检索结果-内蒙古大学图书馆

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

Cross-View Fuzziness and Intra-view Uncertainty-Based Weight Reconstruction for Multi-view Feature Selection 11th

Cross-View Fuzziness and Intra-view Uncertainty-Based Weigh...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Xiang, Biao Chen, Hongmei Mi, Yong Sang, Binbin Horng, Shi-Jinn Li, Tianrui Institute of Artificial Intelligence School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China College of Computer and Information Science Chongqing Normal University Chongqing401331 China Department of Computer Science and Information Engineering Asia University Taichung41354 Taiwan

ISBN: (纸本)9783031927430

Weight assignment is a universal and indispensable process in multi-view feature selection. However, most existing methods overlook the fuzziness and uncertainty implied in multi-view data. This may result in improper weight assignment, degrading the quality of selected features. A cross-view fuzziness and intra-view uncertainty-based weight reconstruction method (CFIUWR) is proposed for multi-view feature selection. With the fuzzy rough set theory, fuzzy approximation operators recognize cross-view fuzziness and intra-view uncertainty, which are evaluated by classification-related measurement. Cross-view fuzziness and intra-view uncertainty are incorporated to develop a reconstruction mechanism for view and feature weights. An optimization algorithm is derived, guaranteeing rapid convergence. Comparisons with state-of-the-art methods on several real-world datasets demonstrate the superiority of the CFIUWR. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Requirement of Production Simulation of DC Distribution Network Containing High Renewable Energy 37

Requirement of Production Simulation of DC Distribution Netw...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Li, Man Zhang, Yi Li, Yan Li, Xiaoxue Fan, Bo Li, Lifeng Li, Yanmei Hu, Yuan National Research Center for Rehabilitation and Technical Aids Testing Department Beijing China China Academy of Industrial Internet Big Data Department Beijing China China Electric Power Research Institute Artificial Intelligence Department Beijing China Beijing Aerospace Data Stock Company General Manager of Key Account Division Beijing China General Headquarters Chengdu Aerospace Science & Industry Big Data Institute Ltd chengdu China National Research Center for Rehabilitation and Technical Aids AI Application Research Department Beijing China Kunlun Digital Technology Co. Ltd Business Department Beijing China

ISBN: (纸本)9781665465366

Renewable energy power generation connected to the DC distribution network, converter station capacity, renewable energy installed capacity and renewable energy operation mode are the primary factors that affect the maximum consumption of renewable energy. Unreasonable converter station capacity and renewable energy installed capacity planning and configuration will result in excessive renewable energy installed capacity, resulting in abandonment of wind and light, or too small installed capacity to make the converter station with full using. The renewable energy power generation operation mode strategy directly affects the DC distribution network transmission capacity and the regulation capacity of the energy storage station, which in turn affects the consumption of renewable energy power generation. The paper studies relevant time series modeling methods of wind and PV power generation, and proposes the technical requirements for optimizing the power generation operation mode considering the hybrid of multiple types of renewable energy and the DC distribution network, so as to achieve maximum consumption renewable energy, and to ensure that the power of renewable energy can be 'controlled and consumed'', and ultimately ensure the stable operation and safe of renewable energy and the DC distribution network. The paper results will provide support for the future planning of the local consumption of a high proportion of renewable energy, and will effectively guide the planning and design of renewable energy and DC distribution networks. © 2022 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Stay Tuned! Analysing Hyperparameters of a Wide-Kernel Architecture for Industrial Faults

Stay Tuned! Analysing Hyperparameters of a Wide-Kernel Archi...

引用

artificial intelligence (CAI), IEEE Conference on

作者： Dan Hudson Jurgen Van Den Hoogen Stefan Bloemheuvel Martin Atzmueller Semantic Information Systems Group (SIS) Osnabrück University Osnabrück Germany CSAI Jheronimus Academy of Data Science (JADS) Tilburg University Tilburg The Netherlands German Research Center for Artificial Intelligence (DFKI) Osnabrück University / SIS Osnabrück Germany

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

The performance of a deep learning model depends heavily on its architectural hyperparameters. However, there is often little guidance on how to tune those hyperparameters. This paper provides insights into how to tune the architectural hyperparameters of a wide-kernel convolutional model for industrial fault detection, by analysing a grid search over 12,960 possible combinations of hyperparameter settings on seven benchmark datasets of vibration time series. By aggregating the results on these seven datasets, we are able to generalise across multiple industrial fault detection settings. We find that, generally speaking, the number of filters in the later convolutional layers and the hyperparameters associated with the first layer are the most important. Additionally, we analyse the relationships between hyperparameters and develop this analysis into a ‘recommended sequence’ for how to tune them one-at-a-time.

