Electronics

23 pages, 4482 KiB

Open AccessArticle

A Novel Two-Channel Classification Approach Using Graph Attention Network with K-Nearest Neighbor

by Yang Wang, Lifeng Yin, Xiaolong Wang, Guanghai Zheng and Wu Deng

Electronics 2024, 13(20), 3985; https://doi.org/10.3390/electronics13203985 (registering DOI) - 10 Oct 2024

Graph neural networks (GNNs) typically exhibit superior performance in shallow architectures. However, as the network depth increases, issues such as overfitting and oversmoothing of hidden vector representations arise, significantly diminishing model performance. To address these challenges, this paper proposes a Two-Channel Classification Algorithm [...] Read more.

Graph neural networks (GNNs) typically exhibit superior performance in shallow architectures. However, as the network depth increases, issues such as overfitting and oversmoothing of hidden vector representations arise, significantly diminishing model performance. To address these challenges, this paper proposes a Two-Channel Classification Algorithm Based on Graph Attention Network (TCC_GAT). Initially, nodes exhibiting similar interaction behaviors are identified through cosine similarity, thereby enhancing the foundational graph structure. Subsequently, an attention mechanism is employed to adaptively integrate neighborhood information within the enhanced graph structure, with a multi-head attention mechanism applied to mitigate overfitting. Furthermore, the K-nearest neighbors algorithm is adopted to reconstruct the basic graph structure, facilitating the learning of structural information and neighborhood features that are challenging to capture on interaction graphs. This approach addresses the difficulties associated with learning high-order neighborhood information. Finally, the embedding representations of identical nodes across different graph structures are fused to optimize model classification performance, significantly enhancing node embedding representations and effectively alleviating the over-smoothing issue. Semi-supervised experiments and ablation studies conducted on the Cora, Citeseer, and Pubmed datasets reveal an accuracy improvement ranging from 1.4% to 4.5% compared to existing node classification algorithms. The experimental outcomes demonstrate that the proposed TCC_GAT achieves superior classification results in node classification tasks. Full article

(This article belongs to the Section Computer Science & Engineering)

► Show Figures

Figure 1

12 pages, 1398 KiB

Open AccessArticle

A Bullet Screen Sentiment Analysis Method That Integrates the Sentiment Lexicon with RoBERTa-CNN

by Yupan Liu, Shuo Wang and Shengshi Yu

Electronics 2024, 13(20), 3984; https://doi.org/10.3390/electronics13203984 (registering DOI) - 10 Oct 2024

Abstract

Bullet screen, a form of online video commentary in emerging social media, is widely used on video websites frequented by young people. It has become a novel means of expressing emotions towards videos. The characteristics, such as varying text lengths and the presence [...] Read more.

Bullet screen, a form of online video commentary in emerging social media, is widely used on video websites frequented by young people. It has become a novel means of expressing emotions towards videos. The characteristics, such as varying text lengths and the presence of numerous new words, lead to ambiguous emotional information. To address these characteristics, this paper proposes a Robustly Optimized BERT Pretraining Approach (RoBERTa) + Convolutional Neural Network (CNN) sentiment classification algorithm integrated with a sentiment lexicon. RoBERTa encodes the input text to enhance semantic feature representation, and CNN extracts local features using multiple convolutional kernels of different sizes. Sentiment classification is then performed by a softmax classifier. Meanwhile, we use the sentiment lexicon to calculate the emotion score of the input text and normalize the emotion score. Finally, the classification results of the sentiment lexicon and RoBERTa+CNN are weighted and calculated. The bullet screens are grouped according to their length, and different weights are assigned to the sentiment lexicon based on their length to enhance the features of the model’s sentiment classification. The method combines the sentiment lexicon can be customized for the domain vocabulary and the pre-trained model can deal with the polysemy. Experimental results demonstrate that the proposed method achieves improvements in precision, recall, and F1 score. The experiments in this paper take the Russia–Ukraine war as the research topic, and the experimental methods can be extended to other events. The experiment demonstrates the effectiveness of the model in the sentiment analysis of bullet screen texts and has a positive effect on grasping the current public opinion status of hot events and guiding the direction of public opinion in a timely manner. Full article

(This article belongs to the Special Issue New Advances in Affective Computing)

► Show Figures

Figure 1

22 pages, 3479 KiB

Open AccessArticle

Modeling, System Identification, and Control of a Railway Running Gear with Independently Rotating Wheels on a Scaled Test Rig

by Tobias Posielek

Electronics 2024, 13(20), 3983; https://doi.org/10.3390/electronics13203983 (registering DOI) - 10 Oct 2024

Abstract

The development and validation of lateral control strategies for railway running gears with independently rotating driven wheels (IRDWs) are an active research area due to their potential to enhance straight-track centering, curve steering performance, and reduce noise and wheel–rail wear. This paper focuses [...] Read more.

The development and validation of lateral control strategies for railway running gears with independently rotating driven wheels (IRDWs) are an active research area due to their potential to enhance straight-track centering, curve steering performance, and reduce noise and wheel–rail wear. This paper focuses on the practical application of theoretical models to a 1:5 scaled test rig developed by the German Aerospace Center (DLR), addressing the challenges posed by unmodeled phenomena such as hysteresis, varying damping and parameter identification. The theoretical model from prior work is adapted based on empirical measurements from the test rig, incorporating the varying open-loop stability of the front and rear wheel carriers, hysteresis effects, and other dynamic properties typically neglected in literature. A transparent procedure for identifying dynamic parameters is developed, validated through closed- and open-loop measurements. The refined model informs the design and tuning of a cascaded PI and PD controller, enhancing system stabilization by compensating for hysteresis and damping variations. The proposed approach demonstrates improved robustness and performance in controlling the lateral displacement of IRDWs, contributing to the advancement of safety-critical railway technologies. Full article

(This article belongs to the Section Systems & Control Engineering)

► Show Figures

Figure 1

12 pages, 6812 KiB

Open AccessArticle

Design of a Dual-Band Filter Based on the Band Gap Waveguide

by Shaohang Li, Yuan Yao, Xiaohe Cheng and Junsheng Yu

Electronics 2024, 13(20), 3982; https://doi.org/10.3390/electronics13203982 (registering DOI) - 10 Oct 2024

Abstract

In this paper, the design of a dual-band filter based on the band gap waveguide (BGW) is presented. In the low-frequency band, the TE₂₀₁ mode rectangular waveguide cavity resonator was used to design the bandpass filter, which significantly reduces the impact of [...] Read more.

In this paper, the design of a dual-band filter based on the band gap waveguide (BGW) is presented. In the low-frequency band, the TE₂₀₁ mode rectangular waveguide cavity resonator was used to design the bandpass filter, which significantly reduces the impact of the high-frequency transmission line (TL). In the high-frequency band, a TE₁₀₁ mode cavity resonator based on the gap waveguide (GW) structure was used to design the high-frequency band filter. A lower insertion loss can be achieved with the use of all-metal structure. A dual-band filter prototype was fabricated to verify its performance. According to the measurement results, the insertion loss is less than 1.3 dB and the return loss is better than 14 dB in the frequency range of 5.92–6.06 GHz; and the insertion loss is less than 1.77 dB and the return loss is better than 15 dB in the frequency range of 80.6–86.2 GHz. The frequency ratio is as large as 13.9, and because the high-frequency band filter is embedded in the cavity resonator of the low-frequency band filter, it saves space to a certain extent and realizes the integrated design of the dual-band filter, which is of great significance for the improvement of the performance of the dual-band communication system in higher-frequency bands. Full article

► Show Figures

Figure 1

24 pages, 738 KiB

Open AccessArticle

Tensor Core-Adapted Sparse Matrix Multiplication for Accelerating Sparse Deep Neural Networks

by Yoonsang Han, Inseo Kim, Jinsung Kim and Gordon Euhyun Moon

Electronics 2024, 13(20), 3981; https://doi.org/10.3390/electronics13203981 (registering DOI) - 10 Oct 2024

Abstract

Sparse matrix–matrix multiplication (SpMM) is essential for deep learning models and scientific computing. Recently, Tensor Cores (TCs) on GPUs, originally designed for dense matrix multiplication with mixed precision, have gained prominence. However, utilizing TCs for SpMM is challenging due to irregular memory access [...] Read more.

