检索结果-内蒙古大学图书馆

Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Liang, Xinyu Wang, Hao Monash University Faculty of Information Technology Monash Energy Institute Department of Data Science and AI MelbourneVIC3800 Australia

The scarcity of high-quality residential load data can pose obstacles for decarbonizing the residential sector as well as effective grid planning and operation. The above challenges have motivated research into generating synthetic load data, but existing methods faced limitations in terms of scalability, diversity, and similarity. This paper proposes a Generative Adversarial Network-based Synthetic Residential Load Pattern (RLP-GAN) generation model, a novel weakly-supervised GAN framework, leveraging an over-complete autoencoder to capture dependencies within complex and diverse load patterns and learn household-level data distribution at scale. We incorporate a model weight selection method to address the mode collapse problem and generate load patterns with high diversity. We develop a holistic evaluation method to validate the effectiveness of RLP-GAN using real-world data of 417 households. The results demonstrate that RLP-GAN outperforms state-of-the-art models in capturing temporal dependencies and generating load patterns with higher similarity to real data. Furthermore, we have publicly released the RLP-GAN generated synthetic dataset1, which comprises one million synthetic residential load pattern profiles. © 1975-2011 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Analysis Geomorphic Flood Index in Determining Flood-Prone Areas in East Kalimantan Province, Indonesia

Analysis Geomorphic Flood Index in Determining Flood-Prone A...

引用

2024 Annual Conference, ASPRS 2024

作者： Virtriana, Riantini Amalia, Annisa Fitri Ihsan, Kalingga Titon Nur Anggraini, Tania Septi Harto, Agung Budi Deliar, Albertus Geospatial Information Science and Technology Research Group Faculty of Earth Science and Technology Bandung Institute of Technology Bandung40132 Indonesia Center for Remote Sensing Bandung Institute of Technology Bandung40132 Indonesia Geodesy and Geomatic Engineering Faculty of Earth Sciences and Technology Bandung40132 Indonesia Doctor Program in Program Study of Geodesy and Geomatic Engineering Faculty of Earth Sciences and Technology Bandung40132 Indonesia Universitas Pendidikan Indonesia Bandung40111 Indonesia Center for Spatial Data Infrastructure Bandung Institute of Technology Bandung40132 Indonesia

In 2022, there are 1,524 flood events out of a total of 3,531 disasters occurring in Indonesia. East Kalimantan Province ranked 20th among the 35 provinces in Indonesia with 28 flood occurrences in 2022, resulting in two fatalities. This highlights the urgent need for addressing flood hazard to prevent future casualties. There are some methods that can be used to determine the flood hazard in a region. In this research aims to identify flood-prone areas in East Kalimantan Province and evaluate the effectiveness of different mapping methods. The methodology that compares are the Pairwise Comparison method and Geomorphic Flood Index (GFI). The study's results provide flood-prone area maps of East Kalimantan Province using both methods, recommend the more efficient method for flood-prone area identification, and offer mitigation strategies based on the findings. This research is intended to serve as a reference for selecting the best method for identifying flood-prone areas and for informing policy decisions to mitigate flood impacts in East Kalimantan Province. © Author(s) 2025.

关键词： Hazards

来源：评论

学校读者我要写书评

暂无评论

gTRAVEL+: Enhancing Ground Segmentation for 3D Point Cloud with Temporal Noise Removal and Adaptive Plane Fitting for Urban and Off-Road Environments

引用

IEEE Access 2025年 13卷 82431-82440页

作者： Dao, Truong Giang Tran, Dinh Tuan Nguyen, Duc Manh Lee, Joo-Ho Nguyen, Anh Quang Hanoi University of Science and Technology School of Electrical and Electronic Engineering Viet Nam Shiga University Faculty of Data Science Japan Ritsumeikan University College of Information Science and Engineering Japan