关键词： Vibrations Deep learning Filters Fault detection Time series analysis Neural networks Computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Gaze Estimation Models

A Comparative Study of Gaze Estimation Models

引用

Information Technology (ACIT)

作者： Abdallah Moubayed MohammadNoor Injadat Mohammad Kanan Computer Engineering Department Interdisciplinary Research Center for Intelligent Secure Systems King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Data Science & Artificial Intelligence Department Zarqa University Zarqa Jordan Department of Industrial Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

The eye-mind hypothesis suggests that people tend to look at what they’re actively thinking about, forming the basis of eye and gaze tracking. This concept is gaining attention in deep learning due to its broad applications. The use of AI alongside webcams to monitor eye movements is increasingly popular and expected to grow further. This is further emphasized by recent data showing a growing use of eye gaze estimation techniques, especially in marketing research, e-commerce, and educational tools. Accordingly, multiple previous research works have developed various eye and gaze estimation and tracking models. However, one main limitation is that many models use their own datasets for performance evaluation as well as having different underlying computing resources that are used during training. Consequently, it becomes harder to compare the effectiveness and efficiency of these models. To that end, this work aims at providing a comprehensive comparative study of three well-established eye gaze estimation models, namely OpenGaze, GazeRefineNet, ODABE, and FAZE models using a unified evaluation framework. Experimental results conducted using GazeCapture dataset illustrate that OpenGaze model achieves a mean error of 2.27 cm mean error, GazeRefineNet model achieves 1.91 cm, ODABE model achieves 3.46 cm, and FAZE model achieves 2.9 cm. This indicates that GazeRefineNet outperforms the other models in terms of accuracy while having comparable computational complexity.

关键词： Training Performance evaluation Webcams Tracking Computational modeling Estimation Gaze tracking Electronic commerce Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Beyond Traditional Doe: Deep Reinforcement Learning for Optimizing Experiments in Model Identification of Battery Dynamics

SSRN

引用

SSRN 2022年

作者： Budan, Gokhan Damiani, Francesca Kurtulus, Can Ure, Nazim Kemal Eatron Technologies Ltd. Research and Development Warwick CV34 6UW United Kingdom Istanbul Technical University Artificial Intelligence and Data Science Application and Research Center Istanbul Turkey

Model identification of battery dynamics is a central problem in energy research;many energy management systems and design processes rely on accurate battery models for efficiency optimization. The standard methodology for battery modelling is traditional design of experiments (DoE), where the battery dynamics are excited with many different current profiles and the measured outputs are used to estimate the system dynamics. However, although it is possible to obtain useful models with the traditional approach, the process is time consuming and expensive because of the need to sweep many different current-profile configurations. In the present work, a novel DoE approach is developed based on deep reinforcement learning, which alters the configuration of the experiments on the fly based on the statistics of past experiments. Instead of sticking to a library of predefined current profiles, the proposed approach modifies the current profiles dynamically by updating the output space covered by past measurements, hence only the current profiles that are informative for future experiments are applied. Simulations and real experiments are used to show that the proposed approach gives models that are as accurate as those obtained with traditional DoE but by using 85% less resources. © 2022, The Authors. All rights reserved.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

引用

CAAI Transactions on intelligence Technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Analysis of Wide-Kernel CNN Architectures in Industrial Fault Detection - An Exploratory Study

Hyperparameter Analysis of Wide-Kernel CNN Architectures in ...

引用

International Conference on data science and Advanced Analytics (DSAA)

作者： Jurgen Van Den Hoogen Dan Hudson Stefan Bloemheuvel Martin Atzmueller Jheronimus Academy of Data Science Tilburg University ’s-Hertogenbosch The Netherlands Semantic Information Systems Group Osnabrück University Osnabrueck Germany Semantic Information Systems Group German Research Center for Artificial Intelligence (DFKI) Osnabrück University Osnabrück Germany

In recent years, industrial fault detection has become more data-driven due to advancements in automated data analysis using Deep Learning (DL). These techniques facilitate meaningful feature extraction, e.g., in time series data retrieved from sensors, which is typically of complex nature. This enables effective fault detection and prognostics, which increases efficiency and productivity of industrial equipment. However, the optimal settings for these DL architectures are generally use-case specific.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-view Clustering Based on Joint Concept Decomposition and Anchor Graph Learning 11th

Incomplete Multi-view Clustering Based on Joint Concept Dec...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Li, Zhuowen Chen, Hongmei Xiang, Biao Yuan, Zhong Luo, Chuan Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China College of Computer Science Sichuan University Chengdu610065 China

ISBN: (纸本)9783031927430

The main objective of incomplete multi-view clustering is to effectively utilize the existing view information to fill in the missing data and to mine the complementary information and potential associations between multiple views to effectively group samples. The existing primary means for recovering missing information are classified into two parts: one uses matrix decomposition or low-rank constraints to fill in the missing views, and the other constructs multiple graph structures and uses graph regularization to recover the corresponding missing parts. However, the two methods are relatively independent and are not used jointly to improve the model performance. This paper proposes an incomplete multi-view clustering method with complete clustering metrics and complete anchor graphs (CFAG). Specifically, each view’s missing samples are recovered by a matrix of consistent clustering metrics and represented by an anchor graph. The recovered complete data performs anchor graph construction and anchor learning and utilizes the orthogonal variation principle to learn the consistency structure of multiple anchor graphs to mine the complementary information among multiple views. The clustering metrics are obtained based on the consistency structure, and the consistency of the clustering metrics is also considered to obtain the final clustering results. The effectiveness of the proposed method is verified on multiple datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Biomedical data and AI

引用

science China Life sciences 2025年第5期68卷 1536-1540页

作者： Hao Xu Shibo Zhou Zefeng Zhu Vincenzo Vitelli Liangyi Chen Ziwei Dai Ning Yang Luhua Lai Shengyong Yang Sergey Ovchinnikov Zhuoran Qiao Sirui Liu Chen Song Jianfeng Pei Han Wen Jianfeng Feng Yaoyao Zhang Zhengwei Xie Yang-Yu Liu Zhiyuan Li Fulai Jin Hao Li Mohammad Lotfollahi Xuegong Zhang Ge Yang Shihua Zhang Ge Gao Pulin Li Qi Liu Jing-Dong Jackie Han Peking-Tsinghua Center for Life Sciences (CLS) Academy for Advanced Interdisciplinary StudiesPeking University Center for Quantitative Biology (CQB) Academy for Advanced Interdisciplinary StudiesPeking University Peking University-Tsinghua University-National Institute of Biological Sciences Joint Graduate Program Academy for Advanced Interdisciplinary StudiesPeking University Department of Physics University of Chicago School of Life Sciences Southern University of Science and Technology Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies College of Chemistry and Molecular Engineering Peking University Department of Biotherapy Cancer Center and State Key Laboratory of BiotherapyWest China HospitalSichuan University Department of Biology Massachusetts Institute of Technology Lambic Therapeutics Inc. Changping Laboratory Al for Science Institute Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Department of Obstetrics and Gynecology West China Second University HospitalSichuan University Peking University International Cancer Institute and Peking University-Yunnan Baiyao International Medical Institute and State Key Laboratory of Natural and Biomimetic Drugs Department of Molecular and Cellular PharmacologySchool of Pharmaceutical SciencesPeking University Health Science CenterPeking University Channing Division of Network Medicine Department of MedicineBrigham and Women's Hospital and Harvard Medical School Center for Artificial Intelligence and Modeling the Carl R.Woese Institute for Genomic BiologyUniversity of Illinois Urbana-Champaign Department of Genetics and Genome Sciences School of Medicine and Department of Computer and Data Sciences and Department of Population and Quantitative Health SciencesCase Western Reserve University Department of Biochemistry and Biophysics University of California Sanger Institute Department of Automation Tsinghua University State Key Laboratory of Multimodal Artificial Intelligence Systems I

The development of artificial intelligence(AI) and the mining of biomedical data complement each other. From the direct use of computer vision results to analyze medical images for disease screening, to now integrating biological knowledge into models and even accelerating the development of new AI based on biological discoveries, the boundaries of both are constantly expanding, and their connections are becoming closer.

关键词：

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：