained from fringe projection. Secondly, threshold segmentation and region growing methods are used to segment the 2D point cloud mapping image, followed by recording and removal of the segmented noise region. Using the relationship between the noise point cloud and the absolute phase noise point in fringe projection, a reference noise-free point is established, and the absolute phase line segment is restored to obtain the absolute phase of the noise-free point. Finally, a new 2D point cloud mapping image is reconstructed in 3D space to obtain a point cloud with noise removed. Experimental results show that the point cloud denoising accuracy calculated by this method can reach up to 99.974%, and the running time is 0.954 s. The proposed method can effectively remove point cloud noise and avoid complex calculations in 3D space. This method can not only remove the noise of the 3D point cloud but also can restore the partly removed noise point cloud into a noise-free 3D point cloud, which can improve the accuracy of the 3D point cloud. Full article
Show Figures

Figure 1

22 pages, 9725 KiB  
Article
Trajectory Tracking Control of Autonomous Vehicles Based on an Improved Sliding Mode Control Scheme
by Baosen Ma, Wenhui Pei and Qi Zhang
Electronics 2023, 12(12), 2748; https://doi.org/10.3390/electronics12122748 - 20 Jun 2023
Cited by 1 | Viewed by 919
Abstract
This paper addresses the issue of external unknown environmental interference affecting the trajectory tracking performance and driving stability of autonomous vehicles. This seriously impacts the performance and stability of the vehicle while driving. In order to provide precise, reliable, and safe trajectory tracking [...] Read more.
This paper addresses the issue of external unknown environmental interference affecting the trajectory tracking performance and driving stability of autonomous vehicles. This seriously impacts the performance and stability of the vehicle while driving. In order to provide precise, reliable, and safe trajectory tracking performance for autonomous vehicles, this paper proposes a recursive integral terminal sliding mode control (RITSMC) method. The proposed RITSMC combines the advantages of recursive integral sliding mode (RISM), terminal sliding mode (TSM), and adaptive algorithms, and can effectively achieve precise trajectory tracking and driving stability of autonomous vehicles. Furthermore, compared with traditional methods, an adaptive algorithm is introduced on the recursive sliding surface to enable real-time adaptation of the control parameters of the recursive controller, further improving the trajectory tracking accuracy and driving stability of autonomous vehicles. The stability of this control system is demonstrated by using a Lyapunov function. Finally, multiple simulation tests were conducted on different lane speeds on both wet and dry asphalt road sections. By comparing the simulation results, it was found that the proposed RITSMC exhibits excellent performance in terms of the precision of tracking trajectories and the stability of driving, in contrast to traditional sliding mode controllers (SMC) and integral terminal sliding mode controllers (ITSMC). Full article
(This article belongs to the Section Electrical and Autonomous Vehicles)
Show Figures

Figure 1

20 pages, 4527 KiB  
Article
Design and Implementation of a Hierarchical Digital Twin for Power Systems Using Real-Time Simulation
by Stephan Ruhe, Kevin Schaefer, Stefan Branz, Steffen Nicolai, Peter Bretschneider and Dirk Westermann
Electronics 2023, 12(12), 2747; https://doi.org/10.3390/electronics12122747 - 20 Jun 2023
Viewed by 1388
Abstract
This paper presents a hierarchical Digital Twin architecture and implementation that uses real-time simulation to emulate the physical grid and support grid planning and operation. With the demand for detailed grid information for automated grid operations and the ongoing transformation of energy systems, [...] Read more.
This paper presents a hierarchical Digital Twin architecture and implementation that uses real-time simulation to emulate the physical grid and support grid planning and operation. With the demand for detailed grid information for automated grid operations and the ongoing transformation of energy systems, the Digital Twin can extend data acquisition by establishing a reliable real-time simulation. The system uses observer algorithms to process model information about the voltage dependencies of grid nodes, providing information about the dynamic behavior of the grid. The architecture implements multiple layers of data monitoring, processing, and simulation to create node-specific Digital Twins that are integrated into a real-time Hardware-in-the-Loop setup. The paper includes a simulation study that validates the accuracy of the Digital Twin, in terms of steady-state conditions, dynamic behavior, and required processing time. The results show that the proposed architecture can replicate the physical grid with high accuracy and corresponding dynamic behavior. Full article
Show Figures

Figure 1

21 pages, 3087 KiB  
Article
Identification of Indoor Radio Environment Properties from Channel Impulse Response with Machine Learning Models
by Teodora Kocevska, Tomaž Javornik, Aleš Švigelj, Aleksandra Rashkovska and Andrej Hrovat
Electronics 2023, 12(12), 2746; https://doi.org/10.3390/electronics12122746 - 20 Jun 2023
Viewed by 1102
Abstract
The design and optimization of next-generation indoor wireless communication networks require detailed and precise descriptions of the indoor environments. Environmental awareness can serve as a fundamental basis for the dynamic adaptation of the wireless system to channel conditions and can improve the system’s [...] Read more.
The design and optimization of next-generation indoor wireless communication networks require detailed and precise descriptions of the indoor environments. Environmental awareness can serve as a fundamental basis for the dynamic adaptation of the wireless system to channel conditions and can improve the system’s performance. Methods that combine wireless technology with machine learning are promising for identifying the properties of the indoor radio environment (RE) without requiring specialized equipment or manual intervention. In the paper, we propose an approach for identifying the materials of the surfaces using channel impulse response (CIR) and RE identification models built with machine learning. To train the models and assess their performance, we acquired radio propagation data from rooms with different sizes and materials using ray tracing. We explored tree-based methods, ensemble-based methods, kernel-based methods, and neural networks for training the models. The performance of the models is evaluated in three realistic scenarios defined by the location of the radio nodes and the room sizes. The multilayer perceptron models performed best in most of the evaluation settings. The results show that the models are capable of accurately predicting the materials in rooms with sizes that were not included in the training procedure. Including CIRs from a large number of rooms with different sizes and surface materials estimated with different radio node positions in the training process results in models with wider practical applicability. Full article
(This article belongs to the Section Microwave and Wireless Communications)
Show Figures

