检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Ying Yuan, Ye Luo, Xin The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from real applications, such as the user contact frequency from a social network services system. A graph convolutional network (GCN) is widely adopted to perform representation learning to a UWG for subsequent pattern analysis tasks such as clustering or missing data estimation. However, existing GCNs mostly neglects the latent collaborative information hidden in its connected node pairs. To address this issue, this study proposes to model the node collaborations via a symmetric latent factor analysis model, and then regards it as a node-collaboration module for supplementing the collaboration loss in a GCN. Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module;b) Building the residual connection and weighted representation propagation to obtain high representation capacity;and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG. Empirical studies on UWGs emerging from real applications demonstrate that owing to its efficient incorporation of node-collaborations, the proposed NGCN significantly outperforms state-of-the-art GCNs in addressing the task of missing weight estimation. Meanwhile, its good scalability ensures its compatibility with more advanced GCN extensions, which will be further investigated in our future studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

arXiv

引用

arXiv 2024年

作者： Li, Haopeng Deng, Andong Liu, Jun Rahmani, Hossein Guo, Yulan Schiele, Bernt Bennamoun, Mohammed Ke, Qiuhong School of Computing and Information Systems University of Melbourne Australia Center for Research in Computer Vision University of Central Florida United States Pillar Singapore University of Technology and Design Singapore School of Computing and Communications Lancaster University United Kingdom School of Electronics and Communication Engineering Sun Yat-sen University China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarland Informatics Campus Germany School of Physics Maths and Computing University of Western Australia Australia Department of Data Science & AI Monash University Australia

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Indonesian Abusive Tweet Classification based on Convolutional Neural Network and Long Short Term Memory Method

Indonesian Abusive Tweet Classification based on Convolution...

引用

2021 International Conference on Artificial Intelligence and Big data Analytics, ICaiBDA 2021

作者： Gultom, Reinaldo Yosafat Zulkarnaen, Fahri Izzuddin Nurhasanah, Yahma Sholahuddin, Asep Universitas Padjadjaran Research Center for Artificial Intelligence and Big Data Bandung Indonesia Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Informatics Engineering Department UPN Veteran Jawa Timur Surabaya Indonesia Department of Statistics Universitas Padjadjaran Bandung Indonesia Department of Computer Science Universitas Padjadjaran Bandung Indonesia

ISBN: (纸本)9781665408905

Twitter is one of the famous social media applications in Indonesia. The study will classify data to detect hate speech on Twitter into two classes: abusive and non-abusive. The abusive class will contain tweets in the form of words that contain negative elements or hate speech, while the non-abusive class contains tweets in the form of words that do not contain negative elements. The desired purpose of this research is to help those who need this research to be able to use it to supervise others from hate speech and find the perpetrators who do it. The data used is secondary data taken from the Kaggle website. The data contains tweets that have been classified based on connotations of abusive or non-abusive. Several processes are carried out to achieve the desired goal, including data acquisition, preprocessing, classification, evaluation, and content detection. The algorithms used in the study were LSTM and CNN. Both algorithms produce the same performance relatively. It's just that CNN is slightly superior. The accuracy value of CNN is 0.9131 or 91.31%, the precision is 0.9131 or 91.31%, the recall is 0.9131 or 91.31%, and the F1-Score of 0.9131 or 91.31%. Meanwhile, for LSTM, the accuracy value is 0.9104 or 91.04%, the precision is 0.9104 or 91.04%, the recall is 0.9104 or 91.04%, and the F1-Score is 0.9104 or 91.04% © 2021 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Testing the Inference Accuracy of Accelerator-Friendly Approximate Phylogeny Tracking

Testing the Inference Accuracy of Accelerator-Friendly Appro...

引用

Computational Intelligence in Artificial Life and Cooperative Intelligent Systems (ALIFE-CIS), IEEE Symposium on

作者： Matthew Andres Moreno Anika Ranjan Emily Dolson Luis Zaman Department of Ecology and Evolutionary Biology University of Michigan Ann Arbor United States Center for the Study of Complex Systems University of Michigan Ann Arbor United States Michigan Institute for Data and AI in Society University of Michigan Ann Arbor United States Undergraduate Research Opportunities Program University of Michigan Ann Arbor United States Department of Computer Science and Engineering Michigan State University East Lansing United States Program in Ecology Evolution and Behavior Michigan State University East Lansing United States