Sparse matrix–matrix multiplication (SpMM) is essential for deep learning models and scientific computing. Recently, Tensor Cores (TCs) on GPUs, originally designed for dense matrix multiplication with mixed precision, have gained prominence. However, utilizing TCs for SpMM is challenging due to irregular memory access patterns and a varying number of non-zero elements in a sparse matrix. To improve data locality, previous studies have proposed reordering sparse matrices before multiplication, but this adds computational overhead. In this paper, we propose Tensor Core-Adapted SpMM (TCA-SpMM), which leverages TCs without requiring matrix reordering and uses the compressed sparse row (CSR) format. To optimize TC usage, the SpMM algorithm’s dot product operation is transformed into a blocked matrix–matrix multiplication. Addressing load imbalance and minimizing data movement are critical to optimizing the SpMM kernel. Our TCA-SpMM dynamically allocates thread blocks to process multiple rows simultaneously and efficiently uses shared memory to reduce data movement. Performance results on sparse matrices from the Deep Learning Matrix Collection public dataset demonstrate that TCA-SpMM achieves up to 29.58× speedup over state-of-the-art SpMM implementations optimized with TCs. Full article

(This article belongs to the Special Issue Compiler and Hardware Design Systems for High-Performance Computing)

► Show Figures

Figure 1

22 pages, 1165 KiB

Open AccessArticle

Advanced Comparative Analysis of Machine Learning and Transformer Models for Depression and Suicide Detection in Social Media Texts

by Biodoumoye George Bokolo and Qingzhong Liu

Electronics 2024, 13(20), 3980; https://doi.org/10.3390/electronics13203980 (registering DOI) - 10 Oct 2024

Abstract

Depression detection through social media analysis has emerged as a promising approach for early intervention and mental health support. This study evaluates the performance of various machine learning and transformer models in identifying depressive content from tweets on X. Utilizing the Sentiment140 and [...] Read more.

Depression detection through social media analysis has emerged as a promising approach for early intervention and mental health support. This study evaluates the performance of various machine learning and transformer models in identifying depressive content from tweets on X. Utilizing the Sentiment140 and the Suicide-Watch dataset, we built several models which include logistic regression, Bernoulli Naive Bayes, Random Forest, and transformer models such as RoBERTa, DeBERTa, DistilBERT, and SqueezeBERT to detect this content. Our findings indicate that transformer models outperform traditional machine learning algorithms, with RoBERTa and DeBERTa, when predicting depression and suicide rates. This performance is attributed to the transformers’ ability to capture contextual nuances in language. On the other hand, logistic regression models outperform transformers in another dataset with more accurate information. This is attributed to the traditional model’s ability to understand simple patterns especially when the classes are straighforward. We employed a comprehensive cross-validation approach to ensure robustness, with transformers demonstrating higher stability and reliability across splits. Despite limitations like dataset scope and computational constraints, the findings contribute significantly to mental health monitoring and suggest promising directions for future research and real-world applications in early depression detection and mental health screening tools. The various models used performed outstandingly. Full article

(This article belongs to the Special Issue Information Retrieval and Cyber Forensics with Data Science)

► Show Figures

Figure 1

20 pages, 10975 KiB

Open AccessArticle

Hardware-Based WebAssembly Accelerator for Embedded System

by Jinyeol Kim, Raehyeong Kim, Jongwon Oh and Seung Eun Lee

Electronics 2024, 13(20), 3979; https://doi.org/10.3390/electronics13203979 (registering DOI) - 10 Oct 2024

Abstract

WebAssembly (WASM) has emerged as a novel standard aimed at enhancing the performance of web applications, developed to complement traditional JavaScript. By offering a platform-independent binary code format, WASM facilitates rapid and efficient execution within web browsers. This attribute is particularly advantageous for [...] Read more.

