检索结果-内蒙古大学图书馆

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Kancharla Nagababu S. Ananthi Neeraj Sunheriya Venkata Siva Prasad Ch J. Jayanthi Hamed Fawareh Department of Computer Applications Aditya University Department of CSE St. Joseph's College of Engineering Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Department of ECE Jeppiaar Engineering College Chennai-119 Department of CSE Sona College of Technology Salem Software Engineering Dept Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The capacity to individually identify and categorize people across sites and apps is vital for trustworthiness, fraud prevention, and personalized experiences in online social networking. In this study, strategies for platform identification among similar and unknown social networking users are evaluated. We study strategies that employ user attributes, behavior history, and inter-network connections to match profiles on multiple platforms and uncover new, previously connected people. This cross-validation on the proposed method uses Social Linkage Identification Strategy (SLIS) and Friend Relationship Evaluator. According to quantitative experiment results, our approach improves search people across multiple social networks more than FRE. The extensive social connection web in many online social networks is used to enhance user identification and verification via the Friend Relationship Evaluator (FRE) system. Our process uses advanced machine learning and data fusion to handle a wide variety of natural ventilation phenomena from different sensors and platform formats. We evaluate attribute-based matching, graph approaches, and behavior analytics for accuracy, scalability, and computing cost. This study advances user identification systems across digital platforms and helps service providers and end-users establish more sophisticated online identity management strategies.

关键词： Couplings Accuracy Social networking (online) Scalability Sensor phenomena and characterization Sensor fusion Ventilation User experience Protection Standards

来源：评论

学校读者我要写书评

暂无评论

Data Analytics for Core Temperature Estimation in Battery Management System for Electric and Hybrid Vehicles

Data Analytics for Core Temperature Estimation in Battery Ma...

引用

International Conference on Energy, Power and Environment: Towards Sustainable Growth (ICEPE)

作者： Ahilya Chhetri Sumukh Surya Mohan Krishna S Vidya Rao Engineering and Technology Cactus Communications Mumbai India Bosch Global Software Technologies Pvt. Limited Bengaluru India Department of Electrical and Electronics Engineering ACED Alliance University Bengaluru India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Compared to conventional means of transport thatuse fossil fuels, electric vehicles are known to reduce pollution levels as they take power from renewable sources of energy stored in energy storage devices like batteries and fuel cells. Core temperature estimation of batteriesis extremely important inbattery management systems for preventing thermal runaway and ensuring safe operation. In this study, core temperature is estimated using a Kalman filter for two different battery chemistries viz; lithium polymer and lithium iron phosphate using a second-order thermal model. Further, a linear regression model is applied to verify the prediction over the trained and tested dataset. The lithium iron phosphate prediction curvehad a fit of approximately 82-83%, whilelithium polymerhad a fit of 72-82% during the charging and discharging of OCV-SOC variation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Approaches for Accurate Brain Tumor Detection in MRI Images

Deep Learning-Based Approaches for Accurate Brain Tumor Dete...

引用

Decision Aid Sciences and Application (DASA), International Conference on

作者： Mohammed Noori Mohsin Ahmed Amer Ibrahim Ali Saeed Mohammad Khishe Mahmoud Mahfuri Al-ma'moon University College Baghdad Iraq Department of Computer Science and Software Engineering College of Information Technology Computer Center Northern Technical University Ninevah Iraq Innovation Center for Artificial Intelligence Applications Yuan Ze University Taiwan Jadara research center Jadara University Jordan Computer and information Technology Department International University for Science and Technology

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

Brain tumor classification is considered one of the major tasks in medical image analysis, where correct and timely diagnosis could be achieved to serve as the key to effective treatment. This research paper proposes a deep learning-based approach for automatic classification of brain tumors from MRI images by fine tuning the ResNet50V2 CNN model. The dataset is made up of four classes, namely: Glioma Tumor, Meningioma Tumor, No Tumor, and Pituitary Tumor, totaling 2,844 images. We have done some strategy data augmentation and class weighting in order to prevent class imbalance, which ensures good performance in all tumor classes. Pre-processing and augmentation of the input images are done via rotation, shifting, zooming, and flipping. It yielded 95.29% on the validation set, with the major highlights of performance metrics for the minority class being class precision equal to 0.97 and class recall equal to 0.92, hence proving the efficiency of performed class balancing. The range of F1-scores, from 0.93 to 0.97, means fantastic predictive capability across all tumor types. Other techniques were also used to make this model optimal, such as early stopping, learning rate reduction, and checkpointing. The high performance of this model shows great promise in helping clinicians toward the right diagnosis of brain tumors in an effective way. Future efforts will involve incorporating larger datasets, exploring advanced augmentation techniques to enhance further model generalizability. Model explainability tools such as Grad-CAM will be used to extract insight into the model's decision-making process. This enhances the clinical interpretability of the results.

