检索结果-内蒙古大学图书馆

3rd International Conference on Automation, computing and Renewable Systems, ICACRS 2024

作者： Manasa, Pokala Veeramalla, Vaishnavi Vanusha, D. Vathana, D. Robinsha, Delsi S. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India

ISBN: (纸本)9798331532420

Tuberculosis (TB) remains a significant global health challenge, especially in remote areas with limited medical resources. Early and accurate diagnosis is crucial to control its spread. This project harnesses high-performance computing (HPC) to address two key issues: managing unreliable medical data and improving TB diagnosis. Given the imbalance between healthy and TB-affected samples, Generative Adversarial Networks (GANs) are used to generate synthetic images, enriching the dataset and making it more diverse. This helps train Convolutional Neural Networks (CNNs), which are highly effective in medical image analysis. By leveraging HPC, we accelerate the training of CNNs on large, augmented datasets, significantly reducing processing time while maintaining accuracy. This system improves TB detection by combining GAN-enhanced data and CNN models, enabling faster and more reliable diagnosis. © 2024 IEEE.

关键词： X ray apparatus

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Treatment Outcomes in Rheumatoid Arthritis Patients: A Data science Approach to Analysing Multimorbidity 5

Optimizing Treatment Outcomes in Rheumatoid Arthritis Patien...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Moovendran, Manikandan Nitheesh, S. Sri Sharvesh, S.S. Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai603203 India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai603203 India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389609

This study aims to explore the data science strategies for new insights into multimorbidity understanding and identifying potential therapy targeting in rheumatoid arthritis patients. Rheumatoid Arthritis (RA) is a chronic inflammatory (auto immune) disease that has the potential to result in co-morbid illnesses, meaning it affects both sides of the equation by making treating patients even tougher than had been previously determined. Although the controversial method of drug-drug interactions remains central to this phenomenon, an even lesser acknowledged mechanism that may exert significant control over disease status and remission rates with RA is the interaction between comorbidities themselves. The presence and types of comorbidities, how they accumulate over time, and their interplay with therapies across the life span remain unknown. To identify comorbidity patterns and predict patient outcomes, we leverage a dataset of patient registries, wearable technology or Electronic Health Records (EHR) using advanced machine learning techniques like clustering and predictive analytics. Image analysis of these data is done by Convolutional Neural Network (CNN). Clinical notes can be particularly informative using random forest, Gradient Boosting Machine (GBM), Support Vector Machine (SVM), by combining these to get an Ensemble Model which improves overall performances of the model and network analysis which enables creating a comprehensive understanding of the relationships between different chronic conditions alongside their treatments. These findings imply that in some cases there may be relationships between specific comorbidity profiles and treatment outcomes, providing a practical basis for investigating individual-level factored medicine. This study analyses these data with different models and highlights the power of data science both in clinical decision-making and uncovering previously unknown patterns of illness to improve patient care. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Few-shot Prompting for Pairwise Ranking: An Effective Non-Pa...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ENCODING UNITIG-LEVEL ASSEMBLY GRAPHS WITH HETEROPHILOUS CONSTRAINTS FOR METAGENOMIC CONTIGS BINNING 12

ENCODING UNITIG-LEVEL ASSEMBLY GRAPHS WITH HETEROPHILOUS CON...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Xue, Hansheng Mallawaarachchi, Vijini Xie, Lexing Rajan, Vaibhav School of Computing Australian National University Canberra Australia School of Computing National University of Singapore Singapore College of Science and Engineering Flinders University Adelaide Australia

Metagenomics studies genomic material derived from mixed microbial communities in diverse environments, holding considerable significance for both human health and environmental sustainability. Metagenomic binning refers to the clustering of genomic subsequences obtained from high-throughput DNA sequencing into distinct bins, each representing a constituent organism within the community. Mainstream binning methods primarily rely on sequence features such as composition and abundance, making them unable to effectively handle sequences shorter than 1,000 bp and inherent noise within sequences. Several binning tools have emerged, aiming to enhance binning outcomes by using the assembly graph generated by assemblers, which encodes valuable overlapping information among genomic sequences. However, existing assembly graph-based binners mainly focus on simplified contig-level assembly graphs that are recreated from assembler's original graphs, unitig-level assembly graphs. The simplification reduces the resolution of the connectivity information in original graphs. In this paper, we design a novel binning tool named UNITIGBIN, which leverages representation learning on unitig-level assembly graphs while adhering to heterophilous constraints imposed by single-copy marker genes, ensuring that constrained contigs cannot be grouped together. Extensive experiments conducted on synthetic and real datasets demonstrate that UNITIGBIN significantly surpasses state-of-the-art binning tools. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Graphic methods

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

Cyber-Syndrome:Concept,Theoretical Characterization,and Control Mechanism

引用

Tsinghua science and Technology 2024年第3期29卷 721-735页

作者： Feifei Shi Huansheng Ning Liming Chen Sahraoui Dhelim School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Faculty of Computing Ulster UniversityNewtownabbeyBT370QBUK School of Computer Science University College DublinDublinD04 V1W8Ireland

The prevalence of social media and mobile computing has led to intensive user engagement in the emergent Cyber-Physical-Social-Thinking(CPST)***,the easy access,the lack of governance,and excessive use has generated a raft of new behaviors within CPST,which affects users’physical,social,and mental *** this paper,we conceive the Cyber-Syndrome concept to denote the collection of cyber disorders due to excessive or problematic Cyberspace interactions based on CPST *** we characterize the Cyber-Syndrome concept in terms of Maslow’s theory of Needs,from which we establish an in-depth theoretical understanding of Cyber-Syndrome from its etiology,formation,symptoms,and ***,we propose an entropy-based Cyber-Syndrome control mechanism for its computation and *** goal of this study is to give new insights into this rising phenomenon and offer guidance for further research and development.

关键词： Cyber-Syndrome cyber-physical systems Cyber-Physical-Social-Thinking(CPST)space Maslow’sHierarchy of Needs entropy

来源：评论

学校读者我要写书评

暂无评论

DIFFERENTIAL EVOLUTION ALGORITHM SUPPORTED RANDOM FOREST CLASSIFIER FOR EFFECTIVE FEATURE SELECTION AND CLASSIFICATION OF POWER QUALITY DISTURBANCES

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer science 2023年第1期85卷 131-142页

作者： Vidhya, S. Balaji, M. Fantin Irudaya Raj, E. Kamaraj, V. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Electrical and Electronics Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai India Department of Electrical and Electronics Engineering Dr. Sivanthi Aditanar College of Engineering Chennai India

The rise in the usage of power electronic equipment, which induces a deviation in the voltage and current waveforms, has raised the relevance of power quality (PQ) issues. It is important to classify them accurately in order to address the PQ problems. One of the most effective methods to classify PQ problems is to combine Machine Learning (ML) algorithms with efficient feature extraction and feature selection techniques. In the present work, the S-transform-based feature extraction technique is adopted and extracts around 20 features from the PQ disturbance signal. And then, Differential Evolution (DE) based feature selection technique is utilized for feature selection and five optimized features are selected and given as input to the ML classifiers. It is a method that is essential in data mining in order to reduce dimensionality and enhance the performance of ML classifiers. Eight different ML classifiers namely the K-Means, Adaptive Boosting (AdaBoost), K-nearest neighbor (KNN), Naive Bayes, Recursive Support Vector Machine (R-SVM), Linear SVM, Decision Tree, and Random Forest (RF) algorithms have been employed in this work. The effectiveness of the ML Classifiers is measured in terms of various performance evaluation measures namely precision, accuracy, F1-score, recall, and specificity. The results revealed that the DE-supported RF classifier is more efficient when compared with other classifiers in classifying the PQ disturbances even in environments with noise inference. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

FARMER: Forecasting Agricultural Results with Machine Learning Evaluation and Regression 11

FARMER: Forecasting Agricultural Results with Machine Learni...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Chauhan, Naman Bharathi Mohan, G. Sulochana, V. Kumar, R. Prasanna Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Amrita School of Computing Department of Computer Science and Engineering Chennai India Anna Administrative Staff College Dehradun India

ISBN: (纸本)9798350350357

Agriculture plays an important role, in Indias economy providing support to a portion of the population and contributing significantly to the GDP. It is crucial to predict crop yields in order to make decisions and promote sustainable agricultural practices. To achieve this a research study proposes an approach that utilizes machine learning techniques such as Decision Tree, Support Vector Machine (SVM) Random Forest, Multiple Linear Regression and Partial Least Squares Regression. The study carefully evaluates the performance of these models. Reveals some findings while comparing them to determine the best model. Multiple Linear Regression achieves the accuracy at 81.2% followed by Decision Tree at 83.5% SVM at 92.1% Random Forest at 91.5%. Partial Least Squares Regression at 85.3%. Notably SVM emerges as the performing model demonstrating its potential in improving precision, for predicting agricultural yields. Ultimately an Android application is developed using Kotlin and Android Studio for an user experience. © 2024 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Cricket Performance Analysis System Using Machine Learning Techniques 5

Cricket Performance Analysis System Using Machine Learning T...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mishra, Suraj Garg, Animesh Batra, Vansh Saxena, Devansh Om Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications 603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications India

ISBN: (纸本)9798331530013

The Cricket Performance Analysis System based on big data tools, like Hadoop and Apache Spark, gives realtime deep insights into performances from players and teams and conditions in matches based on large-scale cricket match data. It scales up speedily and finds patterns using distributed computing capabilities of Spark, which makes it possible to take decisions around performance improvements and strategies. The system applies a set of machine learning techniques including K-means clustering, Logistic Regression, and Random Forest classifiers to be used for the analysis of player performance metrics and match outcomes. Thus, through the conversion of raw data into actionable insights, teams can improve their strategies, make better improvements in performance, and thus gain an upper hand against other competing professional cricket teams. As a result, teams are best positioned to make adjustments in good time and direct finer tactics toward further enhancement of overall performance. © 2024 IEEE.

关键词： Adversarial machine learning

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：