检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial intelligence 2025年

作者： Zhao, Hongbo Zhang, Hengzhe Tian, Chutian Wei, Zhi Zhou, Aimin East China Normal University Lab of Artificial Intelligence for Education School of Computer Science and Technology Shanghai200062 China Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand New Jersey Institute of Technology Department of Computer Science NewarkNJ07102 United States

Long-term Time Series Forecasting (LTSF) plays a crucial role in various fields, including energy consumption and weather prediction. Recent advancements in deep learning, particularly transformer models, have significantly improved LTSF performance. However, these models often face criticism for their lack of transparency, limited interpretability, and high computational requirements, which can hinder their practical application. Simple linear models have emerged as a promising alternative, demonstrating excellent performance in LTSF while offering greater simplicity. Yet, as these models become more complex, they tend to lose their advantages. To address these challenges, we introduce SRLinear, a lightweight and interpretable LTSF framework based on symbolic regression. Our approach first breaks down time series data into seasonal and trend components, then divides these into smaller segments. We use symbolic regression to extract meaningful and interpretable features from these components, which are then combined and processed through a single linear layer for future predictions. This lightweight design ensures computational efficiency, while symbolic regression generates symbolic expressions, providing clear insights into the feature extraction process and enhancing model interpretability. We tested SRLinear on 8 real-world datasets, achieving state-of-the-art results on multiple benchmarks. Importantly, our framework produces highly interpretable features that can be easily visualized, enhancing the overall transparency of the prediction process. © 2020 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diversity in Multi-Objective Feature Selection

Enhancing Diversity in Multi-Objective Feature Selection

引用

Congress on Evolutionary Computation

作者： Sevil Zanjani Miyandoab Shahryar Rahnamayan Azam Asilian Bidgoli Sevda Ebrahimi Masoud Makrehchi Nature-Inspired Computational Intelligence (NICI) Lab Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa ON Canada Department of Engineering Brock University St. Catharines ON Canada Paculty of Science Wilfrid Laurier University Waterloo ON Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Feature selection plays a pivotal role in the data preprocessing and model-building pipeline, significantly en-hancing model performance, interpretability, and resource efficiency across diverse domains. In population-based optimization methods, the generation of diverse individuals holds utmost importance for adequately exploring the problem landscape, particularly in highly multi-modal multi-objective optimization problems. Our study reveals that, in line with findings from sev-eral prior research papers, commonly employed crossover and mutation operations lack the capability to generate high-quality diverse individuals and tend to become confined to limited areas around various local optima. This paper introduces an augmen-tation to the diversity of the population in the well-established multi-objective scheme of the genetic algorithm, NSGA-II. This enhancement is achieved through two key components: the genuine initialization method and the substitution of the worst individuals with new randomly generated individuals as a re-initialization approach in each generation. The proposed multi-objective feature selection method undergoes testing on twelve real-world classification problems, with the number of features ranging from 2,400 to nearly 50,000. The results demonstrate that replacing the last front of the population with an equivalent number of new random individuals generated using the genuine initialization method and featuring a limited number of features substantially improves the population's quality and, consequently, enhances the performance of the multi-objective algorithm.

关键词： Sociology Pipelines Optimization methods Evolutionary computation Feature extraction data models Distance measurement

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dental Caries Identification with Deep Learning: A Study of Convolutional Neural Networks and Transfer Learning Approaches

SSRN

引用

SSRN 2024年

作者： Mannan, Fayqa Adeel, Muhammad Arif, Erssa Li, Jianqiang Ullah, Amin Nawazish, Samra Mahmood, Tariq Rehman, Amjad Shoukat, Ijaz Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Computer Science Government College University Faisalabad38000 Pakistan Department of Computer Science School of Science National Textile University Faisalabad37610 Pakistan Department of Computer Science Faculty of Computing Riphah International University Faisalabad38000 Pakistan Beijing Engineering Research Center for IoT Software and Systems 100124 China Department of Computer Science Faculty of IT and Computer Science University of Central Punjab Lahore Pakistan School of Computer Science and Engineering Southeast University Nanjing China Software Engineering Department University of Engineering and Technology Taxila Pakistan Artificial Intelligence & Data Analytics Lab CCIS Prince Sultan University Riyadh11586 Saudi Arabia Faculty of information Sciences University of Education Vehari Campus Vehari61100 Pakistan

Various deep learning techniques have been employed to diagnose dental caries using X-ray images. In this study, we utilized deep learning models, including Convolutional Neural Networks (CNNs) and transfer learning models such as Visual Geometry Group (VGG16), VGG19, ResNet50, and Inception V3, to identify dental caries in periapical radiographs. The traditional CNN model comprises three sets of 2D convolutional layers, followed by an activation layer, a max-pooling layer, a flatten layer, one dense layer, another activation layer, dropout, another dense layer, and a final activation layer. For the VGG models, ResNet50, and Inception V3, the top convolutional layers were frozen to prevent retraining of the model, with only the last layers trained to produce the required output. The accuracy achieved by CNN, VGG16, VGG19, ResNet50, and Inception V3 was 90%, 96%, 73%, 70%, and 73%, respectively. VGG16 exhibited the highest accuracy among the models. Hyperparameters were carefully selected using a grid search approach, and the results were validated using the Shuffle-Split-Cross (SSC) validation method. These findings underscore the effectiveness of transfer learning in analyzing medical images, particularly in the diagnosis of dental caries. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Dfier: A Directed Vulnerability Verifier for Ethereum Smart Contracts

SSRN

引用

SSRN 2023年

作者： Wang, Zeli Dai, Weiqi Li, Ming Choo, Kim-Kwang Raymond Zou, Deqing Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing40065 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio United States

Existing smart contract vulnerability identification approaches mainly focus on complete program detection. Consequently, lots of known potentially vulnerable locations need manual verification, which is energy-exhaustive and error-prone. Fuzzing is an effective way to detect vulnerabilities. However, current fuzzers cannot effectively probe these suspicious targets because they overlook two key factors: exploring all paths toward the targets and providing high-quality directed seed inputs. This paper presents a Directed vulnerability veriFier (DFier), elaborating effective transaction sequences with directed inputs for the fuzzer, to focus on analyzing target paths and automatically detect whether the given locations are vulnerable. Specifically, DFier fuses the effectiveness of static analysis and the efficiency of fuzzing. The static analysis helps locate target paths and generate directed inputs for the fuzzer under three heuristic strategies. The first prefers inputs with the larger possibility of triggering potential vulnerabilities based on target features. The second guides the value mutation to satisfy the path constraints. The third adequately leverages execution information to help find exploits faster. Extensive experiments demonstrate that DFier is effective in verifying contract security, compared with three existing contract fuzzers (i.e., contractFuzzer, sFuzz, and conFuzzius). And the performance losses are in an acceptable range. © 2023, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Bridging Machine Learning and Formal Concept Analysis for Effective Crowd Detection

Bridging Machine Learning and Formal Concept Analysis for Ef...

引用

Information Technology (ACIT)

作者： Anas M. Al-Oraiqat Oleksandr Drieiev Ghassan Samara Sattam Almatarneh Karim A. Al-Oraiqat Hazim Alrawashdeh Hanna Drieieva Ali Elrashidi Yassin M. Y. Hasan Department of Computer Science Faculty of Information Technology Zarqa University Jordan Department of Cybersecurity and Software Central Ukrainian National Technical University Kropyvnytskyi Ukraine Department of Data Science and Artificial Intelligence Faculty of Information Technology Zarqa University Jordan Department of Software Engineering Faculty of Information Technology Zarqa University Jordan Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia Electrical Engineering Department Assiut University Egypt

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Crowd detection and prevention systems have become essential for managing densely populated areas. Modern systems leverage the combined power of machine learning, data mining, and image processing to extract and analyse features from crowded zones, enabling the identification of behavioural patterns and anomalies. However, most current solutions primarily focus on detection and lack robust decision-making and recommendation mechanisms for selecting appropriate crowd-prevention strategies. To address this gap, we integrate the predictive capabilities of machine learning models with the analytical and clustering strengths of Fuzzy Formal Concept Analysis (fuzzy FCA). Machine learning is employed to extract valuable insights from images of the area, with a neural network used to identify human figures, track individuals' positions, and predict crowd levels. This data is fed into an FFCA-based decision system, where crowd information is structured and clustered using lattice theory. This latter helped exclude low-crowd zones and cluster the rest of the monitored areas based on their crowd features. Additionally, we define bottom-up parsing algorithms to recommend suitable crowd-prevention plans based on crowd density levels within fuzzy formal concepts. Experiments confirmed not only the ability of fuzzy FCA to "exclude" low-crowd zones thanks to a used crowd threshold but also the efficient "feature-based clustering" of crowded zones into hierarchical formal concepts and these latter’s "bottom-up parsing" to finally identify the dense zones.

关键词： Formal concept analysis Scalability Prevention and mitigation Decision making Lattices Machine learning Feature extraction Prediction algorithms Real-time systems data mining

来源：评论

学校读者我要写书评

暂无评论

Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning 39

Boosting Fine-Grained Visual Anomaly Detection with Coarse-K...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Fang, Qingqing Su, Qinliang Lv, Wenxi Xu, Wenchao Yu, Jianxing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Artificial Intelligence Sun Yat-sen University Guangdong China Pazhou Lab Guangzhou510330 China

ISBN: (纸本)157735897X

Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and generalization ability of neural networks, some anomalies can also be well reconstructed, resulting in unsatisfactory detection and localization accuracy. In this paper, a small coarsely-labeled anomaly dataset is first collected. Then, a coarse-knowledge-aware adversarial learning method is developed to align the distribution of reconstructed features with that of normal features. The alignment can effectively suppress the auto-encoder’s reconstruction ability on anomalies and thus improve the detection accuracy. Considering that anomalies often only occupy very small areas in anomalous images, a patch-level adversarial learning strategy is further developed. Although no patch-level anomalous information is available, we rigorously prove that by simply viewing any patch features from anomalous images as anomalies, the proposed knowledge-aware method can also align the distribution of reconstructed patch features with the normal ones. Experimental results on four medical datasets and two industrial datasets demonstrate the effectiveness of our method in improving the detection and localization performance. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

How Graph Neural Networks Learn: Lessons from Training Dynamics

arXiv

引用

arXiv 2023年

作者： Yang, Chenxiao Wu, Qitian Wipf, David Sun, Ruoyu Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University China Amazon Web Services United States School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection using Machine Learning on Network Traffic

Cybersecurity Threat Detection using Machine Learning on Net...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： R. Rithi N. Nithya A. Akila R. Saravanakumar M. Vargheese S. Jeya Lakshmi Master of Computer Applications Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Computer Applications Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India Department of Computer Science and Engineering PSN College of Engineering and Technology Tirunelveli Tamil Nadu India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Web phishing is a prevalent online attack in which victims are tricked into revealing their personal information by visiting fraudulent websites. Phishers often use URL shortening tools to disguise malicious links, making it easier to steal sensitive data such as usernames, passwords, and banking details. These phishing websites are designed to mimic legitimate ones, making detection more challenging. As phishing techniques continue to evolve rapidly alongside technological advancements, the need for effective anti-phishing systems has become increasingly crucial. Machine learning has emerged as a powerful tool for recognizing and mitigating phishing scams. This article provides a comprehensive overview of machine learning techniques for phishing detection and their effectiveness in combating online threats.

关键词： Uniform resource locators Accuracy Reviews Phishing Scalability Machine learning Telecommunication traffic Passwords Threat assessment Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Traffic Aware Power Saving Communication Assisted By Double-Faced Active RIS

Traffic Aware Power Saving Communication Assisted By Double-...

引用

IEEE International Conference on Communications (ICC)

作者： Yuyan Zhou Yang Liu Qingqing Wu Qingjiang Shi Jun Zhao School of Information and Communication Engineering Dalian University of Technology Department of Electronic Engineering Shanghai Jiao Tong University School of Software Engineering Tongji University and Shenzhen Research Institute of Big Data Shenzhen China School of Computer Science and Engineering Nanyang Technological University

Despite its high energy and hardware efficiency, some defects of the reconfigurable intelligence surface (RIS) technology have come to be realized, including the severe fading loss and restricted-to-half-space coverage. This paper proposes a novel double-faced-active (DFA)-RIS structure to overcome these defects. Besides, we utilize this novel DFA-RIS to improve power saving of the communication system. Unlike traditional power saving literature, we aim at fulfilling queueing stability and long-term power minimization in a downlink system assisted by the DFA-RIS, with a realistic data arriving process taken into consideration. Enlightened by Lyapunov control theory, we propose an online optimization strategy that adaptively adjusts DFA-RIS configuration. Each online problem can be efficiently solved by leveraging alternative directional method of multipliers (ADMM) method. Numerical results demonstrate the effectiveness of our proposed Lyapunov-guided strategy and DFA-RIS’ superiority over the classical passive RIS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach Towards Student Performance Prediction in Online Courses: Challenges Based on a Global Perspective

arXiv

引用

arXiv 2024年

作者： Moubayed, Abdallah Injadat, MohammadNoor Alhindawi, Nouh Samara, Ghassan Abuasal, Sara Alazaidah, Raed School of Computing and Augmented Intelligence Arizona State University GilbertAZ United States Electrical and Computer Engineering Department Lebanese American University Byblos Lebanon Data Science and Artificial Intelligence Department Faculty of Information Technology Zarqa University Zarqa Jordan Electrical and Computer Engineering Department Western University LondonON Canada Faculty of Science and Information Technology Jadara University Irbid Jordan Computer Science Department Faculty of Information Technology Zarqa University Zarqa Jordan Software Engineering Department Faculty of Information Technology Zarqa University Zarqa Jordan

Analyzing and evaluating students’ progress in any learning environment is stressful and time consuming if done using traditional analysis methods. This is further exasperated by the increasing number of students due to the shift of focus toward integrating the Internet technologies in education and the focus of academic institutions on moving toward e-Learning, blended, or online learning models. As a result, the topic of student performance prediction has become a vibrant research area in recent years. To address this, machine learning and data mining techniques have emerged as a viable solution. To that end, this work proposes the use of deep learning techniques (CNN and RNN-LSTM) to predict the students’ performance at the midpoint stage of the online course delivery using three distinct datasets collected from three different regions of the world. Experimental results show that deep learning models have promising performance as they outperform other optimized traditional ML models in two of the three considered datasets while also having comparable performance for the third dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

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：