关键词： Accuracy Magnetic resonance imaging Decision making Brain tumors Predictive models Brain modeling Data augmentation Data models Optimization Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Client Segmentation and Customization in E-Commerce: applications of Machine Learning from a Management Perspective

Client Segmentation and Customization in E-Commerce: Applica...

引用

Communication, computer Sciences and engineering (IC3SE), International Conference on

作者： Sriprasadh K Shamik Palit B Pravallika Manjunatha Reena Lenka Atul Singla Department of Computer Science and Applications Faculty of Science and Humanities SRM Institute of Science and Technology Vadapalani Chennai Department of Computing Science and Software Engineering RAK Campus University of Stirling UAE Institute of Aeronautical Engineering Hyderabad Department of Mechanical Engineering New Horizon College of Engineering Bangalore Symbiosis Institute of Management Studies Symbiosis International (Deemed) University Pune Lovely Professional University Phagwara India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

A machine learning-based e-commerce personalised recommendation system helps address the issue of information overload that inevitably arises when consumers have more and more options in e-commerce, leading to an increasingly complex structure. Customer segmentation is a crucial component of contemporary marketing strategy since it enables companies to effectively adjust their advertising campaigns and customise their communications with customers. Through the analysis of enormous quantities of consumer behaviour data and the discovery of trends that can be utilised for dividing customers into segments, ML algorithms provide a potent tool for automating the procedure of customer segmentation. We report our research and results for identifying a customer's segment. In order to perform machine learning, we integrate the Python Tensorflow library with Pandas for manipulating data frames. To address any discrepancies or gaps in the collected client data, it is refined. Key features are found, and to find hidden patterns and relationships, an exploratory analysis of the data is done. After that, we decide on a suitable machine learning technique to divide the clientele into various groups. We also experiment with several clustering models, including conventional machine learning techniques.

关键词： Consumer behavior Social networking (online) Machine learning Companies Market research Real-time systems Libraries

来源：评论

学校读者我要写书评

暂无评论

Robust frequent directions with application in online learning

arXiv

引用

arXiv 2017年

作者： Luo, Luo Chen, Cheng Zhang, Zhihua Li, Wu-Jun Zhang, Tong Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China National Engineering Lab for Big Data Analysis and Applications School of Mathematical Sciences Peking University 5 Yiheyuan Road Beijing100871 China National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Department of Computer Science and Technology Nanjing University 163 Xianlin Avenue Nanjing210023 China Computer Science & Mathematics Hong Kong University of Science and Technology Hong Kong

The frequent directions (FD) technique is a deterministic approach for online sketching that has many applications in machine learning. The conventional FD is a heuristic procedure that often outputs rank deficient matrices. To overcome the rank deficiency problem, we propose a new sketching strategy called robust frequent directions (RFD) by introducing a regularization term. RFD can be derived from an optimization problem. It updates the sketch matrix and the regularization term adaptively and jointly. RFD reduces the approximation error of FD without increasing the computational cost. We also apply RFD to online learning and propose an effective hyperparameter-free online Newton algorithm. We derive a regret bound for our online Newton algorithm based on RFD, which guarantees the robustness of the algorithm. The experimental studies demonstrate that the proposed method outperforms state-of-the-art second order online learning algorithms. Copyright © 2017, The Authors. All rights reserved.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

Optimal computerized model for designing cellular manufacturing systems using neural network

引用

Journal of Applied Sciences 2011年第15期11卷 2837-2842页

作者： Mukattash, Adnan Idwan, Sahar Ashhab, Moh'd Sami Samhouri, Murad Matar, Izzeddin A. Department of Industrial Engineering The Hashemite University P.O. Box 150459 Zarqa 13115 Jordan Department of Computer Science and Applications The Hashemite University P.O. Box 150459 Zarqa 13115 Jordan Department of Mechanical Engineering The Hashemite University P.O. Box 150459 Zarqa 13115 Jordan Department of Software Engineering Faculty of Information Technology Petra University Queen Alia International Road P.O. Box 961343 Amman 11196 Jordan

In this study, a computerized model has been developed to obtain the optimal distribution of the machines on three cells based on Artificial Neural Network (ANN's). These networks rely on the historical input-output data to learn input output implicit mapping. They are trained using back propagation algorithm. Comparing the results with those in the literature, it has been proved that the artificial neural network is superior in finding all the possible optimal solution (s) since it gives the minimum sum of voids and/or exceptions for all the possible ways of forming three cells from n machines. Taking all the possible ways of forming the cells is of great advantage since;it will provide the designer with more flexibility. An important feature of the optimization model is that it finds the solution fast regardless the number of machines and parts. The distinct superiority of the proposed model is that, machine cells and part families are identified and done concurrently which will decrease the computational time. Results are verified with the aid of computer simulation. © 2011 Asian Network for Scientific Information.

关键词： Cellular manufacturing

来源：评论

学校读者我要写书评

暂无评论

A FAST HEURISTIC FOR LOOP PARALLELIZATION

引用

Parallel Processing Letters 1994年第3期4卷 281-299页

作者： RICHARD J. ANDERSON BARBARA B. SIMONS Department of Computer Science and Engineering University of Washington USA This work supported by NSF Presidential Young Investigator Award CCR-86-57562 and NSF/Darpa grant CCR-8907960. Applications Development Technology Institute IBM Software Solutions Division M24/E254 555 Bailey Road San Jose CA 95141 USA

We present a fast loop parallelization heuristic that assigns separate invocations of a loop to different processors. If the loop contains data dependences between iterations, later iterations can be delayed while awaiting a result computed in an earlier iteration. In this paper we study a scheduling problem, called the Delay Problem, that approximates the problem of minimizing the delay in the start time of loops with loop-carried dependences. Our major result is a fast (O(n log 2 n)) time algorithm for the case where the precedence constraints are a forest of in-trees or a forest of out-trees. Since most graphs for the Delay Problem that arise in practice are sparse and consist of such a forest with possibly a few additional edges, this is an important case. We prove that the Delay Problem becomes NP-Complete when the precedence constraints are a set of arbitrary trees. We also prove that the Delay Problem becomes NP-Complete for independent chains when it is generalized to allow either non-unit execution times or release times and deadlines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-Based Feature Selection for Accurate Breast Cancer Classification

Genetic Algorithm-Based Feature Selection for Accurate Breas...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Attia Shabbir Raja Hashim Ali Muhammad Zeeshan Shabbir Zain Ul Abideen Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Muhammad Imad Muhammad Abu Bakar Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany Department of Electrical Engineering University of Engineering & Technology (UET) Lahore Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Leioa Basque Country Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

Breast cancer is a significant global healthcare challenge, particularly in developing and underdeveloped countries, with profound physical, emotional, and psychological consequences, including mortality. Timely diagnosis and accurate treatment are crucial in addressing this issue. We propose the utilization of a feature selection technique to identify the most relevant features from among all features for breast cancer diagnosis, and show that Genetic Algorithms are impressive for this task. The study compares the results of GA with no selection and an alternative method, Principle Component Analysis (PCA). Three machine learning models, all based on supervised learning with data split into training and test data, are employed for binary classification using the selected feature subset. The evaluation metrics employed encompass accuracy, precision, recall, and F1-score. Among the selected models, Random Forest demonstrates the most favorable outcomes, achieving an accuracy score of 0.96, precision score of 0.96, recall value of 0.98, and an F1-score of 0.97. These results underscore the effectiveness of GA in feature selection for breast cancer diagnosis. Consequently, the integration of Genetic Algorithms (GA) with Random Forest showcases the superior performance among the evaluated models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving reliability redundancy allocation problems with orthogonal simplified swarm optimization

Solving reliability redundancy allocation problems with orth...

引用

International Joint Conference on Neural Networks

作者： Wei-Chang Yeh Vera Yuk Ying Chung Yun-Zhi Jiang Xiangjian He Department of Industrial Engineering and Engineering Managemen National Tsing Hua University Hsinchu 300 Taiwan School of Information Technology University of Sydney NSW 2006 Australia School of Software Jiangxi Agricultural University Nanchang China 330045 School of Software Engineering South China University of Technology Guangzhou China 510006 Computer Vision and Recognition Laboratory Research Centre for Innovation in IT Services and Applications (iNEXT) University of Technology Sydney (UTS) PO Box 123 Broadway NSW 2007 Australia

ISBN: (纸本)9781479919611

This study applies a penalty guided strategy and the orthogonal array test (OA) based on the Simplified Swarm Optimization algorithm (SSO) to solve the reliability redundancy allocation problems (RRAP) in the series system, the series-parallel system, the complex (bridge) system, and the overspeed protection of gas turbine system. For several decades, the RRAP has been one of the most well known techniques. The maximization of system reliability, the number of redundant components, and the reliability of corresponding components in each subsystem have to be decided simultaneously with nonlinear constraints, acting as one difficulty for the use of the RRAP. In other words, the objective function of the RRAP is the mixed-integer programming problem with the nonlinear constraints. The RRAP is of the class of NP-hard. Hence, in this paper, the SSO algorithm is proposed to solve the RRAP and improve computation efficiency for these NP-hard problems. There are four RRAP problems used to illustrate the applicability and the effectiveness of the SSO. The experimental results are compared with previously developed algorithms in literature. Moreover, the maximum-possible-improvement (MPI) is used to measure the amount of improvement of the solution found by the SSO to the previous solutions. According to the results, the system reliabilities obtained by the proposed SSO for the four RRAP problems are as well as or better than the previously best-known solutions.

关键词： Reliability Redundancy allocation problem RRAP Simplified Swarm Optimization algorithm SSO Mixed-integer nonlinear programming

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：