Figure 1

18 pages, 11512 KiB  
Article
BiGA-YOLO: A Lightweight Object Detection Network Based on YOLOv5 for Autonomous Driving
by Jun Liu, Qiqin Cai, Fumin Zou, Yintian Zhu, Lyuchao Liao and Feng Guo
Electronics 2023, 12(12), 2745; https://doi.org/10.3390/electronics12122745 - 20 Jun 2023
Cited by 4 | Viewed by 1680
Abstract
Object detection in autonomous driving scenarios has become a popular task in recent years. Due to the high-speed movement of vehicles and the complex changes in the surrounding environment, objects of different scales need to be detected, which places high demands on the [...] Read more.
Object detection in autonomous driving scenarios has become a popular task in recent years. Due to the high-speed movement of vehicles and the complex changes in the surrounding environment, objects of different scales need to be detected, which places high demands on the performance of the network model. Additionally, different driving devices have varying performance capabilities, and a lightweight model is needed to ensure the stable operation of devices with limited computing power. To address these challenges, we propose a lightweight network called BiGA-YOLO based on YOLOv5. We design the Ghost-Hardswish Conv module to simplify the convolution operations and incorporate spatial coordinate information into feature maps using Coordinate Attention. We also replace the PANet structure with the BiFPN structure to enhance the expression ability of features through different weights during the process of fusing multi-scale feature maps. Finally, we conducted extensive experiments on the KITTI dataset, and our BiGA-YOLO achieved a mAP@0.5 of 92.2% and a mAP@0.5:0.95 of 68.3%. Compared to the baseline model YOLOv5, our proposed model achieved improvements of 1.9% and 4.7% in mAP@0.5 and mAP@0.5:0.95, respectively, while reducing the model size by 15.7% and the computational cost by 16%. The detection speed was also increased by 6.3 FPS. Through analysis and discussion of the experimental results, we demonstrate that our proposed model is superior, achieving a balance between detection accuracy, model size, and detection speed. Full article
Show Figures

Figure 1

20 pages, 6597 KiB  
Article
Dynamic Reconfiguration Method of Photovoltaic Array Based on Improved HPSO Combined with Coefficient of Variation
by Shuainan Hou and Wu Zhu
Electronics 2023, 12(12), 2744; https://doi.org/10.3390/electronics12122744 - 20 Jun 2023
Cited by 3 | Viewed by 1242
Abstract
In order to address the issue of power loss resulting from partial shadow and enhance the efficiency of photovoltaic power generation, the photovoltaic array reconfiguration technology is being increasingly utilized in photovoltaic power generation systems. This paper proposes a reconfiguration method based on [...] Read more.
In order to address the issue of power loss resulting from partial shadow and enhance the efficiency of photovoltaic power generation, the photovoltaic array reconfiguration technology is being increasingly utilized in photovoltaic power generation systems. This paper proposes a reconfiguration method based on improved hybrid particle swarm optimization (HPSO) for the photovoltaic array of TCT (total-cross-tied) structure. The motivation behind this method is to get the best reconfiguration scheme in a simple and efficient manner. The ultimate goal is to enhance the output power of the array, save energy, and improve its overall efficiency. The improved HPSO introduces the concept of hybridization in genetic algorithms and adopts a nonlinear decreasing weight method to balance the local search and global search ability of the algorithm and prevent it from falling into the local optimal solution. The objective function used is the variation coefficient of the row current without the weight factor. This approach saves time and balances the row current of the array by altering the electrical connection of the component. In the 4 × 3 array, the improved HPSO is compared with the Zig-Zag method. In the 9 × 9 array, the improved HPSO is compared with the CS (competence square) method and the improved SuDoKu method. The simulation results show that the power enhancement percentage of the improved HPSO is between 6.39% and 28.26%, and the power curve tends to single peak characteristics. The improved HPSO has a smaller mismatch loss and a higher fill factor in the five shadow modes, which can effectively improve the output power, and it is convenient to track the maximum power point later. Full article
(This article belongs to the Topic Energy Saving and Energy Efficiency Technologies)
Show Figures

