检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Panchal, Aneesh Khan, Kainat Katarya, Rahul Department of Computational and Data Sciences Indian Institute of Science Karnataka Bangalore560012 India Big Data Analytics and Web Intelligence Laboratory Department of Computer Science & Engineering Delhi Technological University Delhi110042 India

Autism Spectrum Disorder (ASD) is a chronic neurodevelopmental disorder symptoms of which includes repetitive behaviour and lack of social and communication skills. Even though these symptoms can be seen very clearly in social but a large number of individuals with ASD remains undiagnosed. In this paper, we worked on a methodology for detection of ASD from 3-dimensional walking video dataset, utilizing supervised machine learning (ML) classification algorithms and using nature-inspired optimization algorithms for feature extraction from dataset. The proposed methodology involve the classification of ASD using supervised ML classification algorithm and extracting important and relevant features from the dataset using nature-inspired optimization algorithms. We also included the ranking coefficients for finding the initial leading particle. This selection of particle significantly reduces the computation time and hence, improving the total efficiency and accuracy for the ASD detection. To evaluate the efficiency of the proposed methodology, we deployed various combination of classification algorithm and nature-inspired algorithms resulting in an outstanding classification accuracy of 100% using random forest classification algorithm and gravitational search algorithm for feature selection. The application of the proposed methodology with different datasets would enhance the robustness and generalizability of the proposed methodology. Due to high accuracy and less total computation time, the proposed methodology will offer a significant contribution to the medical and academia fields, providing a foundation for future research and advancements in ASD diagnosis. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

EXPLAINING THE PERFORMANCE OF COLLABORATIVE FILTERING METHODS WITH OPTIMAL data CHARACTERISTICS

arXiv

引用

arXiv 2023年

作者： Poudel, Samin Bikdash, Marwan Department of Computational Data Science and Engineering North Carolina A & T University Greensboro United States

The performance of a Collaborative Filtering (CF) method is based on the properties of a User-Item Rating Matrix (URM). And the properties or Rating data Characteristics (RDC) of a URM are constantly changing. Recent studies significantly explained the variation in the performances of CF methods resulted due to the change in URM using six or more RDC. Here, we found that the significant proportion of variation in the performances of different CF techniques can be accounted to two RDC only. The two RDC are the number of ratings per user or Information per User (IpU) and the number of ratings per item or Information per Item (IpI). And the performances of CF algorithms are quadratic to IpU (or IpI) for a square URM. The findings of this study are based on seven well-established CF methods and three popular public recommender datasets: 1M MovieLens, 25M MovieLens, and Yahoo! Music Rating datasets. © 2023, CC BY.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Churn Prediction in Telecommunication with CNN-Gradient Boosting Machine

Enhancing Customer Churn Prediction in Telecommunication wit...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Subaash, Sls Raajavinayaga Nimma, Divya Bala, B Kiran Khan, Shamim Ahmad Roy, Manidipa Rao, Vuda Sreenivasa Chennai India University of Southern Mississippi Data Analyst UMMC Computational Science United States K. Ramakrishnan College of Engineering Department of AI & DS Trichy India Glocal University Glocal School of Science & Technology U.P India ABES Engineering College Department of ECE Uttar Pradesh Ghaziabad India Koneru Lakshmaiah Education Foundation Department of CSE AP Vaddeswaram India

ISBN: (纸本)9798350369175

The telecommunications industry faces a constant challenge in retaining customers amidst fierce competition, making accurate churn prediction a critical aspect of business strategy. In this paper, we propose a novel hybrid model, implemented in Python, that combines Convolutional Neural Networks (CNNs) with Gradient Boosting Machines (GBMs) to enhance customer churn prediction accuracy. Leveraging a comprehensive dataset encompassing demographic details, service usage, payment information, and customer support interactions, our model extracts intricate patterns from the data using CNNs and integrates them with traditional features for robust prediction. Through extensive experimentation and evaluation, we demonstrate that our proposed CNN-GBM model achieves an outstanding accuracy of 99%, surpassing other existing approaches by $\mathbf{2.6 \%}$. The model's performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-Score, showcasing its superiority over traditional methods like Random Forest and Support Vector Machine. The CNN-GBM model's remarkable accuracy and superior performance highlight its efficacy in accurately identifying churned customers while minimizing false positives, thus providing a valuable tool for telecom companies to implement targeted retention strategies. Moreover, our methodology offers scalability and generalizability, making it applicable across industries facing similar churn challenges. Overall, our proposed hybrid CNNGBM model presents a significant advancement in customer churn prediction, offering telecom companies a reliable solution to improve customer retention and competitiveness in the market. © 2024 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Chronic Kidney Disease Prediction Through data Preprocessing Optimization and Machine Learning Techniques

Enhancing Chronic Kidney Disease Prediction Through Data Pre...

引用

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Akinyemi, Lateef Adesola Oshinuga, Olamide Peter Ekwe, Stephen Obono Oladejo, Sunday Oladayo University of South Africa Cset Department of Compt. Science & Electrical Engineering Johannesburg South Africa Lagos State University Department of Electronic and Computer Engineering Lagos Nigeria Cape Peninsula University of Technology Department of Elect. Electronic and Computer Engineering Cape Town South Africa School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (纸本)9798350327816

Health care is the improvement of health through the avoidance and cure of diseases. Chronic kidney disease (CKD) poses a substantial health issue, ranking as the eighth leading cause of death and the tenth leading cause of disability-adjusted life years for both genders. This research aims to utilize machine learning (ML) algorithms to accurately predict the presence of CKD, which affects people worldwide. Timely identification of CKD is crucial to prevent it from progressing to its final and most critical phase. Machine learning algorithms, such as Decision Tree (DT), Naïve Bayes (NB), and others, are used in this study for the prediction of CKD. Various health parameters such as age, albumin level, and more are used as input into each ML algorithm to predict the presence of CKD. data preprocessing is carried out to improve the quality of the data for more accurate prediction. The data is analyzed to uncover the connections between CKD health parameters and their impact on the occurrence of CKD. This research further examines the influence of different train and test data ratios on the accuracy of the employed algorithms. Evaluation metrics such as accuracy, sensitivity, and more are employed to gauge the effectiveness of each algorithm in making predictions. Random Forest stood out as the most accurate algorithm, with a score of 96.25%. Naive Bayes and XGBoost demonstrated the highest sensitivity, achieving a perfect score of 100%. © 2023 IEEE.

关键词： Chronic Kidney Disease (CKD) data Analysis data Preprocessing Health Care Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Co-linear Chaining with Overlaps and Gap Costs 26th

Co-linear Chaining with Overlaps and Gap Costs

引用

26th International Conference on Research in computational Molecular Biology, RECOMB 2022

作者： Jain, Chirag Gibney, Daniel Thankachan, Sharma V. Department of Computational and Data Sciences Indian Institute of Science Bangalore India School of Computer Science and Engineering Georgia Institute of Technology Atlanta United States Department of Computer Science University of Central Florida Orlando United States

ISBN: (纸本)9783031047480

Co-linear chaining has proven to be a powerful heuristic for finding near-optimal alignments of long DNA sequences (e.g., long reads or a genome assembly) to a reference. It is used as an intermediate step in several alignment tools that employ a seed-chain-extend strategy. Despite this popularity, efficient subquadratic-time algorithms for the general case where chains support anchor overlaps and gap costs are not currently known. We present algorithms to solve the co-linear chaining problem with anchor overlaps and gap costs in O~ (n) time, where n denotes the count of anchors. We also establish the first theoretical connection between co-linear chaining cost and edit distance. Specifically, we prove that for a fixed set of anchors under a carefully designed chaining cost function, the optimal ‘anchored’ edit distance equals the optimal co-linear chaining cost. Finally, we demonstrate experimentally that optimal co-linear chaining cost under the proposed cost function can be computed orders of magnitude faster than edit distance, and achieves correlation coefficient above 0.9 with edit distance for closely as well as distantly related sequences. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Development of Phylum Chordata Sound Recognition System using Machine Learning and Deep Learning Techniques: A Case Study of Catfish

Development of Phylum Chordata Sound Recognition System usin...

引用

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Akinyemi, Lateef Adesola Oshinuga, Olamide Peter Eshilokun, Oluwafikunmi Adegbenga Oladejo, Sunday Oladayo Ekwe, Stephen Obono Cset University of South Africa Departments of Computer Science and Electrical Engineering Johannesburg South Africa Lagos State University Department of Electronic and Computer Engineering Lagos Nigeria School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa Cape Peninsula University of Technology Department of Electrical Electronic and Computer Engineering Cape Town South Africa

ISBN: (纸本)9798350327816

Sound recognition refers to the technology or process of identifying and classifying different sounds or audio signals. This study aims to develop a sound recognition system using machine learning (ML) and deep learning (DL) techniques to classify and identify the gender of catfish based on their speech patterns. The study explores a range of supervised ML and DL algorithms, such as the Artificial Neural Network (ANN), Naïve Bayes (NB), and others, to predict the gender of catfish. The extracted features from the audio signals of the catfish serve as inputs to these algorithms, which produce binary predictions classifying the catfish samples as either male or female. This study further explores data analysis of the audio signals from the male and female catfish. The automated sound recognition system proves to be a more efficient and accurate approach compared to traditional methods, which rely on time-consuming visual observations. Evaluation metrics such as Accuracy, Sensitivity, and more, were employed to gauge the effectiveness of the algorithms in predicting the gender of catfish based on speech patterns. Among the employed algorithms, ANN and NB demonstrate the highest accuracy, achieving a score of 89.47%. © 2023 IEEE.

关键词： Catfish Deep Learning Gender Prediction Machine Learning Audio data Analysis Sound Recognition

来源：评论

学校读者我要写书评

暂无评论

Asynchrony-Tolerant Schemes to Enhance Scalability of High-Order Compressible Flow Solver

Asynchrony-Tolerant Schemes to Enhance Scalability of High-O...

引用

IEEE International Conference on High Performance Computing Workshops (HiPCW)

作者： Aswin Kumar A Nagabhushana Rao Vadlamani Konduri Aditya Department of Aerospace Engineering Indian Institute of Technology Madras Chennai India Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

ISBN: (数字)9798331509118

ISBN: (纸本)9798331509125

High-order asynchrony-tolerant (AT) schemes are used to solve the compressible Navier-Stokes equations. The AT schemes are validated for accuracy using canonical flow problems and are found to be in excellent agreement with the standard schemes. Strong and weak scaling analyses are performed, and significant speedups (up to 3.5×) are observed for the asynchronous algorithms compared to the standard synchronous algorithm.

关键词： Accuracy Scalability High performance computing Conferences Standards Navier-Stokes equations

来源：评论

学校读者我要写书评

暂无评论

Detecting lithium plating dynamics in a solid-state battery with operando X-ray computed tomography using machine learning

引用

npj computational Materials 2023年第1期9卷 1402-1410页

作者： Ying Huang David Perlmutter Andrea Fei-Huei Su Jerome Quenum Pavel Shevchenko Dilworth Y.Parkinson Iryna V.Zenyuk Daniela Ushizima Department of Materials Science&Engineering University of California IrvineIrvineCaliforniaUSA National Fuel Cell Research Center University of California IrvineIrvineCaliforniaUSA Applied Math and Computational Research Division Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA Department of Chemical&Biomolecular Engineering University of California IrvineIrvineCaliforniaUSA Department of Electrical Engineering and Computer Sciences College of EngineeringUniversity of California BerkeleyBerkeleyCaliforniaUSA Advanced Photon Source Argonne National Laboratory9700 South Cass AvenueLemontIllinoisUSA Advanced Light Source Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA Berkeley Institute for Data Science University of California BerkeleyBerkeleyCaliforniaUSA

Operando X-ray micro-computed tomography(µCT)provides an opportunity to observe the evolution of Li structures inside pouch *** is an essential step to quantitatively analyzingµCT datasets but is challenging to achieve on operando Li-metal battery datasets due to the low X-ray attenuation of the Li metal and the sheer size of the ***,we report a computational approach,batteryNET,to train an Iterative Residual U-Net-based network to detect Li *** resulting semantic segmentation shows singular Li-related component changes,addressing diverse morphologies in the *** addition,visualizations of the dead Li are provided,including calculations about the volume and effective thickness of electrodes,deposited Li,and redeposited *** also report discoveries about the spatial relationships between these *** approach focuses on a method for analyzing battery performance,which brings insight that significantly benefits future Li-metal battery design and a semantic segmentation transferrable to other datasets.

关键词： battery lithium state

来源：评论

学校读者我要写书评

暂无评论

Utilizing Hybrid Deep Reinforcement Learning and Transformer Networks for Predictive Maintenance in Product Safety engineering

Utilizing Hybrid Deep Reinforcement Learning and Transformer...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Nimma, Divya Kannaiyan, Mathi Gupta, Deepak Roy, Manidipa Al Ansari, Mohammed Saleh Balakumar, A. PhD in Computational Science University of Southern Mississippi Data Analyst in UMMC United States University College of Kancheepuram Anna University Kancheepuram Campus Department of Mechanical Engineering Tamil Nadu Kanchipuram India Graphic Era Hill University Department of Mechanical Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Department of Mechanical Engineering Uttarakhand Dehradun India ABES Engineering College Department of ECE Uttar Pradesh Ghaziabad India College of Engineering University of Bahrain Department of Chemical Engineering Bahrain K.Ramakrishnan College of Engineering Department of ECE Trichy India

ISBN: (纸本)9798331517953

Predictive maintenance (PdM) is essential to make sure the protection and reliability of the technology. This paper affords a remarkable technique that mixes hybrid deep reinforcement getting to know (DRL) with transformer networks to enhance predictive protection strategies for protection in material safety engineering. In most cases, inefficient and costly implementation strategies are based on predefined guidelines or ad hoc practices in traditional management. A system that integrates DRL and Transformer Networks to quickly identify and predict operational needs and respond effectively to various conditions. Hybrid DRL approach has the capability of non-modeling and reinforcing model-based learning for maintenance a it is best through communication with the system. enabling the study of systems Environmental and historical data. The recognized efficiency of transformer networks in sequential data processing will enhances the ability of the model to process and interpret the time series sensor data, helps to improves the prediction performanceThis method uses dual stage architecture which extract the time based features from sensor data. This approach agrees real-time optimization of emerging patterns and anomalies, This will improves prediction capabilities and reduces false positives. This model was tested on various industrial datasets, indicating significant developments in prediction accuracy and maintenance scheduling efficiency compared to traditional methods. By integrating these advanced techniques, The approach provides a more vigorous and adaptive solution for ensuring product safety and reliability in complex industrial environments. Proposed model achieved a notable reduction in Mean Absolute Error (MAE) 0.15 compared to traditional predictive maintenance methods. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Mesoscale Wind Farm Placement via Linear Optimization Constrained by Power System and Techno-economics

引用

Journal of Modern Power Systems and Clean Energy 2021年第2期9卷 356-366页

作者： Ali Erduman Bahri Uzunoglu Bedri Kekezoglu Ali Durusu the Electrical Engineering Department Hakkari UniversityHakkari30000 Turkey Department of Engineering Sciences Department of Electrical EngineeringComputational and Data-enabled Science and Engineering in Energy SystemsUppsala University75121 UppsalaSweden Department of Mathematics Florida State UniversityTallahasseeFL 32310USA the Electrical Engineering Department Yildiz Technical UniversityIstanbul34220 Turkey

The objective of this study is to develop a wind farm placement and investment methodology based on a linear optimization *** problem has a major significance for the investment success for the projects of renewable energy such as wind *** this study,a mesoscale approach is adopted whereby the wind farm location is investigated in comparison with a microscale approach where the location of each individual turbine is *** study focuses on the placement of a wind farm by economical optimization constrained by the power system,wind resources,and *** optimization is introduced in this context at the power system which is constrained by wind farm planning.

关键词： Generation expansion grid integration mesoscale wind farm linear optimization wind power

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：