检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Bolisetty, Prashanth Kumar Midhunchakkaravarthy Lincoln University College Faculty of Ai Ai Computing and Multimedia Selangor Darul Eshan Malaysia Lincoln University College Faculty of Ai Computing and Multimedia Selangor Darul Eshan Malaysia

ISBN: (纸本)9798331529246

Software reliability plays a crucial role in assessing the overall quality of software systems. Developing highly reliable software presents challenges, including ensuring usability, maintaining consistent performance, offering reliable service, and facilitating smooth maintenance. To overcome these limitations, researchers have turned to intelligent prediction and optimization algorithms. This paper presents a comprehensive review of software reliability prediction, emphasizing the application of machine learning techniques. It also provides an analytical evaluation of existing methods to identify areas for improvement and future research opportunities in software reliability prediction. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Document Classification Using Modified Relative Discrimination Criterion and RSS-ELM Techniques

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 824-833页

作者： Anwaar, Muhammad Gilanie, Ghulam Namoun, Abdallah Sharif, Wareesa Department of Artificial Intelligence-Faculty of Computing The Islamia University of Bahawalpur Bahawalpur Pakistan AI Center-Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia

Internet content is increasing daily, and more data are being digitized due to technological advancements. Everincreasing textual data in words, phrases, terms, sentences, and paragraphs pose significant challenges in classifying them effectively and require sophisticated techniques to arrange them automatically. The vast amount of textual data presents an opportunity to organise and extract valuable insights by identifying crucial pieces of information using feature selection techniques. Our article proposes "a Modified Relative Discrimination Criterion (MRDC) Technique and Ringed Seal Search-Extreme Learning Machine (RSS-ELM) to improve document classification", which prioritizes key data and fits corresponding documents into appropriate classes. The proposed MRDC and RSS-ELM techniques are compared with several existing techniques, such as the Relative Discrimination Criterion (RDC), the Improved Relative Discrimination Criterion (IRDC), GA-EM, and CS-ELM. The MRDC technique produced superior classification results with 91.60% accuracy compared to existing RDC and IRDC for feature selection. Moreover, the RSS-ELM optimization technique improved predictions significantly, with 98.9% accuracy compared to CS-ELM and GA-ELM on the Reuter21578 dataset. © (2025), (Science and Information Organization). All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A survey of data stream-based intrusion detection systems

引用

IEEE Access 2025年 13卷 72953-72983页

作者： Miani, Rodrigo Sanches Bernardo, Gustavo Di Giovanni Cassales, Guilherme Weigert Senger, Hermes Faria, Elaine Ribeiro Federal University of Uberlandia Faculty of Computing Brazil AI Institute University of Waikato New Zealand Federal University of Sao Carlos Department of Computer Science Brazil

Detecting malicious activities in network environments poses a challenge that attracts significant attention due to its complexity and importance. Advances in the field have led to the development of several algorithms that approach the problem under the view of a data stream machine learning task. This task involves a set of steps: data collection or choice of public datasets, data pre-processing, data reduction, development or application of data mining techniques, and evaluation methodology. However, these steps must address the inherent issues of dynamic environments such as data streams and intrusion detection systems. These issues include, but are not limited to, the continuous influx of data, changes in both normal and attack class distributions, the emergence of new attack types, and the scarcity of labeled data examples to update the decision models. This survey provides an overview of intrusion detection systems (IDS) using data stream machine learning techniques, characterizing the literature approaches according to the classic steps of the data mining task. In addition, we discuss recommendations for practical IDS development and highlight datasets and tools that can aid in detecting malicious behavior. Finally, we outline potential avenues for future research and open questions in the field. © 2013 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Software Reliability Prediction and Optimization using Machine Learning Algorithms

Comparative Analysis of Software Reliability Prediction and ...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Prashanth Kumar Bolisetty Midhunchakkaravarthy Faculty of AI AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia Faculty of AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

关键词： Machine learning algorithms Reviews Software algorithms Machine learning Software systems Prediction algorithms Software reliability Maintenance Usability Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Mobile Cloud computing: A Comparative Analysis and Innovative Cost-Efficient Partitioning Model

引用

SN Computer Science 2025年第1期6卷 1-25页

作者： Ali, Mushtaq Muhammad, Dost Khalaf, Osamah Ibrahim Habib, Raja Faculty of Computing Riphah International University Islamabad Pakistan CRT-AI and ADAPT Research Centers School of Computer Science University of Galway Galway Ireland Department of Solar Al-Nahrain Research Center for Renewable Energy Al-Nahrain University Jadriya Iraq Department of Computing Shifa Tameer-e-Millat University Islamabad Pakistan

Mobile cloud computing (MCC) integrates mobile devices with cloud computing to enhance performance and provide scalable services. It enables the partitioning of computationally intensive mobile applications, utilizing the cloud resources for remote execution. This process is vital for optimizing resource utilization and energy efficiency in distributed computing environments. Initially, static application partitioning was developed, dividing system resources into fixed-sized partitions. Though it is simple and reduces operational overhead, it lacks adaptability to dynamic computing environments due to mobility. Modern frameworks use runtime partitioning, dynamically allocating resources based on runtime profiling, which increases computational overhead and energy consumption. Despite various studies on MCC, there is a notable oversight in numerical analysis of application partitioning. This paper presents a comparative numerical study of existing partitioning techniques and proposes a Cost-Efficient Partitioning (CEP) model. The CEP model combines the static nature to reduce computational overhead with the dynamic nature to address runtime challenges. This research addresses the shortcomings of existing approaches, potentially transforming computational offloading into energy-saving solutions. Our results show that the execution time (ET) of a task in the CEP model is 0.826 s, which is longer than the ET of static partitioning however shorter than the 0.962 s of dynamic partitioning models. Similarly, the CEP's energy consumption in a test scenario is 0.609 J, slightly higher than the 0.587 J of static partitioning but lower than the 0.711 J of dynamic partitioning. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Computational offloading Dynamic partitioning Energy consumption Execution cost Mobile computing Remote execution Static partitioning

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

引用

Computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

“Lost in the crowd”: ethical concerns in crowdsourced evaluations of LLMs

AI and Ethics

引用

ai and Ethics 2025年 1-7页

作者： Cheong, Marc Bush, Gabby Wildenauer, Michael Centre for AI and Digital Ethics University of Melbourne Melbourne Connect Parkville Australia School of Computing and Information Systems Faculty of Engineering and IT University of Melbourne Melbourne Connect Parkville Australia

With the acceleration of Large Language Model (LLM) use by the public, there is an urgent need to make sure the downstream effects have beneficial impacts on humans and society. Therefore, there is an increasing push for ethical evaluation of LLMs to look for potential bias, toxic behaviour, and misinformation. Thus, crowdsourcing has become a popular practice, such as Openai’s 2023 Evals initiative. Firstly, by reviewing the literature from software development and ethics, we wish to highlight several cautions on applying the crowdsourcing model to LLMs: including participant self-selection and non-representativeness; the diffusion of responsibility effect including ethics washing and burden shifting; and requisition of ‘incentives’ vis-a-vis issues faced by gig workers. Using the Evals GitHub repository as a case study, we study the effectiveness of an expert-driven, voluntary, crowdsourced scheme on GitHub to address socioethical issues in LLMs. This is achieved by evaluating the statistics of crowdsourced contributions on ethical and bias considerations, which pales in comparison to other technical contributions. This commentary hopes to highlight the issues of ethics, equity, and justice in LLM crowdsourcing, drawing upon interdisciplinary literature, and presents open considerations on how we can improve the state of play.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Histopathological Image Classification Using Imbalanced Domain Learning 11th

Cervical Cancer Histopathological Image Classification Using...

引用

11th Eai International Conference on Advancement of Science and Technology, ICAST 2023

作者： Simegn, Gizeaddis Lamesgin Degu, Mizanu Zelalem Tegenaw, Geletaw Sahle Biomedical Imaging Unit School of Biomedical Engineering Jimma Institute of Technology Jimma University Jimma Ethiopia AI and Biomedical Imaging Research Unit Jimma Institute of Technology Jimma University Jimma Ethiopia Faculty of computing and informatics Jimma Institute of Technology Jimma University Jimma Ethiopia

ISBN: (纸本)9783031641503

Early diagnosis of cervical cancer is challenging, especially in developing countries due to limited resource, infrastructure, and experts. Recent improvements in deep learning-based early cervical cancer detection techniques can potentially lower these challenges while increasing diagnosis accuracy. In this study, experiments were conducted on 465 histopathological images collected from patients with adenocarcinoma, squamous cell carcinoma, and squamous intraepithelial lesion. CNN and ResNet-50 models were trained for classification after the application of data augmentation, color normalization, and synthetic minority oversampling technique (SMOTE) on the data. Classification accuracies of 86.43% and 92.14% were found using CNN and ResNet-50 trained on raw data, respectively. ResNet-50 trained on a dataset "without a preprocessing technique," "affine transform-based data augmentation," "data augmentation and histogram match-based color normalization," "SMOTE," and "color normalization and SMOTE" achieved accuracies of 94.20%, 96.39%, 95.32%, 99.14%, and 90.56%, respectively. In general, the study investigated how image preprocessing, specifically data balancing, influences the effectiveness of deep learning models. Additionally, it examined the possibilities of utilizing computer-aided image processing to detect cervical cancer. The findings show that, with proper data processing, the proposed technique might be used as a cervical cancer screening tool, particularly in low-resource settings. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification Refactoring Framework Using Hopfield Neural Network for Sustainable Software Development

引用

IEEE Access 2025年 13卷 31785-31808页

作者： Almogahed, Abdullah Mahdin, Hairulnizam Hyeon Gu, Yeong Al-Masni, Mohammed A. Alzaeemi, Shehab Abdulhabib Omar, Mazni Alawadhi, Abdulwadood Obaid Barraood, Samera Rehman Gilal, Abdul Ameen Bakather, Adnan Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Parit Raja Johor86400 Malaysia Sejong University College of AI Convergence Department of Artificial Intelligence and Data Science Seoul05006 Korea Republic of King Fahd University of Petroleum and Minerals Interdisciplinary Research Center in Finance and Digital Economy Business School Dhahran31261 Saudi Arabia Universiti Utara Malaysia School of Computing Sintok06010 Malaysia Hadhramout University College of Computers and Information Technology Department of Computer Science Hadhramaut Yemen Florida International University Knight Foundation School of Computing and Information Sciences MiamiFL33199 United States

Adopting high-quality source code is the ultimate way through which software evolution can be ensured as sustainable. Continuous refactoring in complex software systems ensures longevity and increases architecture knowledge sustainability. However, decision-making about refactoring is a challenge because the benefits of refactoring are vague and very difficult for the developers to quantify, as different refactoring strategies have different effects on quality attributes. No research has developed a multi-classification refactoring framework using artificial neural networks (ANN), specifically hopfield neural networks (HNN), to classify refactoring strategies and improve external software quality and sustainability. Therefore, this study proposes a multi-classification refactoring framework using HNN that classifies refactoring strategies by their impact on external quality attributes. Five stages have been conducted to perform this study, including selecting case studies, identifying the external quality attributes, identifying the most commonly used refactoring strategies in practice, conducting the experiments, and conducting the classification process using HNN. The proposed framework categorizes the refactoring strategies into three categories (positive, negative, and ineffective). By providing clear classifications and descriptions of each strategy, the proposed framework helps developers make informed decisions about how to improve the design and structure of their code. It helps developers mitigate risks associated with code changes by providing guidance on which strategies are likely to yield positive results for specific quality attributes. The proposed multi-classification refactoring framework enhances software sustainability by enhancing critical quality attributes. It supports maintainability, adaptability, and long-term viability, helping to ensure that the software systems remain relevant, efficient, and valuable over time. © 2025 IEEE.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Dual Impact of Augmented Reality-Based Serious Games on Student Performance and Creative Thinking in Education: A Comprehensive Review

SSRN

引用

SSRN 2025年

作者： Abdul Razak, Fatin Nasuha Kamsin, Amirrudin Rahman, Hameedur Faculty of Computer Science and Information Technology Universiti Malaya Wilayah Persekutuan Kuala Lumpur Kuala Lumpur50603 Malaysia Faculty of Computing & AI Air University E9 Islamabad44400 Pakistan

This study explores the dual role of augmented reality (AR)-based serious games (SGs) in enhancing student performance and fostering creative thinking in education. Despite the recognized potential of AR-based SGs, the mechanisms through which they impact academic performance and creativity are not well understood, posing challenges for effective integration into curricula. Existing research often focuses on isolated aspects, leaving a gap in understanding their overall impact on learning and creativity. To address this, the study reviews 271 articles from the past decade, selecting 25 for in-depth analysis based on PRISMA guidelines. It examines the characteristics, design, implementation, and evaluation methods of AR-based SGs, emphasizing their effects on student outcomes and creativity. The study’s novel approach simultaneously explores both academic and creative benefits, offering a comprehensive understanding of their educational value. Beyond assessing performance, the research investigates how AR-based SGs stimulate critical thinking, enhance digital literacy, and foster positive learning attitudes. By identifying trends and providing practical strategies, the study offers a new framework for maximizing both performance and creativity in education. The findings have significant implications for educators, curriculum designers, and policymakers, providing actionable insights to optimize learning outcomes and create a more innovative and engaging educational experience. This research advances the field by deepening the understanding of how AR-based SGs can dynamically and effectively shape the future of education. © 2025, The Authors. All rights reserved.

关键词： Serious games

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：