Figure 1

15 pages, 6186 KiB  
Article
Deep Comparisons of Neural Networks from the EEGNet Family
by Csaba Márton Köllőd, András Adolf, Kristóf Iván, Gergely Márton and István Ulbert
Electronics 2023, 12(12), 2743; https://doi.org/10.3390/electronics12122743 - 20 Jun 2023
Viewed by 1512
Abstract
A preponderance of brain–computer interface (BCI) publications proposing artificial neural networks for motor imagery (MI) electroencephalography (EEG) signal classification utilize one of the BCI Competition datasets. However, these databases encompass MI EEG data from a limited number of subjects, typically less than or [...] Read more.
A preponderance of brain–computer interface (BCI) publications proposing artificial neural networks for motor imagery (MI) electroencephalography (EEG) signal classification utilize one of the BCI Competition datasets. However, these databases encompass MI EEG data from a limited number of subjects, typically less than or equal to 10. Furthermore, the algorithms usually include only bandpass filtering as a means of reducing noise and increasing signal quality. In this study, we conducted a comparative analysis of five renowned neural networks (Shallow ConvNet, Deep ConvNet, EEGNet, EEGNet Fusion, and MI-EEGNet) utilizing open-access databases with a larger subject pool in conjunction with the BCI Competition IV 2a dataset to obtain statistically significant results. We employed the FASTER algorithm to eliminate artifacts from the EEG as a signal processing step and explored the potential for transfer learning to enhance classification results on artifact-filtered data. Our objective was to rank the neural networks; hence, in addition to classification accuracy, we introduced two supplementary metrics: accuracy improvement from chance level and the effect of transfer learning. The former is applicable to databases with varying numbers of classes, while the latter can underscore neural networks with robust generalization capabilities. Our metrics indicated that researchers should not disregard Shallow ConvNet and Deep ConvNet as they can outperform later published members of the EEGNet family. Full article
(This article belongs to the Special Issue Advances in Augmenting Human-Machine Interface)
Show Figures

Figure 1

26 pages, 5835 KiB  
Article
Chaos Moth Flame Algorithm for Multi-Objective Dynamic Economic Dispatch Integrating with Plug-In Electric Vehicles
by Wenqiang Yang, Xinxin Zhu, Fuquan Nie, Hongwei Jiao, Qinge Xiao and Zhile Yang
Electronics 2023, 12(12), 2742; https://doi.org/10.3390/electronics12122742 - 20 Jun 2023
Viewed by 847
Abstract
Dynamic economic dispatch (DED) plays an important role in the operation and control of power systems. The integration of DED with space and time makes it a complex and challenging problem in optimal decision making. By connecting plug-in electric vehicles (PEVs) to the [...] Read more.
Dynamic economic dispatch (DED) plays an important role in the operation and control of power systems. The integration of DED with space and time makes it a complex and challenging problem in optimal decision making. By connecting plug-in electric vehicles (PEVs) to the grid (V2G), the fluctuations in the grid can be mitigated, and the benefits of balancing peaks and filling valleys can be realized. However, the complexity of DED has increased with the emergence of the penetration of plug-in electric vehicles. This paper proposes a model that takes into account the day-ahead, hourly-based scheduling of power systems and the impact of PEVs. To solve the model, an improved chaos moth flame optimization algorithm (CMFO) is introduced. This algorithm has a faster convergence rate and better global optimization capabilities due to the incorporation of chaotic mapping. The feasibility of the proposed CMFO is validated through numerical experiments on benchmark functions and various generation units of different sizes. The results demonstrate the superiority of CMFO compared with other commonly used swarm intelligence algorithms. Full article
Show Figures

Figure 1

20 pages, 1917 KiB  
Article
An FPGA Architecture for the RRT Algorithm Based on Membrane Computing
by Zeyi Shang, Zhe Wei, Sergey Verlan, Jianming Li and Zhige He
Electronics 2023, 12(12), 2741; https://doi.org/10.3390/electronics12122741 - 20 Jun 2023
Viewed by 1068
Abstract
This paper investigates an FPGA architecture whose primary function is to accelerate parallel computations involved in the rapid-exploring random tree (RRT) algorithm. The RRT algorithm is inherently serial, while in each computing step there are many computations that can be executed simultaneously. Nevertheless, [...] Read more.
This paper investigates an FPGA architecture whose primary function is to accelerate parallel computations involved in the rapid-exploring random tree (RRT) algorithm. The RRT algorithm is inherently serial, while in each computing step there are many computations that can be executed simultaneously. Nevertheless, how to carry out these parallel computations on an FPGA so that a high degree of acceleration can be realized is the key issue. Membrane computing is a parallel computing paradigm inspired from the structures and functions of eukaryotic cells. As a newly proposed membrane computing model, the generalized numerical P system (GNPS) is intrinsically parallel; so, it is a good candidate for modeling parallel computations in the RRT algorithm. Open problems for the FPGA implementation of the RRT algorithm and GNPS include: (1) whether it possible to model the RRT with GNPS; (2) if yes, how to design such an FPGA architecture to achieve a better speedup; and (3) instead of implementing GNPSs with a fixed-point-number format, how to devise a GNPS FPGA architecture working with a floating-point-number format. In this paper, we modeled the RRT with a GNPS at first, showing that it is feasible to model the RRT with a GNPS. An FPGA architecture was fabricated according to the GNPS-modeled RRT. In this architecture, computations, which can be executed in parallel, are accommodated in different inner membranes of the GNPS. These membranes are designed as Verilog modules in the register transfer level model. All the computations within a membrane are triggered by the same clock impulse to implement parallel computing. The proposed architecture is validated by implementing it on the Xilinx VC707 FPGA evaluation board. Compared with the software simulation of the GNPS-modeled RRT, the FPGA architecture achieves a speedup of a 104 order of magnitude. Although this speedup is obtained on a small map, it reveals that this architecture promises to accelerate the RRT algorithm to a higher level compared with the previously reported architectures. Full article
(This article belongs to the Topic Theory and Applications of High Performance Computing)
Show Figures

Figure 1

19 pages, 7483 KiB  
Article
MGFCTFuse: A Novel Fusion Approach for Infrared and Visible Images
by Shuai Hao, Jiahao Li, Xu Ma, Siya Sun, Zhuo Tian and Le Cao
Electronics 2023, 12(12), 2740; https://doi.org/10.3390/electronics12122740 - 20 Jun 2023
Cited by 1 | Viewed by 823
Abstract
Traditional deep-learning-based fusion algorithms usually take the original image as input to extract features, which easily leads to a lack of rich details and background information in the fusion results. To address this issue, we propose a fusion algorithm, based on mutually guided [...] Read more.
Traditional deep-learning-based fusion algorithms usually take the original image as input to extract features, which easily leads to a lack of rich details and background information in the fusion results. To address this issue, we propose a fusion algorithm, based on mutually guided image filtering and cross-transmission, termed MGFCTFuse. First, an image decomposition method based on mutually guided image filtering is designed, one which decomposes the original image into a base layer and a detail layer. Second, in order to preserve as much background and detail as possible during feature extraction, the base layer is concatenated with the corresponding original image to extract deeper features. Moreover, in order to enhance the texture details in the fusion results, the information in the visible and infrared detail layers is fused, and an enhancement module is constructed to enhance the texture detail contrast. Finally, in order to enhance the communication between different features, a decoding network based on cross-transmission is designed within feature reconstruction, which further improves the quality of image fusion. In order to verify the advantages of the proposed algorithm, experiments are conducted on the TNO, MSRS, and RoadScene image fusion datasets, and the results demonstrate that the algorithm outperforms nine comparative algorithms in both subjective and objective aspects. Full article
(This article belongs to the Special Issue Robotics Vision in Challenging Environment and Applications)
Show Figures

Figure 1

16 pages, 2067 KiB  
Article
Lightweight Small Target Detection Algorithm with Multi-Feature Fusion
by Rujin Yang, Jingwei Zhang, Xinna Shang and Wenfa Li
Electronics 2023, 12(12), 2739; https://doi.org/10.3390/electronics12122739 - 20 Jun 2023
Cited by 2 | Viewed by 1433
Abstract
Unmanned aerial vehicles (UAVs) are a highly sought-after technology with numerous applications in both military and non-military uses. The identification of targets is a crucial aspect of UAV applications, but there are challenges associated with complex detection models and difficulty in detecting small [...] Read more.
Unmanned aerial vehicles (UAVs) are a highly sought-after technology with numerous applications in both military and non-military uses. The identification of targets is a crucial aspect of UAV applications, but there are challenges associated with complex detection models and difficulty in detecting small targets. To address these issues, this study proposes the lightweight L-YOLO algorithm for target detection tasks from a UAV perspective. The L-YOLO algorithm improves on YOLOv5 by improving the model’s detection performance for small targets while reducing the number of parameters and computational effort. The GhostNet module replaces the relevant convolution in the YOLOv5 model to create a lightweight model. The EIoU loss is used as the loss function of the algorithm to accelerate convergence and improve regression accuracy. Furthermore, feature-level extensions based on YOLOv5 are implemented, and a new detection head is proposed to improve the model’s detection accuracy for small targets. The size of the anchor boxes is redesigned to suit the small targets using the K-means++ clustering algorithm. The experiments were conducted on the VisDrone-2022 dataset, and the L-YOLO algorithm demonstrated a reduction in computational effort by 42.42% and number of parameters by 48.6% compared to the original algorithm. Furthermore, recall and mAP@0.5 improved by 2.1% and 1.4%, respectively. These results demonstrate that the L-YOLO algorithm not only has better detection performance for small targets but is also a lighter model, indicating promising prospects for target detection from a UAV perspective. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

16 pages, 5315 KiB  
Article
Theoretical DFT Investigation of Structure and Electronic Properties of η5-Cyclopentadienyl Half-Sandwich Organochalcogenide Complexes
by G. T. Oyeniyi, Iu. A. Melchakova, S. P. Polyutov and P. V. Avramov
Electronics 2023, 12(12), 2738; https://doi.org/10.3390/electronics12122738 - 19 Jun 2023
Viewed by 1403
Abstract
For the first time, an extensive theoretical comparative study of the electronic structure and spectra of the η5-cyclopentadienyl half-sandwich [(Cp)(EPh3)], E = Se, Te) organochalcogenides was carried out using direct space electronic structure calculations within hybrid, meta, and meta-hybrid [...] Read more.
For the first time, an extensive theoretical comparative study of the electronic structure and spectra of the η5-cyclopentadienyl half-sandwich [(Cp)(EPh3)], E = Se, Te) organochalcogenides was carried out using direct space electronic structure calculations within hybrid, meta, and meta-hybrid DFT GGA functionals coupled with double-ζ polarized 6-31G* and correlation-consistent triple-zeta cc-pVTZ-pp basis sets. The absence of covalent bonding between the cyclopentadienyl (Cp) ligands and Te/Se coordination centers was revealed. It was found that the chalcogens are partially positively charged and Cp ligands are partially negatively charged, which directly indicates a visible ionic contribution to Te/Se-Cp chemical bonding. Simulated UV–Vis absorption spectra show that all complexes have a UV-active nature, with a considerable shift in their visible light absorption due to the addition of methyl groups. The highest occupied molecular orbitals exhibit π-bonding between the Te/Se centers and Cp rings, although the majority of the orbital density is localized inside the Cp π-system. The presence of the chalcogen atoms and the extension of π-bonds across the chalcogen-ligand interface make the species promising for advanced photovoltaic and light-emitting applications. Full article
Show Figures

