检索结果-内蒙古大学图书馆

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Sarisa, Hemanth Kumar Khurana, Varun Koti, Venkat Chandu Garg, Neha Manav Rachna International Institute of Research and Studies Department of Computer Science & Engineering India

ISBN: (纸本)9798350344387

Loan prediction is a significant problem in the banking industry. Using Technology, will change and make some improvements in Loan prediction by bank employees manually. By using "Machine learning "in loan prediction. The machine learning system will check the data for a loan of the applicant and the data will be checked so fast and without any human error. So, it will help to improve technology in Bank sectors. By this, processing the data will be checked quickly, making the data output in less time. It helps both the applicant and the bank *** learning algorithms can be used to analyze historical data and make accurate predictions about whether a loan application will be approved or not. In this study, we propose a machine learning-based loan prediction model that utilizes various features such as credit score, income, loan amount, and loan term. We explore different classification algorithms, including logistic regression, decision tree, and random forest, to build the loan prediction model. Our experimental results show that the random forest algorithm outperforms other models with an accuracy rate of 83.45%. The proposed model can help banks and financial institutions streamline their loan approval process, reduce manual effort, and minimize the risk of bad loans. © 2023 IEEE.

关键词： Data Pre-Processing Decision Tree K-Neighbours Classifier Machine Learning Python Random Forest Classifier

来源：评论

学校读者我要写书评

暂无评论

pFedES: Generalized Proxy Feature Extractor Sharing for Model Heterogeneous Personalized Federated Learning 39

pFedES: Generalized Proxy Feature Extractor Sharing for Mode...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yi, Liping Yu, Han Ren, Chao Wang, Gang Liu, Xiaoguang Li, Xiaoxiao College of Computer Science TMCC SysNet DISSec GTIISC Nankai University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

ISBN: (纸本)157735897X

Federated learning (FL), as a privacy-preserving collaborative machine learning paradigm, has attracted significant interest from industry and academia. To allow each data owner (FL client) to train a heterogeneous and personalized local model based on its local data distribution, system resources and requirements on model structure, the field of model-heterogeneous personalized federated learning (MHPFL) has emerged. Existing MHPFL approaches either rely on the availability of a public dataset with special characteristics to facilitate knowledge transfer, incur high computational and communication costs, or face potential model leakage risks. To address these limitations, we propose a model-heterogeneous personalized Federated learning approach based on generalized proxy feature Extractor Sharing (pFedES) for supervised image classification tasks. (1) We devise a shared small proxy homogeneous feature extractor before each client’s heterogeneous local model. (2) Clients train them via the proposed iterative learning to enable the exchange of global generalized knowledge and local personalized knowledge. (3) The small proxy local homogeneous extractors produced after local training are uploaded to the server for aggregation to facilitate knowledge fusion across clients. We theoretically prove pFedES converges with a non-convex convergence rate O(1/T). Experiments on 3 benchmark datasets against 9 baselines demonstrate that pFedES performs state-of-the-art model accuracy while maintaining efficient communication and computation. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based AI Solutions for Personal Finance Management

Cloud-Based AI Solutions for Personal Finance Management

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Chhabra, Gurpreet Kaur Mishra, Ashutosh Kumar Tyagi, Varsha Mani, Chandra Tyagi, Vani Sagar, Pramod Kumar Management Education and Research Institute Department of Management Delhi India Srm Business School Department of Management UP Lucknow India Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Mangalmay Institute of Engineering & Technology Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798331508685

Cloud-based AI answers for private finance control are out-of-the-field tools that leverage synthetic intelligence and cloud computing technologies to manage people's money higher. In this article, I have described various solutions with features ranging from budgeting to personalized financial planning and investment suggestions. Utilizing superior system learning algorithms and cloud-based AI solutions can help understand an individual's fiscal information, including expenses, profits, or savings transactions, for generating personalized insights and advice. This lets people learn about their spending habits and make more informed financial choices. Through the power of the cloud, these solutions can securely store and access financial data from multiple devices, which helps individuals, manage their finances on the go easily. It also enables the client to get real-time updates and notifications, which offers him more comprehensive knowledge regarding his existing financial scenario. These offerings also come with more automation features like reminders to pay payments and computerized enough transfers for a price range, keeping customers from spending further effort and time on their funds. They also offer financial advisors, tax planning tools, and wealth management. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Enhancement of mechanical properties in AA5083 aluminum metal matrix composites through alumina and titanium carbide reinforcement

引用

Interactions 2024年第1期245卷 1-12页

作者： Vadivel, M. Seenivasan, S. Satishkumar, P. Gomkale, Shruti Saminathan, Rajasekaran Department of Civil Engineering Nehru Institute of Technology Tamilnadu Coimbatore India Department of Mechanical Engineering Rathinam Technical Campus Tamilnadu Coimbatore India Applied Chemistry Yeshwantrao Chavan College of Engineering Maharashtra Nagpur India Department of Mechanical Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia

As a result of its remarkable resistance to corrosion, strong wear resistance, high strength, and low weight, aluminum metal matrix composites (AMMC’s) have garnered tremendous widespread recognition for structural and aeronautical applications. Several mechanical properties of aluminum alloy (AA5083) are examined in this experimental study, which focuses on the impact of reinforcing particles (alumina and titanium carbide). The stir casting method was used to manufacture AMMC. Fabrication was carried out using the less difficult ex-situ approach. Reinforcement particle weight percentages ranging from 4 to 12% were used in the MMC preparation process. Machine operations were performed on the ingots following manufacturing in order to prepare test samples. To investigate the mechanical and tribological properties and effects of different reinforcement weight percentages, tests were conducted including tensile, compression, impact, hardness and wear tests. Adding alumina and titanium carbide resulted in a gradual rise of the tensile and compression strengths. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Aluminum corrosion

来源：评论

学校读者我要写书评

暂无评论

Precision Forecasting of Stock Prices: Leveraging XGBoost and Technical Indicator for Advanced Predictive Modeling 1

Precision Forecasting of Stock Prices: Leveraging XGBoost an...

引用

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

作者： Yuvaraj, S. Chenni Kumaran, J. Vinston Raja, R. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

The investigation aims to evaluate the performance of machine learning techniques, particularly the XGBoost regression method, for stock price prediction with the help of technical indicators. The research targets the adjusted closing price to reduce the autocorrelation problem in time series. The Five Days and Ten Days Exponential Moving Averages (EMA-5 and EMA-10) are involved in refining feature selection. The performance of the model was evaluated using different error metrics, namely, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). The results indicate that the XGBoost model, combined with EMA-5 and EMA-10, achieves high predictive performance, obtaining an r2 value of 0.98. It implies that incorporating short-term EMAs into advanced machine learning techniques drastically improves stock price forecasting. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Node Velocity on Communication Overhead and Energy Consumption in WSNs Using Fuzzy Clustering

Exploring the Impact of Node Velocity on Communication Overh...

引用

2024 International Conference on Advances in computing research on science engineering and Technology, ACROSET 2024

作者： Sharma, Dilip Kumar Yadav, Aaditya Patidar, Mukesh Patil, Pooja Sanjay Patidar, Praveen Kumar Mandloi, Devendra Singh Sheikh, Rashid Rajpoot, Shivshankar Ujjain Engineering College Department of Electronics and Communication Engineering Ujjain India Piet Parul University Department of Computer Science and Engineering Vadodara India Credit Acceptance Financial Institution in Southfield Michigan United States Parul Institute of Technology Parul University Department of Computer Science & Engineering Vadodara India Indore Institute of Science and Technology Department of Electronics and Communication Engineering Indore India Acropolis Institute of Technology and Research Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798350388800

Clustering, an unsupervised machine learning technique with numerous practical applications, has received a great deal of research attention. Along with deterministic and probabilistic approaches, fuzzy C-means clustering (FCM) is commonly employed. Over time, improvements to the FCM approach have been implemented to improve clustering efficiency. In this paper, we perform the results of communication overhead, energy consumption, and link distance travel in WSN with different velocities for the clustering-based protocol. In this performance, we are considering the number of nodes in the networks as 100, 175, and 200, having considered the start node as five using fuzzy clustering methodology in the unsupervised ML technique. In the communication overhead result analysis, we observed that the communication overhead increases as the nodes velocity increases, and another case of energy consumption also increases with the rising trend as node velocity increases. The results presented in this paper have been simulated using the Matlab R2020a tool. © 2024 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN 2

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Krishna, Tiruveedula Gopi Sreenivas, Nune Ajay Kumar, M. Reddy, Chandra Sekhar Rathee, Davinder Sing Urgessa, Teklu College of Electrical Engineering and Computing Adama Science and Technology University Department of Computer Science and Engineering Adama Ethiopia Andhra Loyala institute of Engineering and Technology Department of Electrical and Electronics Engineering Vijayawada India College of Electrical Engineering and Computing Adama Science and Technology University Department of Electrical Power and Control Engineering Adama Ethiopia College of Electrical Engineering and Computing Adama Science and Technology University Department of ECE Adama Ethiopia