WebAssembly (WASM) has emerged as a novel standard aimed at enhancing the performance of web applications, developed to complement traditional JavaScript. By offering a platform-independent binary code format, WASM facilitates rapid and efficient execution within web browsers. This attribute is particularly advantageous for tasks demanding significant computational power. However, in resource-constrained environments such as embedded systems, the processing speed and memory requirements of WASM become prominent drawbacks. To address these challenges, this paper introduces the design and implementation of a hardware accelerator specifically for WASM. The proposed WASM accelerator achieves up to a 142-fold increase in computation speed for the selected algorithms compared to embedded systems. This advancement significantly enhances the execution efficiency and real-time processing capabilities of WASM in embedded systems. The paper analyzes the fundamentals of WebAssembly and provides a comprehensive description of the architecture of the accelerator designed to optimize WASM execution. Also, this paper includes the implementation details and the evaluation process, validating the utility and effectiveness of this methodology. This research makes a critical contribution to extending the applicability of WASM in embedded systems, offering a strategic direction for future technological advancements that ensure efficient execution of WASM in resource-limited environments. Full article

(This article belongs to the Special Issue Progress and Future Development of Real-Time Systems on Chip)

► Show Figures

Figure 1

22 pages, 3152 KiB

Open AccessArticle

Hybrid Feature Engineering Based on Customer Spending Behavior for Credit Card Anomaly and Fraud Detection

by Maram Alamri and Mourad Ykhlef

Electronics 2024, 13(20), 3978; https://doi.org/10.3390/electronics13203978 (registering DOI) - 10 Oct 2024

Abstract

For financial institutions, credit card fraud detection is a critical activity where the accuracy and efficiency of detection models are important. Traditional methods often use standard feature selection techniques that may ignore refined patterns in transaction data. This paper presents a new approach [...] Read more.

For financial institutions, credit card fraud detection is a critical activity where the accuracy and efficiency of detection models are important. Traditional methods often use standard feature selection techniques that may ignore refined patterns in transaction data. This paper presents a new approach that combines feature aggregation with Exhaustive Feature Selection (EFS) to enhance the performance of credit card fraud detection models. Through feature aggregation, higher-order characteristics are created to capture complex relationships within the data, then find the most relevant features by evaluating all possible subsets of features systemically using EFS. Our method was tested using a public credit card fraud dataset, PaySim. Four popular learning classifiers—random forest (RF), decision tree (DT), logistic regression (LR), and deep neural network (DNN)—are used with balanced datasets to evaluate the techniques. The findings show a large improvement in detection accuracy, F1 score, and AUPRC compared to other approaches. Specifically, our method had improved F1 score, precision, and recall measures, which underlines its ability to handle fraudulent transactions’ nuances more effectively as compared to other approaches. This article provides an overall analysis of this method’s impact on model performance, giving some insights for future studies regarding fraud detection and related fields. Full article

(This article belongs to the Special Issue New Challenges in Information Security and Privacy and Cyber Resilience)

► Show Figures

Figure 1

27 pages, 2374 KiB

Open AccessArticle

Advanced Visitor Profiling for Personalized Museum Experiences Using Telemetry-Driven Smart Badges

by Rosen Ivanov

Electronics 2024, 13(20), 3977; https://doi.org/10.3390/electronics13203977 (registering DOI) - 10 Oct 2024

Abstract

This paper presents an innovative methodology for enhancing museum visitor experiences through personalized content delivery using a combination of explicit and implicit visitor profiling. The approach integrates Bluetooth Low Energy (BLE) smart badges to collect telemetry data, enabling precise visitor localization and dynamic [...] Read more.

