检索结果-内蒙古大学图书馆

5th International Conference on Computing, Communications, and Cyber Security, IC4S 2023

作者： Alhabib, Abdulaziz Abdulrhman Alasiri, Abdulaziz Fae Alharbi, Mazen Bunayan Ahmad, Sultan Eljialy, A.E.M. Department of Information Systems College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University P.O.Box. 151 Alkharj11942 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University P.O.Box. 151 Alkharj11942 Saudi Arabia Chandigarh University Punjab Mohali Gharuan140413 India

ISBN: (纸本)9789819773701

In this paper, we explored the application of both the Random Forest and K-Nearest Neighbors (KNN) algorithms for fraud detection. Fraudulent activities pose significant threats to various industries, making their detection crucial. We reviewed related works on fraud detection, highlighting the effectiveness of both the Random Forest and KNN methods. We proposed a system utilizing a combination of Random Forest and KNN models for credit card fraud detection, detailing its architecture and methodology. The system preprocesses and splits data, trains the models, and evaluates their performance on a testing set. We analyzed the results, demonstrating the accuracy, robustness, and scalability of the proposed system. Additionally, we presented data on the most common hours for fraudulent transactions and the top jobs associated with them. Overall, this study emphasizes the efficacy of utilizing both Random Forest and KNN algorithms in mitigating the risks associated with fraud and offers a valuable tool for safeguarding against financial malfeasance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Interpretable Arabic Hate Speech Detection using Large Language Model

Interpretable Arabic Hate Speech Detection using Large Langu...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Majed Alwateer Ibrahim Gad Mahmoud Elmarhomy Ghada Elmarhomy Hasan Hashim Malik Almaliki El-Sayed Atlam Department of Computer Science College of Computer Science and Engineering Taibah University Saudi Arabia Computer Science Department Faculty of Science Tanta University Tanta Egypt Computer Science and Information College of Applied Taibah University Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Saudi Arabia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

Social media platforms serve as significant spaces for users to have conversations, discussions and express their opinions. However, anonymity provided to users on these platforms allows the spread of hate speech and other offensive material. Due to the wide-ranging nature of these platforms, there is a critical need to automatically detect and report occurrences of hate speech. There are various detection methods, but many of them operate as black boxes, lacking interpretability and explainability by design. To address the lack of interpretability, this study explores the development of an interpretable framework to detect hate speech in Arabic using large language models (LLMs). The proposed approach combines advanced natural language processing techniques with interpretable machine learning methods to enhance understanding of model decisions. The experimental results demonstrate that the model achieves high accuracy while maintaining interpretability, enabling users to understand the reasoning behind the detections. The proposed method achieves an accuracy of 0.846%, with a precision of 0.843% and a recall of 0.846%, outperforming existing Arabic hate speech detection models. These results show the effectiveness of combining LLM with interpretability for this critical task, providing a reliable and transparent solution for automated moderation of harmful content.

关键词： Technological innovation Accuracy Social networking (online) Smart cities Large language models Hate speech Text categorization Writing Reliability Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Robust Mean Field Social control: A Unified Reinforcement Learning Framework

arXiv

引用

arXiv 2025年

作者： Xu, Zhenhui Chen, Jiayu Wang, Bing-Chang Wu, Yuhu Shen, Tielong Department of Systems and Control Engineering The Institute of Science Tokyo Tokyo152-8552 Japan School of Control Science and Engineering Shandong University Jinan250061 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China

This paper studies linear quadratic Gaussian robust mean field social control problems in the presence of multiplicative noise. We aim to compute asymptotic decentralized strategies without requiring full prior knowledge of agents’ dynamics. The primary challenges lie in solving an indefinite stochastic algebraic Riccati equation for feedback gains, and an indefinite algebraic Riccati equation for feedforward gains. To overcome these challenges, we first propose a unified dual-loop iterative framework that simultaneously handles both indefinite Riccati-type equations, and provide rigorous convergence proofs for both outer-loop and inner-loop iterations. Second, recognizing that biases may arise in iterative processes due to estimation and modeling errors, we analyze the robustness of the proposed algorithm by using the small-disturbance input-to-state stability technique. This ensures convergence to a neighborhood of the optimal solution, even in the existence of disturbances. Finally, to address the limitation of requiring precise knowledge of agents’ dynamics, we employ the integral reinforcement learning technique to develop a data-driven method within the dual-loop iterative framework. A numerical example is provided to demonstrate the effectiveness of the proposed algorithm. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variations in Rural PM2.5 Sources and Composition in the Post Coal-to-Gas Period Based on a Three-Year Observation

引用

Aerosol and Air Quality Research 2025年第1期25卷 1-13页

作者： Ning, Zhi Li, Zhiyong Wei, Jihong Liu, Jinming Ma, Huichun Ren, Zhuangzhuang Ma, Xiaohua Liu, Chen Chen, Lan Liu, Aiqin Wang, Binglin Wang, Jiaqi Gao, Huiying Hebei Key Lab of Power Plant Flue Gas Multi-Pollutants Control Department of Environmental Science and Engineering North China Electric Power University Baoding071003 China MOE Key Laboratory of Resources and Environmental Systems Optimization College of Environmental Science and Engineering North China Electric Power University Beijing102206 China Department of Pediatrics Affiliated Hospital of Hebei University Baoding071000 China Hebei Key Lab of Mineral Resources and Ecological Environment Monitoring Hebei Research Center for Geoanalysis Baoding071051 China School of Control Science and Engineering North China Electric Power University Baoding071003 China China Environmental United Certification Center Co. Ltd. Beijing100029 China

Introduction: Various studies were conducted focused on the coal-to-gas (CTG) impacts on urban PM2.5 during its implementation. However, the continuity of CTG effectiveness on PM2.5 control in the post CTG remained unclear, especially in rural area, retarding the further emission-control policy optimization. To address this gap, we examined the wintertime rural PM2.5 variations within the Beijing–Tianjin–Hebei during the non-epidemic-lockdown period of winter 2020–2022. Of which, 2020 holds the most stringent CTG enforcement, 2021 marks the conclusion of CTG, and 2022 represents the post CTG. Methods: In this study, the PM2.5 levels in rural areas of the Beijing–Tianjin–Hebei region were monitored during the winters of 2020, 2021, and 2022. Meanwhile, multiple chemical analysis methods were employed to determine its chemical components. The Positive Matrix Factorization (PMF) modeling and Potential source contribution function (PSCF) analysis were employed to analyze the contributions of different sources to PM2.5. Results and Discussion: PM2.5 exhibited an average decrease of 30.4%, and PMF modeling indicated the contributions of coal combustion (CC) to PM2.5 fell from 22.4% in 2020 to 17.8% in 2021, and further to 10.8% by 2022, highlighting the enduring CTG effectiveness. The continuously decreasing CC-specific As, Pb, and SO42– was another evidence for scattered coal prohibition. Reluctantly, the biomass burning (BB) contributions held higher increase of 17.2% in 2021–2022 than 8.86% in 2020–2021, and it has leapt to be the largest PM2.5 contributor (25.4%) in winter 2022. The natural gas shortage and subsidy reduction in winter 2022, as well as the man, and forced demolition of coal-stoves in winter 2022 should be the main inducements. Contrary to the recent upward trend of secondary aerosols, SO42–, NO3–, and NH4+ showed a downward trend, with annual average dropped of 52.6%, 23.4%, and 53.8%, respectively. This should be ascribed to the enhanced primary emiss

关键词： Coal

来源：评论

学校读者我要写书评

暂无评论

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural Networks for Medical Image Classification 5th

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural ...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Ghosh, Triyas Chakraborty, Soham Kaplun, Dmitrii Gulvanskii, Vyacheslav Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9789819638628

In this paper, we have proposed a novel model, called Bonferroni Mean Operator-aided Fusion of Neural Networks (BFuse-Net). Here, we have taken advantage of the capabilities of four deep learning models as the base learners and then applied a customized attention method to prioritize different fine-grained features by passing their outputs via four parallel pipelines. Next, we have employed a novel aggregation method, a modified Bonferroni Mean operator, to merge the decision scores acquired from every pipeline, prioritizing their individual contributions above their interactions with others in the decision scores. Three medical image datasets— LC25000 (colon cancer), Oral Squamous Cell Carcinoma, and Malaria Cell Images have been used for experimentation. The model yields state-of-the-art outcomes for the three datasets. The source codes and additional results can be found at GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Pose Estimation and Machine Learning Classifiers for Precise Yoga Pose Detection and Classification

引用

Procedia computer science 2025年 258卷 3345-3356页

作者： Meghana J.H. Chethan H.K. K.S. Santhosh Kumar S.P. Shiva Prakash Department of Studies in Computer Science University of Mysore Karnataka Mysuru-570006 India Department of Computer Science and Engineering Maharaja Institute of Technology Thandavapura Mysuru-571302 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering University of Mysore Mysuru-570006 Karnataka India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru-570006 Karnataka India

Yoga contributes to mental and physical well-being by improving flexibility, strength, balance, and emotional stability when integrated into daily routines. This ancient practice can become more accessible and adaptable to a wider audience when combined with modern artificial intelligence (AI). This study introduces a comprehensive system for detecting and classifying yoga poses using computer vision and machine learning techniques. Central to this work is the application of posture estimation algorithms, such as MediaPipe, PoseNet, and OpenPose, to identify key points on the human body within a single image or video frame. These key points are analyzed in both two-dimensional (2D) and three-dimensional (3D) spaces to construct a skeletal representation of the body, enabling accurate classification of yoga poses. The study focuses on five distinct yoga poses: Downdog, Goddess, Plank, Tree, and Warrior II. To categorize these poses, machine learning classifiers including Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Naive Bayes utilize the key points extracted from the pose estimation models. This research is distinctive in its thorough evaluation of various conventional classifiers across multiple yoga positions. A comprehensive comparative analysis is essential for identifying the most effective classifiers for posture detection and classification. The dataset used in this study has been carefully curated to encompass a wide array of yoga poses and is divided into training and testing sets at various ratios (90:10, 80:20, 70:30, and 60:40) to ensure robust validation. Results indicate the system’s effectiveness, with SVM and KNN consistently achieving high values for Accuracy PE , Precision PE , Recall PE , and F1-S core PE across all yoga poses. Notably, Random Forest attains up to 100% Accuracy PE in detecting and classifying certain poses, demonstrating its robustness and reliability. This research highlights the potential of integ

关键词： Yoga Pose Estimation Machine Learning Deep Learning

来源：评论

学校读者我要写书评

暂无评论

StreamTag: A Platform for Flexible Tagged Data Management 11

StreamTag: A Platform for Flexible Tagged Data Management

引用

11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025

作者： Díaz-Jiménez, David Mata-Mata, Francisco López, José L. Pérez-Cordón, Luis G. Serrano, José-María Martínez-Cruz, Carmen Morcillo-Martínez, Juana M. Verdejo-Espinosa, Ángeles Cuevas-Martínez, Juan C. Viciana-Abad, Raquel Reche-López, Pedro J. Pérez-Lorenzo, José M. Gaitán-Guerrero, Juan F. Espinilla, Macarena Department of Computer Science University of Jaén Jaén23071 Spain Department of Languages and Computer Systems University of Granada Granada18071 Spain Psycology Department Faculty of Social Work University of Jaén Jaén23071 Spain Electrical Engineering Department University of Jaén Jaén23071 Spain Telecommunication Engineering Department University of Jaén Jaén23071 Spain

ISBN: (纸本)9789897587436

This paper presents StreamTag, a platform designed for the efficient management of labeled data in healthcare environments, particularly for activity recognition systems in residential and nursing home settings. Human Activity Recognition (HAR) is crucial for monitoring patient behaviors and supporting personalized care, and this field has evolved significantly with advances in IoT and AI. StreamTag integrates a flexible data labeling structure and a modular architecture, enabling data collection, labeling, and secure management of activity data. The system leverages non-relational databases for scalable data handling, along with secure protocols to ensure data integrity and privacy. This work examines existing approaches in HAR, including data-driven, knowledge-based, and hybrid models, and situates StreamTag as a versatile solution that combines flexible user-controlled labeling with high adaptability for diverse healthcare contexts. Future directions are suggested for enhancing system functionality and integration with more advanced analytical tools. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Bayes and Biased Estimators Without Hyper-parameter Estimation: Comparable Performance to the Empirical-Bayes-Based Regularized Estimator

arXiv

引用

arXiv 2025年

作者： Ju, Yue Wahlberg, Bo Hjalmarsson, Håkan Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

Regularized system identification has become a significant complement to more classical system identification. It has been numerically shown that kernel-based regularized estimators often perform better than the maximum likelihood estimator in terms of minimizing mean squared error (MSE). However, regularized estimators often require hyper-parameter estimation. This paper focuses on ridge regression and the regularized estimator by employing the empirical Bayes hyperparameter estimator. We utilize the excess MSE to quantify the MSE difference between the empirical-Bayes-based regularized estimator and the maximum likelihood estimator for large sample sizes. We then exploit the excess MSE expressions to develop both a family of generalized Bayes estimators and a family of closed-form biased estimators. They have the same excess MSE as the empirical-Bayes-based regularized estimator but eliminate the need for hyper-parameter estimation. Moreover, we conduct numerical simulations to show that the performance of these new estimators is comparable to the empirical-Bayes-based regularized estimator, while computationally, they are more efficient. Copyright © 2025, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

The Cost of Balanced Training-Data Production in an Online Data Market 34

The Cost of Balanced Training-Data Production in an Online D...

引用

34th ACM Web Conference, WWW 2025

作者： Chaintreau, Augustin Maio, Roland Ziani, Juba Columbia University Computer Science Department New York NY United States Georgia Institute of Technology Industrial and Systems Engineering Atlanta GA United States

ISBN: (纸本)9798400712746

Many ethical issues in machine learning are connected to the training data. Online data markets are an important source of training data, facilitating both production and distribution. Recently, a trend has emerged of for-profit “ethical” participants in online data markets. This trend raises a fascinating question: Can online data markets sustainably and efficiently address ethical issues in the broader machine-learning economy? In this work, we study this question in a stylized model of an online data market. We investigate the effects of intervening in the data market to achieve balanced training-data production. The model reveals the crucial role of market conditions. In small and emerging markets, an intervention can drive the data producers out of the market, so that the cost of fairness is maximal. Yet, in large and established markets, the cost of fairness can vanish (as a fraction of overall welfare) as the market grows. Our results suggest that “ethical” online data markets can be economically feasible under favorable market conditions, and motivate more models to consider the role of data production and distribution in mediating the impacts of ethical interventions. © 2025 Copyright held by the owner/author(s).

关键词： algorithmic fairness cost of fairness economics of fairness ethics fairness intervention online data markets

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：