Figure 1

23 pages, 10195 KiB  
Article
A Secure Data-Sharing Scheme for Privacy-Preserving Supporting Node–Edge–Cloud Collaborative Computation
by Kaifa Zheng, Caiyang Ding and Jinchen Wang
Electronics 2023, 12(12), 2737; https://doi.org/10.3390/electronics12122737 - 19 Jun 2023
Cited by 1 | Viewed by 1242
Abstract
The node–edge–cloud collaborative computation paradigm has introduced new security challenges to data sharing. Existing data-sharing schemes suffer from limitations such as low efficiency and inflexibility and are not easily integrated with the node–edge–cloud environment. Additionally, they do not provide hierarchical access control or [...] Read more.
The node–edge–cloud collaborative computation paradigm has introduced new security challenges to data sharing. Existing data-sharing schemes suffer from limitations such as low efficiency and inflexibility and are not easily integrated with the node–edge–cloud environment. Additionally, they do not provide hierarchical access control or dynamic changes to access policies for data privacy preservation, leading to a poor user experience and lower security. To address these issues, we propose a data-sharing scheme using attribute-based encryption (ABE) that supports node–edge–cloud collaborative computation (DS-ABE-CC). Our scheme incorporates access policies into ciphertext, achieving fine-grained access control and data privacy preservation. Firstly, considering node–edge–cloud collaborative computation, it outsources the significant computational overhead of data sharing from the owner and user to the edge nodes and the cloud. Secondly, integrating deeply with the “node–edge–cloud” scenario, the key distribution and agreement between all entities embedded in the encryption and decryption process, with a data privacy-preserving mechanism, improve the efficiency and security. Finally, our scheme supports flexible and dynamic access control policies and realizes hierarchical access control, thereby enhancing the user experience of data sharing. The theoretical analysis confirmed the security of our scheme, while the comparison experiments with other schemes demonstrated the practical feasibility and efficiency of our approach in node–edge–cloud collaborative computation. Full article
(This article belongs to the Special Issue Security and Privacy Evaluation of Machine Learning in Networks)
Show Figures

Figure 1

16 pages, 2083 KiB  
Article
Load Disaggregation Based on a Bidirectional Dilated Residual Network with Multihead Attention
by Yifei Shu, Jieying Kang, Mei Zhou, Qi Yang, Lai Zeng and Xiaomei Yang
Electronics 2023, 12(12), 2736; https://doi.org/10.3390/electronics12122736 - 19 Jun 2023
Cited by 1 | Viewed by 1010
Abstract
Load disaggregation determines appliance-level energy consumption unintrusively from aggregated consumption measured by a single meter. Deep neural networks have been proven to have great potential in load disaggregation. In this article, a temporal convolution network, mainly consisting of residual blocks with bidirectional dilated [...] Read more.
Load disaggregation determines appliance-level energy consumption unintrusively from aggregated consumption measured by a single meter. Deep neural networks have been proven to have great potential in load disaggregation. In this article, a temporal convolution network, mainly consisting of residual blocks with bidirectional dilated convolution, the GeLu activation function, and multihead attention, is proposed to improve the prediction accuracy of individual appliances. Bidirectional dilated convolution is applied to enlarge the receptive field and effectively extract load features from historical and future information. Meanwhile, GeLU is introduced into the residual structure to overcome the “dead state” issue of traditional ReLU. Furthermore, multihead attention aims to improve the prediction accuracy by giving different weights according to the importance of different-level load features. The proposed model is validated using the REDD and UK-DALE datasets. Among six existing neural networks, the experimental results demonstrate that the proposed algorithm achieves the least average errors when disaggregating four appliances in terms of mean absolute error (MAE) and signal aggregate error (SAE), respectively, reduced by 22.33% and 60.58% compared with the model with the second-best performance on the REDD dataset. Additionally, the proposed algorithm shows superior results in identifying the on/off state in four appliances from the UK-DALE dataset. Full article
(This article belongs to the Special Issue Recent Advances in Data Science and Information Technology)
Show Figures

Figure 1

10 pages, 1361 KiB  
Communication
Self-Location Based on Grid-like Representations for Artificial Agents
by Chuanjin Dai and Lijin Xie
Electronics 2023, 12(12), 2735; https://doi.org/10.3390/electronics12122735 - 19 Jun 2023
Viewed by 680
Abstract
Self-location plays a crucial role in a framework of autonomous navigation, especially in a GNSS/radio-denied environment. At the current time, self-location for artificial agents still has to resort to the visual and laser technologies in the framework of deep neural networks, which cannot [...] Read more.
Self-location plays a crucial role in a framework of autonomous navigation, especially in a GNSS/radio-denied environment. At the current time, self-location for artificial agents still has to resort to the visual and laser technologies in the framework of deep neural networks, which cannot model the environments effectively, especially in some dynamic and complex scenes. Instead, researchers have attempted to transplant the navigation principle of mammals into artificial intelligence (AI) fields. As a kind of mammalian neuron, the grid cells are believed to provide a context-independent spatial metric and update the representation of self-location. By exploiting the mechanism of grid cells, we adopt the oscillatory interference model for location encoding. Furthermore, in the process of location decoding, the capacity of autonomous navigation is extended to a significantly wide range without the phase ambiguity, based on a multi-scale periodic representation mechanism supported by a step-wise phase unwrapping algorithm. Compared with the previous methods, the proposed grid-like self-location can achieve a much wider spatial range without the limitation imposed by the spatial scales of grid cells. It is also able to suppress the phase noise efficiently. The proposed method is validated by simulation results. Full article
(This article belongs to the Special Issue Machine Learning for Radar and Communication Signal Processing)
Show Figures

Figure 1

17 pages, 6149 KiB  
Article
An Automatic Generation and Verification Method of Software Requirements Specification
by Xiaoyang Wei, Zhengdi Wang and Shuangyuan Yang
Electronics 2023, 12(12), 2734; https://doi.org/10.3390/electronics12122734 - 19 Jun 2023
Viewed by 1067
Abstract
The generation of standardized requirements specification documents plays a crucial role in software processes. However, the manual composition of software requirements specifications is a laborious and time-consuming task, often leading to errors that deviate from the actual requirements. To address this issue, this [...] Read more.
The generation of standardized requirements specification documents plays a crucial role in software processes. However, the manual composition of software requirements specifications is a laborious and time-consuming task, often leading to errors that deviate from the actual requirements. To address this issue, this paper proposes an automated method for generating requirements specifications utilizing a knowledge graph and graphviz. Furthermore, in order to overcome the limitations of the existing automated requirement generation process, such as inadequate emphasis on data information and evaluation, we enhance the traditional U/C matrix by introducing an S/U/C matrix. This novel matrix represents the outcomes of data/function systematic analysis, and verification is facilitated through the design of inspection rules. Experimental results demonstrate that the requirements specifications generated using this method achieve standardization and adherence to regulations, while the devised S/U/C inspection rules facilitate the updating and iteration of the requirements specifications. Full article
(This article belongs to the Special Issue Applications of Big Data and AI)
Show Figures

Figure 1

24 pages, 11722 KiB  
Article
Effect of the Particle Size Distribution of Irregular Al Powder on Properties of Parts for Electronics Fabricated by Binder Jetting
by Joanna Marczyk and Marek Hebda
Electronics 2023, 12(12), 2733; https://doi.org/10.3390/electronics12122733 - 19 Jun 2023
Cited by 1 | Viewed by 1424
Abstract
The present work analyzed the influence of the particle size of irregular aluminum powder on the properties of Binder-Jetting-printed parts, which can be used as electronic components. Powders of various particle sizes as well as blends in the ratio of 73–27 wt.% or [...] Read more.
The present work analyzed the influence of the particle size of irregular aluminum powder on the properties of Binder-Jetting-printed parts, which can be used as electronic components. Powders of various particle sizes as well as blends in the ratio of 73–27 wt.% or 27–73 wt.% of coarse to fine powder particles were used. The parts were printed with constant parameters, such as a layer thickness of 120 µm, roller traverse speed of 10 mm/s, and binder saturation of 80%. For parts made of individual blends, analysis of the XRD, density, porosity, surface roughness, and dimensional changes in X, Y, and Z axes after the sintering process was conducted. The results confirmed the trend of smoothing the surface of 3D-printed parts with a reduction in the size of the powder particles used. The best results in terms of surface roughness were obtained for powder in which coarse particles (73%) had 50 µm and fine particles (27%) had 20 µm. However, the incorporation of coarser particles in an amount of 27 wt.% (AL160) to the fine-grained powder base (ALC100) allowed for the obtaining of details with higher density, lower total porosity, and relatively low surface roughness. The combination of these two powder particle sizes allowed the fine powder to fill the voids between the larger particles, resulting in properties that represent an excellent relationship between density, porosity, and surface quality. The research results indicate that the three-dimensional parts produced by Binder Jetting technology, through the phenomenal thermal conductivity of aluminum, can be successfully used as electronic components, such as heat sinks or transistor housings. Full article
(This article belongs to the Special Issue New Trends in 3D Printing for Novel Materials)
Show Figures

Figure 1

18 pages, 11703 KiB  
Article
CEEMDAN-ICA-Based Radar Monitoring of Adjacent Multi-Target Vital Signs
by Xichao Dong, Yun Feng, Chang Cui and Jun Lu
Electronics 2023, 12(12), 2732; https://doi.org/10.3390/electronics12122732 - 19 Jun 2023
Cited by 1 | Viewed by 861
Abstract
In recent years, radar, especially frequency-modulated continuous wave (FMCW) radar, has been extensively used in non-contact vital signs (NCVS) research. However, current research does not work when multiple human targets are close to each other, especially when adjacent human targets lie in the [...] Read more.
In recent years, radar, especially frequency-modulated continuous wave (FMCW) radar, has been extensively used in non-contact vital signs (NCVS) research. However, current research does not work when multiple human targets are close to each other, especially when adjacent human targets lie in the same resolution cell. In this paper, a novel method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)–independent component analysis (ICA) was proposed to obtain the vital-sign information (including respiratory rate and heart rate) of adjacent human targets by using a single FMCW radar. Firstly, the data observed at a single angle were decomposed by the CEEMDAN separation algorithm to construct virtual multi-angle observations. It can effectively transform the undetermined blind source separation (UBSS) problem into an overdetermined blind source separation (BSS) problem. Thus, a BSS algorithm based on FastICA can be used to reconstruct each person’s vital-sign signal and then calculate their respiratory rate/heart rate. To validate the effectiveness of the proposed method, experiments based on the measured data were conducted and the results show that the proposed method can obtain multi-target vital-sign information even when they are in the same resolution cell. Full article
(This article belongs to the Section Bioelectronics)
Show Figures

Figure 1

20 pages, 1582 KiB  
Article
A Location and Velocity Prediction-Assisted FANET Networking Scheme for Highly Mobile Scenarios
by Jiachi Zhang, Xueyun Wang and Liu Liu
Electronics 2023, 12(12), 2731; https://doi.org/10.3390/electronics12122731 - 19 Jun 2023
Viewed by 903
Abstract
The proliferation of flying ad hoc networks (FANETs) enables multiple applications in various scenarios. In order to construct and maintain an effective hierarchical structure in FANETs where mobile nodes proceed at high mobility, we propose a novel FANET clustering algorithm by using the [...] Read more.
The proliferation of flying ad hoc networks (FANETs) enables multiple applications in various scenarios. In order to construct and maintain an effective hierarchical structure in FANETs where mobile nodes proceed at high mobility, we propose a novel FANET clustering algorithm by using the Kalman-filter-predicted location and velocity information. First, we use the Silhouette coefficient to determine the number of clusters and the k-means++ method is utilized to group nodes into clusters. Regarding the external disturbances in highly mobile scenarios, a Kalman filter is used to predict locations and velocities for all nodes. When clustering, the relative speeds together with relative distances are considered, and the previous selected cluster heads (CHs) are utilized to initialize current centroids. Furthermore, we propose two metrics, including the cluster stability and the ratio of changed edges, to evaluate the network performance. Relevant simulation results reveal that our proposal can yield a cumulative distribution function (CDF) of cluster stability values close to the sensor-measurement-based data. Moreover, it can reduce communication overheads significantly. Full article
(This article belongs to the Special Issue Positioning and Localization in UAV Networks/Flying Ad Hoc Networks)
Show Figures

Figure 1

49 pages, 4529 KiB  
Review
Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review
by Busra Emek Soylu, Mehmet Serdar Guzel, Gazi Erkan Bostanci, Fatih Ekinci, Tunc Asuroglu and Koray Acici
Electronics 2023, 12(12), 2730; https://doi.org/10.3390/electronics12122730 - 19 Jun 2023
Cited by 7 | Viewed by 5078
Abstract
The task of semantic segmentation holds a fundamental position in the field of computer vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent times, significant advancements have been achieved in the field of semantic segmentation [...] Read more.
The task of semantic segmentation holds a fundamental position in the field of computer vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent times, significant advancements have been achieved in the field of semantic segmentation through the application of Convolutional Neural Networks (CNN) techniques based on deep learning. This paper presents a comprehensive and structured analysis of approximately 150 methods of semantic segmentation based on CNN within the last decade. Moreover, it examines 15 well-known datasets in the semantic segmentation field. These datasets consist of 2D and 3D image and video frames, including general, indoor, outdoor, and street scenes. Furthermore, this paper mentions several recent techniques, such as SAM, UDA, and common post-processing algorithms, such as CRF and MRF. Additionally, this paper analyzes the performance evaluation of reviewed state-of-the-art methods, pioneering methods, common backbone networks, and popular datasets. These have been compared according to the results of Mean Intersection over Union (MIoU), the most popular evaluation metric of semantic segmentation. Finally, it discusses the main challenges and possible solutions and underlines some future research directions in the semantic segmentation task. We hope that our survey article will be useful to provide a foreknowledge to the readers who will work in this field. Full article
Show Figures

Figure 1

18 pages, 5577 KiB  
Article
FPGA-Based Chaotic Image Encryption Using Systolic Arrays
by Furkan Ciylan, Bünyamin Ciylan and Mehmet Atak
Electronics 2023, 12(12), 2729; https://doi.org/10.3390/electronics12122729 - 19 Jun 2023
Cited by 3 | Viewed by 1071
Abstract
Along with the recent advancements in video streaming, concerns over the security of transferred data have increased. Thus, the development of fast and reliable image encryption methodologies has become an emerging research area in the field of communications. In this paper, a systolic [...] Read more.
Along with the recent advancements in video streaming, concerns over the security of transferred data have increased. Thus, the development of fast and reliable image encryption methodologies has become an emerging research area in the field of communications. In this paper, a systolic array-based image encryption architecture is proposed. Systolic arrays are used to apply the convolution operation, and a Lü–Chen chaotic oscillator is used to obtain a convolutional filter. To decrease resource consumption, a method to fuse confusion and diffusion processes by using systolic arrays is also proposed in this paper. The results show that the proposed method is highly secure against some differential and statistical attacks. It is also shown that the proposed method has a high speed of encryption compared to other methods. Full article
Show Figures