This paper presents an innovative methodology for enhancing museum visitor experiences through personalized content delivery using a combination of explicit and implicit visitor profiling. The approach integrates Bluetooth Low Energy (BLE) smart badges to collect telemetry data, enabling precise visitor localization and dynamic group formation based on real-time proximity and shared interests. Initial profiling begins with OAuth registration and brief surveys and is then refined through the continuous tracking of exhibit interactions and the time spent at each exhibit. An AI-driven system delivers content to individual and group profiles, fostering both personalized learning and social interaction. This methodology addresses the limitations of traditional profiling by adapting to visitor behaviors in real time while maintaining a strong focus on data privacy and ethical considerations. The proposed system not only enhances engagement and satisfaction but also sets the stage for future advancements in personalized cultural experiences. Full article

(This article belongs to the Special Issue Electronics and Computer Science for Cultural Heritage: Advancements, Preservation, and Applications)

► Show Figures

Figure 1

20 pages, 4388 KiB

Open AccessArticle

A Software Defect Prediction Method That Simultaneously Addresses Class Overlap and Noise Issues after Oversampling

by Renliang Wang, Feng Liu and Yanhui Bai

Electronics 2024, 13(20), 3976; https://doi.org/10.3390/electronics13203976 (registering DOI) - 10 Oct 2024

Abstract

Software defect prediction datasets often suffer from issues such as class imbalance, noise, and class overlap, making it difficult for classifiers to identify instances of defects. In response, researchers have proposed various techniques to mitigate the impact of these issues on classifier performance. [...] Read more.

Software defect prediction datasets often suffer from issues such as class imbalance, noise, and class overlap, making it difficult for classifiers to identify instances of defects. In response, researchers have proposed various techniques to mitigate the impact of these issues on classifier performance. Oversampling is a widely used method to address class imbalance. However, in addition to inherent noise and class overlap in the datasets themselves, oversampling methods can introduce new noise and class overlap while addressing class imbalance. To tackle these challenges, we propose a software defect prediction method called AS-KDENN, which simultaneously improves the effects of class imbalance, noise, and class overlap on classification models. AS-KDENN first performs oversampling using the Adaptive Synthetic Sampling Method (ADASYN), followed by our proposed KDENN method to address noise and class overlap. Unlike traditional methods, KDENN takes into account both the distance and local density information of overlapping samples, allowing for a more reasonable elimination of noise and instances of overlapping. To demonstrate the effectiveness of the AS-KDENN method, we conducted extensive experiments on 19 publicly available software defect prediction datasets. Compared to four commonly used oversampling techniques that also address class overlap or noise, the AS-KDENN method effectively alleviates issues of class imbalance, noise, and class overlap, subsequently improving the performance of the classifier models. Full article

► Show Figures

Figure 1

13 pages, 6806 KiB

Open AccessArticle

Dual-Branch Dynamic Object Segmentation Network Based on Spatio-Temporal Information Fusion

by Fei Huang, Zhiwen Wang, Yu Zheng, Qi Wang, Bingsen Hao and Yangkai Xiang

Electronics 2024, 13(20), 3975; https://doi.org/10.3390/electronics13203975 (registering DOI) - 10 Oct 2024

Abstract

To address the issue of low accuracy in the segmentation of dynamic objects using semantic segmentation networks, a dual-branch dynamic object segmentation network has been proposed, which is based on the fusion of spatiotemporal information. First, an appearance–motion feature fusion module is designed, [...] Read more.

To address the issue of low accuracy in the segmentation of dynamic objects using semantic segmentation networks, a dual-branch dynamic object segmentation network has been proposed, which is based on the fusion of spatiotemporal information. First, an appearance–motion feature fusion module is designed, which characterizes the motion information of objects by introducing a residual graph. This module combines a co-attention mechanism and a motion correction method to enhance the extraction of appearance features for dynamic objects. Furthermore, to mitigate boundary blurring and misclassification issues when 2D semantic information is projected back into 3D point clouds, a majority voting strategy based on time-series point cloud information has been proposed. This approach aims to overcome the limitations of post-processing in single-frame point clouds. By doing this, this method can significantly enhance the accuracy of segmenting moving objects in practical scenarios. Test results from the semantic KITTI public dataset demonstrate that our improved method outperforms mainstream dynamic object segmentation networks like LMNet and MotionSeg3D. Specifically, it achieves an Intersection over Union (IoU) of 72.19%, representing an improvement of 9.68% and 4.86% compared to LMNet and MotionSeg3D, respectively. The proposed method, with its precise algorithm, has practical applications in autonomous driving perception. Full article

