检索结果-内蒙古大学图书馆

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Subramani, Nandhagopal Jithesh, M.D. Harish, R. Rithish Hari, G. KPR Institute of Engineering and Technology Department of Artificial Intelligence and Machine Learning Coimbatore India KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India KPR Institute of Engineering and Technology Department of Mechanical Engineering Coimbatore India

ISBN: (纸本)9798331505745

The automated detection of pipeline cracks is vital for maintaining the safety and operational lifespan of this crucial infrastructure. Early crack detection prevents costly repairs and minimizes the risk of catastrophic failures and environmental damage. Existing methods primarily rely on manual inspections and traditional image processing techniques, which often lead to inaccuracies and inefficiencies. These methods suffer from high false-negative rates and poor adaptability to different environmental conditions. This study proposes a deep learning framework utilizing YOLOv10 to automate the detection of pipeline cracks with enhanced accuracy. Studies using deep learning report detection accuracies between 80% and 92%, although performance varies across different studies. The range reflects the influence of factors such as dataset and model specifics. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multi-View Heterogeneous Hypergraph Convolutional Network for Heterogeneous Information Network Representation learning

引用

IEEE Transactions on Big Data 2025年第3期11卷 1144-1157页

作者： Bing, Rui Yuan, Guan Zhang, Yanmei Wang, Senzhang Li, Bohan Zhou, Yong China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Engineering Research Center of Mine Digitalization Xuzhou221116 China Central South University School of Computer Science and Engineering Changsha410083 China Nanjing University of Aeronautics and Astronautics College of Artificial Intelligence and Computer Science and Technology Nanjing211106 China Ministry of Education Key Laboratory of Brain-Machine Intelligence Technology Nanjing211106 China

Heterogeneous hypergraph neural networks are powerful tools to capture complex correlations among various nodes in Heterogeneous Information Networks (HINs). Despite satisfied performances of them, they are still plagued by the following problems: 1) They cannot capture the correlations in structural and semantic view at once, leading to topological information loss. 2) Due to the number of nodes being greater than the number of node types, node-level self-attention they used causes massive parameters and leads to high time consumption. 3) Interactions in meta-paths may be redundant, resulting in the correlations bias. To address the three issues, we propose an efficient Multi View Heterogeneous Hypergraph Convolutional Network (MVH, Member, IEEE, 2 GCN). It first constructs relational andsemantic hypergraphs based on different types of edges and meta-paths respectively, to represent the complex correlations in structural view and semantic view. Meanwhile, the clean semantic hypergraphs are generated by structure learning network to avoid redundancy. Then, an efficient hypergraph convolutional network is designed to learn node embeddings. By doing so, correlations in the two views are captured. Finally, the learned node embeddings from two views are aggregated via a gated embedding fusion module for downstream *** results demonstrate that MVH2GCN is effective and efficient. © 2015 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

From 5G to 6G: The Role of AI, machine learning, and Deep learning in Wireless Systems 4

From 5G to 6G: The Role of AI, Machine Learning, and Deep Le...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Gote, Pradnyawant M. Kumar, Praveen Verma, Prateek Yesankar, Prajyot Pawar, Adesh Saratkar, Saniya Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Computer Science & Medical Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

The swift progression of wireless communication technologies-specifically from 5G to 6G is an approach that could be the most significant revolutionary leap towards changing connectivity and data transmission forever. Additionally, algorithms of machine learning (ML) and deep learning (DL) in 5G and 6G can offer promising advancements toward predictive maintenance, dynamic spectrum management, and enhanced security. The review of the potentially transformative nature of these technologies underlines the need for future directions of research efforts called for in circumventing challenges towards making full capability exploitation of 6G possible. © 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

Biomaterials and Their Applications

引用

Biomedical Materials and Devices 2025年 1-16页

作者： Menagadevi, M. Nirmala, M. Thiyagarajan, D. Somasundram, D. Department of Computer Science and Engineering School of Engineering Malla Reddy University Hyderabad India Department of Biomedical Engineering Dr. N G P Institute of Technology Coimbatore India Department of Artificial Intelligence and Machine Learning School of Engineering Malla Reddy University Hyderabad India Department of Micro & Nanoelectronics School of Electronics Engineering Vellore Institute of Technology Vellore India

A biomaterial is a biocompatible substance engineered to interact with biological systems for therapeutic and diagnostic, such as pacemakers, dental implants, vascular stents, artificial joints, drug delivery systems, tissue engineering, biosensors, image contrast agents in computer Tomography, Magnetic Resonance Imaging, optical imaging, and ultrasound. Biomaterials are also used as assays in point-of-care testing devices. Based on the organs’ biological properties, the biomaterials are mainly classified into metals, polymers, ceramics, and composite biomaterials. The success rate of the implant depends on the physical, chemical, and mechanical properties of the selected material. Each biomaterials have unique properties, so it is used in both soft and hard tissue replacements. In this review, various properties and applications of biomaterials are discussed. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Applications Biocompatibility Biomaterials Properties Types

来源：评论

学校读者我要写书评

暂无评论

Estimation of Response Time with Neural Networks in Cloud Computing System 1

Estimation of Response Time with Neural Networks in Cloud Co...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： More, Rajesh Suresh, Sanjna Veerappampalayam Easwaramoorthy, Sathish Kumar Rizvi, Haider Ali Kunnathully, Kannan Gupta, Sahil K. Cloudwerx Wordwide Departmen of AIML Hyderabad India Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Coimbatore India School of Engineering and Technology Sunway University Selangor Darul Ehsan Malaysia Yogananda School of Artificial Intelligence Shoolini University Department of Artificial Intelligence and Machine Learning India Veltech University Department of Research Chennai India Tula's Institute Department of Computer Science and Engineering Dehradun248197 India

ISBN: (纸本)9798331518578

Resource allotment, responsiveness, connection, research of unexplored assets, related resource modeling, and asset scheduling are just a few of the numerous factors and concerns that need to be considered to enhance cloud computing efficiency. The functionality of the cloud has a significant impact on the propagation of cloud architecture. Consequently, it is important to determine the components that influence cloud function to analyze it. Response duration is the primary aspect that significantly affects cloud computation functioning, according to the research. The response duration assistance is among the numerous different variables that may be used to organize resource applications. artificial neural networks (ANNs) were employed as a technique for evaluating the parameter of pursuit, and a fork-join framework or an architecture with demand partitioning was selected as the queuing paradigm. As a result, this study suggests a load-managing method depending on cloud demand response duration using the ARIMA Estimation of Response Duration Method. The fundamental concept is to employ ARIMA methods to estimate the future response duration, providing a more efficient method of allocating resources with limited values. The results of the investigation demonstrated that the estimations were more precise compared to those that had been recently established. The results of the study indicate that estimation is an outstanding path for load balance and has possibility and value for load balance with displayed response duration. Additionally, the suggested method makes it feasible to acquire estimations for a wider range of cloud structure functioning signs compared to earlier feasible and also to extend the evaluation of the cloud platform to the instance of a structure with a non-Poisson data flow and non-exponential assistance duration. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Efficient Chromosome Abnormal Detection using Yolo-V8 model 3

Efficient Chromosome Abnormal Detection using Yolo-V8 model

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Umarani, V. Isaac, Augustian Premnath, K. Kannan, G. Sanjay, A. Hari Haran, L.K. Saveetha Engineering College Dept of Computer Science and Engineering TamilNadu Chennai India Saveetha Engineering College Dept of Artificial Intelligence & Machine Learning TamilNadu Chennai India

ISBN: (纸本)9798331523893

Human chromosomes exhibit complex and intricate patterns, making their analysis and data interpretation challenging. Studying chromosomes is crucial for identifying genetic disorders, such as Down syndrome, and various types of cancer. Traditional karyotyping methods depend heavily on manual method, which causes human error and high cost. To address these challenges, a deep learning-based approach is proposed to automate the karyotyping process, improving both accuracy and efficiency while minimizing human involvement and errors. This research leverages advanced deep learning techniques, specifically the YOLOv8 object detection framework, to enhance chromosomal analysis. From experiments, the proposed YOLO V8 model achieves a 95.2% accuracy, surpassing other models such as DCNN, CNN, and VGG-19. This work represents a significant step toward developing a more reliable and efficient diagnostic tool for detecting genetic disorders. © 2025 IEEE.

关键词： Chromosome defeat prediction Deep learning YOLO-V8 model

来源：评论

学校读者我要写书评

暂无评论

The EcoSync: A Comprehensive Study on Water Quality Prediction and Waste Image Recognition

The EcoSync: A Comprehensive Study on Water Quality Predicti...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Ahana Mukherjee Bipasha Chatterjee Indrakshi Das Koushiki Chakraborty Madhushree Pramanik Anjan Kumar Payra Computer Science (Artificial Intelligence & Machine Learning) Institute of Engineering and Management Newtown Kolkata India Computer Science (Artificial Intelligence & Machine Learning) Institute of Engineering and Management Newtown Institute of Engineering and Management Newtown Kolkata India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

This research was devised to analyze how machine learning tools could assess water quality and classify waste aiming to build a better system for sustaining our environment. We unified decision trees, random forests, and convolutional neural networks to create a multi-model system that identifies and sorts waste via image recognition. To strengthen our model's performance, we expanded our dataset to include sundry labelled images. Using a multilayer perceptron with Adam optimizer, our system achieved 89% accuracy in classifying waste types and 94% accuracy in identifying waste materials. Water potability analysis, however, relied on machine learning models that were trained on a comprehensive dataset of chemical and physical water parameters. The system was able to show an accuracy of 87% in predicting water safety with a low false positive rate of 3.2% when real time monitoring was integrated. These systems when integrated gave a solution that was better than traditional methods by 47% and the processing time was reduced by 62%. Our results showed that machine learning can effectively enhance environmental management systems. This scalable, technology-driven approach proved successful for both waste and water management, making it particularly valuable for regions struggling with these challenges, regardless of their development status.

关键词： Waste management Waste materials Accuracy Image recognition Biological system modeling Water quality Real-time systems Decision trees Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

The EcoSync: A Comprehensive Study on Water Quality Prediction and Waste Image Recognition 3

The EcoSync: A Comprehensive Study on Water Quality Predicti...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Mukherjee, Ahana Chatterjee, Bipasha Das, Indrakshi Chakraborty, Koushiki Pramanik, Madhushree Payra, Anjan Kumar Institute of Engineering and Management Newtown Computer Science (Artificial Intelligence & Machine Learning) Kolkata India Institute of Engineering and Management Newtown Computer Science (Artificial Intelligence & Machine Learning) India Institute of Engineering and Management Kolkata Newtown India

ISBN: (纸本)9798331523893

关键词： Adam Optimizer Classifiers machine learning Algorithms Sustainable development Waste analysis Waste Image Recognition Waste Management Water analysis Water and Waste Management Water potability XG Boost

来源：评论

学校读者我要写书评

暂无评论

machine learning in Healthcare: A Review of Current Applications and Future Trends 2

Machine Learning in Healthcare: A Review of Current Applicat...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Yesankar, Prajyot Puri, Chetan Barahate, Aditya Gote, Pradanywant M. Hajbe, Janhavi Pawar, Adesh Department of Computer Science & Design Maharashtra Wardha442001 India Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India Department of Computer Science & Medical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

machine learning (ML) has been a main force behind important breakthroughs in patient tracking, personalized medicine, medical tests, and operating efficiency in the healthcare business in recent years. machine learning algorithms provide unique insights into early disease identification, picture analysis, and prediction analytics, improving diagnosis accuracy and treatment results. These programs are able to examine big and complex information. By predicting treatment effectiveness and genetic risks, machine learning (ML) allows personalized medicine by allowing customized care through tailored therapy approaches. Furthermore, preventative health management is backed by ML-driven prediction analytics and online patient tracking, especially for chronic illnesses. Operationally, machine learning increases process efficiency and cuts costs, allowing for data- driven decision-making and individualized patient care. However, there are important ethics issues with machine learning acceptance in the healthcare business as well, such as data protection, computer bias, and legal problems. This study offers a full analysis of the state-of-the-art machine learning applications in healthcare, stressing their revolutionary potential while discussing the ethics issues and hurdles that must be addressed to ensure execution that is both responsible and fair. © 2025 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Similarity-Based Movie Recommendation Using Bag-of-Words Model

Feature Extraction and Similarity-Based Movie Recommendation...

引用

International Conference on Smart Systems and Wireless Communication, SSWC 2024

作者： Raj, Swati Dutta, Jhalak Bandopadhyay, Saikat Prasad, Rajesh Department of Computer Science and Engineering Christ University Bengaluru India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Artificial Intelligence and Machine Learning Netaji Subhash Engineering College Kolkata India Department of Computer Science and Engineering MIT Art Design and Technology University Pune India

ISBN: (纸本)9789819613472

Recommender systems have become pervasive in guiding users through a lot of choices available in today’s digital landscape. This paper presents a content-based recommender system focused specifically for movie recommendations, offering a viable alternative to collaborative filtering methods. Unlike collaborative filtering, which relies on user ratings and demographic data, the proposed system operates without such prerequisites, making it particularly advantageous in scenarios with limited user engagement. By leveraging content attributes such as title, genre, cast, and crew, the system identifies similarities between movies and recommends those akin to a user’s preferences. Through innovative preprocessing techniques and feature extraction methodologies, the system transforms textual descriptions into numerical vectors, enabling efficient recommendation generation. The proposed model contributes to addressing critical challenges inherent in collaborative filtering, including the cold start problem, data sparsity, and popularity bias. Furthermore, it underscores the broad applicability of recommender systems across various domains and emphasizes the continuous evolution of interface designs and algorithms within the research community. Overall, the proposed content-based recommender system offers a promising solution for delivering personalized movie recommendations while advancing the state of the art in recommendation technology. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bag-of-words Cosine similarity Filtering system Recommender system TF-IDF

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：