检索结果-内蒙古大学图书馆

Privacy-preserving explainable AI: a survey

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

Enhanced Distance-based Weighted K-Nearest Neighbor Algorithm for Data Classification

引用

KSII Transactions on Internet and information Systems 2025年第4期19卷 1097-1121页

作者： Amer, Ali A. Ravana, Sri Devi Habeeb, Riyaz Ahamed Ariyaluran Department of Information Systems Faculty of Computer Science & Information Technology Universiti Malaya Malaysia

The k-Nearest Neighbors (kNN) algorithm is one of the most widely used techniques for data classification. However, the imbalanced class is a key problem for its declining performance. Therefore, the kNN algorithm is kept updated to mitigate this problem’s effects. Following the pattern of the literature, our paper proposes a novel weighted kNN that aims to significantly reduce the negative consequences of this problem. An enhanced distance-based weighted KNN, EDWkNN, is developed to improve the overall KNN performance. For the test sample, the number of neighbors (k) is initially determined. Next, normalized weights are computed for these neighbors and assigned a value between 0 and 1. The weights of the nearest and farthest neighbors are 1 and 0, respectively. The weight values of the remaining neighbors range from 0 to 1, with the closest one having a heavier weight and the farthest neighbor having a lower weight value. In extreme circumstances, a few neighbors have equal distance from the test sample, leading to assigning uniform weights to each of these neighbors. Further, the EDWkNN considers both the magnitude of the distance and the proximity of neighbors. Comparing EDWkNN to its state-of-the-art rivals, its simplistic architecture and competitive performance demonstrate its uniqueness. In four experimental phases, a thorough assessment study is conducted utilizing four evaluation metrics (accuracy, precision, recall, and MAE) over forty-four datasets. The findings show that, on average and for individual k values, EDWkNN is substantially promising. Copyright © 2025 KSII.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Efficient and lightweight CNN model for COVID-19 diagnosis from CT and X-ray images using customized pruning and quantization techniques

引用

Neural Computing and Applications 2025年 1-20页

作者： Sriwiboon, Nattavut Department of Computer Science and Information Technology Faculty of Science and Health Technology Kalasin University Kalasin Thailand

The coronavirus disease 2019 (COVID-19) has posed significant challenges globally, with image classification becoming a critical tool for detecting COVID-19 from chest X-ray and CT images. Convolutional neural network (CNN) architectures are widely employed for this purpose, yet many previous models have struggled to balance high accuracy with low storage requirements, limiting their applicability in resource-constrained environments. This paper introduces an efficient and lightweight CNN model optimized for COVID-19 diagnosis through pruning and quantization techniques, addressing these limitations. Our approach significantly reduces storage size and parameter count while maintaining high accuracy. We customized several CNNs, particularly EfficientNetV2 and MobileNetV2, to achieve these goals. We specifically selected EfficientNetV2 and MobileNetV2 due to their superior balance of accuracy and efficiency, making them well-suited for lightweight medical applications. EfficientNetV2’s storage size has been reduced from 568 to 142 KB through customized pruning, achieving 98.9% accuracy for 2-class and 98.28% for 3-class X-ray classification, as well as 98.3% and 98.05% for 2-class and 3-class CT classification, respectively. MobileNetV2, after hybrid pruning and quantization, achieved a remarkably low storage size of 70 KB, making it highly effective for deployment in environments with limited resources. Despite a slight accuracy decrease of 0.9 to 1.58%, both models have maintained robust performance suitable for COVID-19 diagnosis. The results demonstrate that our pruning and quantization techniques are effective in developing lightweight, high-performance CNN models, making them suitable for broader applications in medical imaging where both efficiency and accuracy are critical. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Enhanced model for abstractive Arabic text summarization using natural language generation and named entity recognition

引用

Neural Computing and Applications 2025年第10期37卷 7279-7301页

作者： Essa, Nada El-Gayar, M.M. El-Daydamony, Eman M. Department of Information Technology Faculty of Computer and Information Science Mansoura University Mansoura35516 Egypt

With the rise of Arabic digital content, effective summarization methods are essential. Current Arabic text summarization systems face challenges such as language complexity and vocabulary limitations. We introduce an innovative framework using Arabic Named Entity Recognition to enhance abstractive summarization, crucial for NLP applications like question answering and knowledge graph construction. Our model, based on natural language generation techniques, adapts to diverse datasets. It identifies key information, synthesizes it into coherent summaries, and ensures grammatical accuracy through deep learning. Evaluated on the EASC dataset, our model achieved a 74% ROUGE1 score and a 97.6% accuracy in semantic coherence, with high readability and relevance scores. This sets a new standard for Arabic text summarization, greatly improving NLP information processing. © The Author(s) 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Leveraging CuMeta for enhanced document classification in cursive languages with transformer stacking

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Shahid, Muhammad Iqbal, Muhammad Amjad Umair, Muhammad Faculty of Information Technology and Computer Science University of Central Punjab Lahore Pakistan

Classifying textual data is crucial in the expanding digital landscape, especially for underrepresented cursive languages like Urdu, which pose unique challenges due to their intricate linguistic features and vast digital content. Despite the growing demand, research in effective Urdu text classification remains limited. This study introduces CuMeta, a novel meta-stacking classifier designed specifically to address these challenges. CuMeta integrates the strengths of various deep learning algorithms, including CNN and LSTM, alongside multiple Transformer-based models, to provide a comprehensive solution to issues such as tokenization, spatial inconsistencies, lack of case distinctions, and complex dialects inherent in Urdu. Through rigorous evaluation across diverse datasets, CuMeta has demonstrated its superiority over traditional and deep learning models, achieving an impressive F1-score of 97.52%. The innovative approach of CuMeta not only enhances text classification for Urdu but also offers significant implications for other low-resource, cursive-script languages like Arabic and Persian. This research marks a significant advancement in NLP, particularly for languages that have historically been underrepresented in digital and academic platforms. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Augmented reality for interactive promotion media at faculty of computer science and information technology Mulawarman University 3

Augmented reality for interactive promotion media at Faculty...

引用

3rd International Conference on science, ICOS 2019

作者： Firdaus, M.B. Widians, J.A. Padant, J.Y. Informatics Engineering Department Faculty of Computer Science and Information Technology Mulawarman University Samarinda Indonesia

Showing the design and layout of the building using a model, making this model requires time and accuracy because the model is built on a scale that has been adjusted to the building to be made later, a problem that often occurs in modeling is the suitability of the scale and detail of the model. Augmented Reality as a variation of the virtual environment. Users of AR technology can see the real world, with virtual objects added to the real world. So, users see virtual objects and real objects in the same place. Submission of information by utilizing the three-dimensional visualization technique is very interesting because it can display the 3D model of an object before it is built in real terms. The faculty of computer science and information technology Mulawarman University Samarinda has an exterior building design of a new building, but there are no interactive media that can display the exterior of the building as a whole and in detail. This application is able to be used to apply the 3D model of the building as a whole and can be seen from various viewpoints. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Abnormal Data Detection Model Based on Autoencoder and Random Forest Algorithm: Camera Sensor Data in Autonomous Driving Systems

引用

International Journal of Advanced computer science and Applications 2025年第3期16卷 222-231页

作者： Shengwen, Geng Osman, Mohd Hafeez Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia

This project develops an AI-based anomaly detection system. In the field of autonomous driving, abnormal data will directly affect the safety of autonomous driving systems, especially in terms of abnormal camera sensor data. Sensor failure, environmental changes, or bad weather can lead to the emergence of abnormal data, which can affect the decision-making process and may have disastrous consequences. Based on the above problems, this study addresses this challenge by proposing a hybrid anomaly detection model (called CAE-RF) that combines convolutional autoencoders and random forest algorithms to achieve efficient and accurate identification of abnormal data patterns to improve the safety of autonomous driving systems. The proposed method will use convolutional autoencoders to calculate the reconstruction error and combine the hidden features extracted by the encoder as the input of the random forest to distinguish normal data from abnormal data. The key performance indicators such as accuracy, precision, recall, and F1 score are used to evaluate the model, and the robustness is guaranteed by cross-validation. Experimental results show that the CAE-RF model has an accuracy of 92% in distinguishing normal and abnormal data. Compared with traditional methods, the CAE-RF model achieves higher accuracy and reliability. The implementation of this model can timely identify and process abnormal data, reduce the risks brought by sensor failure or external environment changes, prevent potential accidents, and improve the safety and reliability of the autonomous driving system. © (2025), (science and information Organization). All rights reserved.

关键词： Tachometers

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Vehicle Location Prediction Using Machine Learning: A Case Study of Campus Shuttle Bus

引用

IEEE Access 2025年 13卷 78290-78302页

作者： Nandy, Tarak Kolandaisamy, Raenu Noor, Rafidah Md Bhattacharyya, Sananda UCSI University Institute of Computer Science and Digital Innovation Kuala Lumpur56000 Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer Systems and Technology Kuala Lumpur50603 Malaysia Faculty of Computer Science and Information Technology Kuala Lumpur50603 Malaysia Maldives Business School Department of Information Technology Male20175 Maldives

Vehicle location prediction and the use of vehicle location tracking are increasingly important topics of discussion among connected vehicle researchers. Location tracking for mobile users is essential due to the correlated services and to improve the quality of service;however, it is challenging. On the other hand, the stateless predictive model is unsuitable due to less accuracy and mismatch pattern analysis. This paper proposed a vehicle location prediction model using machine learning based on a case study of a campus shuttle bus scenario. Firstly, this paper comprehensively analyzes the recent research on vehicle location prediction models and provides a complete taxonomy. The proposed model uses the Support Vector Regression (SVR) based vehicle location predictive model in the implementation phase. In addition, a significant time-series predictive model, ARIMA, is configured and tested. Moreover, the seasonal ARIMA model is experimented with to predict the location of a mobile vehicle. The whole experiment is performed on a real dataset based on the university shuttle bus service. The results of the experiments, analysis, and discussions on the proposed model show the accuracy and effectiveness of their use on others. As a result, seasonal ARIMA outperformed ARIMA and SVR infractions. © 2013 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An enhanced hybrid single-image-based structure-guided 0-norm and radiance–reflectance optimization

引用

Neural Computing and Applications 2025年 1-21页

作者： WangNo, Nitit Thaiklang, Saowaluk Major of Computer Science Faculty of Information Technology Roi Et Rajabhat University Roi Et Thailand Major of Computer Science Faculty of Computer Science Ubon Ratchathani Rajabhat University Ubon Ratchathani Thailand

The reduced visibility during the winter season in an outdoor setting can be attributed primarily to the presence of haze or fog. Despite adjusting the lens of an optical sensor system for various purposes, such as automated driver assistance, remote sensing, and visual surveillance, the visual quality remains compromised. Owing to the overcast and murky atmosphere, it is difficult to remove these haziness emissions from a single image. To address this problem, we present a novel optimization-based dehazing algorithm that combines radiance and reflectance components with an additional refinement via a structure-guided 0-norm filter. We first estimate the poor reflectance map and optimize our transmission maps by using an estimated diffuse map. In addition, we estimate the removal of dehazing artifacts via a structure-guided 0 transmission map. In terms of qualitative and quantitative measures, compared with simulated pairs of images, the experimental results show that the proposed method is superior to the state-of-the-art algorithms. Moreover, the results of real-world enhancements confirm that the proposed method can provide high-quality images with no undesirable effects. In addition, textures may be removed, and edges can be preserved by the guided 0-norm filter, while the general image enhancement algorithms are being applied. The test results indicate that the proposed algorithm effectively generates enhanced images with greater visibility. The proposed approach has demonstrated superior performance metrics, including a 25.17% improvement in the peak signal-to-noise ratio (PSNR) and a 6.51% enhancement in the structural similarity index (SSI), surpassing the average performance of alternative methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

Single-Valued Neutrosophic Graph with Heptapartitioend Structure

引用

Neutrosophic Sets and Systems 2025年 80卷 728-748页

作者： Fathi, Hanaa Myvizhi, M. Abdelhafeez, Ahmed Abdellah, Mohamed Refaat Eassa, Mohamed Sawah, Mohamed S. Elbehiery, Hussam College of Information Technology Amman Arab University Amman Jordan KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan The Department of Computer Science College of Information Technology Misr University for Science and Technology Cairo Egypt Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan

This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neutrosophic Graphs (SVHNG) and investigate their characteristics through comprehensive proofs and illustrative examples. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioend Neutrosophic Set Neutrosophic Graph Neutrosophic Sets SVHN-Graph

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：