检索结果-内蒙古大学图书馆

Efficient COVID-19 detection using data mining algorithms: a comparison of basic and hybrid approaches

Soft Computing 2025年第3期29卷 1437-1451页

作者： Saidi, Mohammad Gheibi, Mohammad Ghazikhani, Adel Lotfata, Aynaz Chahkandi, Benyamin Familsamavati, Sajad Behzadian, Kourosh Department of Computer Science Imam Reza International University Mashhad Iran MS of Software Engineering Information and Communication Technology Unit Mashhad Municipality Fire and Safety Services Organization Mashhad Iran Big Data Lab Imam Reza International University Mashhad Iran Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec46117 Czech Republic Tallinn10615 Estonia Department of Pathology Microbiology and Immunology School of Veterinary Medicine University of California Davis95616 United States Department of Urban and Regional Planning San Jose State University San Jose95192 United States Faculty of Civil and Environmental Engineering Gdansk University of Technology Narutowicza Street 11/12 80-233 Gdansk Poland Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey Mexico School of Computing and Engineering University of West London London United Kingdom

Accurate and efficient diagnosis of COVID-19 remains a significant challenge due to the limitations of current detection methods, such as blood tests and chest scans, which can be time-consuming and error-prone. This study aims to compare the performance of basic and hybrid data mining algorithms in diagnosing COVID-19, using blood test results and clinical information to identify the most effective approach. A dataset of 200 records from suspected and infected COVID-19 patients, with 23 characteristics and one diagnostic class, was analysed. Nine data mining algorithms were tested: four basic algorithms (Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor) and five hybrid algorithms (Random Forest, AdaBoost, Majority Voting, XGBoost, Bagging). The study also integrated Response Surface Methodology (RSM) and Adaptive-Network-based Fuzzy Inference System (ANFIS) to enhance model performance. The Bagging algorithm demonstrated superior performance with an accuracy of 88%, sensitivity of 74%, and F-criterion of 78%. The integration of RSM and ANFIS further showed that a smart model could be developed for efficient pandemic crisis management, achieving up to 100% accuracy when considering key factors like AST, Albumin, and CRP. The findings suggest that Bagging and hybrid data mining algorithms can significantly improve COVID-19 detection, reducing time and errors in identifying exposed individuals. The study highlights the potential of combining machine learning techniques with RSM-ANFIS models for effective pandemic management and decision-making in medical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Automated information mining in hazardous chemical accident reporting: An improved deep learning approach

引用

Journal of Loss Prevention in the Process Industries 2025年 97卷

作者： Zhao, Kai Wan, Lining Lu, Xilei Zhao, Jun Chen, Fei He, Miao Gao, Jinhao Wang, Qibo Zhang, Linlin Zhang, Li School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Uygur Autonomous Region Academy of Safety Science and Technology Urumqi830011 China Xinjiang Yihua Chemical Co. Changji Hui Autonomous Prefecture 831100 China School of Chemical Engineering and Technology Xinjiang University Urumqi830017 China School of Software Xinjiang University Urumqi830000 China

Mining and accumulating lessons learned from incident reports, accurately identifying and extracting accident knowledge, can help managers recognize patterns, analyze common attributes, and thus prevent the recurrence of similar incidents. Due to the limitations of unstructured or semi-structured text records, current hazardous chemical accident research heavily relies on expert evaluations, often resulting in inefficiency, lack of intelligence, and subjectivity. To overcome this limitation, we propose an accident analysis framework that combines deep learning-based Named Entity Recognition (NER) and topic mining algorithms. First, we employ a RoBERTa-BiLSTM-Attention-CRF method based on a pre-trained model to automatically recognize and extract information from accident reports according to predefined accident entities. Second, we construct a dictionary specific to the hazardous chemicals domain and apply the Latent Dirichlet Allocation (LDA) model to analyze the causes of accidents within the "CAUSE" entity, thereby deriving the hazardous themes implied in the accidents. Finally, we validate the model on a self-constructed hazardous chemical named entity recognition incident report dataset (HCNER). The research findings indicate that the methodology proposed in this study effectively addresses the challenges associated with dispersed textual information, specialized terminology, and data formatting in the digital processing of hazardous chemical incidents. This advancement propels the development within the domain of hazardous chemical safety management and serves as a viable approach for investigating the causes of such incidents. © 2025 Elsevier Ltd

关键词： Chemical hazards

来源：评论

学校读者我要写书评

暂无评论

2M3DF: Advancing 3D Industrial Defect Detection with Multi Perspective Multimodal Fusion Network

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Asad, Mujtaba Azeem, Waqar Jiang, He Mustafa, Hafiz Tayyab Yang, Jie Liu, Wei Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Department of Automation Shanghai200240 China Lahore Garrison University Department of Software Engineering Lahore54000 Pakistan China University of Mining and Technology School of Information and Control Engineering Jiangsu Xuzhou221116 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China

In the context of Industrial Anomaly Detection (IAD), ensuring the quality of manufactured products is critical. Traditional 2D based methods often fail to capture anomalies present in complex 3D shapes. For effective anomaly detection in 3D shapes, it is essential to incorporate global semantic context, local geometric structure, and color information of the object. To fully leverage these features, we propose a network named 2M3DF, that leverages knowledge from multi-view RGB images and corresponding point cloud information for enhanced anomaly detection performance. Our model initially employs pre-trained feature extractors that generate local features from multi-view RGB images and corresponding point clouds. The novel inter-modality feature representation and fusion module first adapts these inter-modality features and then effectively aligns and aggregates these multimodality features on a pixel-to-point basis. To learn the normality from point-wise fused multimodal features, we fit a multivariate Gaussian distribution to model the normal feature distribution. Comprehensive experimental evaluations using the MVTec3D-AD and Eyecandies dataset validate the effectiveness of our propose model and demonstrate significant improvements in comparison to existing state-of-the-art methods. Our model achieves a 96.6% mean I-AUROC while delivering real-time results. © 1991-2012 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Encryption Traffic Classification Based on Mining Traffic Context and Transport Relationship

Encryption Traffic Classification Based on Mining Traffic Co...

引用

IEEE Conference on Wireless Communications and Networking

作者： Weilin Gai Runqing Zhang Huiyuan Zhang Yu Guo Jun Yin Peng Zhang TCA Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China National Computer Network Emergency Response TechnicalTeam/Coordination Center of China Beijing China School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

This paper proposes a novel ETC-MTCTR, which is designed to enable more accurate, versatile and efficient traffic classification in the context of multi-scenario, low-resource encrypted traffic. Through three modules of Datagram Token conversion, pretraining and fine-tuning, the method uses large-scale unlabeled encrypted traffic for pretraining, mining and learning the traffic context and transmission relationship of encrypted traffic classification tasks, so that a small number of labeled data samples can be effectively used in the fine-tuning stage. Significantly improve the performance of the model on specific downstream classification tasks, enhance the accuracy, adaptability and robustness of the model in diverse environments, limited resources and new encryption security protocols, and realize efficient encryption traffic classification in multi-scenario and low-resource background. The results show that ETC-MTCTR achieves the best performance on three tasks: encryption malware classification, VPN encrypted traffic classification, and TLS 1.3 encryption application classification. Its F1 score is improved by 0.22% in the classification task of encrypted malware, 1.4% in the classification task of VPN encrypted traffic App, 4.56% in the classification task of VPN encrypted traffic Service, and 9.89% in the classification task of TLS 1.3 encrypted application, which is significantly better than other comparison methods.

关键词： Adaptation models Accuracy Protocols Malware Robustness Encryption Virtual private networks Data mining

来源：评论

学校读者我要写书评

暂无评论

Attribute-Based Policy-Hiding Redactable Blockchain With Authorizable Verification for Energy Internet

引用

IEEE Internet of Things Journal 2025年

作者： Xue, Jingting Liu, Liang Li, Fagen Jing, Ximin Zhang, Wenzheng Zhang, Xiaojun Zhou, Yu Southwest Petroleum University School of Computer Science and Software Engineering Engineering Research Center for Intelligent Oil and Gas Exploration Chengdu610500 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Institute of Southwestern Communication Science and Technology on Communication Security Laboratory Chengdu610041 China

The goal of the energy internet is to enable communication between distributed energy endpoints to facilitate information exchange and trading matching. Blockchain, which ensures content consistency, bridges the gaps between multiple energy stakeholders and satisfies the need for universal trust. However, applying blockchain directly in peer-to-peer trading can result in the permanent inclusion of illegal or outdated data in blockchain databases, hindering efficient interaction. Driven by emerging application requirements and legal regulations, redactable blockchain (EuroS&P 2017) was introduced, allowing the block history to be rewritten via collisions in chameleon hash functions. Nevertheless, current solutions still face challenges, including trapdoor security risks, privacy leakage, and indefinite redactions. This paper presents a redactable energy blockchain scheme (REBS) with partially attribute-based policy hiding, which enables controlled multi-authority key generation and redactor attribute verification. To prevent the abuse of redaction permission, REBS employs time-updatable chameleon hash functions for redaction. Additionally, we design a delegation algorithm that adds dynamic flexibility to attribute verification nodes, permitting them to delegate key share distribution authority to other nodes on demand. The detailed security proofs and performance evaluations demonstrate the feasibility of REBS. © 2014 IEEE.

关键词： Energy policy

来源：评论

学校读者我要写书评

暂无评论

Highly Accurate Crow Search Optimized CNN Classifier for Cyclone Prediction

Highly Accurate Crow Search Optimized CNN Classifier for Cyc...

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： R. Ramya Kavin K. S R. Anuja A. T. R. Krishna Priya D. Karthikeyan Kiruba Thangam Raja Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Tamilnadu India Department of Electrical and Electronics Engineering Government College of Engineering Tirunelveli Tamilnadu India Department of Computer Science and Engineering Rohini College of Engineering and Technology Kanyakumari Tamilnadu India Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Chennai India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems (SCORE) VIT University Vellore

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Accurate and timely prediction of cyclone events is essential for effective disaster management and risk mitigation. This study introduces a highly precise cyclone prediction model that combines Convolutional Neural Networks (CNNs) with the optimization capabilities of the Crow Search Algorithm (CSA). The resulting model, called Crow Search Optimized CNN (CSO-CNN), harnesses the feature extraction and classification strengths of CNNs, while the CSA is used to optimize the hyperparameters of the CNN architecture for optimal performance. The model is trained and validated on a comprehensive dataset that includes satellite imagery and meteorological data from a wide range of cyclone events. The CSO-CNN achieves remarkable classification accuracy, surpassing traditional CNN models and other leading techniques. Its ability to quickly and accurately assess the likelihood of cyclone formation provides crucial decision support for disaster management authorities, enabling timely and effective response strategies. By integrating the CSA optimization technique with the CNN framework, this study presents a novel approach to cyclone prediction. It highlights the potential of combining advanced Machine Learning (ML) algorithms to tackle complex environmental challenges and deepen our understanding of intricate atmospheric phenomena.

关键词： Accuracy Atmospheric modeling Disaster management Predictive models Prediction algorithms Feature extraction Cyclones Satellite images Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

BoxPolypSAM: Leveraging SAM in Box-Supervised Polyp Segmentation

BoxPolypSAM: Leveraging SAM in Box-Supervised Polyp Segmenta...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yinqi Cai De-jun Fan Feng Gao Mingzhi Mao Weijun Sun Guanbin Li School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Sixth Affiliated Hospital Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China Guangdong University of Technology Guangzhou China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Automatic polyp segmentation from colonoscopy images is crucial for colon cancer diagnosis. Nonetheless, training fully supervised polyp segmentation models requires timeconsuming pixel-level annotations. Instead, box annotations of polyps are more attainable. To reduce the burden of annotation, we propose BoxPolypSAM, a box-supervised polyp segmentation model based on the Segment Anything Model (SAM). We leverage a box-supervised projection loss to confine predicted masks within ground-truth boxes and an augmentation consistency loss to reduce the variability of predicted masks. For adapting SAM, we propose a model architecture AutoPromptSAM, which creates a dense prompt from the image encoder's features for automatic segmentation and employs efficient fine-tuning techniques to transfer the capabilities of the SAM model. Moreover, we distill the model to a lightweight model for quicker inference and less GPU memory cost, which also improves performance. Experimental results on six datasets demonstrate our proposed model and the distilled model show excellent performance in polyp segmentation without relying on any pixel-level labels.

关键词： Training Image segmentation Adaptation models Costs Annotations Biological system modeling Memory management Graphics processing units Colonoscopy Colorectal cancer

来源：评论

学校读者我要写书评

暂无评论

Corporate Fraud Detection in Rich-yet-Noisy Financial Graph

arXiv

引用

arXiv 2025年

作者： Wang, Shiqi Zhang, Zhibo Fang, Libing Nguyen, Cam-Tu Li, Wenzhon School of Artificial Intelligence Nanjing University Jiangsu Nanjing China School of Computer Science and Technology Nanjing University Jiangsu Nanjing China School of Management and Engineering Nanjing University Jiangsu Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China

Corporate fraud detection aims to automatically recognize companies that conduct wrongful activities such as fraudulent financial statements or illegal insider trading. Previous learning-based methods fail to effectively integrate rich interactions in the company network. To close this gap, we collect 18-year financial records in China to form three graph datasets with fraud labels. We analyze the characteristics of the financial graphs, highlighting two pronounced issues: (1) information overload: the dominance of (noisy) non-company nodes over company nodes hinders the message-passing process in Graph Convolution Networks (GCN);and (2) hidden fraud: there exists a large percentage of possible undetected violations in the collected data. The hidden fraud problem will introduce noisy labels in the training dataset and compromise fraud detection results. To handle such challenges, we propose a novel graph-based method, namely, Knowledge-enhanced GCN with Robust Two-stage Learning (KeGCNR), which leverages Knowledge Graph Embeddings to mitigate the information overload and effectively learns rich representations. The proposed model adopts a two-stage learning method to enhance robustness against hidden frauds. Extensive experimental results not only confirm the importance of interactions but also show the superiority of KeGCNR over a number of strong baselines in terms of fraud detection effectiveness and robustness. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yujun Zhang Yanqu Chen Jiakai Wang Jin Hu Renshuai Tao Xianglong Liu State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression.

关键词： Accuracy Target recognition Perturbation methods Noise Robustness Acoustics Speech processing Digital audio players Automatic speech recognition Resilience

来源：评论

学校读者我要写书评

暂无评论

Listwise ranking predictor for evolutionary neural architecture search

引用

Swarm and Evolutionary Computation 2025年 96卷

作者： Li, Nan Ma, Lianbo Wang, Rui Cheng, Shi Sun, Yanan Xue, Bing Zhang, Mengjie College of Software Northeastern University Liaoning Shenyang110819 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington 6140 New Zealand Foshan Graduate School of Innovation Guangdong Foshan528000 China College of System Engineering National University of Defense Technology Hunan Changsha410073 China School of Computer Science Shaanxi Normal University Shaanxi Xian710119 China School of Computer Science Sichuan University Sichuan Chengdu610000 China

In evolutionary neural architecture search (ENAS), the accuracy predictors (i.e., regression models) have been successfully applied to save computational costs for the evaluation of network architectures. However, the accuracy of these predictors is largely limited by the small amount of evaluated architectures that may be difficult to obtain. Such accuracy predictors with prediction bias often lead to an inaccurate ranking, misleading the selection of ENAS. To alleviate the above limitations, we design an efficient and novel listwise ranking predictor (LRP) for ENAS to directly predict the ranking of each architecture instead of the numerical accuracy value of each architecture. Specifically, the training data is constructed by the proposed random encoding-combination (REC) strategy, which can generate substantial training data using the small number of evaluated architectures (data level). These specially constructed training data are used to train LRP, which can convert the complex regression task into a ranking task to reduce ranking bias (model level). The proposed NAS method is compared with state-of-the-art NAS methods on widely-used benchmark datasets and practical application. Experimental results demonstrate that LRP can alleviate the ranking disorder problem and outperform others in terms of both effectiveness and efficiency. © 2025 Elsevier B.V.

关键词： Linear regression

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：