检索结果-内蒙古大学图书馆

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Mishra, Annu Chaturvedi, Ravi Prakash Sharma, Hirdesh Kumar, Prashant Asthana, Sameer Parashar, Mayank Sharda School of Engineeringand Technology Department of Computer Science and Engineering Greater Noida India Sharda School of Engineeringand Technology Department of Computer Science and Applications Greater Noida India JEMTEC Department of Computer Science and Engineering Greater Noida India ITS Engineering College Department of Computer Science and Engineering Greater Noida India GNIOT Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350378092

The learning rate of a CNN determines the efficiency of the neural network. In brain tumor detection, the learning rate and the optimization function plays a key role in deciding the final output. The Optimized Stochastic Gradient Descent (OSGD) optimizer giver better result in terms of Accuracy, Recall and other determining factors. We have also compared the results obtained with other optimizers and it could be clearly stated that our proposed model. The OSGD optimizer controls the maxima and minima, and move the near optimum solution buy controlling the learning rate. So via this method we can control our right *** we detect our object in les error. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

GraphXAI: a survey of graph neural networks (GNNs) for explainable AI (XAI)

引用

Neural Computing and applications 2025年第17期37卷 10949-11000页

作者： Nandan, Mauparna Mitra, Soma De, Debashis Department of Computer Applications Techno Main Salt Lake West Bengal Kolkata India Department of Computational Science Brainware University West Bengal Barasat India Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology West Bengal West Bengal Kolkata India

Graphs find wide applications in numerous domains, ranging from simulating physical systems to learning molecular fingerprints, predicting protein interfaces, diagnosing diseases, etc. These applications encompass simulations in non-Euclidean space, in which a graph serves as an ideal representation, and are also an indispensable means of illustrating the connections and interdependencies among its various constituents. Graph neural networks (GNNs) are specific types of neural networks that are specifically built to handle data possessing a graph structure. They are highly effective at capturing intricate relationships among different entities. Nonetheless, their "black-box" characteristics pose difficulties in transparency, trust, and interpretability, especially in critical sectors like heath care, banking, and autonomous systems. Explainable artificial intelligence (XAI) has emerged to clarify these obscure decision-making processes, thus enhancing trust and accountability in AI systems. This survey paper delves into the intricate interplay between GNNs and XAI, including an exhaustive taxonomy of the various explainability methods designed for graph-structured data. It classifies the existing explainability methods into post hoc and self-interpretable models. The paper analyzes their practical applications in diversified fields, highlighting the significance of transparent GNNs in essential sectors such as fraud detection, drug development, and network security. The survey also delineates evaluation parameters for assessing explainability along with addressing persistent issues in scalability and fairness. The paper concludes by addressing prospective advancements in the subject, including the creation of innovative XAI methodologies tailored for GNN architectures, integration with federated learning, and utilization of these models in interdisciplinary fields. This study bridges the gap between GNNs and XAI, providing an essential resource for researchers and p

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An Emperical Analysis of Machine Learning Algorithms for Used Car Price Prediction System

An Emperical Analysis of Machine Learning Algorithms for Use...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Bhatt, Nirav Sanjay Nath Pandey, Trilok Reddy, Suravaram Rishabh Jayasurya, B. Dash, Bibhuti Bhusan Shekhar Patra, Sudhansu Vellore Institute of Technology School of Computer Science and Engineering Chennai India Kiit Deemed to Be University School of Computer Applications Bhubaneswar India

ISBN: (纸本)9798350308167

The market for used cars is a dynamic and ever-expanding industry, with various factors influencing the pricing of pre-owned vehicles. Accurate pricing is crucial for both buyers and sellers, as it ensures fair transactions and minimizes the risk of financial loss. This paper introduces a machine learning algorithms developed for the purpose of predicting used car prices based on a comprehensive set of features. Various machine learning (ML) techniques such as multiple linear regression, ridge regression, lasso regression, Bayesian regression, Decision tree regression, random forest regression, eXtreme Gradient Boost (XGB) regression, Light Gradient Boosting Machine (LGBM) regression, Gradient boosting regression and Multilayer Perceptron (MLP) regression. To assess the algorithm's performance, rigorous evaluation metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared (R2) score has been employed. © 2023 IEEE.

关键词： ANN Bayesian Regression Decision Tree Regression Lasso Regression LGB Linear Regression MLP Random Forest Regression Ridge Regression XGB

来源：评论

学校读者我要写书评

暂无评论

5G in Smart Cities: Enhancing Urban Futures for Sustainable Growth

5G in Smart Cities: Enhancing Urban Futures for Sustainable ...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Rajvanshi, Anita Mahajan, Prerna Singh, Alka Tula's Institute Department of Computer Science and Engineering Dehradun India Department of Computer Bangalore India Noida Institute of Engineering and Technology Computer Applications Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350357769

This essay delves into the concept of 'Smart Cities,' outlining its numerous benefits. It elucidates the diverse applications and services essential for transforming a city into a Smart City, underscoring the pivotal role of Information and Communication Technology (ICT) in their realization. Furthermore, it scrutinizes the challenges posed by the deployment of Smart Cities for contemporary ICT systems. The study investigates the promised attributes of 5G technology and its potential as a linchpin for the efficient implementation of urban smart cities. Additionally, it provides a catalog of 5G-enabled Smart City use cases, emphasizing how 5G will serve as the bedrock for the Internet of Things (IoT), fostering the evolution of smart cities. © 2023 IEEE.

关键词： 5G technology ICT infrastructure Information and Communication Technology Internet of Things Quality of Life Smart Cities Smart ICT infrastructure Sustainable City Urban Transit and City Governance

来源：评论

学校读者我要写书评

暂无评论

Analysis of Educational Recommender System Techniques for Enhancing Student's Learning Outcomes 3

Analysis of Educational Recommender System Techniques for En...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Pal, Neeti Dahiya, Omdev School of Computer Applications Lovely Professional University Jalandhar India School of Computer Science and Engineering Lovely Professional University Jalandhar India

ISBN: (纸本)9798350336238

Recommender System was widely used in commercial websites for the past few years. These systems track past activities of customers and recommend them the relevant items. The emergence of E-learning activities over a few decades develops a variety of E-learning content available for virtual learning environments (VLE). A large amount of learning objects is present in E-learning repositories. Dealing with problems of the diversity of data, Educational Recommender System (ERS) plays a vital role in the educational sector. Educational recommender systems track the learners' past activities, know the users' preferences, assist the educators and learners, provide relevant content to learners, and enhance their learning outcomes. A personalized recommender system will intensify the learners' interest in particular content and reduce the course dropout rate. The recommender system makes the decision-making process for choosing the appropriate content easy for learners. ERS uses various approaches and technologies for assisting the learners' and helps them to run their learning process smoothly. Collaborative filtering, Content-based, and knowledge-based are the basic techniques of recommender systems. The research shows that a combination of these approaches will give more effective and efficient results. This mixing of approaches refers to the hybridization techniques. Traditional approaches with deep learning networks will improve the recommendations and provide results with higher accuracy. This paper provides how E-learning support recommender systems produce recommendations using different techniques. The technical results of recommender techniques help to find the best approach for making a recommender system in the future. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Diagnostics Using Machine Learning Algorithms 5

Cervical Cancer Diagnostics Using Machine Learning Algorithm...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Chikaraddi, Ashok K. Kanakaraddi, Suvarna Kalwad, Priyadarshini Kadole, Atharv Budni, Shashikala Computer Applications K L E Technological University Karnataka Hubli India School of Computer Science and Engineering K L E Technological University Karnataka Hubli India

ISBN: (纸本)9798350361155

A rising number of people and businesses are using Deep Learning (DL) and Machine Learning (ML) to analyze vast volumes of data and provide insights that can be put to use. In medical practice, it is becoming more and more usual to use machine learning methods to predict major illnesses such as cancer, kidney failure, and heart attacks in their early stages. One of the most common illnesses affecting for women is cervical cancer, which may be prevented with an early diagnosis. As a result, this work considers suitable ML algorithms to detect cervical cancer. Predictive Model Selection (PMS), data pre-processing, are performed for the chosen dataset. A variety of traditional machine learning techniques, such as Decision Trees (DT), Logistic Regression (LR), Support Vector Machines (SVM), adaptive boosting, gradient boosting, random forest, K-Nearest Neighbors algorithm (KNN), and XG-Boost, are tested and reported in the PMS section. Regarding the prognosis of cervical cancer. In this work trained the dataset on three models, VGG16, Inception-v3, ResNet-50, and also developed and analyzed the performance of Ensemble model. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Prediction of Diabetes Using Machine Learning in the Healthcare System 5th

The Prediction of Diabetes Using Machine Learning in the Hea...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Deep, Ishaan Singh, Payaswini Senapati, Biswa Ranjan Swain, Rakesh Ranjan Nayak, Subrat Kumar Patra, Binaya Kumar University Odisha Bhubaneswar751030 India Department of Computer Science Engineering and Applications Indira Gandhi Institute of Technology Sarang Dhenkanal India

ISBN: (纸本)9789819719228

Diabetes has been increasing at an exponential rate in India in recent years, and it is expected to reach 537 million by 2030. Diabetes will also cause a large rise in a variety of other health issues. Many machine learning techniques are being employed to solve the problem of diabetes prediction. In this paper, the authors have considered two machine learning techniques, such as support vector machine (SVM) and logistic regression (LR) for diabetes prediction. The SVM accuracy was found to be 87% when eight independent parameters were used to predict it, whereas the logistic regression accuracy was 87.01%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Current Perspectives and Virtualisation solutions with SDN for IoT 2

Current Perspectives and Virtualisation solutions with SDN f...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Bhardwaj, Shanu Kumar, Shailender Girdhar, Ashish Department of Computer Science and Engineering Delhi Technological University Delhi India Department of Computer Science and Applications Kurukshetra University Kurukshetra India

ISBN: (纸本)9798350305418

During the past years, IoT has acquired a lot of consideration since it incorporates intelligent gadgets which empower many applications that work in our day-to-day existence. Due to this the rising number of clients and the interest in more different and specific applications have prompted a tremendous expansion in the network traffic. Managing different traffic requests from various applications is a difficult task for the current traditional networking architecture. Therefore, the paper provides a thorough analysis of the SDN and various other technologies-based network virtualization methods as well as current perspectives for the IoT. The representation provides the working of various up-going technologies such as Machine Learning, Edge Computing, and Virtualization with SDN to betray the performance of the SDN applications in today’s world. © 2023 IEEE.

关键词： edge computing internet of things machine learning network traffic software-defined networking

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Routing in Marine Communication Network of Fishing Vessels

引用

SN computer Science 2025年第1期6卷 1-12页

作者： Surendran, Simi Montresor, Alberto Vinodini Ramesh, Maneesha Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri Kollam India Department of Information Engineering and Computer Science University of Trento Trento Italy Amrita Center for Wireless Networks & Applications (AmritaWNA) Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri Kollam India

The lack of affordable communication facilities to the shore remains a fundamental problem for fishermen engaged in deep-sea fishing. The Offshore Communication Network (OCN) is a wireless network of fishing vessels, whose goal is to provide Internet over the ocean. However, the dynamic nature of OCNs characterized by extreme weather, the difficulty of deploying additional infrastructure, wave-induced vessel movements, and high mobility causes significant challenges for traditional routing protocols. This paper proposes OCN-AR, a Q-learning-based adaptive routing strategy for ocean networks. The quality of the learning process relies on the reward function, which has been carefully designed to incorporate the most important features, including real-time forecasts of connectivity quality, path probability, link availability duration, and distance to the destination. The routing performance is evaluated through extensive simulations conducted under diverse conditions, including varying mobility scenarios, transmission rates, vessel rocking intensities, and node densities, and is compared against traditional protocols. The results demonstrate that OCN-AR significantly outperforms existing routing approaches, making it a reliable solution for maritime communication. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fishing vessel network Marine communication network Reinforcement learning Routing protocol

来源：评论

学校读者我要写书评

暂无评论

Towards Seamless Integration of AI-Driven Agents in Video Games: Techniques, Challenges, and Implications 3

Towards Seamless Integration of AI-Driven Agents in Video Ga...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Tyagi, Vishal Gundecha, Harshada Manipal University Jaipur Department of Computer Applications Jaipur India PVG'S Coet Department of e & Tc Engineering Pune India

ISBN: (纸本)9798350384598

The integration of AI-driven agents in video games enhances gameplay automation and player experience. This research leverages a custom-trained object detection model op-timized for low-latency performance to automate tasks such as aiming and uses dead reckoning for player movement prediction. An Arduino-based system is implemented for real-time command transmission, facilitating interaction between the AI agent and the game environment. Experiments demonstrate precise aiming and responsive gameplay, showcasing the potential to improve player experience and automate testing processes. Ethical considerations regarding AI deployment in competitive gaming emphasize the importance of fair play and integrity. Our findings advance AI technology in gaming and offer valuable insights for industry stakeholders. © 2024 IEEE.

关键词： Object detection

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：