检索结果-内蒙古大学图书馆

Combinatorial Multi-Armed Bandits with Fairness Constraints: An Online Convex Optimization Perspective

Journal of Artificial Intelligence Research 2025年 82卷 1909-1942页

作者： Chen, Xiaosong Zhuang, Hanqin Liu, Yang Xu, Huanle Lau, Wing Cheong Department of Computer and Information Science University of Macau Macau China Department of Computer Science Shanghai University Shanghai China Department of Information Engineering The Chinese University of Hong Kong Hong Kong

The problem of multi-armed bandit (MAB) with fairness constraints has emerged as an important research topic recently. For such problems, one common objective is to maximize the total rewards within a fixed number of pull rounds, while satisfying the fairness requirement of a minimum selection fraction for each individual arm in the long run. Previous works have made substantial advancements in designing various online selection solutions for MAB, however, when incorporating such fairness constraints, they fail to achieve a sublinear regret bound. In this paper, we study a combinatorial MAB problem with concave objective and fairness constraints. In particular, we design a new selection algorithm that solves MAB problems from an online convex optimization perspective. Our algorithm is computationally efficient, and more importantly, manages to achieve a sublinear regret bound of O(√T ln T) with high probability guarantees in T selection rounds. We also extend our framework to include more general knapsack constraints. Finally, we assess the performance of our algorithm through extensive simulations and real dataset applications, demonstrating its significant advantages over baseline schemes. ©2025 The Authors.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

science China(information sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Approach for Automating App Review Classification:Advancing Usability Metrics Classification with an Aspect-Based Sentiment Analysis Framework

引用

computers, Materials & Continua 2025年第1期82卷 949-976页

作者： Nahed Alsaleh Reem Alnanih Nahed Alowidi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computer Science and EngineeringUniversity of HailHail81451Saudi Arabia

App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their *** the analysis of these reviews is vital for efficient review *** traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior *** research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and *** propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification *** analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,*** contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews *** advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.

关键词： Requirements engineering(RE) app review analysis usabilitymetrics hybrid deep learning BERT-BiLSTM-CNN

来源：评论

学校读者我要写书评

暂无评论

Decomposition-based hybrid methods employing statistical, machine learning, and deep learning models for crude oil price forecasting

引用

Neural Computing and Applications 2025年 1-46页

作者： Purohit, Sourav Kumar Panigrahi, Sibarama Department of Computer Science and Engineering Sambalpur University Institute of Information Technology Burla India Department of Computer Science and Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India

Crude oil prices (COP) profoundly influence global economic stability, with fluctuations reverberating across various sectors. Accurate forecasting of COP is indispensable for governments, policymakers, and stakeholders to make well-informed decisions and effectively mitigate risks. The decomposition-based hybrid models have been showing promising COP forecasting accuracy than other time series forecasting methods. Despite this fact, no systematic study has been conducted to evaluate the true potential of different decomposition-based hybrid methods employing different forecasting models to forecast the COP. Therefore, a hybrid modeling framework is developed by combining efficient decomposition techniques, namely empirical mode decomposition (EMD), ensemble EMD (EEMD), complete EEMD with adaptive noise (CEEMDAN), and variational mode decomposition (VMD) with seven statistical models, fourteen machine learning (ML) models, and six deep learning (DL) models. Further, a systematic study is conducted on the resulting decomposition-based hybrid models to find the best hybrid model for COP forecasting. Three distinct train-test data splits are employed to ensure a reliable evaluation of the models using four performance metrics. Extensive statistical analysis is conducted to identify the optimal combination of the decomposition technique and forecasting model for precise COP prediction. The results demonstrate that the proposed decomposition-based hybrid model employing VMD and Huber Regression is statistically the best method among all alternatives to forecast monthly COP. The proposed hybrid method VMD-Huber Regression improves the root mean square error (RMSE) by 21% than CEEMDAN-ARIMA, 58.31% than EEMD-Theta, 13.18% than EMD-Random Walk, and 49.44% than VMD-TBATS hybrid methods in 60–40 Train-Test split ratio. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Image Watermarking Using Catalan Transform and Non-Negative Matrix Factorization

引用

IEEE Access 2025年 13卷 68995-69020页

作者： Fahim Hossain Saikat, Md. Provath, Md. Al-Mamun Deb, Kaushik Dhar, Pranab Kumar Shimamura, Tetsuya Department of Computer Science and Engineering Chittagong4349 Bangladesh Saitama University Department of Information and Computer Sciences Saitama338-8570 Japan

In the digital age, embedding imperceptible data into images for authenticating ownership and content integrity through watermarking has gained immense importance. Existing watermarking methods struggle to balance imperceptibility, robustness, and security, resulting in suboptimal peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), normalized correlation (NC) values, along with higher time complexity. To overcome these constraints, this study proposes a new method for image watermarking that uses deep learning and operates within the YIQ color space. The main contribution of the proposed method is its new combination of the Catalan transform (CT) and non-negative matrix factorization (NMF) with an artificial neural network (ANN) for enhanced watermark embedding and extraction. CT enhances pixel intensity while NMF extracts the most significant features from each (m x m) block (with m= 2 in simulations), improving the method's robustness and imperceptibility. Before embedding, the watermark undergoes a new scrambling technique combining adaptive diffusion and non-linear transform, significantly enhancing security. A new embedding equation integrates the watermark into the non-negative elements of the host image blocks. Statistical features from watermarked blocks are used to create a dataset for extraction, and an ANN model trained on this dataset enables accurate watermark recovery. The proposed method achieves a PSNR of 66.43 to 77.02 dB (31.91% improvement), SSIM of 0.99 to 1.00 (1.02% improvement), and NC of 0.99 to 1.00 (1.88% improvement). Its computational complexity is O(n2), a 33.33% reduction compared to traditional O(n3) methods. Security metrics include RE = 0.3094, UACI = 34.21%, and NPCR = 99.15%, demonstrating superior robustness and efficiency over existing approaches. © 2013 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

HCBiL-DMN: an effective food infestation detection from stored food grains using deep learning model

引用

Multimedia Tools and Applications 2025年第14期84卷 14047-14070页

作者： Vedavathi, N. Suhas Bharadwaj, R. Department of Computer Science and Engineering Vidyavardhaka College of Engineering Karnataka Mysuru570002 India Department of Information Science and Engineering The National Institute of Engineering Karnataka Mysuru570008 India

Food Infestation Detection is more important for food safety and health concerns. It is a challenging task to separate the grains into infested or non-infested. It is found that in the existing system, there is no effective approach for the early detection of pest populations and for classifying crops as infested or non-infested. Therefore, the identification and categorization of early-stage grain infestations is in high demand. To address the above problem, this research presents a better technique for detecting and classifying infested and non-infested grains. Initially, the maize, wheat and olive image datasets are collected, which are then pre-processed using data normalization and adaptive wiener filtering (AdwF) approach to improve the excellence of the input images. Image quality helps in achieving better performance and also helps in analyzing the quality of food grains effectively. Feature extraction is done using the Dense Residual Pyramidal Dilated Convolution Network (DR-PDCNet) technique, and feature selection is done using the Linear Discriminant Coati Optimization (LD-CoA) algorithm. The Hybrid Convolutional Bi-LSTM based Deep Maxout Network (HCBiL-DMN) model is used to detect the infected food grains in the preserved food grains with high accuracy. This research explores the potential and future possibilities for using technology to ensure the quality, assessment, and monitoring of nutritional grains during storage. The performance results are achieved with 98.3% accuracy, 99.12% recall, 98.65% precision, 98.02% MCC, and 99.32% F1 score. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Decentralized multi-agent federated and reinforcement learning for smart water management and disaster response

引用

Alexandria engineering Journal 2025年 126卷 8-29页

作者： Mancy, H. Ghannam, Naglaa E. Abozeid, Amr Taloba, Ahmed I. Department of Computer Science College of Engineering and Computer Sciences Prince Sattam Bin Abdulaziz University Al-kharj11942 Saudi Arabia Department of Computer Engineering and Information College of Engineering in Wadi Alddawasir Prince Sattam Bin Abdulaziz University Wadi Alddawasir Saudi Arabia Department of Computer Science College of Computer and Information Sciences Jouf University Saudi Arabia Department of Mathematics Faculty of Science Al-Azhar University Cario Egypt Information System Department Faculty of Computers and Information Assiut University Egypt

Water resource management and disaster response have become some of the most challenging tasks, especially when disasters pose a threat, as delays could lead to more impacts. The centralized system used for water dynamics and disaster control usually presents itself as a scalability problem since more clients present a problem, the system's latency is high, and the system is always prone to a single-point failure. The previous approach lacks flexibility and does not synchronously guarantee the integration of several subjects in real time, especially during unpredictable disaster conditions. The proposed FL-MAPPO model surpasses current methods by facilitating decentralized, privacy-protecting decision-making minimizing latency and single-point failures. In contrast to LSTM, Bi-LSTM, and DRNN, which are based on centralized data processing, FL-MAPPO provides real-time adaptability and effective resource management. Experimental results validate that it has lower MSE, higher R² scores, and quicker response times, making it better suited for flood prediction and disaster response. To this end, this study advances a solution through a Decentralized Learning-Driven Multi-Agent Autonomous System (DL-MAAS). The new feature is a Decentralized Cooperation environment in which intelligent and self-managing agents learn utilizing Reinforcement Learning (RL) and Federated Learning (FL) algorithms for enhancing smart water management and real-time disaster relief. IoT devices are adopted for sensing and data acquisition, adaptive learning for decision-making, and optimization of energy use among the agents in the system through metaheuristic algorithms. The research methodology for implementing the proposed solution involves the design of a multi-layered architecture, including data acquisition, decentralized learning, and real-time execution. With a Mean Squared Error (MSE) of 0.112, R-squared (R²) of 0.953, and Mean Absolute Error (MAE) of 0.207, the proposed method is better

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

ProxaDyn: A Proximity-Aware Dynamic Caching Approach for Named Data Networks

引用

IEEE Transactions on Network science and engineering 2025年第3期12卷 2360-2372页

作者： Kumari, Matta Krishna Tripathi, Nikhil Joshi, Piyush Indian Institute of Information Technology Computer Science and Engineering Group Sri City517 646 India Department of Computer Science and Engineering Dhanbad826 004 India

Named Data Network (NDN), a future Internet architecture is introduced to address the shortcomings of the current Internet architecture. NDN supports in-network caching to facilitate scalable content distribution and enhance overall network performance. However, the known NDN caching strategies suffer from a few common drawbacks, such as inefficient cache utilization, high content redundancy, and overhead due to lookup repetition. To address these issues, in this paper, we propose a novel caching strategy called ProxaDyn for efficient content lookup, placement, and replacement. During the content lookup phase, ProxaDyn interacts exclusively with the router responsible for caching a particular content. This eliminates interaction with other intermediate routers, thereby significantly reducing content access latency. For content placement, ProxaDyn strategically selects an on-path router based on content popularity. Popular content is placed in the cache of a router closer to the consumer, while less popular content is cached in a router away from the consumer. This approach significantly improves the cache hits and reduces the access latency. We test ProxaDyn over a diverse range of real-world network topologies. Using extensive experiments, we show that ProxaDyn could achieve significantly better results compared to the state-of-the-art NDN caching strategies. © 2013 IEEE.

关键词： Data communication systems

来源：评论

学校读者我要写书评

暂无评论

An ensembled-deep-learning paradigm trained with a self-improved coyote optimization algorithm (SI-COA) for crop disease detection

引用

Multimedia Tools and Applications 2025年第4期84卷 1697-1724页

作者： Shukla, Preeti Chandanan, Amit Kumar Department of Computer Science and Information Technology Guru Ghasidas Vishwavidyalaya CG Bilaspur India Department of Computer Science & Engineering Guru Ghasidas Vishwavidyalaya CG Bilaspur India

In recent times, drastic climate changes have caused a substantial increase in the growth of crop diseases. This causes large-scale demolition of crops, decreases cultivation, and eventually leads to the financial loss of farmers. Due to the rapid growth in a variety of diseases and adequate knowledge of farmers, identification, and treatment of the disease have become a major challenge. The leaves have texture and visual similarities which are attributes for the identification of disease type. Hence, computer vision employed with deep learning provides a way to solve this problem. In this research work, a novel voting-based ensembled-deep-learning paradigm is developed for crop disease detection. Initially, the collected raw images are pre-processed via Laplacian Filter and morphological operations. From, the pre-processed image, the ROI region is identified using K-means Clustering. Then, from the ROI regions, the features like texture feature (Chi-squared Local Binary Pattern (CLBP)), Scale Invariant Feature Transform (SIFT), Gray-Level Co-occurrence Matrix (GLCM)), color features, and shape features are extracted. Then, the optimal features are selected by using Self-Improved Coyote Optimization Algorithm (SI-COA) is an extended version of the standard Coyote Optimization Algorithm (COA) and is a metaheuristic for optimization that is inspired by the canis latrans species. For crop disease detection, the voting-based ensembled-deep-learning paradigm was used which includes the Attention-based Bi-LSTM, Recurrent Neural Networks (RNNs), and Optimized Deep Neural Networks (O-DNN). The weight of DNN is optimized via Self-Improved Coyote Optimization Algorithm (SI-COA). The overall outcome of this process is evaluated by using various performance metrics such as Precision, Recall, F1-Score, Accuracy, Sensitivity and Specificity, NPV, FNR, FPR, and MCC, as well. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

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：