Figure 1

15 pages, 1150 KiB  
Article
Seismic Data Query Algorithm Based on Edge Computing
by Tenglong Quan, Huifeng Zhang, Yonghao Yu, Yongwei Tang, Fushun Liu and Hao Hao
Electronics 2023, 12(12), 2728; https://doi.org/10.3390/electronics12122728 - 19 Jun 2023
Cited by 2 | Viewed by 881
Abstract
Edge computing can reduce the transmission pressure of wireless networks in earthquakes by pushing computing functionalities to network edges and avoiding the data transmission to cloud servers. However, this also leads to the scattered storage of data content in each edge server, increasing [...] Read more.
Edge computing can reduce the transmission pressure of wireless networks in earthquakes by pushing computing functionalities to network edges and avoiding the data transmission to cloud servers. However, this also leads to the scattered storage of data content in each edge server, increasing the difficulty of content search. This paper investigates the seismic data query problem supported by edge computing. We first design a lookup mechanism based on bloom filter, which can quickly determine if there is the information that we need on a particular edge server. Then, the MEC-based data query problem is formulated as an optimization problem whose goal is to minimize the long-term average task delay with the constraints of computing capacity of edge servers. To reduce the complexity of problem, we further transform it as a Markov Decision Process by defining state space, action space and reward function. A novel DQN-based seismic data query algorithm is proposed to solve problem effectively. Extensive simulation-based testing shows that the proposed algorithm performances better when compared with two state-of-the-art solutions. Full article
Show Figures

Figure 1

15 pages, 3697 KiB  
Article
IoT Device Identification Method Based on Causal Inference
by Xingkui Wang, Yunhao Wu, Dan Yu, Yuli Yang, Yao Ma and Yongle Chen
Electronics 2023, 12(12), 2727; https://doi.org/10.3390/electronics12122727 - 19 Jun 2023
Viewed by 1250
Abstract
With the development of 5G, the number of IoT (Internet of Things) devices connected to the Internet will grow explosively. However, due to the vulnerability of the devices, attackers can launch attacks on the vulnerable IoT devices, causing great impact on the security [...] Read more.
With the development of 5G, the number of IoT (Internet of Things) devices connected to the Internet will grow explosively. However, due to the vulnerability of the devices, attackers can launch attacks on the vulnerable IoT devices, causing great impact on the security of the network environment. Fine-grained identification of IoT devices can help network administrators set up appropriate security policies based on the functionality and heterogeneity of the devices, while enabling timely updates and upgrades for devices with security vulnerabilities or the isolation of these dangerous devices. However, most of the existing IoT device identification methods rely on a priori knowledge or expert experience in selecting features, which cannot weigh the identification performance and labor cost. In this paper, we design a fine-grained identification method for IoT devices based on causal inference, which automatically extracts key features in the protocol fields of device communication from the perspective of causality and then classifies key features using a Stacking integrated learning method to achieve high-precision and fine-grained device identification. Through experimental verification, the proposed method achieves 96.3% and 97.7% device model identification accuracy under HTTP/TCP and SSH/TCP protocol clusters. Full article
Show Figures

Figure 1

14 pages, 5945 KiB  
Article
A Transformer-Based Cross-Window Aggregated Attentional Image Inpainting Model
by Mingju Chen, Tingting Liu, Xingzhong Xiong, Zhengxu Duan and Anle Cui
Electronics 2023, 12(12), 2726; https://doi.org/10.3390/electronics12122726 - 19 Jun 2023
Cited by 2 | Viewed by 1146
Abstract
To overcome the fault of convolutional networks, which can be over-smooth, blurred, or discontinuous, a novel transformer network with cross-window aggregated attention is proposed. Our network as a whole is constructed as a generative adversarial network model, and by embedding the Window Aggregation [...] Read more.
To overcome the fault of convolutional networks, which can be over-smooth, blurred, or discontinuous, a novel transformer network with cross-window aggregated attention is proposed. Our network as a whole is constructed as a generative adversarial network model, and by embedding the Window Aggregation Transformer (WAT) module, we improve the information aggregation between windows without increasing the computational complexity and effectively obtain the image long-range dependencies to solve the problem that convolutional operations are limited by local feature extraction. First, the encoder extracts the multi-scale features of the image with convolution kernels of different scales; second, the feature maps of different scales are input into a WAT module to realize the aggregation between feature information and finally, these features are reconstructed by the decoder, and then, the generated image is input into the global discriminator, in which the discrimination between real and fake images is completed. It is experimentally verified that our designed Transformer window attention network is able to make the structured texture of the restored images richer and more natural when performing the restoration task of large broken or structurally complex images. Full article
Show Figures

Figure 1

12 pages, 485 KiB  
Communication
A Streaming Data Processing Architecture Based on Lookup Tables
by Aximu Yuemaier, Xiaogang Chen, Xingyu Qian, Weibang Dai, Shunfen Li and Zhitang Song
Electronics 2023, 12(12), 2725; https://doi.org/10.3390/electronics12122725 - 19 Jun 2023
Viewed by 1044
Abstract
Processing in memory (PIM) is a new computing paradigm that stores the function values of some input modes in a lookup table (LUT) and retrieves their values when similar input modes are encountered (instead of performing online calculations), which is an effective way [...] Read more.
Processing in memory (PIM) is a new computing paradigm that stores the function values of some input modes in a lookup table (LUT) and retrieves their values when similar input modes are encountered (instead of performing online calculations), which is an effective way to save energy. In the era of the Internet of Things, the processing of massive data generated by the front-end requires low-power and real-time processing. This paper investigates an energy-efficient processing architecture based on table lookup in phase-change memory (PCM). This architecture replaces logical-based calculations with LUT lookups to minimize power consumption and operation latency. In order to improve the efficiency of table lookup, the RISC-V instruction set has included extended lookup and data stream transmission instructions. Finally, the system architecture is validated by hardware simulation, and the performance of computing the fast Fourier transform (FFT) application is evaluated. The proposed architecture effectively improves the execution efficiency and reduces the power consumption of data flow operations. Full article
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop