检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Jiahao Liu Yipeng Zhou Di Wu Miao Hu Mohsen Guizani Quan Z. Sheng School of Computer Science and Engineering Sun Yat-sen University Guangzhou China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Role of IoT and Machine Learning in Automating Space Docking: Challenges, Advancements, and Future Prospects 2

The Role of IoT and Machine Learning in Automating Space Doc...

引用

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

作者： Jikar, Nayan Tale, Yash Tale, Abhay Barhate, Aditya Verma, Prateek Jikar, Aman Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Space docking is an important aspect of modern-day space exploration, enabling crewed missions, shipment transport, and spacecraft refuelling. Traditionally, manual docking has trusted astronaut precision and floor manipulation coordination, which has grown to be inefficient and blunders-susceptible in deep-space missions because of conversation delays. Integrating the Internet of Things (IoT) and Machine Learning (ML) is reworking area docking by introducing self-reliant, actual-time selection-making structures. IoT-enabled sensors continuously monitor spacecraft role, pace, and orientation, while ML algorithms optimize docking manoeuvres, beautify predictive upkeep, and make certain collision avoidance. Reinforcement learning similarly allows adaptive management strategies, making self-sufficient docking more efficient and dependable. This paper explores the improvements in IoT and ML for automating space docking, reading real-global programs along with SpaceX Dragon, NASA's AR&D systems, and China's Tianzhou cargo deliver. By addressing key demanding situations-precision, pace, and safety-those technologies pave the way for sustainable space exploration, including future Mars missions and autonomous area stations. The observation highlights how AI-driven docking may be integral for deep-space operations, making sure safer and more green missions are made. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Consumer Behavior Using Supervised Learning Techniques

Predictive Analysis of Consumer Behavior Using Supervised Le...

引用

International Conference on Computational and Characterization Techniques in Engineering & sciences (CCTES)

作者： K. Sashi Rekha T. Amutha R. Usharani S. Pushparani V.M. Sivagami Department of Computer Science and Engineering SIMATS Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Artificial Intelligence & Data Science CARE College of Engineering Trichy Tamil Nadu India Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu India Department of Information Technology Sri Venkateswara College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

The study presented here consists of an entire framework for prediction of consumers behavior through the machine training of supervised learning methods. The strategy involves the following: data collection, preprocessing, exploration, feature selection, model selection, training, evaluation, interpretation and deployment. The systematic process is tailored to clear the pathway for combining data about customer taste, sophisticated habits, and purchasing trends. Primary components include data preprocessing, training of machine learning models, feature selection, and ethical issues regarding data privacy and transparency. The outcomes of the implementation are a high accuracy in consumers clustering, efficient classification of customers' behavior, as well as unveiling a bunch of crucial predictors that affect the customers mood and behavior. As a result, the report stresses the necessity of integrated monitoring and redirection strategies to realize the potential of the created models. The idea of predictive analysis as an evolving tool that enables marketers to tailor their campaigns more closely, and improve the overall customer experience therefore also receives attention. The proposed system methodology constitutes a solid process framework for business defined to aim at using predictive analytics to gain competitive edge in the current dynamic marketplace.

关键词： Training Adaptation models Consumer behavior Supervised learning data preprocessing Reinforcement learning Feature extraction data models Predictive analytics Stress

来源：评论

学校读者我要写书评

暂无评论

Efficient and High-quality Recommendations via Momentum-incorporated Parallel Stochastic Gradient Descent-Based Learning

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 402-411页

作者： Xin Luo Wen Qin Ani Dong Khaled Sedraoui MengChu Zhou the School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808 Hengrui(Chongqing)Artificial Intelligence Research Center Department of Big Data Analyses TechniquesCloudwalkChongqing 401331China the School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China the Department of Computer and Information Science City College of Dongguan University of TechnologyDongguan 523419China the Department of Electrical and Computer Engineering Faculty of Engineeringand Center of Research Excellence in Renewable Energy and Power SystemsKing Abdulaziz UniversityJeddah 21481Saudi Arabia the Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA the Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz UniversityJeddah 21481Saudi Arabia

A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning ***,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial *** at addressing this issue,this study proposes a momentum-incorporated parallel stochastic gradient descent(MPSGD)algorithm,whose main idea is two-fold:a)implementing parallelization via a novel datasplitting strategy,and b)accelerating convergence rate by integrating momentum effects into its training *** it,an MPSGD-based latent factor(MLF)model is achieved,which is capable of performing efficient and high-quality *** results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm,an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability.

关键词： Big data industrial application industrial data latent factor analysis machine learning parallel algorithm recommender system(RS) stochastic gradient descent(SGD)

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning in Employee Performance Prediction

Supervised Learning in Employee Performance Prediction

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： Geetha Manoharan Someswari Perla Prema S. Kadam Dr. Manoj Sathe S. Ranichandra Melanie Lourens School of Business SR University Warangal Telangana India Department of CSE - AI&ML GMR Institute of Technology Rajam Andhra Pradesh India Artificial intelligence and Data Science BRACT’s Vishwakarma Institute of Information Technology Pune Maharashtra Computer Science PES Modern Institute of Business Studies Pune India Dept. of Computer Science Dhanalakshmi Srinivasan College of Arts and Science for Women(Autonomous) Perambalur Deputy Dean Faculty of Management Sciences Durban University of Technology South Africa

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

Organisations must have a method of predicting their employees’ performance in order to optimise productivity and efficacy in workforce management. Supervised learning, a subset of machine learning, possesses exceptional potential for anticipating an employee’s future performance by analysing their prior work. This study concentrates on the application of supervised learning methodologies to predict employee performance metrics. Decision trees, logistic regression, and support vector machines comprise three of the methodologies implemented. In an effort to furnish HR departments with valuable insights, the models provided utilise data such as employee demographics, performance records, and engagement levels. The study assesses the interpretability, practical implications, and model correctness of numerous algorithms to aid in the selection of the most suitable ones for real-world applications. The results indicate that supervised learning has the potential to considerably enhance the decision-making and prediction capabilities of employee performance management systems.

关键词： Support vector machines Productivity Measurement Logistic regression Machine learning algorithms Supervised learning Decision making Machine learning Prediction algorithms Decision trees

来源：评论

学校读者我要写书评

暂无评论

Big data in Social Media: Analyzing Trends, Patterns and Challenges

Big Data in Social Media: Analyzing Trends, Patterns and Cha...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Nayan Jikar Yash Tale Abhay Tale Aditya Barhate Prateek Verma Aman Jikar Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India Department of Computer Science and Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The huge volumes of data produced in social media provide both new possibilities and challenges to analytics. The present paper emphasizes Big data analytics and Machine Learning (ML) methods to uncover trends, patterns, and user behavior from social media-related data. Such vital concepts, like the “Four Vs” of Big data: Volume, Velocity, Variety, and Veracity, and innovative tools for datacollection, storage, and preprocessing are covered here as well. Sentiment analysis, trend forecasting, and user behaviormodeling are some of the examples of what is possible using ML and Artificial Intelligence (AI) for deriving actionable insights. Marketing campaigns, crisis communications, and political campaigns are some of the scenarios that are covered to bring out real world applications of such technologies, along with their transformative effects. Lastly, data privacy, quality, and scalability issues are noted, along with ethical concerns and biases. Directions for the future point to developments in real-time data analysis, anonymization, and the changing role of AI in social media platforms. This research emphasizes the significance of Big data and machine learning in driving innovation and decision-making in the digital era.

关键词： data privacy Technological innovation Ethics Social networking (online) Machine learning Big data Market research Real-time systems Information filtering Information integrity

来源：评论

学校读者我要写书评

暂无评论

Role of Machine Learning in Climate Change Prediction and Mitigation 2

Role of Machine Learning in Climate Change Prediction and Mi...

引用

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

ISBN: (纸本)9798331505745

Climate change is one of the biggest challenges of the 21st century, with profound environmental, economic, and social impacts. Machine learning (ML) has emerged as a transformative tool to address climate challenges through data-driven solutions, offering predictive capabilities for extreme weather events and enhancing the efficiency of clean-energy systems. This technology benefits the optimization of renewable energy generation, intelligent grid management, and resource utilization towards reducing greenhouse gas emissions. Moreover, ML promotes climate justice through targeted region-specific intervention and inclusive solution-making for the most vulnerable. Several technical and ethical challenges associated with data quality, scalability, and model generalization must still be overcome for ML to realize its potential. This paper reviews the role of ML in climate change prediction and mitigation discusses ongoing real-world applications and outlines the future research agenda necessary to address existing challenges. Integrating ML with emerging technologies like the Internet of Things (IoT) and explainable AI, alongside global collaboration and a focus on climate justice, will be essential in advancing effective climate action. © 2025 IEEE.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effectiveness of Deep Learning in Audio Compression and Restoration

Exploring the Effectiveness of Deep Learning in Audio Compre...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： S. Pushparani K. Sashi Rekha V. M. Sivagami R. Usharani M. Jothi Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Information Technology Sri Venkateswara College of Engineering Sriperumbudur Chennai Tamil Nadu Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Department of Artificial Intelligence & Data Science CARE College of Engineering Trichy Tamil Nadu

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

Modern audio processing requires compression and restoration for streaming services and data storage and transmission. This study examines how deep learning can address these difficulties and includes an architecture flow diagram. The suggested complex design has numerous integral stages optimized for audio compression and restoration. The input layer contains raw audio data. The pre-processing module normalizes and extracts features from raw data, frequently using Mel-frequency cepstral coefficients (MFCC) to capture audio characteristics. This module improves data quality by reducing noise and filtering. The architecture's heart is the compression module, where deep learning is used. This module compresses audio data using neural networks, maybe CNNs or RNNs. This compression is quantified by compression ratio and bitrate, with hypothetical values representing audio quality trade-offs. The compression module compacts audio data for storage or transmission. To minimize data size, quantization and encoding are common here. To accurately decompress audio, the decompression module mimics the compression module's architecture. Depending on needs, error correction or quality enhancement layers may be added. Filtering, equalization, and dynamic range compression may be used in the post-processing module to improve audio quality. If needed, a restoration module uses deep learning models to minimize noise and artifacts. This study presents four hypothetical scenarios to demonstrate different results. The scenarios emphasize high compression, balanced approaches, quality prioritization, and low resource utilization. Deep learning approaches can adapt to varied audio processing needs by balancing compression ratio, bitrate, audio quality (measured by PSNR), and restoration accuracy in each case.

关键词： Deep learning Training Filtering Bit rate Noise computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Similarity Computation Model Based on Optimised SBERT

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Simila...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Shuo Zhao Qiliang Gu Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets.

关键词： Deep learning Computational modeling Semantics Neural networks Feature extraction Natural language processing Multilingual Convolutional neural networks Cybernetics Overfitting

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Relation Matrix Bidirectional Approach for Relational Triple Extraction

Hybrid Deep Relation Matrix Bidirectional Approach for Relat...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yushuai Hu Jing Zhao Ming Li Lin Yuan Qingzhi Zou Ronghuan Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Relation extraction is a crucial task within information extraction, and numerous models have demonstrated impressive results. However, most of the tagging-based relation triple extraction methods employ unidirectional approaches to extract subjects, objects, and relations, which may overlook crucial information. In this paper, we introduce a novel deep matrix-based bidirectional relation extraction model. Firstly, we extract forward and backward entity pairs. During the bidirectional extraction process,there may be some redundant relationships,so we use a shared encoder to connect and enhance the extraction process. Secondly, we design a low-complexity relation extraction matrix to allocate all possible relations. We assess our model using diverse benchmark datasets, and comprehensive experiments show that our approach effectively addresses subsequent triple extraction issues stemming from entity extraction failures.

关键词： Learning systems Federated learning Computational modeling Benchmark testing Information retrieval data mining Task analysis

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：