检索结果-内蒙古大学图书馆

Automated Detection of Heart Arrhythmia Signals by Using a Convolutional Takagi–Sugeno–Kang-type Fuzzy Neural Network

引用

Sensors and Materials 2024年第2-3期36卷 639-653页

作者： Lin, Cheng-Jian Cheng, Han Chang, Chun-Lung Department of Computer Science & Information Engineering National Chin-Yi University of Technology Taichung411 Taiwan Department of Artificial Intelligence & Computer Engineering National Chin-Yi University of Technology Taichung411 Taiwan

In clinical practice, electrocardiography is used to diagnose cardiac abnormalities. Because of the extended time required to monitor electrocardiographic signals, the necessity of interpretation by physicians, and the vulnerability of electrocardiographic signals to noise interference, electrocardiography is laborious and places a heavy burden on healthcare providers. Therefore, in this paper, a convolutional Takagi–Sugeno–Kang (TSK)-type fuzzy neural network (CTFNN) is proposed to address the challenges of arrhythmia signal classification. The proposed CTFNN is divided into three parts, namely, a convolutional layer, a feature fusion layer, and a TSK fuzzy neural network. The TSK fuzzy neural network is used to replace the fully connected neural network, thereby reducing the number of parameters and enabling the model to mimic the human brain when classifying signals. In addition, because the parameters of the CTFNN are difficult to determine, the uniform experimental design method, which requires only a small number of experiments, is used to determine the optimal parameter combination. The proposed model was tested using the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, which contains 1000 records belonging to 17 categories. Each record has a duration of 10 s and contains 3600 sampling points. According to our experimental results, the accuracy, recall, precision, and F1-score of the CTFNN for long-term signals were 97.33, 97.96, 96.00, and 96.97%, respectively. In addition, the number of parameters for the proposed model was only 558,728, which was less than that for LeNet (i.e., 1734501). © 2024 M Y U Scientific Publishing Division. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Joint fuzzy background and adaptive foreground model for moving target detection

引用

Frontiers of computer Science 2024年第2期18卷 93-106页

作者： Dawei ZHANG Peng WANG Yongfeng DONG Linhao LI Xin LI School of Artificial Intelligence Hebei University of TechnologyTianjin 300401China Lane Department of Computer Science and Electrical Engineering West Virginia UniversityMorgantownWV 26506-6109USA

Moving target detection is one of the most basic tasks in computer *** conventional wisdom,the problem is solved by iterative optimization under either Matrix Decomposition(MD)or Matrix Factorization(MF)*** utilizes foreground information to facilitate background *** uses noise-based weights to fine-tune the *** both noise and foreground information contribute to the recovery of the *** jointly exploit their advantages,inspired by two framework complementary characteristics,we propose to simultaneously exploit the advantages of these two optimizing approaches in a unified framework called Joint Matrix Decomposition and Factorization(JMDF).To improve background extraction,a fuzzy factorization is *** fuzzy membership of the background/foreground association is calculated during the factorization process to distinguish their contributions of both to background *** describe the spatio-temporal continuity of foreground more accurately,we propose to incorporate the first order temporal difference into the group sparsity constraint *** temporal constraint is adjusted *** foreground and the background are jointly estimated through an effective alternate optimization process,and the noise can be modeled with the specific probability *** experimental results of vast real videos illustrate the effectiveness of our *** with the current state-of-the-art technology,our method can usually form the clearer background and extract the more accurate ***-noise experiments show the noise robustness of our method.

关键词： matrixdecomposition matrix factorization generalized sparsity noise modeling

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

Science China(Information Sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis 41

UP2ME: Univariate Pre-training to Multivariate Fine-tuning a...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yunhao Liu, Minghao Zhou, Shengyang Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

Despite the success of self-supervised pre-training in texts and images, applying it to multivariate time series (MTS) falls behind tailored methods for tasks like forecasting, imputation and anomaly *** propose a general-purpose framework, named UP2ME (Univariate Pre-training to Multivariate Fine-tuning).It conducts task-agnostic pre-training when downstream tasks are *** the task and setting (*** length) are determined, it gives sensible solutions with frozen pre-trained parameters, which has not been achieved ***2ME is further refined by fine-tuning.A univariate-to-multivariate paradigm is devised to address the heterogeneity of temporal and cross-channel *** univariate pre-training, univariate instances with diverse lengths are generated for Masked AutoEncoder (MAE) pre-training, discarding cross-channel *** pretrained model handles downstream tasks by formulating them into specific mask-reconstruction *** multivariate fine-tuning, it constructs a dependency graph among channels using the pre-trained encoder to enhance cross-channel dependency *** on eight real-world datasets show its SOTA performance in forecasting and imputation, approaching task-specific performance in anomaly *** code is available at https://***/Thinklab-SJTU/UP2ME. Copyright 2024 by the author(s)

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Literature Review on Model Conversion, Inference, and Learning Strategies in EdgeML with TinyML Deployment

引用

computers, Materials & Continua 2025年第4期83卷 13-64页

作者： Muhammad Arif Muhammad Rashid Department of Computer Science and Artificial Intelligence Umm Al-Qura UniversityMakkah Al-Mukarama21955Saudi Arabia Department of Computer and Network Engineering Umm Al-Qura UniversityMakkah Al-Mukarama21955Saudi Arabia

Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’s ***,the complexity of model conversion techniques,diverse inference mechanisms,and varied learning strategies make designing and deploying these models ***,deploying TinyML models on resource-constrained hardware with specific software frameworks has broadened EdgeML’s applications across various *** factors underscore the necessity for a comprehensive literature review,as current reviews do not systematically encompass the most recent findings on these ***,it provides a comprehensive overview of state-of-the-art techniques in model conversion,inference mechanisms,learning strategies within EdgeML,and deploying these models on resource-constrained edge devices using *** identifies 90 research articles published between 2018 and 2025,categorizing them into two main areas:(1)model conversion,inference,and learning strategies in EdgeML and(2)deploying TinyML models on resource-constrained hardware using specific software *** the first category,the synthesis of selected research articles compares and critically reviews various model conversion techniques,inference mechanisms,and learning *** the second category,the synthesis identifies and elaborates on major development boards,software frameworks,sensors,and algorithms used in various applications across six major *** a result,this article provides valuable insights for researchers,practitioners,and *** assists them in choosing suitable model conversion techniques,inference mechanisms,learning strategies,hardware development boards,software frameworks,sensors,and algorithms tailored to their specific needs and applications across various sectors.

关键词： Edge machine learning tiny machine learning model compression inference learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Graph-Aware Unsupervised Feature Scoring Using Reconstruction Errors in GNN Embeddings

Graph-Aware Unsupervised Feature Scoring Using Reconstructio...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Sehee Kim, So Yeon Sohn, Kyung-Ah Ajou University Department of Artificial Intelligence Suwon Korea Republic of Ajou University Department of Artificial Intelligence Department of Software and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9798350386226

Graph neural networks (GNNs) have recently gained significant attention for their ability to model and analyze complex relationships, leading to numerous applications in a variety of fields. In line with this, explainable models such as GNNExplainer have been developed to provide insights into how GNN models make decisions. However, much of the research has focused on identifying important edges and subgraphs, with relatively less emphasis on feature importance. To address this gap, we propose a novel unsupervised feature scoring method aimed at extracting features that are well-aligned with graph structures. Our approach leverages the distinction between features that explain the overall structural characteristics of the graph and those that do not. Through comparative experiments with other algorithms, we demonstrated that our proposed method is effective in selecting important features in unsupervised settings. Additionally, empirical analysis of gene expression data confirmed that our method could aid in biomarker discovery, highlighting its potential for practical applications in biological studies. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Disentangled Cross-modal Fusion for Event-Guided Image Super-resolution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第10期5卷 5314-5324页

作者： Liu, Minjie Wang, Hongjian Yoon, Kuk-Jin Wang, Lin Artificial Intelligence Thrust Information Hub Guangzhou511466 China Tsinghua University Shenzhen International Graduate School Shenzhen518000 China Visual Intelligence Lab Department of Mechanical Engineering Daejeon366100 Korea Republic of Artificial Intelligence Thrust Guangzhou511466 China Department of Computer Science and Engineering SAR 999077 Hong Kong

Event cameras detect the intensity changes and produce asynchronous events with high dynamic range and no motion blur. Recently, several attempts have been made to superresolve the intensity images guided by events. However, these methods directly fuse the event and image features without distinguishing the modality difference and achieve image superresolution (SR) in multiple steps, leading to error-prone image SR results. Also, they lack quantitative evaluation of real-world data. In this article, we present an end-to-end framework, called event-guided image (EGI)-SR to narrow the modality gap and subtly integrate the event and RGB modality features for effective image SR. Specifically, EGI-SR employs three crossmodality encoders (CME) to learn modality-specific and modality-shared features from the stacked events and the intensity image, respectively. As such, EGI-SR can better mitigate the negative impact of modality varieties and reduce the difference in the feature space between the events and the intensity image. Subsequently, a transformer-based decoder is deployed to reconstruct the SR image. Moreover, we collect a real-world dataset, with temporally and spatially aligned events and color image pairs. We conduct extensive experiments on the synthetic and real-world datasets, showing EGI-SR favorably surpassing the existing methods by a large margin. © 2020 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Video-Based Depth Estimation Autoencoder With Weighted Temporal Feature and Spatial Edge Guided Modules

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第2期5卷 613-623页

作者： Yang, Wei-Jong Tsung, Wan-Nung Chung, Pau-Choo Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung411030 Taiwan Department of Electrical Engineering National Cheng Kung University Tainan701 Taiwan

Convolutional neural networks with encoder and decoder structures, generally referred to as autoencoders, are used in many pixelwise transformation, detection, segmentation, and estimation applications, for example, which can be applied for face swapping, lane detection, semantic segmentation, and depth estimation, respectively. However, traditional autoencoders, which are based on single-frame inputs, ignore the temporal consistency between consecutive frames, and may, hence, produce unsatisfactory results. Accordingly, in this article, a video-based depth estimation (VDE) autoencoder is proposed to improve the quality of depth estimation through the inclusion of two weighted temporal feature (WTF) modules in the encoder and a single spatial edge guided (SEG) module in the decoder. The WTF modules designed with channel weighted block submodule effectively extract the temporal similarities in consecutive frames, whereas the SEG module provides spatial edge guidance of the object contours. Through the collaboration of the proposed modules, the accuracy of the depth estimation is greatly improved. The experimental results confirm that the proposed VDE autoencoder achieves a better monocular depth estimation performance than the existing autoencoders with only a slight increase in the computational cost. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Scheduling and Optimization of Wireless Sensor Networks Lifetime using Soft Computing 13

Scheduling and Optimization of Wireless Sensor Networks Life...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Alqahtani, Abeer College of Computer Science and Engineering University of Jeddah Department of Computer Science and Artificial Intelligence Saudi Arabia

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305463

The paper presents a novel approach to address the problem of lifetime maximization in Wireless Sensor Networks (WSNs) with limited initial energy constraints. The authors introduce a scheduling approach called Non-disjoint Set Cover (NDSC) and propose a method based on the Particle Swarm Optimization (PSO) algorithm to optimize the lifetime of randomly deployed WSNs. The approach involves dividing the problem into two sub-problems. The first sub-problem focuses on finding the maximum number of NDSCs that achieve full coverage of the targets in the area. PSO, using a heuristic method, is employed to address this sub-problem. The second sub-problem deals with finding an optimal scheduling approach to maximize the WSN lifetime while considering the limited initial energy reserve in each sensor. Again, PSO, based on a heuristic method, is used to tackle this sub-problem. The NDSCs obtained from the first sub-problem serve as inputs for the scheduling in the second sub-problem. The solutions obtained by the proposed NDSC-PSO method are compared with those obtained by the NDSC-GA (Genetic Algorithm) method from the literature. Additionally, the quality of the NDSC-PSO solutions is evaluated by comparing them with exact solutions obtained using an Integer Linear Programming (ILP) method from the literature. The experimental results demonstrate that the NDSC-PSO method outperforms the NDSC-GA method in terms of finding optimal solutions for the same instances. The proposed method effectively maximizes the lifetime of WSNs while considering limited initial energy constraints. The paper contributes to the existing literature by presenting a novel approach that utilizes the PSO algorithm for finding NDSCs and scheduling them in WSNs. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

ChemDFM-X: towards large multimodal model for chemistry

引用

Science China(Information Sciences) 2024年第12期67卷 99-100页

作者： Zihan ZHAO Bo CHEN Jingpiao LI Lu CHEN Liyang WEN Pengyu WANG Zichen ZHU Danyang ZHANG Yansi LI Zhongyang DAI Xin CHEN Kai YU X-LANCE Lab Department of Computer Science and EngineeringMoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Suzhou Laboratory

Chemistry, as a naturally multimodal discipline, plays a crucial role in various vital fields such as pharmaceutical research and material manufacturing. Therefore, research on artificial intelligence(AI) for chemistry has garnered increasing attention. Despite the rapid development, most of the chemical AI models today mainly focus on single tasks with unimodal input [1].

关键词：

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：