Electronics

15 pages, 2232 KiB

Open AccessArticle

Mixed Label Assignment Realizes End-to-End Object Detection

by Jiaquan Chen, Changbin Shao and Zhen Su

Electronics 2024, 13(23), 4856; https://doi.org/10.3390/electronics13234856 - 9 Dec 2024

Viewed by 388

Currently, detectors have made significant progress in inference speed and accuracy. However, these detectors require Non-Maximum Suppression (NMS) during the post-processing stage to eliminate redundant boxes, which limits the optimization of model inference speed. We first analyzed the reason for the dependence on [...] Read more.

Currently, detectors have made significant progress in inference speed and accuracy. However, these detectors require Non-Maximum Suppression (NMS) during the post-processing stage to eliminate redundant boxes, which limits the optimization of model inference speed. We first analyzed the reason for the dependence on NMS in the post-processing stage. The result showed that a score loss in a one-to-many label assignment leads to the presence of high-quality redundant boxes, making them difficult to remove. To realize end-to-end object detection and simplify the detection pipeline, we propose herein a mixed label assignment (MLA) training method, which uses one-to-many label assignment to provide rich supervision signals, alleviating the performance degradation, and we eliminate the need for NMS in the post-processing stage by using one-to-one label assignment. Additionally, a window feature propagation block (WFPB) is introduced, utilizing the inductive bias of images to enable feature sharing in local regions. Through these methods, we conducted experiments on the VOC and DUO datasets; our end-to-end detector MA-YOLOX achieved 66.0 mAP and 52.6 mAP, respectively, outperforming the YOLOX by 1.7 and 1.6. Additionally, our model performed faster than other real-time detectors without NMS. Full article

(This article belongs to the Special Issue Applications of Computer Vision, 3rd Edition)

► Show Figures

Figure 1

Figure 1
MA-YOLOX network architecture. Full article ">Figure 2
Visualization of confidence heatmaps predicted by various methods. The image is sourced from the VOC2007 test set and contains examples: ‘Man’ and ‘horse’. The methods are sequentially trained using one-to-many matching (Baseline), one-to-one matching (O2O), and mixed label allocation (MLA) proposed in this paper. The heatmaps represent the confidence scores for predictions at the “P4, P5” scale. It can be found that the O2O and MLA methods significantly reduce the redundant prediction of the same object compared to Baseline. Full article ">Figure 3
The end-to-end training method of mixed label assignment (MLA). For input images, based on the model’s predictions of regression, classification, and confidence information, compute the matching cost and choose positive samples, then use the best positive sample ‘1’ to optimize the confidence prediction head by one-to-one label assignment; the positive samples ‘1, 2, 3, 4’ are optimized by performing one-to-many matching for the regression and classification. Full article ">Figure 4
(a) The basic composition of the YOLOX backbone’s dark module; (b) the window feature propagation block (WFPB). Full article ">Figure 5
Visualization of model detection results for the VOC dataset. Full article ">Figure 6
Visualization of detection results with or without NMS by YOLOX and MA-YOLOX. Full article ">Figure 7
Visualization of ablation experiment results. Full article ">

15 pages, 5906 KiB

Open AccessArticle

A Tight Load Regulation Hysteretic Boost Converter with Compact and Energy-Efficient Anti-Phase Emulated Current Control

by Xiaohui Hu, Wanyuan Qu, Xu Yang and Yong Ding

Electronics 2024, 13(23), 4855; https://doi.org/10.3390/electronics13234855 - 9 Dec 2024

Viewed by 401

Abstract

This paper presents a novel, compact, and energy-efficient hysteretic boost converter that employs an anti-phase AC-coupling emulate current control. The proposed scheme utilizes a two-transistor current emulator and a comparator, which allow for fast transient responses and tight closed-loop regulations. This converter was [...] Read more.

This paper presents a novel, compact, and energy-efficient hysteretic boost converter that employs an anti-phase AC-coupling emulate current control. The proposed scheme utilizes a two-transistor current emulator and a comparator, which allow for fast transient responses and tight closed-loop regulations. This converter was fabricated using a 180 nm CMOS process and was capable of regulating a 5 V output with a 400 mA load capacity from an input voltage range of 2.7 V to 4.5 V. The experimental results demonstrate that the proposed anti-phase AC-coupling emulate current controlling and single hysteretic comparator controlling scheme show lower power/circuit complexity and better static and transient performance. Specifically, under load transitions ranging from 0 mA to 300 mA, the converter exhibits over/undershoot voltages of 38 mV and −42 mV, respectively. Furthermore, the measured load and line regulation performances are 5 mV/A and 2.3 mV/V, respectively. Overall, this study offers a practical and efficient solution for boosting voltage levels while maintaining stable and precise regulation. Full article

► Show Figures

Figure 1

12 pages, 325 KiB

Open AccessArticle

Supporting the Characterization of Preeclampsia Patients Through Descriptive and Clustering Analysis

by Franklin Parrales-Bravo, Rosangela Caicedo-Quiroz, Leonel Vasquez-Cevallos, Elena Tolozano-Benites, Jorge Charco-Aguirre, Julio Barzola-Monteses and Lorenzo Cevallos-Torres

Electronics 2024, 13(23), 4854; https://doi.org/10.3390/electronics13234854 - 9 Dec 2024

Viewed by 375

Abstract

One of the most common causes of maternal death during pregnancy is preeclampsia. A deeper understanding of the patient’s features can aid in the hospital’s clinical care distribution. However, at the IESS Los Ceibos Hospital, these types of studies have not been carried [...] Read more.

One of the most common causes of maternal death during pregnancy is preeclampsia. A deeper understanding of the patient’s features can aid in the hospital’s clinical care distribution. However, at the IESS Los Ceibos Hospital, these types of studies have not been carried out for preeclampsia. Therefore, in this work, we describe the application of descriptive and clustering analysis to characterize preeclamptic patients. Preeclamptic patients treated at the IESS Los Ceibos Hospital in Guayaquil comprised the dataset used in this study. Descriptive and clustering analysis allowed us to find that severe preeclampsia (O141) is the most common diagnosis when preeclamptic patients arrive at the hospitalization unit, representing 79.5% of the cases. Moreover, women whose maternal age falls between 26 and 35 years have the highest prevalence of preeclampsia, representing 55.4% of the cases. Finally, adult patients in their late 30s or older are often diagnosed with severe preeclampsia (O141) and often require many hours of hospital care during the first two visits. These findings will help to generate care and prevention policies, such as the use of a low dose of aspirin, in these age groups to avoid the complications that preeclampsia can cause. Full article

(This article belongs to the Special Issue Medical Applications of Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 16744 KiB

Open AccessArticle

Bearing Fault Diagnosis Method Based on Osprey–Cauchy–Sparrow Search Algorithm-Variational Mode Decomposition and Convolutional Neural Network-Bidirectional Long Short-Term Memory

by Zhiyuan Xiong, Haochen Jiang, Da Wang, Xu Wu and Kenan Wu

Electronics 2024, 13(23), 4853; https://doi.org/10.3390/electronics13234853 - 9 Dec 2024

Viewed by 344

Abstract

To solve the problem of the low diagnosis rate of early weak faults of rolling bearings, a novel bearing fault diagnosis method based on Variational Mode Decomposition (VMD) and convolutional neural network (CNN)−Bidirectional Long Short-Term Memory (BiLSTM) was proposed. Based on the basic [...] Read more.

To solve the problem of the low diagnosis rate of early weak faults of rolling bearings, a novel bearing fault diagnosis method based on Variational Mode Decomposition (VMD) and convolutional neural network (CNN)−Bidirectional Long Short-Term Memory (BiLSTM) was proposed. Based on the basic Sparrow Search Algorithm, the tent chaotic mapping, the Osprey Optimization Algorithm, and the Cauchy mutation were used to enhance the global search ability of the algorithm. To improve the accuracy of fault diagnosis, the BiLSTM layer is introduced into CNN to preserve the global and local features to the maximum extent. The experimental results show that VMD avoids the end effect problem in Empirical Mode Decomposition (EMD). The accuracy rate of the diagnosis model based on CNN-BILSTM reached 97.6667%, which was higher than that of the common diagnosis model. Full article

► Show Figures

Figure 1

13 pages, 2146 KiB

Open AccessArticle

Developing an Alert System for Agricultural Protection: Sika Deer Detection Using Raspberry Pi

by Sandhya Sharma, Buchaputara Pansri, Suresh Timilsina, Bishnu Prasad Gautam, Yoshifumi Okada, Shinya Watanabe, Satoshi Kondo and Kazuhiko Sato

Electronics 2024, 13(23), 4852; https://doi.org/10.3390/electronics13234852 - 9 Dec 2024

Viewed by 403

Abstract

Agricultural loss due to the overpopulation of Sika deer poses a significant challenge in Japan, leading to frequent human–wildlife conflicts. We conducted a study in Muroran, Hokkaido (42°22′56.1″ N–141°01′51.5″ E), with the objective of monitoring Sika deer and notifying farmers and locals. We [...] Read more.

Agricultural loss due to the overpopulation of Sika deer poses a significant challenge in Japan, leading to frequent human–wildlife conflicts. We conducted a study in Muroran, Hokkaido (42°22′56.1″ N–141°01′51.5″ E), with the objective of monitoring Sika deer and notifying farmers and locals. We deployed a Sika deer detection model (YOLOv8-nano) on a Raspberry Pi, integrated with an infrared camera that captured images only when a PIR sensor was triggered. To further understand the timing of Sika deer visits and potential correlations with environmental temperature and humidity, respective sensors were installed on Raspberry Pi and the data were analyzed using an ANOVA test. In addition, a buzzer was deployed to deter Sika deer from the study area. The buzzer was deactivated in the first 10 days after deployment and was activated in the following 20 days. The Sika deer detection model demonstrated excellent performance, with precision and recall values approaching 1, and a bounding box creation latency of 0.82 frames per second. Once a bounding box was established after Sika deer detection, alert notifications were automatically sent via email and the LINE messaging application, with an average notification time of 0.32 s. Regarding the buzzer’s impact on Sika deer, 35% of the detected individuals reacted by standing upright with alert ears, while 65% immediately fled the area. Analysis revealed that the time of day for Sika deer visits was significantly correlated with humidity (F = 8.95, p < 0.05), but no significant association with temperature (F = 0.681, p > 0.05). These findings represent a significant step toward mitigating human–wildlife conflicts and reducing agricultural production losses through effective conservation measures. Full article

(This article belongs to the Special Issue Machine Learning and Deep Learning in Image Analysis for Biological Systems)

► Show Figures

Figure 1

23 pages, 4776 KiB

Open AccessArticle

Research on Personalized Recommendation of Complementary Products Based on Demand Cross-Elasticity and Hypergraphs

by Ganglong Duan, Yutong Du and Yanying Shang

Electronics 2024, 13(23), 4851; https://doi.org/10.3390/electronics13234851 - 9 Dec 2024

Viewed by 337

Abstract

To improve recommendation systems, it is essential to enhance both their practicality and accuracy, thereby supporting users in making informed shopping decisions. Incorporating two types of product relationships can effectively achieve these goals: first, the product relationships, like complements, and second, the social [...] Read more.

To improve recommendation systems, it is essential to enhance both their practicality and accuracy, thereby supporting users in making informed shopping decisions. Incorporating two types of product relationships can effectively achieve these goals: first, the product relationships, like complements, and second, the social relationships among users. However, existing studies have paid little attention to user-side information or item-side information. This paper proposes a product recommendation model that utilizes cross-elasticity of demand and hypergraphs, referred to as Hg-CR. First, users and items build a hypergraph. The user–item interactions form the hyperedges. Also, users build a hypergraph between themselves based on their social relationships. Second, hypergraph attention networks (HANs) learn the relationships between nodes. They capture the key features of nodes and hyperedges with a high degree of adaptability. A community detection algorithm organizes users into groups for product recommendations by assessing their similarities. Within different communities, individuals seek complementary products based on the cross-elasticity theory of demand. Additionally, we provide recommendations for complementary products. Tests on real datasets show that the Hg-CR model is about 10% more accurate than the other baseline models. Full article

► Show Figures

Figure 1

17 pages, 1061 KiB

Open AccessReview

A Review of Emerging Sensor Technologies for Tank Inspection: A Focus on LiDAR and Hyperspectral Imaging and Their Automation and Deployment

by Sergio Pallas Enguita, Chung-Hao Chen and Samuel Kovacic

Electronics 2024, 13(23), 4850; https://doi.org/10.3390/electronics13234850 - 9 Dec 2024

Viewed by 458

Abstract

This paper reviews various sensor technologies for tank inspection, focusing on Light Detection and Ranging (LiDAR) and Hyperspectral Imaging (HSI) as advanced solutions for corrosion detection. These technologies are evaluated alongside traditional methods such as ultrasonic, electromagnetic, and thermographic inspections. This review highlights [...] Read more.

This paper reviews various sensor technologies for tank inspection, focusing on Light Detection and Ranging (LiDAR) and Hyperspectral Imaging (HSI) as advanced solutions for corrosion detection. These technologies are evaluated alongside traditional methods such as ultrasonic, electromagnetic, and thermographic inspections. This review highlights their potential to enhance inspection accuracy, reduce the limitations of manual inspection, and support integrated data analysis for comprehensive asset management. Additionally, this paper proposes a pathway for automating these techniques to streamline inspection processes and improve implementation in practical applications. Full article

(This article belongs to the Special Issue Feature Review Papers in Electronics)

► Show Figures

Figure 1

17 pages, 2114 KiB

Open AccessArticle

Research on a Passenger Flow Prediction Model Based on BWO-TCLS-Self-Attention

by Sheng Liu, Lang Du, Ting Cao and Tong Zhang

Electronics 2024, 13(23), 4849; https://doi.org/10.3390/electronics13234849 - 9 Dec 2024

Viewed by 350

Abstract

In recent years, with the rapid development of the global demand and scale for deep underground space utilization, deep space has gradually transitioned from single-purpose uses such as underground transportation, civil defense, and commerce to a comprehensive, livable, and disaster-resistant underground ecosystem. This [...] Read more.

In recent years, with the rapid development of the global demand and scale for deep underground space utilization, deep space has gradually transitioned from single-purpose uses such as underground transportation, civil defense, and commerce to a comprehensive, livable, and disaster-resistant underground ecosystem. This shift has brought increasing attention to the safety of personnel flow in deep spaces. In addressing challenges in deep space passenger flow prediction, such as irregular flow patterns, surges in extreme conditions, large data dimensions, and redundant features complicating the model, this paper proposes a deep space passenger flow prediction model that integrates a Temporal Convolutional Network (TCN) and Long Short-Term Memory (LSTM) network. The model first employs a dual-layer LSTM network structure with a Dropout layer to capture complex temporal dynamics while preventing overfitting. Then, a Self-Attention mechanism and TCN network are introduced to reduce redundant feature data and enhance the model’s performance and speed. Finally, the Beluga Whale Optimization (BWO) algorithm is used to optimize hyperparameters, further improving the prediction accuracy of the network. Experimental results demonstrate that the BWO-TCLS-Self-Attention model proposed in this paper achieves an R2 value of 96.94%, with MAE and RMSE values of 118.464 and 218.118, respectively. Compared with some mainstream prediction models, the R2 value has increased, while both MAE and RMSE values have decreased, indicating its ability to accurately predict passenger flow in deep underground spaces. Full article

(This article belongs to the Special Issue Intelligent Transportation Systems: Advances in Object Detection and Traffic Management)

► Show Figures

Figure 1

22 pages, 6936 KiB

Open AccessArticle

Design and Performance Analysis of a Parallel Pipeline Robot

by Zhonghua Shen, Menglin Xie, Zhendong Song and Danyang Bao

Electronics 2024, 13(23), 4848; https://doi.org/10.3390/electronics13234848 - 9 Dec 2024

Viewed by 316

Abstract

A parallel four-legged pipeline robot is designed to mitigate the issue of uneven motor loading on the single-leg linkage responsible for movement along the pipe diameter. This issue occurs because the drive motor located closer to the robot body requires higher torque when [...] Read more.

A parallel four-legged pipeline robot is designed to mitigate the issue of uneven motor loading on the single-leg linkage responsible for movement along the pipe diameter. This issue occurs because the drive motor located closer to the robot body requires higher torque when the serial robot operates along the inner wall of a circular polyethylene gas pipe in an urban environment. The forward and inverse kinematic equations for a single-leg linkage are derived to establish the relationship between joint angles and foot trajectories. Building on this analysis, the forward and inverse kinematic solutions for all four legs are also derived. An optimized diagonal trotting gait is selected as the robot’s walking pattern to ensure a balance between stability and movement efficiency, considering the robot’s structural configuration. Motion simulations for both the serial and parallel robots are performed using simulation software, with a detailed analysis of the displacement of the robot’s center of mass and the leg centers during movement. The driving torque of the leg motors in both configurations is controlled and examined. Simulation results indicate that the designed parallel four-legged pipeline robot achieves lower motion error and smoother leg movements within the pipe. Compared to the serial robot, the maximum torque required to drive the leg motors is reduced by approximately 33%, demonstrating the effectiveness and validity of the overall structural design. Full article

► Show Figures

Figure 1

18 pages, 1071 KiB

Open AccessArticle

PMHR: Path-Based Multi-Hop Reasoning Incorporating Rule-Enhanced Reinforcement Learning and KG Embeddings

by Ang Ma, Yanhua Yu, Chuan Shi, Shuai Zhen, Liang Pang and Tat-Seng Chua

Electronics 2024, 13(23), 4847; https://doi.org/10.3390/electronics13234847 - 9 Dec 2024

Viewed by 364

Abstract

Multi-hop reasoning provides a means for inferring indirect relationships and missing information from knowledge graphs (KGs). Reinforcement learning (RL) was recently employed for multi-hop reasoning. Although RL-based methods provide explainability, they face challenges such as sparse rewards, spurious paths, large action spaces, and [...] Read more.

Multi-hop reasoning provides a means for inferring indirect relationships and missing information from knowledge graphs (KGs). Reinforcement learning (RL) was recently employed for multi-hop reasoning. Although RL-based methods provide explainability, they face challenges such as sparse rewards, spurious paths, large action spaces, and long training and running times. In this study, we present a novel approach that combines KG embeddings and RL strategies for multi-hop reasoning called path-based multi-hop reasoning (PMHR). We address the issues of sparse rewards and spurious paths by incorporating a well-designed reward function that combines soft rewards with rule-based rewards. The rewards are adjusted based on the target entity and the path to it. Furthermore, we perform action filtering and utilize the vectors of entities and relations acquired through KG embeddings to initialize the environment, thereby significantly reducing the runtime. Experiments involving a comprehensive performance evaluation, efficiency analysis, ablation studies, and a case study were performed. The experimental results on benchmark datasets demonstrate the effectiveness of PMHR in improving KG reasoning accuracy while preserving interpretability. Compared to existing state-of-the-art models, PMHR achieved Hit@1 improvements of 0.63%, 2.02%, and 3.17% on the UMLS, Kinship, and NELL-995 datasets, respectively. PMHR provides not only improved reasoning accuracy and explainability but also optimized computational efficiency, thereby offering a robust solution for multi-hop reasoning. Full article

(This article belongs to the Special Issue Future Technologies for Data Management, Processing and Application)

► Show Figures

Figure 1

12 pages, 4219 KiB

Open AccessArticle

Analysis of the Influence of Time Harmonics on the Leakage Coefficient of Canned Permanent Magnet Synchronous Motors

by Ming Li, Rong Wang, Lei Chi and Shuxian Lun

Electronics 2024, 13(23), 4846; https://doi.org/10.3390/electronics13234846 - 9 Dec 2024

Viewed by 292

Abstract

At present, the influence of time-harmonic currents on the leakage flux coefficient of canned permanent magnet synchronous motors (CPMSMs) remains unclear. Therefore, this paper investigates and summarizes the effects of inverter time-harmonic currents on the leakage flux coefficient of the CPMSM. A 1.5 [...] Read more.

At present, the influence of time-harmonic currents on the leakage flux coefficient of canned permanent magnet synchronous motors (CPMSMs) remains unclear. Therefore, this paper investigates and summarizes the effects of inverter time-harmonic currents on the leakage flux coefficient of the CPMSM. A 1.5 kW, 9000 RPM (Revolutions Per Minute) CPMSM is used as the research subject. Based on a finite element model, the leakage flux coefficients under sinusoidal and non-sinusoidal supply conditions are calculated using the magnetic flux density integration method. Additionally, the study examines changes in the leakage flux coefficient under different harmonic orders and amplitudes. The results indicate that the introduction of fifth and seventh time-harmonic currents by the inverter reduces the leakage flux coefficient, which helps to improve the utilization of the permanent magnets. This research significantly contributes to enriching the theory of inverter-fed permanent magnet motors. Full article

► Show Figures

Figure 1

28 pages, 5412 KiB

Open AccessArticle

A Declarative Modeling Framework for Intuitive Multiple Criteria Decision Analysis in a Visual Semantic Urban Planning Environment

by Georgios Bardis

Electronics 2024, 13(23), 4845; https://doi.org/10.3390/electronics13234845 - 9 Dec 2024

Viewed by 319

Abstract

The magnitude and multiformity of recorded and readily available urban data from independent sensors and mobile user devices have paved new possibilities for city environment planning and evolution. In previous works, a visual semantic decision support system for urban planning was presented, and [...] Read more.

The magnitude and multiformity of recorded and readily available urban data from independent sensors and mobile user devices have paved new possibilities for city environment planning and evolution. In previous works, a visual semantic decision support system for urban planning was presented, and the capability of machine learning approaches, ranging from random forests to graph-based convolutional neural networks, to infer preferable directions for future development was explored, extrapolating upon previous opted locations and selected alternatives for publicly commercial services. In this work, the anterior decision-making process leading to establishment choices is addressed with the same sets of criteria and samples within the same environment. A Declarative Modeling shell is proposed, and Multiple Criteria Decision Analysis processes are adopted to encompass the DM’s/DMs’ rationale, solely relying on methodologies close to human intuition. To this end, outranking representatives from the PROMETHEE family as well as weighted sum approaches are employed, fueled by the interpretation of the declarative description of decision parameters on behalf of the DM(s), exploring the ability to achieve classifications in a straight synthetic manner, i.e., in the absence of previous knowledge, thus exhibiting the potential of decision analysis methodologies, enhanced by Declarative Modeling, to be used as powerful intuitive tools in similar paradigm contexts. Full article

(This article belongs to the Special Issue New Challenges of Decision Support Systems)

► Show Figures

Figure 1

17 pages, 1791 KiB

Open AccessArticle

Apple Defect Detection in Complex Environments

by Wei Shan and Yurong Yue

Electronics 2024, 13(23), 4844; https://doi.org/10.3390/electronics13234844 - 9 Dec 2024

Viewed by 349

Abstract

Aiming at the problem of high false detection and missed detection rate of apple surface defects in complex environments, a new apple surface defect detection network: space-to-depth convolution-Multi-scale Empty Attention-Context Guided Feature Pyramid Network-You Only Look Once version 8 nano (SMC-YOLOv8n) is designed. [...] Read more.

Aiming at the problem of high false detection and missed detection rate of apple surface defects in complex environments, a new apple surface defect detection network: space-to-depth convolution-Multi-scale Empty Attention-Context Guided Feature Pyramid Network-You Only Look Once version 8 nano (SMC-YOLOv8n) is designed. Firstly, space-to-depth convolution (SPD-Conv) is introduced before each Faster Implementation of CSP Bottleneck with 2 convolutions (C2f) in the backbone network as a preprocessing step to improve the quality of input data. Secondly, the Bottleneck in C2f is removed in the neck, and Multi-scale Empty Attention (MSDA) is introduced to enhance the feature extraction ability. Finally, the Context Guided Feature Pyramid Network (CGFPN) is used to replace the Concat method of the neck for feature fusion, thereby improving the expression ability of the features. Compared with the YOLOv8n baseline network, mean Average Precision (mAP) 50 increased by 2.7% and 1.1%, respectively, and mAP50-95 increased by 4.1% and 2.7%, respectively, on the visible light apple surface defect data set and public data set in the self-made complex environments.The experimental results show that SMC-YOLOv8n shows higher efficiency in apple defect detection, which lays a solid foundation for intelligent picking and grading of apples. Full article

► Show Figures

Figure 1

23 pages, 4893 KiB

Open AccessFeature PaperArticle

Enhancing Software Effort Estimation with Pre-Trained Word Embeddings: A Small-Dataset Solution for Accurate Story Point Prediction

by Issa Atoum and Ahmed Ali Otoom

Electronics 2024, 13(23), 4843; https://doi.org/10.3390/electronics13234843 - 8 Dec 2024

Viewed by 613

Abstract

Traditional software effort estimation methods, such as term frequency–inverse document frequency (TF-IDF), are widely used due to their simplicity and interpretability. However, they struggle with limited datasets, fail to capture intricate semantics, and suffer from dimensionality, sparsity, and computational inefficiency. This study used [...] Read more.

Traditional software effort estimation methods, such as term frequency–inverse document frequency (TF-IDF), are widely used due to their simplicity and interpretability. However, they struggle with limited datasets, fail to capture intricate semantics, and suffer from dimensionality, sparsity, and computational inefficiency. This study used pre-trained word embeddings, including FastText and GPT-2, to improve estimation accuracy in such cases. Seven pre-trained models were evaluated for their ability to effectively represent textual data, addressing the fundamental limitations of TF-IDF through contextualized embeddings. The results show that combining FastText embeddings with support vector machines (SVMs) consistently outperforms traditional approaches, reducing the mean absolute error (MAE) by 5–18% while achieving accuracy comparable to deep learning models like GPT-2. This approach demonstrated the adaptability of pre-trained embeddings for small datasets, balancing semantic richness with computational efficiency. The proposed method optimized project planning and resource allocation while enhancing software development through accurate story point prediction while safeguarding privacy and security through data anonymization. Future research will explore task-specific embeddings tailored to software engineering domains and investigate how dataset characteristics, such as cultural variations, influence model performance, ensuring the development of adaptable, robust, and secure machine learning models for diverse contexts. Full article

(This article belongs to the Special Issue Intelligent Approaches for Solving Software Problems with AI Techniques)

► Show Figures

Figure 1

21 pages, 759 KiB

Open AccessArticle

Optimizing Privacy in Set-Valued Data: Comparing Certainty Penalty and Information Gain

by Soonseok Kim

Electronics 2024, 13(23), 4842; https://doi.org/10.3390/electronics13234842 - 8 Dec 2024

Viewed by 516

Abstract

The increase in set-valued data such as transaction records and medical histories has introduced new challenges in data anonymization. Traditional anonymization techniques targeting structured microdata comprising single-attribute- rather than set-valued records are often insufficient to ensure privacy protection in complex datasets, particularly when [...] Read more.

The increase in set-valued data such as transaction records and medical histories has introduced new challenges in data anonymization. Traditional anonymization techniques targeting structured microdata comprising single-attribute- rather than set-valued records are often insufficient to ensure privacy protection in complex datasets, particularly when re-identification attacks leverage partial background knowledge. To address these limitations, this study proposed the Local Generalization and Reallocation (LGR) + algorithm to replace the Normalized Certainty Penalty loss measure (hereafter, NCP) used in traditional LGR algorithms with the Information Gain Heuristic metric (hereafter, IGH). IGH, an entropy-based metric, evaluates information loss based on uncertainty and provides users with the advantage of balancing privacy protection and data utility. For instance, when IGH causes greater information-scale data annotation loss than NCP, it ensures stronger privacy protection for datasets that contain sensitive or high-risk information. Conversely, when IGH induces less information loss, it provides better data utility for less sensitive or low-risk datasets. The experimental results based on using the BMS-WebView-2 and BMS-POS datasets showed that the IGH-based LGR + algorithm caused up to 100 times greater information loss than NCP, indicating significantly improved privacy protection. Although the opposite case also exists, the use of IGH introduces the issue of increased computational complexity. Future research will focus on optimizing efficiency through parallel processing and sampling techniques. Ultimately, LGR+ provides the only viable solution for improving the balance between data utility and privacy protection, particularly in scenarios that prioritize strong privacy or utility guarantees. Full article

► Show Figures

Figure 1

31 pages, 19634 KiB

Open AccessFeature PaperArticle

Particle Swarm Optimization for k-Coverage and 1-Connectivity in Wireless Sensor Networks

by Georgios Siamantas and Dionisis Kandris

Electronics 2024, 13(23), 4841; https://doi.org/10.3390/electronics13234841 - 8 Dec 2024

Viewed by 334

Abstract

Wireless Sensor Networks are used in an ever-increasing range of applications, thanks to their ability to monitor and transmit data related to ambient conditions in almost any area of interest. The optimization of coverage and the assurance of connectivity are fundamental for the [...] Read more.

Wireless Sensor Networks are used in an ever-increasing range of applications, thanks to their ability to monitor and transmit data related to ambient conditions in almost any area of interest. The optimization of coverage and the assurance of connectivity are fundamental for the efficiency and consistency of Wireless Sensor Networks. Optimal coverage guarantees that all points in the field of interest are monitored, while the assurance of the connectivity of the network nodes assures that the gathered data are reliably transferred among the nodes and the base station. In this research article, a novel algorithm based on Particle Swarm Optimization is proposed to ensure coverage and connectivity in Wireless Sensor Networks. The objective function is derived from energy function minimization methodologies commonly applied in bounded space circle packing problems. The performance of the novel algorithm is not only evaluated through both simulation and statistical tests that demonstrate the efficacy of the proposed methodology but also compared against that of relative algorithms. Finally, concluding remarks are drawn on the potential extensibility and actual use of the algorithm in real-world scenarios. Full article

(This article belongs to the Special Issue Recent Advances in Wireless Ad Hoc and Sensor Networks)

► Show Figures

Figure 1

15 pages, 1523 KiB

Open AccessFeature PaperArticle

Efficient Neural Network-Based Compact Modeling for Novel Device Structures Using a Multi-Fidelity Model and Active Learning

by HyunJoon Jeong, JinYoung Choi, Yohan Kim, Jeong-Taek Kong and SoYoung Kim

Electronics 2024, 13(23), 4840; https://doi.org/10.3390/electronics13234840 - 8 Dec 2024

Viewed by 451

Abstract

Neural network (NN)-based compact modeling methodologies are gaining attention due to the challenges of device complexity, narrow model coverage, and SPICE simulation speed in advanced semiconductor technology nodes. As device complexity increases, the number of process and structural variables also increases, which significantly [...] Read more.

Neural network (NN)-based compact modeling methodologies are gaining attention due to the challenges of device complexity, narrow model coverage, and SPICE simulation speed in advanced semiconductor technology nodes. As device complexity increases, the number of process and structural variables also increases, which significantly increases the amount of technology computer-aided design (TCAD) simulation data required for NN-based compact modeling. This study proposes a multi-fidelity model and active learning approach to predict global and local variations of nanosheet FETs (NSFETs) with less than 1.5% error, significantly reducing the number of required TCAD simulations by more than half compared with conventional modeling techniques. In addition, the simplified NN model with a smaller training dataset significantly reduces the SPICE simulation time. Full article

(This article belongs to the Special Issue Advanced CMOS Devices and Applications, 2nd Edition)

► Show Figures

Figure 1

12 pages, 2538 KiB

Open AccessArticle

A Fault Diagnosis Method for Turnout Switch Machines Based on Sound Signals

by Yong Li, Xinyi Tao and Yongkui Sun

Electronics 2024, 13(23), 4839; https://doi.org/10.3390/electronics13234839 - 7 Dec 2024

Viewed by 399

Abstract

The turnout switch machine, a vital outdoor component of railway signaling, controls train steering amidst complex operations and high frequencies. Its malfunction significantly disrupts train operations, potentially causing derailments. This paper proposes a sound-based fault diagnosis method, termed ERS (a method combining EMD, [...] Read more.

The turnout switch machine, a vital outdoor component of railway signaling, controls train steering amidst complex operations and high frequencies. Its malfunction significantly disrupts train operations, potentially causing derailments. This paper proposes a sound-based fault diagnosis method, termed ERS (a method combining EMD, ReliefF, and SVM), for effective monitoring and detection of turnout switch machines. The method employs Eigenmode Decomposition (EMD) to smooth the sound signal, reduce noise, and extract key statistical parameters of both the time and frequency domains. To address redundant information in high-dimensional features, the ReliefF algorithm is utilized for feature selection, dimension reduction, and fault classification based on weighted parameters. Subsequently, the selected feature parameters are used to train the Support Vector Machine (SVM). A comparison with results obtained without ReliefF feature selection demonstrates the necessity of this step. The results show that the fault diagnosis accuracy reaches 98% in the positioning work mode and 95.67% in the reversing work mode, verifying the method’s effectiveness and feasibility. Full article

► Show Figures

Figure 1

16 pages, 4458 KiB

Open AccessArticle

High-Performance Garbage Collection Scheme with Low Data Transfer Overhead for NoC-Based SSDC

by Seyeon Ahn, Donghyuk Im, Donggon You and Youpyo Hong

Electronics 2024, 13(23), 4838; https://doi.org/10.3390/electronics13234838 - 7 Dec 2024

Viewed by 392

Abstract

Solid-state drives (SSDs) have become the preferred storage solution for performance-critical applications due to their high speed, durability, and energy efficiency. However, the inherent characteristics of NAND flash memory, such as block-level erasure and data fragmentation, necessitate frequent garbage collection (GC) operations to [...] Read more.

Solid-state drives (SSDs) have become the preferred storage solution for performance-critical applications due to their high speed, durability, and energy efficiency. However, the inherent characteristics of NAND flash memory, such as block-level erasure and data fragmentation, necessitate frequent garbage collection (GC) operations to reclaim storage space. These operations, while essential, introduce significant performance overhead, particularly in modern SSD controllers (SSDCs) that utilize network-on-chip (NoC) architectures. In such architectures, GC requires substantial data transfer over interconnects for error correction, leading to increased latency and reduced throughput. This paper presents a novel GC scheme designed to minimize latency in NoC-based SSDCs. Unlike conventional methods that unconditionally transfer data for error correction, the proposed approach selectively determines the data transfer path based on the presence of errors. By leveraging the low error probability of NAND flash memory, this scheme avoids unnecessary data traversal across the interconnect, significantly reducing GC overhead. A hardware implementation using task queues ensures efficient parallelism without disrupting other operations. The experimental results demonstrate that the proposed scheme improves SSD performance across various real-world workloads, achieving up to a 26.9% reduction in average latency and a 50.0% reduction in peak latency compared to traditional GC methods. These findings highlight the potential of optimizing data traversal paths in NoC architectures, providing a scalable solution for enhancing SSD performance for diverse applications. Full article

► Show Figures

Figure 1

12 pages, 3245 KiB

Open AccessArticle

GDE-Pose: A Real-Time Adaptive Compression and Multi-Scale Dynamic Feature Fusion Approach for Pose Estimation

by Kaiian Kuok, Xuan Liu, Jinwei Ye, Yaokang Wang and Wenjian Liu

Electronics 2024, 13(23), 4837; https://doi.org/10.3390/electronics13234837 - 7 Dec 2024

Viewed by 386

Abstract

This paper introduces a novel lightweight pose estimation model, GDE-pose, which addresses the current trade-off between accuracy and computational efficiency in existing models. GDE-pose builds upon the baseline YOLO-pose model by incorporating Ghost Bottleneck, a Dynamic Feature Fusion Module (DFFM), and ECA Attention [...] Read more.

This paper introduces a novel lightweight pose estimation model, GDE-pose, which addresses the current trade-off between accuracy and computational efficiency in existing models. GDE-pose builds upon the baseline YOLO-pose model by incorporating Ghost Bottleneck, a Dynamic Feature Fusion Module (DFFM), and ECA Attention to achieve more effective feature representation and selection. The Ghost Bottleneck reduces computational complexity, DFFM enhances multi-scale feature fusion, and ECA Attention optimizes the selection of key features. GDE-pose improves pose estimation accuracy while preserving real-time performance. Experimental results demonstrate that GDE-pose achieves higher accuracy on the COCO dataset, with a substantial reduction in parameters, over 80% fewer FLOPs, and an increased inference speed of 31 FPS, underscoring its exceptional lightweight and real-time capabilities. Ablation studies confirm the independent contribution of each module to the model’s overall performance. GDE-pose’s design highlights its broad applicability in real-time pose estimation tasks. Full article

► Show Figures

Figure 1

17 pages, 3917 KiB

Open AccessArticle

SincNet-Based Speaker Identification for Robotic Environments with Varying Human–Robot Interaction Distance

by Seo-Hyun Kim, A-Hyeon Jo and Keun-Chang Kwak

Electronics 2024, 13(23), 4836; https://doi.org/10.3390/electronics13234836 - 7 Dec 2024

Viewed by 383

Abstract

As human–robot interaction (HRI) becomes increasingly significant, various studies have focused on speaker recognition. However, few studies have explored this topic in the specific environment of home service robots. Notably, most existing research relies on databases composed of English-language data, while studies utilizing [...] Read more.

As human–robot interaction (HRI) becomes increasingly significant, various studies have focused on speaker recognition. However, few studies have explored this topic in the specific environment of home service robots. Notably, most existing research relies on databases composed of English-language data, while studies utilizing Korean speech data are exceedingly scarce. This gap underscores the need for research on speaker recognition in robotic environments, specifically using Korean data. In response, this paper conducts experiments using a speaker recognition database tailored to the Korean language and set in a robotic context. The database includes noise generated by robot movement as well as common environmental noise, accounting for variable distances between humans and robots, which are partitioned accordingly. The deep learning model employed is SincNet, with experiments conducted under two settings for the SincNet filter parameters: one with learnable parameters and the other with fixed values. After training the model with data collected at varying distances, performance was tested across these distances. Experimental results indicate that SincNet with learnable parameters achieved a peak accuracy of 99%. Full article

(This article belongs to the Special Issue Control and Applications of Intelligent Robotic System)

► Show Figures

Figure 1

23 pages, 696 KiB

Open AccessArticle

KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models

by Kun Hou, Jingyuan Li, Yingying Liu, Shiqi Sun, Haoliang Zhang and Haiyang Jiang

Electronics 2024, 13(23), 4835; https://doi.org/10.3390/electronics13234835 - 7 Dec 2024

Viewed by 456

Abstract

Despite the remarkable progress of large language models (LLMs) in understanding and generating unstructured text, their application in structured data domains and their multi-role capabilities remain underexplored. In particular, utilizing LLMs to perform complex reasoning tasks on knowledge graphs (KGs) is still an [...] Read more.

Despite the remarkable progress of large language models (LLMs) in understanding and generating unstructured text, their application in structured data domains and their multi-role capabilities remain underexplored. In particular, utilizing LLMs to perform complex reasoning tasks on knowledge graphs (KGs) is still an emerging area with limited research. To address this gap, we propose KG-EGV, a versatile framework leveraging LLMs to perform KG-based tasks. KG-EGV consists of four core steps: sentence segmentation, graph retrieval, EGV, and backward updating, each designed to segment sentences, retrieve relevant KG components, and derive logical conclusions. EGV, a novel integrated framework for LLM inference, enables comprehensive reasoning beyond retrieval by synthesizing diverse evidence, which is often unattainable via retrieval alone due to noise or hallucinations. The framework incorporates six key stages: generation expansion, expansion evaluation, document re-ranking, re-ranking evaluation, answer generation, and answer verification. Within this framework, LLMs take on various roles, such as generator, re-ranker, evaluator, and verifier, collaboratively enhancing answer precision and logical coherence. By combining the strengths of retrieval-based and generation-based evidence, KG-EGV achieves greater flexibility and accuracy in evidence gathering and answer formulation. Extensive experiments on widely used benchmarks, including FactKG, MetaQA, NQ, WebQ, and TriviaQA, demonstrate that KG-EGV achieves state-of-the-art performance in answer accuracy and evidence quality, showcasing its potential to advance QA research and applications. Full article

(This article belongs to the Special Issue Big Data Analytics and Information Technology for Smart Cities and Citizen Wellbeing)

► Show Figures

Figure 1

Figure 1
Illustration of the multi-role capabilities in the KG-EGV framework. KG-EGV incorporates multiple roles within large language models (LLMs) to perform generation, re-ranking, evaluation, and verification. Full article ">Figure 2
Overview of the KG-EGV framework for knowledge graph-based question answering and fact verification. KG-EGV operates in six steps: (1) sentence segmentation, (2) graph retrieval, (3) query expansion and generation, (4) re-ranking and evaluation, (5) answer generation, and (6) answer verification with dynamic updates. Full article ">Figure 3
Diagram illustrating the integration of knowledge graphs (KGs) and large language models (LLMs) in the KG-EGV framework for question answering (QA) tasks. Full article ">Figure 4
Bar chart comparing the performance of various methods (KG-EGV, ToG, SearChain, KG-GPT, and CoT) across tasks (FactKG, MetaQA, and WebQA). Full article ">Figure A1
Line chart illustrating the dynamic knowledge graph update process. The number of new triples added increases with the number of trials, demonstrating the framework’s ability to incrementally augment the knowledge graph. All new triples were manually validated for correctness, achieving a 100% accuracy rate. Full article ">

25 pages, 1778 KiB

Open AccessArticle

Efficient User Pairing and Resource Optimization for NOMA-OMA Switching Enabled Dynamic Urban Vehicular Networks

by Aravindh Balaraman, Shigeo Shioda, Yonggang Kim, Yohan Kim and Taewoon Kim

Electronics 2024, 13(23), 4834; https://doi.org/10.3390/electronics13234834 - 7 Dec 2024

Viewed by 404

Abstract

Vehicular communication is revolutionizing transportation by enhancing passenger experience and improving safety through seamless message exchanges with nearby vehicles and roadside units (RSUs). To accommodate the growing number of vehicles in dense urban traffic with limited channel availability, non-orthogonal multiple access (NOMA) is [...] Read more.

Vehicular communication is revolutionizing transportation by enhancing passenger experience and improving safety through seamless message exchanges with nearby vehicles and roadside units (RSUs). To accommodate the growing number of vehicles in dense urban traffic with limited channel availability, non-orthogonal multiple access (NOMA) is a promising solution due to its ability to improve spectral efficiency by sharing channels among multiple users. However, to completely leverage NOMA on mobile vehicular networks, a chain of operations and resources must be optimized, including vehicle user (VU) and RSU association, channel assignment, and optimal power control. In contrast, traditional orthogonal multiple access (OMA) allocates separate channels to users, simplifying management but falling short in high-density environments. Additionally, enabling NOMA-OMA switching can further enhance the system performance while significantly increasing the complexity of the optimization task. In this study, we propose an optimized framework to jointly utilize the power domain NOMA in a vehicular network, where dynamic NOMA-OMA switching is enabled, by integrating the optimization of vehicle-to-RSU association, channel assignment, NOMA-OMA switching, and transmit power allocation into a single solution. To handle the complexity of these operations, we also propose simplified formulations that make the solution practical for real-time applications. The proposed framework reduces total power consumption by up to

27 %

compared to Util&LB/opt, improves fairness in user association by

18 %

, and operates efficiently with minimal computational overhead. These findings highlight the potential of the proposed framework to enhance communication performance in dynamic, densely populated urban environments. Full article

(This article belongs to the Special Issue Wireless Sensor Network: Latest Advances and Prospects)

► Show Figures

Figure 1

15 pages, 3698 KiB

Open AccessArticle

Multichannel Wavelet Kernel Network for High Dimensional Inverse Modeling of Microwave Filters

by Di Zhang, Min Zhou, Zhiyu Wang and Hua Chen

Electronics 2024, 13(23), 4833; https://doi.org/10.3390/electronics13234833 - 7 Dec 2024

Viewed by 389

Abstract

This paper proposes a multichannel wavelet kernel network (MWKN) modeling technique with a two-stage training technique for high-dimensional inverse modeling of microwave filters. The real and imaginary parts of the transmission and reflection characteristics are used as the model inputs, while the geometric [...] Read more.

This paper proposes a multichannel wavelet kernel network (MWKN) modeling technique with a two-stage training technique for high-dimensional inverse modeling of microwave filters. The real and imaginary parts of the transmission and reflection characteristics are used as the model inputs, while the geometric parameters of the filter are designated as the outputs. Since the electrical signal in microwave inverse modeling encompasses multiple frequency components and complex information arising from the subtle dimensional changes in the metal pattern, the wavelet transform is introduced by leveraging its powerful multi-scale and approximate detail features to form the discrete wavelet convolution layer in the proposed MWKN. To adapt to the learning of approximate detailed features at different scales, the learnable parameters of this layer and the weights of the backbone network are adjusted in stages through a two-stage training strategy based on particle swarm optimization (PSO), which jointly promotes the rapid convergence of the model. Three numerical examples demonstrate the effectiveness and robustness of the proposed MWKN model. Compared with the traditional design method using electromagnetic (EM) simulation, this approach significantly and substantially reduces the repeated calculation time and is capable of predicting the geometry that meets the design specifications within 0.42 s. Full article

► Show Figures

Figure 1

18 pages, 5670 KiB

Open AccessArticle

An All-Digital Dual-Mode Clock and Data Recovery Circuit for Human Body Communication Systems

by Yoon Heo and Won-Young Lee

Electronics 2024, 13(23), 4832; https://doi.org/10.3390/electronics13234832 - 7 Dec 2024

Viewed by 429

Abstract

This paper describes an all-digital clock and data recovery (CDR) circuit for implementing edge processing with a wireless body area network (WBAN). The CDR circuit performs delay-locked loop (DLL)-based and phase-locked loop (PLL)-based operations depending on the use of an external reference clock [...] Read more.

This paper describes an all-digital clock and data recovery (CDR) circuit for implementing edge processing with a wireless body area network (WBAN). The CDR circuit performs delay-locked loop (DLL)-based and phase-locked loop (PLL)-based operations depending on the use of an external reference clock and is implemented using a digital method that is robust against external noise. The clock generator circuit shared by the two operation methods is described in detail, and the CDR circuit recovers 42 Mb/s input data and a 42 MHz clock, which are the specifications of human body communication (HBC). In DLL-based CDR operation, the clock generator operates as a digitally controlled delay line (DCDL) that delays the reference clock by more than one period. In PLL-based CDR operations, it operates as a digitally controlled oscillator (DCO) that oscillates the 42 MHz clock and adjusts the clock frequency. The proposed all-digital CDR is fabricated in 65 nm CMOS technology with an area of 0.091 mm² and operates with a supply voltage of 1.0 V. Post-layout simulation results show that the lock time for DLL-based CDR operation is 1.6 μs, the clock peak-to-peak jitter is 0.38 ns, and the power consumption is 341.8 μW. For PLL-based CDR operations, the lock time is 6 μs, the clock peak-to-peak jitter is 2.92 ns, and the power consumption is 280.2 μW, respectively. Full article

► Show Figures

Figure 1

12 pages, 3096 KiB

Open AccessFeature PaperArticle

Digital Twin-Based Smart Feeding System Design for Machine Tools

by Baris Yuce, Haobing Li, Linlin Wang and Voicu Ion Sucala

Electronics 2024, 13(23), 4831; https://doi.org/10.3390/electronics13234831 - 6 Dec 2024

Viewed by 484

Abstract

With the continuous development of intelligent manufacturing technology, the application of intelligent feed systems in modern machine tools is becoming increasingly widespread. Digital twin technology achieves the monitoring and optimization of the entire life cycle of a physical system by constructing a virtual [...] Read more.

With the continuous development of intelligent manufacturing technology, the application of intelligent feed systems in modern machine tools is becoming increasingly widespread. Digital twin technology achieves the monitoring and optimization of the entire life cycle of a physical system by constructing a virtual image of the system, while neural network controllers, with their powerful nonlinear fitting ability, can accurately capture and simulate the dynamic behavior of complex systems, providing strong support for the optimization control of intelligent feed systems. This article discusses the design and implementation of an intelligent feed system based on digital twins and neural network controllers. Firstly, this article establishes a mathematical model based on the traditional ball screw structure and analyzes the dynamic characteristics and operating mechanism of the system. Subsequently, the mathematical model is fitted using a neural network controller to improve control accuracy and system response speed. The experimental results demonstrate that the neural network controller shows good consistency in fitting traditional mathematical models, not only effectively capturing the nonlinear characteristics of the system but also maintaining stable control performance under complex operating conditions. Full article

► Show Figures

Figure 1

24 pages, 5497 KiB

Open AccessArticle

Finding All Solutions with Grover’s Algorithm by Integrating Estimation and Discovery

by Sihyung Lee and Seung Yeob Nam

Electronics 2024, 13(23), 4830; https://doi.org/10.3390/electronics13234830 - 6 Dec 2024

Viewed by 381

Abstract

Grover’s algorithm leverages quantum computing to efficiently locate solutions in unstructured search spaces, outperforming classical approaches. Since Grover’s algorithm requires prior knowledge of the number of solutions (M) within a search space of size N, previous studies assume M is [...] Read more.

Grover’s algorithm leverages quantum computing to efficiently locate solutions in unstructured search spaces, outperforming classical approaches. Since Grover’s algorithm requires prior knowledge of the number of solutions (M) within a search space of size N, previous studies assume M is estimated beforehand and focus on identifying all solutions. Here, we propose a two-step process that integrates both the estimation of M and the discovery of the solutions, optimizing the interactions between the two steps. To enhance efficiency, the estimation step captures as many solutions as possible, leaving the discovery step to focus on the remaining ones. To ensure accuracy, the discovery step continues searching until the probability of finding additional solutions becomes sufficiently low. We implemented and evaluated our methods, showing that over 80% of solutions were found during the estimation phase, allowing the discovery phase to conclude earlier, while identifying over 99% of solutions on average. In theory, the process requires

\sqrt{N M}

× log(M) Grover’s iterations in the worst case, but in practice, it typically terminates after iterations proportional to

\sqrt{N}

. We expect that our methods will be applicable to various search problems and inspire further research on efficiently finding all solutions. Full article

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

► Show Figures

Figure 1

35 pages, 6215 KiB

Open AccessArticle

MIVNDN: Ultra-Short-Term Wind Power Prediction Method with MSDBO-ICEEMDAN-VMD-Nons-DCTransformer Net

by Qingze Zhuang, Lu Gao, Fei Zhang, Xiaoying Ren, Ling Qin and Yongping Wang

Electronics 2024, 13(23), 4829; https://doi.org/10.3390/electronics13234829 - 6 Dec 2024

Viewed by 434

Abstract

Wind speed, wind direction, humidity, temperature, altitude, and other factors affect wind power generation, and the uncertainty and instability of the above factors bring challenges to the regulation and control of wind power generation, which requires flexible management and scheduling strategies. Therefore, it [...] Read more.

Wind speed, wind direction, humidity, temperature, altitude, and other factors affect wind power generation, and the uncertainty and instability of the above factors bring challenges to the regulation and control of wind power generation, which requires flexible management and scheduling strategies. Therefore, it is crucial to improve the accuracy of ultra-short-term wind power prediction. To solve this problem, this paper proposes an ultra-short-term wind power prediction method with MIVNDN. Firstly, the Spearman’s and Kendall’s correlation coefficients are integrated to select the appropriate features. Secondly, the multi-strategy dung beetle optimization algorithm (MSDBO) is used to optimize the parameter combinations in the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method, and the optimized decomposition method is used to decompose the historical wind power sequence to obtain a series of intrinsic modal function (IMF) components with different frequency ranges. Then, the high-frequency band IMF components and low-frequency band IMF components are reconstructed using the t-mean test and sample entropy, and the reconstructed high-frequency IMF component is decomposed quadratically using the variational modal decomposition (VMD) to obtain a new set of IMF components. Finally, the Nons-Transformer model is improved by adding dilated causal convolution to its encoder, and the new set of IMF components, as well as the unreconstructed mid-frequency band IMF components and the reconstructed low-frequency IMF, component are used as inputs to the model to obtain the prediction results and perform error analysis. The experimental results show that our proposed model outperforms other single and combined models. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

13 pages, 1482 KiB

Open AccessArticle

Novel Low-Power Computing-In-Memory (CIM) Design for Binary and Ternary Deep Neural Networks by Using 8T XNOR SRAM

by Achyuth Gundrapally, Nader Alnatsheh and Kyuwon Ken Choi

Electronics 2024, 13(23), 4828; https://doi.org/10.3390/electronics13234828 - 6 Dec 2024

Viewed by 372

Abstract

The increasing demand for high-performance and low-power hardware in artificial intelligence (AI) applications, such as speech recognition, facial recognition, and object detection, has driven the exploration of advanced memory designs. Convolutional neural networks (CNNs) and deep neural networks (DNNs) require intensive computational resources, [...] Read more.

The increasing demand for high-performance and low-power hardware in artificial intelligence (AI) applications, such as speech recognition, facial recognition, and object detection, has driven the exploration of advanced memory designs. Convolutional neural networks (CNNs) and deep neural networks (DNNs) require intensive computational resources, leading to memory access times and power consumption challenges. To address these challenges, we propose the application of computing-in-memory (CIM) within FinFET-based 8T SRAM structures, specifically utilizing P-latch N-access (PLNA) and single-ended (SE) configurations. Our design significantly reduces power consumption by up to 56% in the PLNA configuration and 60% in the SEconfiguration compared to traditional FinFET SRAM designs. These reductions are achieved while maintaining competitive delay performance, making our approach a promising solution for implementing efficient and low-power AI hardware. Detailed simulations in 7 nm FinFET technology underscore the potential of these CIM-based SRAM structures in overcoming the computational bottlenecks associated with DNNs and CNNs. Full article

(This article belongs to the Special Issue Recent Advances in AI Hardware Design)

► Show Figures

Figure 1

Figure 1
Comparison between von Neumann and computing-in-memory(CIM) architecture. Full article ">Figure 2
Ternary XNOR operation with fixed weights and varying inputs. Subfigures (a–d) explains different XNOR inputs and desired outputs. Full article ">Figure 3
P-Latch N-Access (PLNA) SRAM structure with XNOR logic. Full article ">Figure 4
Single-Ended (SE) SRAM structure with XNOR logic. Full article ">Figure 5
Original SRAM waveform analysis of the proposed XNOR-SRAM CIM operation for ternary inputs. The input signals (+1, 0, −1, +0) are represented by yellow, black, cyan, and magenta lines, respectively. The ternary combination output (−1, 0, +1) is shown by the orange line. The complementary output Qb is indicated by the green line, while the primary output Q is represented by the blue line. The results illustrate correct ternary computation, highlighting the functionality of the XNOR pass transistor logic. Full article ">Figure 6
PLNA SRAM waveform analysis of the proposed XNOR-SRAM CIM operation for ternary inputs. The input signals (+1, 0, −1, +0) are represented by yellow, black, cyan, and magenta lines, respectively. The ternary combination output (−1, 0, +1) is shown by the orange line. The complementary output Qb is indicated by the green line, while the primary output Q is represented by the blue line. The results illustrate correct ternary computation, highlighting the functionality of the XNOR pass transistor logic. Full article ">Figure 7
SE SRAM waveform analysis of the proposed XNOR-SRAM CIM operation for ternary inputs. The input signals (+1, 0, −1, +0) are represented by yellow, black, cyan, and magenta lines, respectively. The ternary combination output (−1, 0, +1) is shown by the orange line. The complementary output Qb is indicated by the green line, while the primary output Q is represented by the blue line. The results illustrate correct ternary computation, highlighting the functionality of the XNOR pass transistor logic. Full article ">

23 pages, 1948 KiB

Open AccessArticle

PerFuSIT: Personalized Fuzzy Logic Strategies for Intelligent Tutoring of Programming

by Konstantina Chrysafiadi and Maria Virvou

Electronics 2024, 13(23), 4827; https://doi.org/10.3390/electronics13234827 - 6 Dec 2024

Viewed by 365

Abstract

Recent advancements in intelligent tutoring systems (ITS) driven by artificial intelligence (AI) have attracted substantial research interest, particularly in the domain of computer programming education. Given the diversity in learners’ backgrounds, cognitive abilities, and learning paces, the development of personalized tutoring strategies to [...] Read more.

Recent advancements in intelligent tutoring systems (ITS) driven by artificial intelligence (AI) have attracted substantial research interest, particularly in the domain of computer programming education. Given the diversity in learners’ backgrounds, cognitive abilities, and learning paces, the development of personalized tutoring strategies to support the effective attainment of learning objectives has become a critical challenge. This paper introduces personalized fuzzy logic strategies for intelligent programming tutoring (PerFuSIT), an innovative fuzzy logic-based module designed to select the most appropriate tutoring strategy from five available options, based on individual learner characteristics. The available strategies include revisiting previous content, progressing to the next topic, providing supplementary materials, assigning additional exercises, or advising the learner to take a break. PerFuSIT’s decision-making process incorporates a range of learner-specific parameters, such as performance metrics, error types, indicators of carelessness, frequency of help requests, and the time required to complete tasks. Embedded within the traditional ITS framework, PerFuSIT introduces a sophisticated reasoning mechanism for dynamically determining the optimal instructional approach. Experimental evaluations demonstrate that PerFuSIT significantly enhances learner performance and improves the overall efficacy of interactions with the ITS. The findings highlight the potential of fuzzy logic to optimize adaptive tutoring strategies by customizing instruction to individual learners’ strengths and weaknesses, thereby providing more effective and personalized educational support in programming instruction. Full article

(This article belongs to the Special Issue Fuzzy-Logic-Based Approaches for Knowledge Management and User Modelling)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 13, Issue 23 (December-1 2024) – 280 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI