检索结果-内蒙古大学图书馆

Intrinsically and Post-Hoc Interpretable Kolmogorov-Arnold Network and Genetic Algorithm for Laser Deep Penetration Welding Parameters Optimization

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Ma, Shuai Leng, Jiewu Chen, Zhuyun Du, Yixian Zhang, Xiaoji Liu, Qiang Guangdong Univ Technol State Key Lab Precis Elect Mfg Technol & Equipment Guangzhou 510006 Peoples R China Guangdong Univ Technol Guangdong Prov Key Lab Comp Integrated Mfg Syst Guangzhou 510006 Peoples R China Guangdong Lyr Robot Automation Co Ltd Guangdong Prov Key Lab Intelligent Lithium Battery Huizhou 516000 Peoples R China

Process parameters are critical in determining the quality and performance of laser deep penetration welding (LDPW) by influencing key factors like breakpoint tensile strength (BTS). Optimizing these parameters is essential for ensuring consistent weld quality and improving overall efficiency. As the dimensionality of process parameters and sample sizes increase, the relationship between process parameters and BTS becomes increasingly complex, uncertain, and nonlinear. While machine learning (ML) techniques struggle to handle this complexity, deep learning (DL) methods, although effective at capturing nonlinear patterns, are constrained by their lack of interpretability, limiting their wider application in industrial environments. To address these challenges, an intrinsically and post-hoc interpretable approach combining the Kolmogorov-Arnold network (KAN) and genetic algorithm (GA) is proposed. An LDPW experimental platform is first established, employing an orthogonal design (L-81) with five factors at three levels to gather datasets. A lightweight and interpretable KAN with a single hidden layer is then developed to establish the nonlinear relationship between process parameters and BTS. During optimization, the trained KAN serves as a surrogate model to define decision variables, constraints, and objective functions, with interpretability enhanced through graphical and symbolic representations that clarify how process parameters impact the BTS. Furthermore, the post-hoc Shapley additive explanation (SHAP) method is employed to provide global and local insight into the overall and sample-specific influence on BTS. Validation of the optimization results confirms that the proposed method outperforms other state-of-the-art approaches.

关键词： Welding computational modeling Predictive models Genetic algorithms Optimization Mathematical models Training Laser beams Additives Laser modes Genetic algorithm (GA) Kolmogorov-Arnold Network (KAN) laser deep penetration welding (LDPW) process parameters optimization (PPO) Shapley additive explanation (SHAP)

来源：评论

学校读者我要写书评

暂无评论

Application of Temporal Action Detection Technology in Abnormal Event Detection of Surveillance Video

引用

IEEE ACCESS 2025年 13卷 26958-26972页

作者： Lin, Chenxiang Ma, Teng Wu, Fei Qian, Jian Liao, Feilong Huang, Jinaye State Grid Fujian Elect Power Co Ltd Elect Power Sci Res Inst Fuzhou 350000 Fujian Peoples R China

By detecting abnormal violation event in surveillance videos, the safety management capabilities in high-risk power operations can be improved. This research constructs an intelligent abnormal event detection technology using deep learning algorithms, aiming to improve the detection accuracy of anomaly event. This research improves the parameter setting method and fully connected layer of three-dimensional convolutional networks to enhance their ability to recognize three-dimensional features. An improved algorithm is adopted as the basic structure of temporal action detection technology. Frame interpolation is applied to improve the accuracy of temporal action detection. A monitoring video anomaly event detection model based on the improved temporal action detection technology is established. The experiment outcomes show that the improved three-dimensional convolutional network achieves convergence after 32 iterations, with an accuracy of 99.15% and a recall rate of 98.3%. The average accuracy of the three datasets tested is better than other algorithms. The average precision of the research model for detecting throwing objects from high altitude, crossing fences, smoking, and checking electricity without gloves are 89.1%, 88.9%, 96.6%, and 96.2%, respectively. The accuracy for abnormal event detection of different time periods is superior to other models. The average recall value of the research model is 94.3%, which is higher than other models. The results indicate that the research model has the capacity to accurately recognize abnormal events in massive, diverse, and complex surveillance videos. The abnormal event detection model proposed in the study can be applied to the intelligent management platform of the power industry, thereby improving the safety management capability in power operations.

关键词： Event detection Feature extraction Accuracy Streaming media Surveillance Power industry Convolutional neural networks Real-time systems computational modeling Anomaly detection Temporal action detection surveillance video abnormal events C3D sequence

来源：评论

学校读者我要写书评

暂无评论

Communication-and-Energy Efficient Over-the-Air Federated Learning

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第1期24卷 767-782页

作者： Liang, Yipeng Chen, Qimei Zhu, Guangxu Jiang, Hao Eldar, Yonina C. Cui, Shuguang Wuhan Univ Sch Elect Informat Wuhan 430072 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China Weizmann Inst Sci Dept Math & Comp Sci IL-7610001 Rehovot Israel Chinese Univ Hong Kong Shenzhen Future Network Intelligence Inst FNii She Sch Sci & Engn SSE Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Guangdong Prov Key Lab Future Networks Intelligenc Shenzhen 518172 Peoples R China

Communication and energy efficiencies are two crucial objectives in the pursuit of edge intelligence in 6G networks, and become increasingly important given the prevalence of large model training. Existing designs typically focus on either communication efficiency or energy efficiency due to the fact that improving one objective generally comes at the expense of the other. Over-the-air federated learning (OTA-FL) has recently emerged as a promising approach to enhance both efficiencies through an integrated communication and computation design. Nevertheless, most previous studies on OTA-FL only consider scenarios where the dataset for the entire FL procedure is collected and available prior to training. In real-world applications, devices continuously collect new data in an online manner. This underscores the significance of sample collection through sensing in a practical FL pipeline. We propose to integrate sensing with communication and computation into a joint design to further boost the communication-and-energy efficiencies of OTA-FL. Specifically, we consider a training latency and energy consumption minimization problem with performance guarantees. To this end, we first derive an average training error (ATE) metric to quantify convergence performance. Then, a joint sensing, communication and computation resource allocation strategy is developed based on a deep reinforcement learning (DRL) algorithm that nests convex optimization with a deep Q-network. Extensive experiments are conducted to validate our theoretical analysis, and demonstrate the effectiveness of the proposed design for communication-and-energy efficient FL.

关键词： Training computational modeling Sensors Energy consumption Performance evaluation Optimization Energy efficiency Convergence Data models Resource management Federated learning over-the-air computation integrated sensing computation communication

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multilayer Community Detection via Federated Learning

引用

IEEE TRANSACTIONS ON computational SOCIAL SYSTEMS 2025年第2期12卷 832-846页

作者： Ma, Shi-Yao Xu, Xiao-Ke Xiao, Jing Shenzhen Technol Univ Coll Big Data & Internet Shenzhen 518118 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China Beijing Normal Univ Computat Commun Res Ctr Beijing 100875 Peoples R China Beijing Normal Univ Sch Journalism & Commun Beijing 100875 Peoples R China Dalian Minzu Univ Coll Informat & Commun Engn Dalian 116600 Peoples R China

Existing frameworks of privacy-preserving multilayer community detection have room for improving detection performance and reducing communication overhead. To address these issues, we propose a novel privacy-preserving multilayer community detection framework based on federated learning which is called federated multilayer community detection (FMCD). First, we propose a novel aggregation strategy by utilizing the network average degree of local networks to aggregate the parameters uploaded by clients in the step of aggregation, which can improve the performance of community detection. Second, we design a training procedure to complete multilayer community detection in multiorganizations, which can reduce communication overhead by transmitting merged community information instead of the global parameter. Finally, experiment results on synthetic and real networks with different criteria illustrate that FMCD can achieve significant performance gains, compared with state-of-the-art algorithms.

关键词： Nonhomogeneous media Detection algorithms Organizations Periodic structures Data models Training Servers Privacy Federated learning computational modeling Community detection federated learning (FL) multilayer network privacy protection

来源：评论

学校读者我要写书评

暂无评论

L3DML: Facilitating Geo-Distributed Machine Learning in Network Layer

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2025年第2期22卷 1391-1408页

作者： Hou, Xindi Gao, Shuai Liu, Ningchun Yao, Fangtao Lei, Bo Zhang, Hongke Das, Sajal K. Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Zhejiang Lab Res Inst Intelligent Networks Hangzhou 311121 Peoples R China Res Inst China Telecom Network Technol Res Dept Beijing 102209 Peoples R China Missouri Univ Sci & Technol Dept Comp Sci Rolla MO 65409 USA

Geo-Distributed Machine Learning (GDML) aims to train large-scale machine learning models across geographically dispersed datacenters. However, the performance of GDML systems is constrained by the limited Wide Area Network (WAN) bandwidth and the presence of the straggler problem. Existing GDML designs often show contradictory effects in addressing these challenges, while in-network computing attempts are typically restricted to single datacenter environments rather than the more complex GDML scenarios. To overcome these limitations, this paper proposes L3DML to facilitate GDML using the P4-based Software-defined Network (SDN). Our approach incorporates three key innovations. Firstly, we introduce a novel network addressing scheme that enables location-specific in-network gradient aggregation for GDML, eliminating the need for parameter servers. Secondly, we utilize the P4 data plane to integrate lossless gradient transmission within switches. Thirdly, we address the straggler problem by employing a unique Deep Reinforcement Learning (DRL) model set and a corresponding rate synchronization routing approach. L3DML is implemented on a prototype system consisting of several Intel Tofino switches and the Spirent network emulator. Experimental results indicate that L3DML outperforms existing solutions in terms of goodput, model accuracy, and training speed gain for large-scale GDML.

关键词： Wide area networks Training computational modeling Machine learning Synchronization Routing Scheduling Bandwidth Protocols Processor scheduling Distributed training network-layer addressing in-network computing P4 deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Imitation Learning of Model Predictive Control Through Importance Weighting

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年第4期72卷 4073-4083页

作者： Gomez, Pere Izquierdo Gajardo, Miguel E. Lopez Mijatovic, Nenad Dragicevic, Tomislav Tech Univ Denmark Dept Wind & Energy Syst DK-2800 Lyngby Denmark

The approximation of model predictive control (MPC) algorithms with neural network models has received significant attention in the power electronics research community, as a valuable tool to enable the real-time implementation of computationally expensive methods. Training machine learning models to imitate MPC algorithms typically follows a traditional supervised learning flow, with a static training data set generated through either uniform sampling or simulation. Training with uniformly distributed data allows models to maintain consistent performance throughout the entire operating space, but very small models may fail to achieve satisfactory results in the regions corresponding to expected operation. Conversely, simulation data can be used in training to obtain models that can accurately track certain trajectories but fail to achieve adequate performance in underrepresented regions. The present article proposes a method to combine the advantages of both methods, by training models on sampled data with importance weights obtained through the kernel density estimation of experimental data. This allows the training process to target specific regions of the operating space, and results in measurable performance improvements. The method is demonstrated through the imitation of a moving discretized control set MPC algorithm for a dual active bridge converter, and is validated through experimental results.

关键词： Training computational modeling Aerospace electronics Training data Data models Prediction algorithms Voltage control DC-DC converters dual active bridge (DAB) imitation learning importance weighting (IW) model predictive control (MPC) neural networks

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Federated Learning via Generative Model-Aided Knowledge Distillation in the Edge

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第5期12卷 5589-5599页

作者： Sun, Chuanneng Jiang, Tingcong Pompili, Dario Rutgers Univ New Brunswick Dept Elect & Comp Engn New Brunswick NJ 08854 USA

Federated learning (FL) has been popular recently as a framework for training machine learning (ML) models in a distributed and privacy-preserving manner. Traditional FL frameworks often struggle with model and statistical heterogeneity among participating clients, impacting learning performance and practicality. To overcome these fundamental limitations, we introduce Fed2KD+, a novel FL framework that leverages a set of tiny unified models and conditional variational auto-encoders (CVAEs) to enable FL training for heterogeneous models between network clients. Using forward and backward distillation processes, Fed2KD+ allows a seamless exchange of knowledge, mitigating data and heterogeneity problems of the model. Moreover, we propose a cosine similarity penalty in the loss function of CVAE+ to enhance the generalizability of CVAE for non-IID scenarios, improving the adaptability and efficiency of the framework. Furthermore, our framework design incorporates a co-design with radio access network (RAN) architecture, reducing the fronthaul traffic volume and improving scalability. Extensive evaluations of one image and two Internet of Things datasets demonstrate the superiority of Fed2KD+ in achieving higher accuracy and faster convergence compared to existing methods, including FedAvg, FedMD, and FedGen. Furthermore, we also performed hardware profiling on the Raspberry Pi and NVIDIA Jetson Nano to quantify the additional resources required to train the unified and CVAE+ models.

关键词： Data models Training Internet of Things Servers computational modeling Convergence Radio access networks Federated learning Privacy Distributed databases Edge learning federated learning (FL) knowledge distillation (KD) model heterogeneity

来源：评论

学校读者我要写书评

暂无评论

SCAT: Shift Channel Attention Transformer for Remote Sensing Image Super-Resolution

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 10337-10347页

作者： Kang, Yingdong Zhang, Xuemin Wang, Shaoju Jin, Guang Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430072 Peoples R China

The quadratic increase in computational complexity caused by global receptive fields has been a persistent challenge when applying Transformer-based methods in remote sensing image super-resolution (RSISR), involving high-resolution images. Channel attention (CA)-based Transformers offer an efficient approach with linear complexity by computing self-attention across the channel dimension. However, current CA-based Transformers suffer from performance degradation due to two main issues: constrained receptive field in the channel dimension caused by the multihead strategy and insufficient feature diversity resulting from the small size of attention matrices. To address these drawbacks, a novel shift channel attention Transformer (SCAT) is proposed for RSISR in this article. The core innovation of SCAT lies in its shift channel attention block (SCAB), which expands the receptive field by facilitating cross-head communication through a shift channel strategy. This design enables parallel computation of self-attention across multiple heads while ensuring robust cross-channel connections, thereby enhancing the global context modeling capabilities of the network. In addition, an attention supplementation module using depthwise convolution (DWC) is incorporated into SCAB to improve feature diversity. Finally, the proposed gated feedforward network utilizes the gating mechanism and DWC to effectively control the information flow and extract complementary spatial details. In the experiments, the effectiveness of these proposed modules is verified, and the SCAT model demonstrated superior performance in terms of quantitative and qualitative compared to several state-of-the-art RSISR methods.

关键词： Transformers Feature extraction Head Remote sensing Convolution computational complexity Superresolution Logic gates computational modeling Standards Deep learning optical remote sensing super-resolution (SR) transformers

来源：评论

学校读者我要写书评

暂无评论

RepVGG-MEM: A Lightweight Model for Garbage Classification Achieving a Balance Between Accuracy and Speed

引用

IEEE ACCESS 2025年 13卷 36451-36469页

作者： Si, Qiuxin Han, Sang Ik Zibo Vocat Inst Sch Artificial Intelligence & Big Data Zibo 255000 Shandong Peoples R China Semyung Univ Dept Informat & Commun Jecheon Si 27136 South Korea Semyung Univ Sch Smart IT Jecheon Si 27136 South Korea

Currently, existing garbage image classification models predominantly operate on low-end devices and encounter significant challenges, including limitations in computing resources, storage capacity, and classification accuracy. This paper proposes an improved lightweight model, RepVGG-MEM, specifically designed to address the resource constraints of low-end devices. The backbone of this model is derived from the lightweight RepVGG architecture, augmented by the integration of a multi-scale convolutional attention module to enhance high-quality feature extraction. Experimental results demonstrate that the RepVGG-MEM model outperforms its counterparts, achieving an accuracy of 93.26%, with a parameter count of 7.2 million and a floating-point operations (FLOPs) of 1.41 billion. This performance reflects a commendable balance between accuracy and processing speed. Furthermore, the model's redundancy is minimized through pruning techniques, which significantly reduce both complexity and computational overhead. The optimal pruned version of the model is designated as RepVGG-MEM5. In this iteration, the parameter count is further reduced to 1.2 million and the FLOPs decrease to 0.55 billion, with a minor accuracy decline of only 1.17%. These findings indicate that it is possible to significantly reduce the model's parameters and FLOPs without a substantial loss in accuracy, thereby enhancing the overall performance of the model while achieving an optimal balance of accuracy and speed. As a result, this research contributes to the development of an efficient and lightweight convolutional neural network model for garbage classification.

关键词： computational modeling Convolution Accuracy Kernel Biological system modeling Feature extraction Sorting Image classification Data models Adaptation models Garbage image classification RepVGG multi-scale convolutional attention module pruning

来源：评论

学校读者我要写书评

暂无评论

Precise Recognition and Feature Depth Analysis of Tennis Training Actions Based on Multimodal Data Integration and Key Action Classification

引用

IEEE ACCESS 2025年 13卷 25409-25418页

作者： Yang, Weichao Luoyang Inst Sci & Technol Dept Phys Educ Luoyang 471023 Peoples R China

To address the issues of accuracy and generalization in action recognition within complex tennis training scenarios, this study proposes an Adaptive Semantic-Enhanced Convolutional Neural Network (ASE-CNN) model. The model optimizes multimodal data integration and complex action classification performance, enabling precise analysis of key action features in tennis training. Experimental results demonstrate that ASE-CNN excels in multimodal feature extraction, achieving a Receiver Operating Characteristic-Area Under Curve (ROC-AUC) value of 0.85-0.95 and a Feature Distribution Uniformity of 0.75-0.85, validating its accuracy and stability in feature classification. The fused weighted Precision-Recall Area Under Curve (PR-AUC) value ranges from 0.80 to 0.92, highlighting its capability for synergistic optimization of multimodal data. For key action recognition, the classification accuracy reaches up to 0.98, with Euclidean distances between key actions and ideal action templates as low as 0.05-0.15, demonstrating exceptional fine-detail discrimination. Compared to state-of-the-art models, ASE-CNN exhibits significant advantages in per-frame processing time and resource utilization efficiency, offering potential for efficient real-time feedback in resource-constrained environments. This study provides scientific evidence and technical support for optimizing actions and improving strategies in professional training.

关键词： Training Sports Data models Convolutional neural networks computational modeling Semantics Adaptation models Feature extraction Analytical models Accuracy Tennis action recognition convolutional neural network architecture multimodal data feature extraction ASE-CNN

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：