ISBN: (纸本)9798331505745

The research presents a new efficient machine learning method to classify brain tumors because this task remains vital in fighting the high incidence of brain cancers. The proposed approach unites all its operations including image segmentation with feature extraction and classification into a single processing system. This study uses Particle Swarm Optimization (PSO) and Adaptive PSO (APSO) methodologies to optimize Locally Linear Radial Basis Function Neural Network (LLRBFNN) resulting in PSO-LLRBFNN and APSO-LLRBFNN model implementations. The research examined the optimized APSO-LLRBFNN models against Support Vector Machines (SVM) and Least Mean Squares (LMS) based LLRBFNN classifier methods. Results from experiments show that APSO-LLRBFNN gives superior outcomes with 98.93% accuracy and takes 12.23 seconds for execution, which surpasses currently available methods. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Challenges in Recycling Lead Acid Battery and Lithium-Ion Battery: A Comprehensive Review

Challenges in Recycling Lead Acid Battery and Lithium-Ion Ba...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Anuradha, S. Manimegalai, R. Devasena, M. PSG Institute of Technology and Applied Research Department of Computer Science Coimbatore India Indian Institute of Technology Global Sanitation Centre of Excellence Palakkad India

ISBN: (纸本)9798350378177

Battery recycling has become essential due to the rising demand for batteries and the associated risk to the environment caused by the disposal of batteries in various industries. It has become a global concern to recover significant minerals and metals from discarded batteries. The rapid expansion of the electric vehicle market causes a significant challenge in managing battery waste where Lithium-ion batteries (LIBs) are used. Lithium-ion batteries are the best alternative to energy storage devices, which encourages the development of electric vehicles, which in turn reduces greenhouse gas emissions (GHG) pollution in the transportation sector. 28 % of greenhouse gas emissions and 24% of the world's energy consumption are due to the transportation industry globally. The increasing usage of LIBs can result in the accumulation of spent LIBs. To prevent improper disposal of battery waste, recycling approaches can be adopted, which can in turn help reduce landfill waste and enhance environmental quality. This study compares the difficulties of recycling Lead Acid Battery (LAB) and Lithium-Ion Battery (LIB) wastes, emphasizing the need to implement efficient battery recycling procedures towards a circular economy. © 2024 IEEE.

关键词： Land fill

来源：评论

学校读者我要写书评

暂无评论

Multi-Criteria Decision-Making for Energy Management in Smart Homes Using Hybridized Neuro-Fuzzy Approach

引用

Distributed Generation and Alternative Energy Journal 2024年第1期39卷 83-109页

作者： Anbazhagu, U.V. Koti, Manjula Sanjay Muthukumaran, V. Geetha, V. Munrathnam, Meram Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Kattankulathur TN Chennai India Department of MCA Dayananda Sagar Academy of Technology and Management Bangalore560082 India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur Campus 603 203 India Department of Computer Science School of Applied Sciences REVA University Bangalore India Department of Mathematics Rajiv Gandhi University of Knowledge Technologies R.k.Valley Idupulapaya Andhra Pradesh Kadapa516330 India

The necessity for smart energy oversight solutions has arisen in response to the rising popularity of energy-efficient home automation and other energy-saving technologies. Optimizing smart home energy use using multi-criteria decision-making (MCDM) is a proven methodology. However, the procedure for making decisions and MCDM’s capacity to handle various criteria are typically limiting factors. Hybrid methods, which integrate multiple decision-making approaches like Fuzzy Logic (FL) and Modular Neural Networks (MNN), could potentially be able to circumvent these restrictions and boost energy management systems’ efficacy and precision. This investigation presents a hybrid Neuro-Fuzzy (H-NF) method for MCDM in regulating energy for smart homes by combining FL with an MNN. The suggested approach would optimize energy use in smart homes by considering several parameters, notably cost, ease of use, and environmental effects. In addition, this study aims to examine how the H-NF model fares in comparison to other methods of making important decisions in terms of several performance metrics. The suggested hybridized approach has the potential to deliver more precise and effective decision-making processes for energy management in smart homes, allowing users to optimize their energy consumption while preserving comfort and lowering environmental impact. © 2024 Taylor and Francis Inc.. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Approach Based on Logistic Regression in Machine Learning 7th

Fake News Detection Approach Based on Logistic Regression in...

引用

7th International Conference on Information and Communication Technology for Competitive Strategies, ICTCS 2022

作者： Sudhakar, M. Kaliyamurthie, K.P. Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India

ISBN: (纸本)9789811993039

Today, social media is allowing everyone to spread information without any cost, and only a few people will do the small investigation and fewer filters than before. Political events are one of the increases in the popularity and spread of fake news. The increasing of fake news is the major problem of today and will negatively impact the world. To avoid this type of bogus information spreading worldwide, we can use artificial intelligence and machine learning. Recently, deep learning techniques used complex natural language processing also to providing the solution for counterfeit news detection. Facebook is using AI techniques to filter the fake news stories from the user feeds. Now it is possible using the Naïve Bayes classifier to differentiate between fake news and real news. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Logistic regression

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：