检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cross Modal Sentiment Classification of Social Media Based on Meta Heuristic Algorithm

Cross Modal Sentiment Classification of Social Media Based o...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wantong Du Wanli Min Yushui Geng Hu Liang Hehu Zhou Ministry of Education Shandong Computer Science Center Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Synthesis Electronic Technology Co. Ltd

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The evolution of online social media has reshaped public behaviors, and social data infused with emotions provides crucial decision support for sentiment analysis tasks. Conventional multimodal approaches, influenced by redundant information in feature extraction during sentiment analysis, often focus solely on modality interactions without considering the unique content of each modality. This paper introduces the HGB-HFN model, addressing feature redundancy by optimizing extracted features using metaheuristic algorithm techniques, achieving a higher accuracy optimal feature dataset at lower computational costs. To counteract the neglect of modal-independent information, a hybrid fusion approach is adopted. It prioritizes visual features to extract precise semantic and emotional information from textual content, training multiple base classifiers to learn independent and diverse discriminative information. Comparative experiments on streaming datasets MOSI and MOSEI demonstrate the computational approach’s superiority in both accuracy and efficiency over existing methods.

关键词： Training Sentiment analysis Visualization Accuracy Social networking (online) Metaheuristics Semantics

来源：评论

学校读者我要写书评

暂无评论

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Zhiqiang Zhang Yongqiang Jiang Qian Gao Zhipeng Wang Key Laboratory of Computing Power Network and information Security Ministry of Eaucation Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Jinan China

Existing multimodal recommendation research still faces some challenges, such as not being able to fully mine the implicit relevance information of neighbor nodes, and the unreasonable weight allocation to imbalanced nodes. To address the aforementioned challenges, this paper introduces a new multimodal recommendation model called NS-MAR+. Specifically, the model firstly constructs a neighbor similarity graph convolutional network to capture the implicit relevance information and reasonably assigns the attention weights through the graph attention mechanism. Secondly, the model introduces a modal alignment and fusion mechanism by using a multilayer perceptron (MLP) to map image and text features into a shared space for comparison and fusion. In addition, the model constructs a user co-interaction graph and an item semantic graph based on the original information and performs graph convolution operations to enhance the preference information of users and items, and to better capture the interactions and internal features between users and items. Finally, MLP is employed to aggregate user and item representations and predict personalized recommendation rankings. To validate the experiment's efficacy, this paper compares with several leading multimodal recommendation models on public datasets with a performance improvement of 1% to 3%. The experimental outcomes indicate that the model in this paper has good superiority and accuracy in multimodal recommendation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nusec and Midesec: datasets for Histopathological Image Analysis

SSRN

引用

SSRN 2024年

作者： Nemati, Nooshin Samet, Refik Sak, Serpil Hancer, Emrah Kirmizi, Bilge Ayca Yildirim, Zeynep Traoré, Mohamed Department of Computer Engineering Ankara University Ankara06830 Turkey Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand Department of Software Engineering Mehmet Akif Ersoy University Burdur15039 Turkey Department of Pathology Faculty of Medicine Ankara University Ankara06080 Turkey

Hematoxylin and Eosin (H&E) staining stands as the gold standard protocol for the preparationof histopathology tissue samples in breast cancer research. This staining technique facilitates theidentification and differentiation of various cell types within the tissue, providing crucial informationfor pathologists. While deep learning algorithms have shown promise in automating the analysis ofH&E images, their effectiveness relies on extensive datasets for training. Unfortunately, there is ascarcity of publicly available datasets specifically tailored for nuclei and mitosis detection. To addressthis gap, this paper introduces two publicly available datasets, namely NuSeC (Nuclei Segmentationand Classification) and MiDeSeC (Mitosis Detection, Segmentation, and Classification) to serve asvaluable resources for building deep learning models for histopathological image analysis. The NuSeCdataset comprises 75 images for training and an additional 25 images for testing, encompassing around6000 nuclei structures, and the MiDeSeC dataset involves 35 training and 15 test image sets with morethan 500 mitoses. In both datasets, the QuPath tool as a pixel-level annotator is utilized to generatemask images. Moreover, we design two deep learning-based methodologies to conduct experimentalanalysis on the NuSeC and MiDeSeC datasets. The results indicate the potential to achieve substantialperformance on these datasets, facilitating the construction of new models or analysis of existing ones © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based classification of medication adherence among patients with noncommunicable diseases

引用

Informatics in Medicine Unlocked 2025年 52卷

作者： Kanyongo, Wellington Ezugwu, Absalom E. Moyo, Tsitsi Fonou Dombeu, Jean Vincent Department of Computer Science Faculty of Science Engineering Bindura University of Science Education Bindura Zimbabwe Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom 2520 South Africa Cimas Medical Aid Society Borrowdale Office Park Borrowdale Road P. O Box 1243 Harare Zimbabwe School of Mathematics Statistics and Computer Science University of KwaZulu-Natal Pietermaritzburg Campus Pietermaritzburg 3201 South Africa

Non-adherence to medication among individuals with non-communicable diseases (NCDs) leads to increased morbidity, mortality, and healthcare costs. The integration of electronic drug prescription and dispensation systems enables comprehensive analysis of medication adherence (MA). Patient-level and medical claims data for 8141 diabetic and hypertensive patients in Harare, Zimbabwe, were analysed. Non-adherence was defined as medication refills falling below 75 % of the intended 12 monthly claims, while adherence required at least 75 % of the refills. Classification employed multiple machine learning algorithms, including SVM, KNN, DT, Naïve Bayes, DNN, LR, and RF in Python 3.11.3. Significant variables for MA were identified through the Random Forest (RF) feature importance mechanism and the information gain technique. These included the annual quantity of medical supplies, annual claim amount, patient age, wellness program subscription, medical aid cover, contribution towards medical aid cover, comorbidity, diagnosis, hospital cover type, complications development, gender, and medical aid scheme. The total units of medical supplies dispensed annually emerged as the most significant predictor of MA. Considering the 8-feature subset, which consistently produced the most robust machine learning models, the classification accuracy of the ML classifiers ranged from 84.9 % to 88.2 %, while the AUC values varied between 0.857 and 0.934. RF, an ensemble learning technique, was the most robust classifier, achieving 88.2 % accuracy, an AUC of 0.935, and superior precision, recall, and F1-score. This model shows promise as a prognostic tool for enhancing MA, aiding in identifying adherence levels among patients. These findings contribute to addressing disparities in medication refilling and adherence rates among patients with NCDs. The ML model holds potential for the development of intelligent MA and intervention applications to improve patient adherence to medication in the

关键词： Chronic disease Decision trees Deep neural network Diabetes Hypertension k-NN Logistic regression Machine learning Medication adherence Naïve bayes Non-communicable diseases Random forest SVM

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

Smart World Congress (SWC), IEEE

作者： Qiliang Gu Qin Lu Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional Network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to ${2. 2 8 \%}$ and a minimum of ${1. 2 9 \%}$ across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model.

关键词： Attention mechanisms Correlation Law Graph convolutional networks Fuses Text categorization Semantics Predictive models Multitasking Internet

来源：评论

学校读者我要写书评

暂无评论

A Horizontal Federated Learning Approach to IoT Malware Traffic Detection: An Empirical Evaluation with N-BaIoT dataset 26

A Horizontal Federated Learning Approach to IoT Malware Traf...

引用

26th International Conference on Advanced Communications Technology, ICACT 2024

作者： Do, Phuc Hao Le, Tran Duc Vishnevsky, Vladimir Berezkin, Aleksandr Kirichek, Ruslan The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Saint-Petersburg Russia Danang Architecture University Da Nang Viet Nam University of Telecommunications Department of Communication Networks and Data Transmission at Bonch-Bruevich Saint-Petersburg State Russia University of Science and Technology The University of Danang Da Nang Viet Nam The University of Danang University of Science and Technology Information Technology Faculty Danang Viet Nam V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Institute of Control Sciences of Russian Academy of Sciences Russia Bonch Bruevich Saint Petersburg State University of Telecommunications Department of Programming Engineering and Computer Science Russia

ISBN: (纸本)9791188428120

The increasing prevalence of botnet attacks in IoT networks has led to the development of deep learning techniques for their detection. However, conventional centralized deep learning models pose challenges in simultaneously ensuring user data privacy and detecting botnet attacks. To address this issue, this study evaluates the efficacy of Federated Learning (FL) in detecting IoT malware traffic while preserving user privacy. The study employs N-BaIoT, a dataset of real-world IoT network traffic infected by malware, and compares the effectiveness of FL models using Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit models with a centralized approach. The results indicate that FL can achieve high performance in detecting abnormal traffic in IoT networks, with the CNN model yielding the best results among the three models evaluated. The study recommends the use of FL for IoT malware traffic detection due to its ability to preserve data privacy. © 2024 Global IT Research Institute - GIRI.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Flank Predictor for Quadruped Animal Species

引用

IET computer Vision 2025年第1期19卷

作者： Suessle, Vanessa Heurich, Marco Downs, Colleen T. Weinmann, Andreas Hergenroether, Elke Department of Computer Science University of Applied Sciences Darmstadt Darmstadt Germany School of Life Sciences University of KwaZulu-Natal Pietermaritzburg South Africa Algorithms for Computer Vision Imaging and Data Analysis Group University of Applied Sciences Darmstadt Darmstadt Germany Data Science Institute European University of Technology European Union Netherlands Department of National Park Monitoring and Animal Management Bavarian Forest National Park Grafenau Germany Department of Wildlife Ecology and Management Faculty of Environment and Natural Resources University of Freiburg Freiburg Germany Faculty of Applied Ecology Agricultural Sciences and Biotechnology University of Inland Norway Evenstad Norway

The bilateral asymmetry of flanks, where the sides of an animal with unique visual markings are independently patterned, complicates tasks such as individual identification. Automatically generating additional information on the visible side of the animal would improve the accuracy of individual identification. In this study, we used transfer learning on popular convolutional neural network (CNN) image classification architectures to train a flank predictor that predicted the visible flank of quadruped mammalian species in images. We automatically derived the data labels from existing datasets initially labelled for animal pose estimation. The developed models were evaluated across various scenarios involving unseen quadruped species in familiar and unfamiliar habitats. As a real-world scenario, we used a dataset of manually labelled Eurasian lynx (Lynx lynx) from camera traps in the Bavarian Forest National Park, Germany, to evaluate the model. The best model on data obtained in the field was trained on a MobileNetV2 architecture. It achieved an accuracy of 91.7% for the unseen/untrained species lynx in a complex unseen/untrained habitat with challenging light conditions. The developed flank predictor was designed to be embedded as a preprocessing step for automated analysis of camera trap datasets to enhance tasks such as individual identification. © 2025 The Author(s). IET computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature selection and importance of predictors of non-communicable diseases medication adherence from machine learning research perspectives

引用

Informatics in Medicine Unlocked 2023年 38卷

作者： Kanyongo, Wellington Ezugwu, Absalom E. Department of Computer Science Faculty of Science Engineering Bindura University of Science Education Bindura 0771 603 900 Zimbabwe School of Mathematics Statistics and Computer Science University of KwaZulu-Natal Pietermaritzburg Campus Pietermaritzburg 3201 South Africa Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom 2520 South Africa

Medication nonadherence is a significant public health concern that leads to ineffective treatment, which in turn engenders complications such as increased morbidity risks, unnecessary hospitalisations, and premature mortality. Technologies of the Fourth Industrial Revolution, such as machine learning, provide breakthroughs in identifying the most important features for building predictive models of medication adherence. Due to the diversity and complexity of medication adherence, it is crucial to leverage machine learning to determine significant medication adherence factors. This study systematically reviewed articles exhibiting feature selection and feature importance in research utilising machine learning to analyse medication adherence among Non-communicable diseases (NCD) patients. The articles were retrieved using Google Scholar, Research4Life, IEEE Xplore, and PubMed. The requirements for inclusion were met by 27 papers published between 2010 and 2022. The publications reviewed incorporate machine learning while also demonstrating feature selection and the importance of predictors of medication adherence in NCD patients with hypertension (n = 6), cardiovascular diseases (n = 6), diabetes (n = 4), opioid use disorder (n = 3), and other NCDs (n = 8). The findings demonstrate that medication adherence is a multifactorial issue influenced by various features such as sociodemographic and economic characteristics, medication information, behavioural, disease-related, and healthcare system-related factors. Some of these features, such as the patient's age, gender and race, cannot be modified. Once the patients with nonmodifiable features have been identified, they must be proactively monitored for medication adherence. On the other hand, adjustable risk features, such as self-efficacy and medication knowledge, can be modified and improved through medication education or medication adherence awareness. Various techniques for selecting and ranking features have emerg

关键词： Chronic disease Feature importance Feature selection (FS) Machine learning (ML) Medication adherence (MA) Non-communicable disease (NCD) Predictors of MA

来源：评论

学校读者我要写书评

暂无评论

Overlooked Aspects of data Governance: Workflow Framework For Enterprise data Deduplication

Overlooked Aspects of Data Governance: Workflow Framework Fo...

引用

Intelligent Computing, Communication, Networking and Services (ICCNS), International Conference on

作者： Otmane Azeroual Anastasija Nikiforova Kewei Sha German Centre for Higher Education Research and Science Studies (DZHW) Berlin Germany Faculty of Science and Technology Institute of Computer Science Chair of Software Engineering University of Tartu Tartu Estonia Task Force “FAIR Metrics and Data Quality” European Open Science Cloud Brussels Belgium College of Science and Engineering University of Houston Clear Lake Houston USA

data quality in companies is decisive and critical to the benefits their products and services can provide. However, in heterogeneous IT infrastructures where, e.g., different applications for Enterprise Resource Planning (ERP), Customer Relationship Management (CRM), product management, manufacturing, and marketing are used, duplicates, e.g., multiple entries for the same customer or product in a database or information system, occur. There can be several reasons for this, but the result of non-unique or duplicate records is a degraded data quality. This ultimately leads to poorer, inefficient, and inaccurate data-driven decisions. For this reason, in this paper, we develop a conceptual data governance framework for effective and efficient management of duplicate data, and improvement of data accuracy and consistency in large data ecosystems. We present methods and recommendations for companies to deal with duplicate data in a meaningful way.

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：