检索结果-内蒙古大学图书馆

AI-Driven Network Forensics Using Hybrid Anomaly Detection with Enhanced Transformer Based ISO-Encoder and LSTM-CNN Fusion

学校读者我要写书评

暂无评论

AI-Driven Network Forensics Using Hybrid Anomaly Detection w...

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Abisha B. Sheeja Kumari V. Wilfred Blessing N. R Sutherlin Subitha G. Seldev Christopher C. Wasim Haidar SK Department of Computational Intelligence Saveetha School of Engineering SIMATS University Chennai India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computer Science and Engineering Stella Mary's College of Engineering Affiliated to Anna University Tamil Nadu India Department of Computer Science and Engineering St. Xavier's Catholic College of Engineering Nagercoil Tamil Nadu India College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

Traditional network forensic techniques frequently find it difficult to identify and look into sophisticated cybercrimes in today's quickly changing cyber scene. A Transformer-based Iso-Encoder and a Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) fusion model are combined in this research to present an AI-driven method that makes use of a novel hybrid anomaly detection model. The LSTM-CNN fusion model performs exceptionally well in temporal and spatial feature extraction, while the Iso-Encoder is improved to capture complex patterns in network traffic. This hybrid approach is intended to accurately detect known and undiscovered anomalies. By offering practical insights into the nature of the dangers, the suggested framework not only helps with the comprehensive investigation of cyber incidents but also identifies anomalies in real-time. The model is a powerful tool for cybersecurity experts since it incorporates cutting-edge AI techniques to guarantee that it adjusts to changing cyberthreats. According to experimental data, the hybrid model maintains a low false positive rate and processing time of 0.5 ms/packet while outperforming current techniques in terms of detection accuracy (98.7%), precision (98.4%), recall (97.8%), and F1-score (98.1%). Traditional models with somewhat poorer performance include Random Forest (94.5% accuracy), Support Vector Machine (SVM) (93.7% accuracy), and LSTM (96.2 % accuracy). This research paves the way for more resilient and intelligent network forensic solutions, enhancing the ability to counteract and investigate complex cyber threats effectively.

关键词： Support vector machines Accuracy Forensics Telecommunication traffic Transformers Real-time systems Computer crime Long short term memory Anomaly detection Random forests

Classification of attention performance post-longitudinal tDCS via functional connectivity and machine learning methods

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rao, Akash K. Menon, Vishnu K. Bhavsar, Arnav Chowdhury, Shubhajit Roy Negi, Ramsingh Dutt, Varun Applied Cognitive Science Laboratory Indian Institute of Technology Mandi Mandi India School of Computing and Electrical Engineering Indian Institute of Technology Mandi Mandi India Cognitive Control and Machine learning group Institute of Nuclear Medicine and Allied Sciences Delhi India

Attention is the brain's mechanism for selectively processing specific stimuli while filtering out irrelevant information. Characterizing changes in attention following long-term interventions (such as transcranial direct current stimulation (tDCS)) has seldom been emphasized in the literature. To classify attention performance post-tDCS, this study uses functional connectivity and machine learning algorithms. Fifty individuals were split into experimental and control conditions. On Day 1, EEG data was obtained as subjects executed an attention task. From Day 2 through Day 8, the experimental group was administered 1mA tDCS, while the control group received sham tDCS. On Day 10, subjects repeated the task mentioned on Day 1. Functional connectivity metrics were used to classify attention performance using various machine learning methods. Results revealed that combining the Adaboost model and recursive feature elimination yielded a classification accuracy of 91.84%. We discuss the implications of our results in developing neurofeedback frameworks to assess attention. Copyright © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Guoqing Zhang, An Liu, Shuo Cai, Zhibo Yang, Xun Wang, Xiang University of Science and Technology of China Hefei China National University of Singapore School of Computing Singapore East China Normal University Shanghai China Renmin University of China Center for Applied Statistics School of Statistics Beijing China

Recent advancements in sequential recommendation have underscored the potential of Large Language Models (LLMs) for enhancing item embeddings. However, existing approaches face three key limitations: 1) the degradation of the semantic space when high-dimensional language embeddings are mapped to lower-dimensional ID embeddings, 2) the underutilization of language embeddings, and 3) the reliance on additional trainable parameters, such as an adapter, to bridge the gap between the semantic and behavior spaces. In this paper, we introduce AlphaFuse, a simple but effective language-guided learning strategy that addresses these challenges by learning ID embeddings within the null space of language embeddings. Specifically, we decompose the semantic space of language embeddings via Singular Value Decomposition (SVD), distinguishing it into a semantic-rich row space and a semantic-sparse null space. Collaborative signals are then injected into the null space, while preserving the rich semantics of the row space. AlphaFuse prevents degradation of the semantic space, integrates the retained language embeddings into the final item embeddings, and eliminates the need for auxiliary trainable modules, enabling seamless adaptation to any sequential recommendation framework. We validate the effectiveness and flexibility of AlphaFuse through extensive experiments on three benchmark datasets, including cold-start user and long-tail settings, showcasing significant improvements in both discriminative and diffusion-based generative sequential recommenders. Our codes and datasets are available at https://***/Hugo-Chinn/AlphaFuse. Copyright © 2025, The Authors. All rights reserved.

关键词： Network embeddings

Data-Driven Feature Analysis for Student Performance Prediction

学校读者我要写书评

暂无评论

Data-Driven Feature Analysis for Student Performance Predict...

Innovative Engineering Sciences and Technological Research (ICIESTR), International Conference on

作者： Maha Said Al-Anqoudi Mireilla Bikanga Ada Stephen McQuistin College of Computing and Information Sciences University of Technology and Applied Science Nizwa Oman School of Computer Science University of Glasgow Glasgow UK School of Computer Science University of St Andrews St Andrews UK

ISBN: (数字)9798350348637

ISBN: (纸本)9798350348644

We have witnessed the widespread adoption of online teaching and learning platforms in recent years. Teachers employ a variety of learning activities and techniques to follow their students’ learning progress, including summative assessments. However, concerns have been raised about the trustworthiness of summative assessments, such as quizzes and tests. At the same time, online teachers have found other learning activities that are not typically included in predictive machine learning models of online platforms are effective in helping them identify student learning status. This study uses two feature selection techniques, filter and embedded, along with a teacher self-reported questionnaire to evaluate which learning activities influence students’ performance in summative assessments like quizzes. Our findings reveal that features from non-summative learning activities can effectively predict students’ performance in an online environment. Teachers agree on the importance of the identified learning activities’ features in helping them determine their students’ learning status. The study provides practical recommendations for educators, course designers, and policy-makers to optimize online assessment strategies.

关键词： Discussion forums Distance learning Education Machine learning Predictive models Feature extraction

Code Refactoring for Software Reusability: An Experimental Study

学校读者我要写书评

暂无评论

Code Refactoring for Software Reusability: An Experimental S...

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Abdullah Almogahed Hairulnizam Mahdin Mazidah Mat Rejab Abdulwadood Alawadhi Samera Obaid Barraood Manal Othman Omar Al-Jamili Abdulwahab Ali Almazroi Shazlyn Milleana Shaharudin Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Parit Raja Johor Malaysia InterNetWorks Research Laboratory School of Computing Universiti Utara Malaysia Sintok Malaysia College of Computers and Information Technology Hadhramout University Hadhramout Yemen Computer Science Department College of Applied Science Taiz University Taiz Yemen Faculty of Engineering and Computing University of Science and Technology Yemen Department of Information Technology College of Computing and Information Technology at Khulais University of Jeddah Jeddah Saudi Arabia Faculty of Science and Mathematics Universiti Pendidikan Sultan Idris Tanjong Malim Malaysia

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Refactoring plays a critical role in enhancing the quality of software systems, enabling them to accommodate growing user bases, feature sets, and performance demands. Software reusability is an essential aspect of software quality. It is crucial in modern software development as it offers several benefits, including increased productivity, improved code quality, and cost-effectiveness. However, there is a lack of studies investigating how specific refactoring techniques affect reusability. Therefore, this study aims to explore the effects of code refactoring on software reusability. This study was conducted in four stages: selecting refactoring techniques, selecting a large dataset, selecting software metrics to measure the reusability, and applying the refactoring techniques. The five most common refactoring techniques (Extract Interface, Encapsulate Field, Extract Class, Inline Class, and Inline Method) used in practices were selected and applied in the jEdit dataset. The refactoring techniques were carried out 338 times through five experiments in the jEdit dataset. The finding reveals that Extract Interface, Encapsulate Field, and Extract Class significantly improve the code reusability while Inline Class and Inline Method impair it. Developers and software architects can use this knowledge to make well-informed judgments about refactoring techniques and develop more robust and reusable software systems.

关键词： Productivity Industries Codes Software quality Software systems Maintenance Software measurement

Exploring the Synergy of Artificial and Computational Intelligence for Technological Advancements

学校读者我要写书评

暂无评论

Exploring the Synergy of Artificial and Computational Intell...

Data, Computation and Communication (ICDCC), International Conference on

作者： Suresh Palarimath Pyingkodi Maran Prajoona Valsalan Wilfred Blessing N. R S. J. Kavitha Steffi S College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman Department of Computer Applications Kongu Engineering College Erode India Electrical and Computer Engineering Department College of Engineering Dhofar Univesity Salalah Sultanate of Oman College of Computing and Information Sciences Univesity of Technology and Applied Sciences Ibri Sultanate of Oman Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331532956

ISBN: (纸本)9798331532963

Due to the ongoing advancements in science and technology, it seems that artificial intelligence and computers have encountered a limitation in their progress. Contemporary scientific research requires more sophisticated interconnection technology to ensure the continued progress of science and technology. Amidst this setting, the technology of Internet of Things (IoT) has progressively been visible to individuals. This technology will significantly impact human lifestyle and quality of life, and the Internet of Things has seen substantial progress. Information technology is intricately intertwined with the lives of citizens. The integration of information technology with the IoT is aimed at maximizing the technological advancement of the Internet of Things, with Internet technology serving as the central component. The use of artificial intelligence and computer intelligence in Internet technology is versatile, and issues pertaining to artificial intelligence and computing intelligence are progressively emerging. Artificial intelligence and computational intelligence play a significant role in the Internet of Things. However, their application process is challenging and lacks creativity, necessitating ongoing improvements at the application level. This study examines the use of artificial intelligence and computational intelligence in the Internet of Things.

关键词： Computers Planets Internet of Things Artificial intelligence Information technology Computational intelligence Creativity

FROM COLORS TO CLASSES: EMERGENCE OF CONCEPTS IN VISION TRANSFORMERS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dorszewski, Teresa Tětková, Lenka Jenssen, Robert Hansen, Lars Kai Wickstrøm, Kristoffer Knutsen Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Physics and Technology UiT The Arctic University of Norway Norway Pioneer Centre for AI University of Copenhagen Denmark Norwegian Computing Center Oslo Norway

Vision Transformers (ViTs) are increasingly utilized in various computer vision tasks due to their powerful representation capabilities. However, it remains understudied how ViTs process information layer by layer. Numerous studies have shown that convolutional neural networks (CNNs) extract features of increasing complexity throughout their layers, which is crucial for tasks like domain adaptation and transfer learning. ViTs, lacking the same inductive biases as CNNs, can potentially learn global dependencies from the first layers due to their attention mechanisms. Given the increasing importance of ViTs in computer vision, there is a need to improve the layer-wise understanding of ViTs. In this work, we present a novel, layer-wise analysis of concepts encoded in state-of-the-art ViTs using neuron labeling. Our findings reveal that ViTs encode concepts with increasing complexity throughout the network. Early layers primarily encode basic features such as colors and textures, while later layers represent more specific classes, including objects and animals. As the complexity of encoded concepts increases, the number of concepts represented in each layer also rises, reflecting a more diverse and specific set of features. Additionally, different pretraining strategies influence the quantity and category of encoded concepts, with finetuning to specific downstream tasks generally reducing the number of encoded concepts and shifting the concepts to more relevant categories. © 2025, CC BY.

关键词： Convolutional neural networks

WOMBAT v2.S: A Bayesian inversion framework for attributing global CO2 flux components from multiprocess data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jacobson, Josh Bertolacci, Michael Zammit-Mangion, Andrew Schuh, Andrew Cressie, Noel School of Mathematics and Applied Statistics University of Wollongong Australia School of Physics Mathematics and Computing University of Western Australia Australia Colorado State University United States Jet Propulsion Laboratory California Institute of Technology United States

Contributions from photosynthesis and other natural components of the carbon cycle present the largest uncertainties in our understanding of carbon dioxide (CO2) sources and sinks. While the global spatiotemporal distribution of the net flux (the sum of all contributions) can be inferred from atmospheric CO2 concentrations through flux inversion, attributing the net flux to its individual components remains challenging. The advent of solar-induced fluorescence (SIF) satellite observations provides an opportunity to isolate natural components by anchoring gross primary productivity (GPP), the photosynthetic component of the net flux. Here, we introduce a novel statistical flux-inversion framework that simultaneously assimilates observations of SIF and CO2 concentration, extending WOMBAT v2.0 (WOllongong Methodology for Bayesian Assimilation of Trace-gases, version 2.0) with a hierarchical model of spatiotemporal dependence between GPP and SIF processes. We call the new framework WOMBAT v2.S, and we apply it to SIF and CO2 data from NASA’s Orbiting Carbon Observatory-2 (OCO-2) satellite and other instruments to estimate natural fluxes over the globe during a recent six-year period. In a simulation experiment that matches OCO-2’s retrieval characteristics, the inclusion of SIF improves accuracy and uncertainty quantification of component flux estimates. Comparing estimates from WOMBAT v2.S, v2.0, and the independent FLUXCOM initiative, we observe that linking GPP to SIF has little effect on net flux, as expected, but leads to spatial redistribution and more realistic seasonal structure in natural flux components. © 2025, CC BY.

关键词： NASA

Threat Assessment Model in Electrical Power Grid Environment 1

学校读者我要写书评

暂无评论

Threat Assessment Model in Electrical Power Grid Environment

1st International Conference on Engineering and technology, ICoEngTech 2021

作者： Qassim, Qais Saif Jamil, Norziana Mahdi, Mohammed Najah Rahim, Fiza Abd Cob, Zaihisma Che Sidek, Lariyah Mohd University of Technology and Applied Sciences Ibri Oman College of Computing and Informatics Universiti Tenaga Nasional Malaysia Institute of Energy Infrastructure Universiti Tenaga Nasional Malaysia

At the heart of every critical national infrastructure, there is a SCADA system. The wide range of supported applications has made this life-saving management system the key element of every industrial control infrastructure in various sectors. The complexity and sophistication of SCADA systems have been increased dramatically over the last few years. Various cyberattacks have targeted these systems by exploiting zero-day vulnerabilities or targeting a nearby Internet-enabled appliance or computer system. To this end, many efforts have been proposed previously to model the threats on SCADA systems to eliminate potential danger and diminish the catastrophic consequences in the physical domain. The main contribution of this work is to present a multi-facets threat assessment model to aid security teams to systematically perform various cybersecurity analysis practices such as penetration testing, vulnerability assessment and risk analysis. © Published under licence by IOP Publishing Ltd.

关键词： SCADA systems