Ground segmentation plays an increasingly important role as a preprocessing module for numerous applications such as Simultaneous Localization and Mapping (SLAM), place recognition, and point cloud registration. The efficiency and accuracy of ground segmentation can directly influence the performance of these applications. While several methods have been proposed, they continue to struggle to meet the comprehensive requirements of robust ground segmentation. To this end, we propose a ground segmentation method called gTRAVEL+, an improvement of TRAVEL that focuses exclusively on enhancing ground segmentation performance. Our method exploits a temporal and locally-aware noise removal strategy, termed Temporal Node-Wise Noise Removal (TNNR), which effectively eliminates noise points that compromise the ground plane fitting process. Additionally, Merge Node Plane Fitting (MNPF) is proposed to address issues of partial under-segmentation arising from suboptimal region sizing. Finally, Rejected Ground Node Revert (RNGR) ensures thorough geometric relationship verification, significantly improving true positives. Quantitative and qualitative experiments conducted on both urban and off-road environments show that our proposed method demonstrates superior performance, achieving a F₁-score of 95.16% and competitive speed compared to state-of-the-art methods. © 2013 IEEE.

关键词： Ground Segmentation LiDAR-based Perception Mapping

来源：评论

学校读者我要写书评

暂无评论

Mapping the Scientific Landscape of Integrated Scheduling Towards Industry 5.0 with A Bibliometric Analysis 6

Mapping the Scientific Landscape of Integrated Scheduling To...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Putri Ardyanti, Anak Agung Ayu Xie, Zhiqiang Karnyoto, Andrea Stevens Pardamean, Bens Estiyanti, Ni Made School of Computer Science and Technology Harbin University of Science and Technology Harbin150000 China Faculty of Information Technology and Design Primakara University Bali 80226 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia School of Management and Business University of Debrecen Debrecen Hungary

The industry is rapidly transitioning from the 4.0 era to the 5.0 era, prompting renewed interest among scholars in scheduling problems. They allow operations to process and assemble various components simultaneously. This bibliometric analysis provides a comprehensive understanding of the diverse research perspectives on the potential challenges of integrated scheduling within the framework. We identified 357 Scopus articles and analysed co-occurrence keyword (CNK) by VOSViewer tools and Global Citation Score (GCS) by Scopus tools. The research data obtained from 1993 to 2023 mainly in the subject areas of Engineering, Computer science, Maths, and others. CNK identified six cluster keywords, and nine most cited articles based on normalised GCS. These results contribute to our understanding of the development of scheduling algorithms, shifting from an emphasis on manufacturing transfers to contemporary demand-centric research directions. Furthermore, this research provides a valuable perspective for policymakers, plant personnel, and manufacturing managers to make informed decisions. © 2025 The Authors. Published by Elsevier B.V.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Evaluation Method of Motor Coordination Ability in Children Based on Machine Vision

引用

Tsinghua science and technology 2025年第2期30卷 633-649页

作者： Yi Lei Dawei Shu Miao Yu Donglin Shi Jianqiang Li Yanjie Chen Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Department of Automation Tsinghua UniversityBeijing 100084China Pharmacovigilance Research Center for information technology and Data Science Cross-strait Tsinghua Research InstituteXiamen 361000China Institute of Systems Engineering Dalian University of TechnologyDalian 116024China Physical Education Department Hebei Sports UniversityShijiazhuang 050049China Department of Children’s Health Care Center Beijing Children’s HospitalCapital Medical UniversityNational Center for Children’s HealthBeijing 100045China

Motor coordination is crucial for preschoolers’development and is a key factor in assessing childhood *** diagnostic methods often rely on subjective manual *** paper presents a machine vision-based approach aimed at improving the objectivity and adaptability of *** method proposed involves the extraction of key points from the human skeleton through the utilization of a lightweight pose estimation network,thereby transforming video assessments into evaluations of keypoint *** study uses different methods to handle static and dynamic actions,including regularization and Dynamic Time Warping(DTW)for spatial alignment and temporal discrepancies.A penalty-adjusted single-frame pose similarity method is used to evaluate *** lightweight pose estimation model reduces parameters by 85%,uses only 6.6%of the original computational load,and has an average detection missing rate of less than 1%.The average error for static actions is 0.071 with a correlation coefficient of 0.766,and for dynamic actions it is 0.145 with a correlation coefficient of *** results confirm the proposed method’s effectiveness,which includes customized visual components like motion waveform graphs to improve accuracy in pediatric healthcare diagnoses.

关键词： developmental coordination disorder action quality assessment pose estimation dynamic time warping decision support system

来源：评论

学校读者我要写书评

暂无评论

Job Resumes Recommendation using Integration of Fuzzy Discernibility Matrix Feature Selection and Convolutional Neural Network Multi-label Text Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 49-58页

作者： Hayami, Regiolina Yusoff, Nooraini Daud, Kauthar Mohd Fatma, Yulia Department of Informatics Engineering Faculty Computer Science Universitas Muhammadiyah Riau Indonesia Faculty of Data Science and Computing Universiti Malaysia Kelantan 16100 Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Malaysia

The manual analysis of job resumes poses specific challenges, including the time-intensive process and the high likelihood of human error, emphasizing the need for automation in content-based recommendations. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN) for Multi-label Text Classification (MLTC), offer a promising solution for addressing these challenges through artificial intelligence. While CNN is renowned for its robust feature extraction capabilities, it faces specific challenges such as managing high-dimensional data and poor data interpretability. To address these limitations, this study employs the Fuzzy Discernibility Matrix (FDM) feature selection technique to determine the relevance of skills for each job vacancy. FDM assigns weights to the features of each job category and ranks their relevance based on the highest scores, which are then utilized in the MLTC CNN model. The integration of FDM and MLTC CNN serves as the foundation for generating content-based recommendations derived from key features in job resumes. This study produces a content-based job recommendation system that displays the top three job categories, accompanied by explanations of the skills supporting each selected category. These recommendations also consider cosine similarity values between analyzed items and the integrated results of FDM and MLTC CNN. The application of FDM for feature weighting has been proven to enhance multi-label text classification outcomes by providing better insights during the feature selection process. With a recall of 97.26%, precision of 94.81%, and accuracy of 98.58%, the MLTC model integrating FDM feature selection and CNN demonstrates robust performance characteristics in content-based job recommendation tasks. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic Offloading Control for Waste Sorting Based on Deep Q-Network 24th

Dynamic Offloading Control for Waste Sorting Based on Deep...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Jing Wang, Xiaoyang Guo, Jianxiong Tang, Zhiqing Ding, Xingjian Wang, Tian Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (纸本)9789819615278

With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to solve waste sorting in wireless bin communication networks. Due to limited computational power, bins belonging to embedded devices rely on simple classification models with varying accuracy. In this scenario, consider a network of intelligent bins, each acting as an independent agent capable of deciding to offload an image to the edge server with a more accurate but resource-intensive model when the local classification is deemed inaccurate. Thus, Our goal is to find a lightweight online offloading policy that can achieve the best possible sorting accuracy while balancing transmission traffic. The method utilizes a Deep Q-network algorithm that enables each intelligent bin to make image-processing decisions autonomously. In the experiment, we validate the effectiveness of improving the performance of waste classification compared with existing flow control methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed Resource Allocation Intelligent Waste Management Waste Sorting Wireless Communication Network

来源：评论

学校读者我要写书评

暂无评论

An Inconsistency-Based Hybrid Feature Selection Approach for Enhancing Medical Classification Modeling 2nd

An Inconsistency-Based Hybrid Feature Selection Approach for...

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Zhao, Rong ALDharhani, Ghassan Saleh Ratnavelu, Kuru Thambiayya, Sathiyaraj Jasser, Muhammed Basheer Majeed, Anwar P. P. Abdul Luo, Yang Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur56000 Malaysia Institute of Information Science and Technology Dalian University of Science and Technology Dalian China Faculty of Information Science and Technology UKM University Selangor Bangi43000 Malaysia Institute of Mathematical Sciences University of Malaya Kuala Lumpur56000 Malaysia Institute of Actuarial Science and Data Analytics UCSI University Kuala Lumpur56000 Malaysia Department of Data Science and Artificial Intelligence School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia School of Intelligent Manufacturing Ecosystem Xi’an Jiaotong-Liverpool University Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

Artificial Intelligence is an essential tool for early disease recognition and supporting patient condition monitoring in the future. Timely and exact conclusions about the type of disease are significant for treatment and life extension. A combination of classification and feature selection algorithms can effectively handle complex datasets in the medical field and improve the accuracy of disease diagnosis and treatment. In this paper, we propose a new hybrid feature selection algorithm that uses inconsistency metrics as a filter method for the first step, and then feeds the resulting dataset into a wrapper method, which ultimately results in a reduced dataset. The proposed HFSIM algorithm is tested on five datasets in the medical domain from Kaggle. The obtained feature subsets are verified on three classification algorithms, KNN, LR and RF of machine learning to validate the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm obtains feature subsets with low dimensionality on most of the datasets and also has high classification accuracy after testing on the classifiers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Introducing the Hyperdynamic Adaptive Learning Fusion (HALF) model for superior predictive analytics in E-learning

引用

Neural Computing and Applications 2025年 1-21页

作者： Islam, Umar Alali, Ibrahim Khalil Alotaibi, Shoayee Dlaim Alzaid, Zaid Shah, Babar Ali, Ijaz Moreira, Fernando Department of Computer Science IQRA National University Swat Campus Peshawar Pakistan Department of Instructional Technology Jouf University Sakaka Saudi Arabia Department of Artificial Intelligence and Data Science University of Hail Hail Saudi Arabia Faculty of Computer Science and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia College of Technological Innovation Zayed University Dubai United Arab Emirates REMIT Portucalense University & IEETA Aveiro University Aveiro Portugal

Today’s complex world is defined by digital changes in educational paradigms to which E-learning has contributed significantly, and as such, accurate prediction methods are needed for student performance modeling. In this paper a new and complex model is proposed, namely the Hyperdynamic Adaptive Learning Fusion (HALF) model that leverages adaptive computing paradigms and artificial intelligence to build a fusion of learning that adapts to the new learning patterns. Many conventional predictive models employ linear and simplistic relationships to predict an outcome from an input;hence, they fail to decompose complex and heterogenic data patterns of educational data and also suffer from scalability issues for dealing with large volumes of data. To overcome these issues, the HALF model employs the relevant ensemble learning algorithms that consist of bagging, boosting, and an innovative adaptive fusion strategy that integrates base and adaptive models to achieve higher accuracy and resilience in the latter. In doing so, and by adopting the scientific method of working on trials and errors and rigorous assessment employing a database derived from the Open University VLE, the investigation presented in this paper provides compelling evidence of the HALF model’s superior efficacy, which yields an accuracy of 87%. 2%, precision of 85. 4% It has been proved that 3% of all students have significant learning disabilities, while the recall value is 89. 1%, surpassing traditional methods. The model’s equation can be easily applied to any variety of courses and of students, which makes it highly beneficial to educators and administrators;at the same time, the model is highly interpretable. Therefore, HALF model proves to be a revolutionary addition to the current kind of statistical modeling in E-learning that depicts student engagement pattern into more precise and accurate form, reduce biases in all way possible and provides solution that might help to improve the course outc

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PERSONALIZED FEDERATED LEARNING FOR EGOCENTRIC VIDEO GAZE ESTIMATION WITH COMPREHENSIVE PARAMETER FREZZING

arXiv

引用

arXiv 2025年

作者： Feng, Yuhu Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki Graduate School of Information Science and Technology Hokkaido University Japan Data-Driven Interdisciplinary Research Emergence Department Hokkaido University Japan Faculty of Information Science and Technology Hokkaido University Japan

Egocentric video gaze estimation requires models to capture individual gaze patterns while adapting to diverse user data. We propose a Personalized Federated Learning (PFL) framework with Comprehensive Parameters Freezing (FedCPF) to improve gaze estimation in distributed environments. Our approach leverages a transformer-based architecture, integrating it into a PFL framework where only the most significant parameters—those exhibiting the highest rate of change during training—are selected and frozen for personalization in client models. Through extensive experimentation on the EGTEA Gaze+ and Ego4D datasets, we demonstrate that FedCPF significantly outperforms previously reported federated learning methods, achieving superior recall, precision, and F1-score. These results confirm the effectiveness of our comprehensive parameters freezing strategy in enhancing model personalization, making FedCPF a promising approach for tasks requiring both adaptability and accuracy in federated learning settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated 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：