(This article belongs to the Special Issue 3D Computer Vision and 3D Reconstruction)

► Show Figures

Figure 1

15 pages, 5899 KiB

Open AccessArticle

A Bidirectional Simultaneous Wireless Power and Data Transfer System with Non-Contact Slip Ring

by Yuanshuang Fan, Qiurui Chen, Sihan Wu, Jing Xiao and Zhihui Wang

Electronics 2024, 13(20), 3974; https://doi.org/10.3390/electronics13203974 (registering DOI) - 10 Oct 2024

Abstract

A non-contact slip ring is proposed in this paper. The bidirectional simultaneous wireless power and data transfer (BD-SWPDT) technology is utilized to transfer power and data bidirectionally. A bidirectional constant-voltage LC hybrid compensation topology is proposed, which utilizes the LC series parallel structure [...] Read more.

A non-contact slip ring is proposed in this paper. The bidirectional simultaneous wireless power and data transfer (BD-SWPDT) technology is utilized to transfer power and data bidirectionally. A bidirectional constant-voltage LC hybrid compensation topology is proposed, which utilizes the LC series parallel structure to have different equivalent models at different frequencies. By using different operating frequencies for forward and reverse power transfer, the system’s forward and reverse transfer can be equivalent to different constant-voltage output compensation topologies. The resonant parameters of the system are designed to achieve consistent voltage gain for forward and reverse power transfer. And based on this topology, a data carrier injection method is designed to achieve high Signal Noise Ratio (SNR) simultaneous data transfer. To improve the flexibility of non-contact slip ring installation, a caliper-type coupling structure is proposed. Finally, the feasibility of the proposed method is verified through experiments, achieving a forward and reverse output power of 200 W and half duplex communication with a data rate of 19.2 kbps. Full article

(This article belongs to the Section Microwave and Wireless Communications)

► Show Figures

Figure 1

13 pages, 432 KiB

Open AccessArticle

Transmit Precoding via Block Diagonalization with Approximately Optimized Distance Measures for Limited Feedback in Dense Cellular Networks with Multiantenna Base Stations

by Sihoon Kwak, Jae-Ik Kong and Moonsik Min

Electronics 2024, 13(20), 3973; https://doi.org/10.3390/electronics13203973 (registering DOI) - 10 Oct 2024

Abstract

This study introduces distance metrics for quantized-channel-based precoding in multiuser multiantenna systems, aiming to enhance spectral efficiency in dense cellular networks. Traditional metrics, such as the chordal distance, face limitations when dealing with scenarios involving limited feedback and multiple receive antennas. We address [...] Read more.

This study introduces distance metrics for quantized-channel-based precoding in multiuser multiantenna systems, aiming to enhance spectral efficiency in dense cellular networks. Traditional metrics, such as the chordal distance, face limitations when dealing with scenarios involving limited feedback and multiple receive antennas. We address these challenges by developing distance measures that more accurately reflect network conditions, including the impact of intercell interference. Our distance measures are specifically designed to approximate the instantaneous rate of each user by estimating the unknown components during the quantization stage. This approach enables the associated users to efficiently estimate their achievable rates during the quantization process. Our distance measures are specifically designed for block diagonalization precoding, a method known for its computational efficiency and strong performance in multi-user multiple-input and multiple-output systems. The proposed metrics outperform conventional distance measures, particularly in environments where feedback resources are constrained, as is often the case in 5G and emerging 6G networks. The enhancements are especially significant in dense cellular networks, where accurate channel state information is critical for maintaining high spectral efficiency. Our findings suggest that these new distance measures offer a robust solution for improving the performance of limited-feedback-based precoding in cellular networks. Full article

(This article belongs to the Special Issue Machine Learning (ML) Augmented Communication Techniques for Secure Mobile Heterogeneous Wireless Networks and Safety Critical Networks)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 13, Issue 20 (October-2 2024) – 13 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI