检索结果-内蒙古大学图书馆

PRNet: Low-Light Image Enhancement Based on Fourier Transform

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Zhang, Jiayu Wang, Xiaohua Li, Yingjian Wang, Wenjie Xian Polytech Univ Sch Elect & Informat Xian 710600 Peoples R China Xian Polytech Univ Xian Polytech Univ Branch Shaanxi Artificial Intel Xian 710600 Peoples R China Xian Polytech Univ Sch Comp Sci Xian 710048 Peoples R China Shaanxi Key Lab Clothing Intelligence Xian 710048 Peoples R China

Low-light image enhancement (LLIE) techniques constitute a significant approach for enhancing image brightness effectively while preserving image details. In this article, PRNet is proposed, which is a novel lightweight LLIE network that leverages the Fourier transform, performing LLIE in two stages. In the first stage, a pixel enhancement network (PENet) enhances the brightness of the low-light image (LLI) through a dense skip-connection structure. This structure incorporates a custom-designed Fourier-based brightness enhancement block (FBEB). In the second stage, a refinement and restoration network (RRNet) processes the output from the first stage, further restoring image details. Detailed refinement is achieved using a dual-branch UNet structure, incorporating a bidirectional frequency-domain cross-attention solver (BFDCS) to optimize image quality. To thoroughly assess the performance of the proposed PRNet, nine well-established benchmark datasets were employed for detailed quantitative and qualitative evaluations. The experimental results show that PRNet achieves high-quality image enhancement at significantly reduced computational complexity.

关键词： Brightness Frequency-domain analysis Image enhancement Feature extraction Image restoration Training Image color analysis Fast Fourier transforms data mining computational complexity Amplitude component cross-attention Fourier transform low-light image enhancement (LLIE) phase component

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning Subnetworks Towards Parameter-Efficient Class-Incremental Learning

引用

ieee Transactions on Knowledge and data Engineering 2025年第6期37卷 3240-3252页

作者： Li, Depeng Zeng, Zhigang Dai, Wei Suganthan, Ponnuthurai Nagaratnam Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Qatar University Kindi Center for Computing Research College of Engineering Doha2713 Qatar

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. To mitigate the catastrophic forgetting phenomenon, typical CIL methods either cumulatively store exemplars of old classes for retraining model parameters from scratch or progressively expand model size as new classes arrive, which, however, compromises their practical value due to little attention paid to parameter efficiency. In this paper, we contribute a novel solution, effective control of the parameters of a well-trained model, by the synergy between two complementary learning subnetworks. Specifically, we integrate one plastic feature extractor and one analytical feed-forward classifier into a unified framework amenable to streaming data. In each CIL session, it achieves non-overwritten parameter updates in a cost-effective manner, neither revisiting old task data nor extending previously learned networks;Instead, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Experimental results on a variety of task sequences demonstrate that our method achieves competitive results against state-of-the-art CIL approaches, especially in accuracy gain, knowledge transfer, training efficiency, and task-order robustness. Furthermore, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated to make its non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks. © 2025 ieee.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Classification Techniques in data mining: A Comprehensive Study 2

Classification Techniques in Data Mining: A Comprehensive St...

引用

2nd International Conference on computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Baghel, Kirti Bhati, Richa Budhiraja, Aastha School of Computer Applications Manav Rachna International Institute of Reserch & Studies Faridabad India

ISBN: (纸本)9798331530389

data mining classification techniques become increasingly relevant because it is sensible to bring meaningful patterns out from very large data sets;however, cross-comparison and comparison in terms of different domains, in terms of several classifiers that exist, is discussed inadequately. A systematic review of the five prime classification algorithms has been made for a large set of varied datasets that range from healthcare and finance domains up to social media domains. Employed a newly developed multi-metric evaluation approach, which included accuracy, F1-score, computation performance, and model explainability. With the use of the 15 datasets to evaluate 50,000 instances, ensemble algorithms-namely Random Forest and XGBoost-were found to perform steadily better than isolated base learning classifiers, achieving a respective average of 94.2 percent in contrast to 87.6 percent for isolated techniques. In addition, DNN appeared to perform outstandingly on high-dimensional features but was computationally 3.5 times more complex compared to the tree-based technique. The study also found an enormous trade-off between model complexity and interpretability: the simpler models retained 85% of the performance while presenting better explainability. Such findings show empirical evidence for selecting optimum classification techniques on domain requirements and computational constraints, further adding towards decision-making in real-life data-mining applications. © 2025 ieee.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence Methods for Diagnostic and Decision-Making Assistance in Chronic Wounds: A Systematic Review

引用

JOURNAL OF MEDICAL SYSTEMS 2025年第1期49卷 1-39页

作者： Jimenez, David Reifs Casanova-Lozano, Lorena Grau-Carrion, Sergi Reig-Bolano, Ramon Univ Vic Digital Care Res Grp Sagrada Familia 7 Vic 08500 Barcelona Spain

Chronic wounds, which take over four weeks to heal, are a major global health issue linked to conditions such as diabetes, venous insufficiency, arterial diseases, and pressure ulcers. These wounds cause pain, reduce quality of life, and impose significant economic burdens. This systematic review explores the impact of technological advancements on the diagnosis of chronic wounds, focusing on how computational methods in wound image and data analysis improve diagnostic precision and patient outcomes. A literature search was conducted in databases including ACM, ieee, PubMed, Scopus, and Web of Science, covering studies from 2013 to 2023. The focus was on articles applying complex computational techniques to analyze chronic wound images and clinical data. Exclusion criteria were non-image samples, review articles, and non-English or non-Spanish texts. From 2,791 articles identified, 93 full-text studies were selected for final analysis. The review identified significant advancements in tissue classification, wound measurement, segmentation, prediction of wound aetiology, risk indicators, and healing potential. The use of image-based and data-driven methods has proven to enhance diagnostic accuracy and treatment efficiency in chronic wound care. The integration of technology into chronic wound diagnosis has shown a transformative effect, improving diagnostic capabilities, patient care, and reducing healthcare costs. Continued research and innovation in computational techniques are essential to unlock their full potential in managing chronic wounds effectively.

关键词： Wounds and injuries Algorithms data mining Deep learning Computer assisted Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Advances in Big data and data mining: Techniques and Applications in data Fusion for Enhanced Insights and Decision-Making

Advances in Big Data and Data Mining: Techniques and Applica...

引用

2025 ieee International Conference on computational, Communication and Information Technology, ICCCIT 2025

作者： Goyal, Himanshu Rai Shrivastava, Anurag Nagpal, Amandeep Reddy, R. Akhilesh Yadav, Kanchan Revathi, R. Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Lovely Professional University Phagwara India MLR Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India GLA University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Applied Sciences Bangalore India

ISBN: (纸本)9798331512965

The advancement of big data has accelerated over the years to change how companies utilize data to drive decisions. And so, this paper aims to look at big data and data mining in different perspectives while highlighting the importance of data fusion in decision making in the current society. Many times, data fusion combines different data sources to provide better and broader results. Clustering of raw data, anomaly detection and machine learning are discussed as well as their use in healthcare, financial management and smart cities. This paper also presents such issues as data heterogeneity, data quality assurance, as well as scalability issues. Lastly, tomorrow's possibilities, such as artificial intelligence and quantum computing, are presented as possible enhancements of the data fusion effectiveness are mentioned due to the expected marked advancement in real-time and adaptive decisionmaking systems. © 2025 ieee.

关键词： data centers

来源：评论

学校读者我要写书评

暂无评论

DTSG-Net: Dynamic Time Series Graph Neural Network and Its Application in Modulation Recognition

引用

ieee INTERNET OF THINGS JOURNAL 2025年第4期12卷 3742-3754页

作者： Yin, Peng Zhou, Jinchao Ge, Yizheng Chen, Zhuangzhi Univ Chinese Acad Sci Sch Cyber Secur Beijing 101408 Peoples R China Def Ind Secrecy Examinat & Certificat Ctr Beijing 100089 Peoples R China Binjiang Inst Artificial Intelligence Res Ctr Electromagnet Space Secur Hangzhou 310056 Peoples R China Def Ind Secrecy Examinat & Certificat Ctr Beijing 100089 Peoples R China

Modulation recognition of communication signals is of great importance in the context of the Internet of Everything (IoE), as wireless communication technology is a key foundation for implementing the IoE. Recently, graph neural networks (GNNs) have been successfully applied to modulation recognition tasks due to their ability to merge messages transmitted between adjacent nodes in the graph. However, GNN-based models are more computationally intensive when processing long signals, potentially reducing their practicality. In this article, we explore a novel signal representation from a graph perspective and propose a graph-powered modulation recognition framework. We first propose the dynamic time series graph (DTSG) algorithm, which segments the signals and maps each segment into a patch graph, with corresponding patches from different signals sharing connected edges. By integrating DTSG with both GNNs and recurrent neural networks (RNNs), we have designed an end-to-end signal classification framework, DTSG-Net, for modulation recognition. Experimental results on four datasets: 1) RML2016.10a;2) RML2018.01a;3) Sig2019-12;and 4) HKDD_AMC36-demonstrate that our DTSG-Net can achieve high signal modulation classification accuracy (Acc) with minimal computational resources, outperforming existing methods based on signal graph representation in terms of computational resource savings and higher accuracy.

关键词： Modulation Feature extraction Time series analysis Convolutional neural networks Heuristic algorithms data mining computational modeling Graph neural networks Deep learning Classification algorithms Graph graph neural network (GNN) Internet of Everything (IoE) modulation recognition recurrent neural network (RNN)

来源：评论

学校读者我要写书评

暂无评论

DualC: Drug-Drug Interaction Prediction Based on Dual Latent Feature Extractions

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年第1期9卷 946-960页

作者： Guo, Lin Lei, Xiujuan Liu, Lian Chen, Ming Pan, Yi Shaanxi Normal Univ Sch Comp Sci Xian 710119 Peoples R China Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Fac Comp Sci & Control Engn Shenzhen 518055 Peoples R China

Drug-Drug Interaction is characterized by a modification in the action of one drug due to its concurrent use with another. It involves the safety and universality of drugs, and is one of the most meaningful issues in clinical drug combination therapy and drug development. We prefer to use computational methods to achieve DDI prediction in order to achieve large-scale prediction. This article designs a DDI prediction model DualC based on the layer attention mechanism of Graph Convolutional Network and 1 Dimensional-Convolutional Neural Network to extract topological and structural information of drugs. First, the DDI network is obtained from the drug relationship data in the database and the drug similarity network is calculated with the help of drug target features, then they are constructed into a heterogeneous network. Next, the layer attention mechanism and Graph Convolutional Network are used to learn the topological information. Subsequently, the structural information is acquired from the chemical substructure similarity matrix utilizing 1 Dimensional-Convolutional Neural Network. Finally, use the sigmoid function for DDI prediction. The experimental results show advantages of DualC which AUC reaches 0.965 and ACC reaches 0.973. The case study further proves DualC has certain practical significance.

关键词： Drugs Feature extraction databases data mining Vectors Heterogeneous networks Predictive models Medical treatment Bioinformatics Safety Drug-drug interaction graph convolutional network convolutional neural network layer attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Research on Information System Optimization Based on data mining Technology using Hamming Distance based Fuzzy C Means Clustering 1

Research on Information System Optimization Based on Data Mi...

引用

1st International Conference on Intelligent Systems and computational Networks, ICISCN 2025

作者： Zhang, Chi Shanghai International Travel Healthcare Center Shanghai Customs Port Clinic Shanghai China

ISBN: (纸本)9798331529246

An advancement of informatization as well as intelligence is the unpredictable inclination of safety production is various applications. The advancement of data mining becomes a vital part in encouraging the advancement of education safety management. However, the greater education management system according to the data mining advancement needs to be optimized to attain the maximum efficiency. Hence, this research proposes the Hamming Distance based Fuzzy C Means (HD-FCM) clustering approach for an optimization of information system in educational management. HD measures guide variations in feature attributes, designing the clustering outcomes simple to interpret for high authorities and educators. The feature extraction method named FastText is utilized for the extraction of important data from the collected input. The FastText extracts meaningful features that enhances the model effectiveness through understanding word context. The experimental results demonstrates that the proposed HD-FCM approach attains the better parallel efficiency of 91.5%, load balancing efficiency of 99.7%, acceleration ratio of 3.8, parallel time of 398.2s and total time of 1198.3s correspondingly as compared to existing Machine Leaning (ML) approach. © 2025 ieee.

关键词： data mining fasttext fuzzy c means clustering hamming distance information system optimization

来源：评论

学校读者我要写书评

暂无评论

DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing

引用

ieee TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第4期37卷 1714-1727页

作者： Sun, Xinjie Zhang, Kai Liu, Qi Shen, Shuanghong Wang, Fei Guo, Yuxiang Chen, Enhong Univ Sci & Technol China Sch Comp Sci & Technol State Key Lab Cognit Intelligence Hefei 230027 Peoples R China Liupanshui Normal Univ Liupanshui 553004 Guizhou Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol State Key Lab Cognit Intelligence Hefei 230027 Peoples R China

Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT, thereby improving the quality of education. Although traditional KT values students' cognition and learning behaviors, efficient evaluation of students' affective states and their application in KT still require further exploration due to the non-affect-oriented nature of the data and budget constraints. To address this issue, we propose a computation-driven approach, Dynamic Affect Simulation Knowledge Tracing (DASKT), to explore the impact of various student affective states (such as frustration, concentration, boredom, and confusion) on their knowledge states. In this model, we first extract affective factors from students' non-affect-oriented behavioral data, then use clustering and spatiotemporal sequence modeling to accurately simulate students' dynamic affect changes when dealing with different problems. Subsequently, we incorporate affect with time-series analysis to improve the model's ability to infer knowledge states over time and space. Extensive experimental results on two public real-world educational datasets show that DASKT can achieve more reasonable knowledge states under the effect of students' affective states. Moreover, DASKT outperforms the most advanced KT methods in predicting student performance. Our research highlights a promising avenue for future KT studies, focusing on achieving high interpretability and accuracy.

关键词： computational modeling Problem-solving Deep learning data models Accuracy Sun Predictive models Long short term memory Knowledge engineering Trajectory Knowledge tracing data mining user modeling affect simulation

来源：评论

学校读者我要写书评

暂无评论

Triplet Bridge for Zero-Shot Sketch-Based Image Retrieval

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年第2期9卷 2014-2025页

作者： Zheng, Jiahao Tang, Yu Wu, Dapeng City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Shanghai Univ Shanghai Peoples R China

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) has always been a hard nut to crack due to the scarcity of sketch data and the abstract visual information contained in sketches. Previous works focus on designing various network architectures and using the gold standard triplet loss to solve ZS-SBIR, but they have always encountered obstacles in enhancing model generalization and extracting abstract visual information. In contrast, this work proposes a concise and effective Triplet Bridge (TriBri) framework to clear these obstacles fundamentally. Specifically, we use InfoNCE as the core to construct cross-modal representations between images and sketches, which can increase the margin between feature clusters with different categories in the representation space and improve the generalization of the model. Furthermore, we introduce text with abstract properties into the framework to construct a ternary relationship, and the three heterogeneous gaps between text, image, and sketch modalities are connected by InfoNCE. In this process, the common abstract visual cues in both images and sketches can be captured by the feature extractor with the guiding of text abstract information. Ultimately, comprehensive experiments on three commonly used datasets (i.e., TU-Berlin, Sketchy, and QuickDraw) validate that our framework can effectively solve these obstacles in a simple yet powerful manner. Furthermore, compared to state-of-the-art methods, the proposed TriBri exhibits comprehensive performance superiority.

关键词： Feature extraction Semantics Bridges Visualization Contrastive learning Image retrieval data mining Vectors Training Optimization InfoNCE ternary relationship triplet bridge

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：