检索结果-内蒙古大学图书馆

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

science China(information sciences) 2025年第1期68卷 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of Computer Science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of Computer Science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词： graph representation learning graph neural networks graph contrastive learning graph augmentations graph pooling

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

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

Computationally Efficient Single Layer Transformer Convolutional Encoder for Accurate Price Prediction of Agriculture Commodities

引用

IEEE Access 2025年 13卷 82144-82159页

作者： Bundak, Caceja Elyca Anak Abd Rahman, Mohd Amiruddin Haniff, Nurin Syazwina Mohd Afrizal, Nur Syaiful Yusof, Khairul Adib Karim, Muhammad Khalis Abdul Mamat, Md. Shuhazlly Rahmat, Romi Fadillah Faculty of Science Department of Physics Serdang43400 Malaysia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Department of Information Technology Medan20155 Indonesia

Predicting the accurate future price of the agricultural crops is important to avoid overproduction or shortages in the food supply chain. To obtain accurate predictions, the process usually involves large and complex datasets, which would add to computational costs for developing a model with good performance. Therefore, this study introduces the single-layer Transformer Convolutional Encoder algorithm (STCE), an improved version of the traditional transformer encoder. STCE is computationally efficient and does not compromise the accuracy of the prediction. In STCE, the fully connected Convolutional Neural Network (CNN) layer is used in the transformer to get the first temporal features and record long-range dependencies with Multi-Head Attention. To minimize complexity while maintaining performance, a single dense layer is used for the output instead of the Multi-Layer Perceptron (MLP) and omit positional encoding, which leverages the natural sequence order of the time series data. Additionally, since time-series price data normally comes with missing values, this study introduce a sequence nearest neighbor imputation algorithm for anchoring that data to complement the STCE method. This study focuses on various vegetable prices, such as tomatoes, long beans, and cucumbers, with empirical validation across various prediction prices, specifically 30-day, 60-day, and 90-day predictions. Predictions made with Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) show that the STCE algorithm is better than other deep learning algorithms, even the traditional transformer encoder. STCE algorithm not only has better performance, but it also reduces the computational time in the training with 12% fewer seconds compared to the transformer encoder and 22% fewer seconds for LSTM. This study not only provides valuable insights for farmers and planners in the agriculture market but also highlights the robust potential of transforme

关键词： Crops

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 Md Noor, Rafidah Bhattacharyya, Sananda 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 Malé20175 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 lower accuracy and mismatched 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 its 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

FL-Jaya scheduler: an optimized Jaya algorithm for effective independent task scheduling in cloud systems

引用

Computing 2025年第6期107卷 1-38页

作者： Mashaqbeh, Husam S. Mjlae, Salameh A. Department of Computer Science Faculty of Information Technology Isra University Amman Jordan Department of Information Security and Cyberspace Faculty of Information Technology Isra University Amman Jordan Salt Jordan

Efficient task scheduling in Cloud Computing remains an NP-hard challenge due to combinatorial search spaces and resource heterogeneity, often leading to premature convergence in existing metaheuristics. This paper proposes FL-Jaya, an enhanced Jaya algorithm that addresses these limitations through two key innovations: (1) a Fitness-Distance Balance (FDB) mechanism, which preserves population diversity by selecting solutions that optimally trade off fitness quality and spatial distribution, and (2) a Lévy Flight (LF) operator, enabling stochastic long jumps to escape local optima. By unifying FDB and LF into a single update rule, FL-Jaya dynamically balances exploration and exploitation, overcoming stagnation in large-scale scheduling. Experiments on artificial (100–1000 tasks) and real-world Google Cloud Jobs datasets demonstrate FL-Jaya’s superiority over six algorithms—Jaya, Particle Swarm Optimization, Coati Optimization Algorithm, Whale Optimization Algorithm, Bald Eagle Search, and Snake Optimizer. FL-Jaya achieves 38.98% lower makespan and 44.63% higher average resource utilization (ARU) than standard Jaya on artificial workloads, with real-world results showing 35.34% makespan reduction and 44.63% ARU improvement. These gains stem from FL-Jaya’s ability to maintain solution diversity while navigating complex search spaces, outperforming peers in convergence speed and scalability. The algorithm’s parameter-light design and consistent performance underscore its practicality for heterogeneous cloud environments. © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2025.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

A new CNN-based watermarking method for color medical images in a fusion domain

引用

Neural Computing and Applications 2025年 1-19页

作者： Hosny, Khalid M. Abdel-Aziz, Mostafa M. Lashin, Nabil A. Hamza, Hanaa M. Department of Information Technology Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Department of Information Technology Faculty of Information Technology and Computer Science Sinai University Arish Campus Al-Arish45518 Egypt

The transmission of medical images via medical agencies raises security concerns, necessitating increased security measures to ensure integrity and security. However, many watermarking algorithms overlook equipoise;the relation between robustness, invisibility, and payload capacity results in a less satisfactory performance. To bridge this gap, we propose a new blind watermarking method for securing medical images based on a convolutional neural network in a fusion domain. First, we transmute the host color image using a phase-only transform (PHOT) to detect the surface pattern. We feed the detected surface pattern into a pre-trained VGG19 model to impeccably extract the stable feature vector. We encrypt the extracted image features using a hybrid Chirikov map to enhance their robustness and reliability. The synergy between the pre-trained VGG19 model and PHOT in an integrated domain effectively captures additional native and localized image features. A hybrid Fibonacci Q-matrix method scrambles the binary watermark to enhance security. Integrating double encryption into the proposed method markedly enhances its resistance against diverse countermeasures. Experimental outcomes indicate that the proposed scheme performs efficiently in robustness and invisibility. The obtained PSNR value was up to 60.15 dB, which is optimal for human perception. The embedded watermark can be retrieved without any warping. The retrieved watermark seems to be authentic, exhibiting ideal BER and NC values. In almost all attack circumstances, the BER values approached zero while the NC values got closer. The proposed method demonstrates notable enhancements in robustness and invisibility compared to prior methods. © The Author(s) 2025.

关键词： Watermarking

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

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：