检索结果-内蒙古大学图书馆

UNRAVELING THE EFFECTIVENESS OF THE K-NN ALGORITHM FOR IMBALANCED DATA IN RESEARCH TOPIC RECOMMENDATIONS

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2024年第1期59卷 271-282页

作者： Muludi, Kurnia Aisyah, Nonik Nama, Gigih Forda Lumbanraja, Favorisen R. Informatics & Business Institute Darmajaya Bandar Lampung35142 Indonesia Computer Science Department Faculty of Science The University of Lampung Bandar Lampung Indonesia Informatics Engineering Department Faculty of Science The University of Lampung Bandar Lampung Indonesia

This study addresses the challenge of selecting research topics for undergraduate students, focusing on computer science, by evaluating a recommendation model based on the k-Nearest Neighbor algorithm (kNN). The objective is to enhance the accuracy of research topic recommendations in the presence of imbalanced data. The methodology involves data cleaning, transformation, and correlation-based feature selection, with a particular focus on addressing missing values and optimizing the feature set. The Synthetic Minority Over-Sampling Technique (SMOTE) is employed to balance the dataset. The model development includes a comprehensive analysis of various k values, leading to the identification of k=3 with Manhattan distance as the optimal configuration, achieving an accuracy of 82%. The experiment explores different training data proportions, revealing that a 90:10 ratio yields the highest accuracy. This study incorporates a Grid Search technique for hyperparameter tuning, highlighting the importance of selecting appropriate distance metrics and nearest neighbor values. The system implementation is presented with user and administrator interfaces. Findings indicate varying model performance across research categories, emphasizing the need for category-specific evaluation metrics. The study concludes with a discussion on the significance of the results, which contribute to the improvement of research topic recommendation systems for students through the integration of advanced machine learning techniques. © 2024 by the authors.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

computer Vision Empowered Assistive Technology for Blind People 2

Computer Vision Empowered Assistive Technology for Blind Peo...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Mathivanan, P. Bawa Sakthi Harish, S. Yasar Arapath, P. Abishek, N. KIT - Kalaignar Karunanidhi Institute of Technology Department of Computer Science and Business Systems Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

A cost-effective mobile application is being developed to empower visually impaired individuals by enhancing indoor navigation. This innovative solution leverages advanced computer vision technology, specifically the YOLO v9 object detection model, to provide an affordable alternative to expensive assistive devices. The application delivers real-time assistance, helping users avoid obstacles and navigate safely. Using the smartphone's camera, the system captures video and processes it through the YOLO v9 model, chosen for its speed and accuracy in real-time object detection. The model is pre-trained to recognize common indoor obstacles such as furniture, walls, doors, and stairs. By identifying these barriers, the app enhances the user's confidence in navigating complex indoor environments. Feedback is provided through dual channels: audio alerts and haptic feedback. Clear audio cues like "Chair on the left"or "Wall ahead"help users adjust their movements, while haptic feedback provides tactile proximity cues through vibrations that intensify as users approach obstacles. This dual-feedback system ensures usability in noisy environments or when audio guidance is impractical. The app prioritizes accessibility and ease of use, featuring a simple interface for quick activation. The integration of YOLO v9 and real-time feedback creates a practical tool for visually impaired individuals, enabling them to navigate with greater confidence and independence. By offering an affordable and effective solution, this application bridges the gap between advanced assistive technology and inclusivity, improving the quality of life for visually impaired individuals worldwide. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Plant Care AI an AI Based Solution for Plant Disease Diagnosis and Assistance -A Comprehensive Survey

Plant Care AI an AI Based Solution for Plant Disease Diagnos...

引用

2024 International Conference on Advances in Computing Research on science Engineering and Technology, ACROSET 2024

作者： Kulkarni, Abhijit Verma, Seema Shingane, Tanish Ghogare, Snehal Dhupe, Shivkanya JSPM's Rajarshi Shahu College of Engineering Computer Science and Business Systems Pune India

ISBN: (纸本)9798350388800

The field of plant care has seen significant advancements with the increasing application of artificial intelligence (AI) and machine learning (ML) techniques across various domains. This review explores the integration of deep learning and machine learning with image recognition technologies for plant disease identification and treatment. The aim of the proposed project is to develop a comprehensive web application tailored for plant care, featuring automated plant disease detection, treatment recommendations based on identified conditions, suggestions for nearby nurseries to acquire necessary materials, and chatbot support for user inquiries. By leveraging advanced image recognition methods, the proposed system seeks to enhance the efficiency and accessibility of plant maintenance practices. Additionally, the inclusion of Google Maps facilitates seamless navigation to local nurseries, improving the user experience and promoting proactive plant care management. This study provides an overview of current methods, discusses potential opportunities and challenges, and proposes a framework for developing an intelligent plant care system to address the evolving needs of horticulturists and farmers. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Neutrosophic Topological Spaces for Lung Cancer Detection in Chest X-Rays: A Novel Approach to Uncertainty Management

引用

Neutrosophic Sets and systems 2025年 77卷 432-449页

作者： Salama, A.A. Mossa, Doaa E. Shams, Mahmoud Y. Khalid, Huda E. Essa, Ahmed K. Department of Mathematics and Computer Science Faculty of Sciences Port Said University Port Said42526 Egypt High Institute of Computer Science and Information Systems Delta Acadmey City Dakahlia Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33511 Egypt Telafer University Telafer University Telafer Iraq

Decision-making in medical diagnosis is often hampered by uncertainties due to incomplete, ambiguous, and evolving information. In reviewing the traditional methods for lung cancer detection, we found that crisp and logic values have more difficulties and challenges. These challenges related to the big data analytics, uncertainty values, and the different circumstances that make it harder for prediction. In this work, we propose a novel approach that use a Neutrosophic Topological Spaces (NTS) for the lung cancer detection in the chest X-ray images. Furthermore, the proposed NTS leverage the strengths points of Neutrosophic Sets (NS) which include the degrees of truth (T), indeterminacy (I), and falsity (F). The proposed model provides more informative results about the uncertainty cases compared with the traditional methods. The results indicated that the proposed NTS approach achieved highest accuracy reached to 85.5% with a sensitivity 88.2%, specificity 82.1%, and AUC 0.91. which mean that the proposed NTS approach are more reliable and efficient than traditional methods for uncertainty. © 2025, University of New Mexico. All rights reserved.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Expressive sign language system for deaf kids with MPEG-4 approach of virtual human character

引用

Journal of Ambient Intelligence and Humanized Computing 2024年 1-15页

作者： Ali, Itimad Raheem Kolivand, Hoshang Faculty of Business Informatics University of Information Technology and Communications Baghdad Iraq Department of Computer Science Liverpool Jone Moores University Liverpool United Kingdom

Children with language impairments during their significant developmental periods within ‎childhood are exposed to cognitive risk, social impairments, along with language. This is difficult ‎with children born deaf from hearing parents who own little or no experience of communicating ‎in sign language. This system presents the sign language in the context of British ‎Sign Language (BSL) for producing utterances through virtual characters. In capturing, Kinect ‎sensors use a motion capture sensor for motion actors. The connection uses sensors to read data, ‎connect to high-quality 3D scans, and then use these high-quality scans of the animated MPEG-4 ‎face and hand models. The main challenges of this system are the simultaneous capture of data ‎for the whole hand and the development of the MPEG-4 approach considering the animation ‎engines with descriptive sign language features. After synchronizing motion data from motion ‎capture results with Kinect, the combined hand character adjusts points, frames, and time with ‎virtual characters based on the motion of character actors. This study demonstrates the skills of ‎this sign language system instrumental in presenting an assessment by users, highlighting the ‎importance of the hand part in creating new accents and signs in BSL. We have validated this ‎system by testing the reliability and functionality of the virtual characters.‎. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Graphical Password Authentication using Image Processing (GPAIP) 18

Graphical Password Authentication using Image Processing (GP...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sivaranjani, N. Sanjana, P. Sindhubairavi, S. Saishrre, L. Sri Sairam Engineering College Computer Science and Business Systems Tamil Nadu Chennai India

ISBN: (纸本)9789380544519

In today's digital landscape, passwords are a fundamental part of our online experience, required for accessing a wide range of services. With the increasing use of online platforms, security in authentication methods has become a pressing concern. Graphical password systems have gained attention as a potentially more secure and user-friendly alternative to traditional text-based passwords. Creating such a system is a complex task, as it involves finding the right balance between security and ease of use. The main goal is to develop an authentication system that effectively safeguards personal and financial information from cyber threats and data breaches. This project introduces a novel graphical password approach which is highly resistant to common cyber-attacks like brute force or dictionary attacks that is not only more secure but also more efficient than existing ones. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Graphical Password Authentication Image pattern lock Password System Two Factor Authentication

来源：评论

学校读者我要写书评

暂无评论

Enhancing Heart Disease Model Accuracy: A Study of Optimization Hyperparameter Tuning Techniques in Machine Learning Algorithms

Enhancing Heart Disease Model Accuracy: A Study of Optimizat...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Bhargav, S.P. Om Prakash, S. Charles Sagayaraj, A.C. Thandalam Computer Science and Business Systems Chennai602105 India Thandalam Chennai602105 India

ISBN: (数字)9798331541170

ISBN: (纸本)9798331541170

Heart disease (HD) is a major global health issue, This study evaluates Machine learning (ML) models such as Logistic Regression (LR), Decision Tree (DT), K- Nearest Neighbors (KNN), and Support Vector Machine (SVM) for heart disease dataset using Train-Test Split(TTS) and K-Fold Cross-Validation (KF-CV). Initially, accuracy rates improved with KF-CV across all models. The DT model achieved 98.54 percent accuracy with TTS and 99.32 percent with KF-CV in the pre-optimization phase. To further enhance accuracy, four advanced optimization techniques - Grid Search CV, Random Search CV, Ant Colony Optimization (ACO), and Particle Swarm Optimization (PSO) were applied. The findings revealed that the DT model achieved perfect score of 100 percent accuracy with Grid Search CV and Random Search CV. SVM and KNN models also showed significant improvements with advanced tuning. PSO, in particular, was effective for optimizing hyperparameters of the LR model. This study underscores the value of advanced optimization techniques in improving the accuracy of heart disease prediction models. © 2024 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Implementation of Building Stronger Communities for New Safety approach and Recruitment using AIML 2

Implementation of Building Stronger Communities for New Safe...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Manimaran, P. Prathiksha, V.S. Madhan, S. Janani, R. K.S. Rangasamy College of Technology Computer Science and Business Systems Tiruchengode India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

Globally, women's safety is severely impacted by the increasing prevalence of harassment and violence in public areas. According to data from international organizations like the National Crime Records Bureau (NCRB) and the World Health Organization (WHO), around 35% of women experience harassment and distress in public spaces such as parks, transportation hubs, and pedestrian zones. In this proposed software platform integrates a web- based emergency alert system with direct law enforcement integration, community-based notifications, and real-time location tracking. The app's SOS function allows for quick aid mobilization by instantaneously alerting community members and pre-saved emergency contacts within a 2-kilometer radius when a user faces a potential threat. Law enforcement in the area is also alerted to situations to guarantee a prompt reaction. Responders are constantly updated with real-time location monitoring thanks to GPS technology, which gives them precise coordinates so they can find the user quickly. Additional features like geofencing, which alerts users when they approach high-risk areas identified by other community members, are also included in the app to improve preventive safety measures. The program generates a shared, constantly updated safety map that alerts users to possible dangers in real time by combining incident reports and statistics about risky locations. By encouraging community involvement and a shared sense of security, this dual emphasis on fast response and preventive knowledge empowers users. In addition to addressing urgent safety issues, this platform seeks to strengthen women's unity and boost their self-esteem in public places. The system is positioned to be an important instrument for community resilience and personal safety by fusing technology and community support, making the environment safer and more encouraging for everyone. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Robustness of generative AI detection: adversarial attacks on black-box neural text detectors

引用

International Journal of Speech Technology 2024年第4期27卷 861-874页

作者： Fishchuk, Vitalii Braun, Daniel Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Department of High-tech Business and Entrepreneurship University of Twente Enschede Netherlands

The increased quality and human-likeness of AI generated texts has resulted in a rising demand for neural text detectors, i.e. software that is able to detect whether a text was written by a human or generated by an AI. Such tools are often used in contexts where the use of AI is restricted or completely prohibited, e.g. in educational contexts. It is, therefore, important for the effectiveness of such tools that they are robust towards deliberate attempts to hide the fact that a text was generated by an AI. In this article, we investigate a broad range of adversarial attacks in English texts with six different neural text detectors, including commercial and research tools. While the results show that no detector is completely invulnerable to adversarial attacks, the latest generation of commercial detectors proved to be very robust and not significantly influenced by most of the evaluated attack strategies. © The Author(s) 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

EXPLORING THE LINK BETWEEN ACCESSIBLE WEBSITE DESIGN AND USER EXPERIENCE FOR HUMANS WITH BLINDNESS AND VISUAL IMPAIRMENT: A QUALITATIVE STUDY 31

EXPLORING THE LINK BETWEEN ACCESSIBLE WEBSITE DESIGN AND USE...

引用

31st Interdisciplinary Information Management Talks: New Challenges for ICT and Management, IDIMT 2023

作者： Henkelmann, David Fertig, Tobias Faculty of Computer Science and Business Information Systems Technical University of Applied Sciences Würzburg-Schweinfurt Germany

ISBN: (纸本)9783991511762

In today's digital age, web accessibility and barrier-free design are crucial for individuals with disabilities to fully participate in and benefit from the Internet. Despite existing guidelines, there is room for improvement in their implementation. This qualitative study explores the relationship between accessible website design and user experience for individuals with blindness and visual impairments. Through interviews, it aims to understand their current emotions and perceptions towards the Internet. Additionally, the study discusses the importance of involving individuals with visual impairments in the creation and implementation of accessibility policies and laws. The findings of this study will serve as the foundation for further empirical research to test the hypotheses formed. © 2023 IDIMT 2023: New Challenges for ICT and Management - 31st Interdisciplinary Information Management Talks. All rights reserved.

关键词： Web Design

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：