ISBN: (数字)9798331508371

ISBN: (纸本)9798331508388

computer simulations are an important tool for studying the mechanics of biological evolution. In particular, agent-based approaches provide an opportunity to collect high-quality records of ancestry relationships. Such phylogenies can provide insight into evolutionary dynamics within these simulations. Previous work generally tracks lineages directly, yielding an exact phylogenetic record of evolutionary history. However, challenges exist in scaling direct ancestrytracking approaches to highly-distributed, many-processor evolution in silico. An alternative approach is to estimate phylogenetic history via noncoding annotations on digital genomes, akin to how bioinformaticians build phylogenies by assessing genetic similarities between organisms. Recent work has extended this “hereditary stratigraphy” approach to support powerful hardware accelerator platforms, such as the Cerebras Wafer-Scale Engine. Although these second-generation “surface”-based hereditary stratigraphy algorithms have demonstrated order-ofmagnitude speedups over first-generation “column”-based algorithms, it remains unknown how they impact the accuracy of reconstructed phylogenies. To address this question, we assessed reconstruction accuracy under alternative configurations across a matrix of evolutionary conditions varying in selection pressure, spatial structure, and ecological dynamics. Encouragingly, we find that the second-generation approaches provide higher reconstruction quality across most surveyed conditions.

关键词： Surface reconstruction Accuracy Annotations Heuristic algorithms Computational modeling Biological system modeling Stratigraphy Phylogeny History Bars

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Enabled Real-Time Optimization System for Traffic and Power Grid Management in 6G-Driven Smart Cities

引用

IEEE Internet of Things Journal 2025年

作者： Prathiba, Sahaya Beni Krishnamoorthy, Sri Ram Kannan, Karuna Soundari Selvaraj, Arikumar K. Ranganayakulu, Dhanalakshmi Fang, Kai Gadekallu, Thippa Reddy Vellore Institute of Technology Centre for Cyber Physical Systems School of Computer Science and Engineering Chennai600127 India Vellore Institute of Technology School of Electronics Engineering Chennai600127 India College of Engineering and Technology Department of Data Science and Business Systems Kattankulathur603 203 India Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Zhejiang A and F University Division of Research and Development Lovely Professional University College of Mathematics and Computer Science Hangzhou Phagwara311300 India Chitkara University Center of Research Impact and Outcome Punjab Rajpura140401 India

The advent of 6G-enabled Internet of Everything(IoE) technologies is set to revolutionize urban infrastructures by providing fast, consistent, and low-delay capabilities for communication. 6G connectivity will integrate traffic and power grids for adaptive urban management. However, current traffic networks and power grids face critical challenges such as fragmented data processing, delayed responses, and outdated resource management leading to inefficiencies like traffic congestion and power outages. In 6G-enabled smart grid cities, system complexity and interdependence demand dynamic, real-time solutions, further exacerbating inefficiencies. To address these issues, this study introduces Digital Twin-enabled Real-time Optimization System (DT-ROS), a dynamic framework designed to optimize urban traffic and power grid systems. DT-ROS integrates a dual-tier Digital Twin (DT) and an advanced scheduling framework based on Priority Age of Information Deep Q Scheduler (PAoI-QS). The dual-tier framework builds an elementary and Integrated Digital Twin (IDT) with Auto-Regressive Integrated Moving Average (ARIMA)-based forecasting for accurate real-time traffic and energy demand predictions. The advanced scheduling framework minimizes the Age of Information (AoI), ensuring decision-making relies on the most current and relevant data. By continuously monitoring and processing real-time data, DT-ROS creates virtual models to simulate system behavior and dynamically allocate resources. Simulation results demonstrate the effectiveness of DT-ROS, achieving a 30% reduction in traffic congestion and a 25% improvement in power grid stability compared to existing methods. To create effective, robust, and sustainable urban systems for future smart cities, DT-ROS addresses traffic and electricity problems. © 2014 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Optimization Design for Federated Learning in Heterogeneous 6G Networks

arXiv

引用

arXiv 2023年

作者： Luo, Bing Ouyang, Xiaomin Sun, Peng Han, Pengchao Ding, Ningning Huang, Jianwei The Data Science Research Center the Division of Natural and Applied Sciences Duke Kunshan University Jiangsu Kunshan China The department of Information Engineering The Chinese University of Hong Kong Hong Kong The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China The Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States

With the rapid advancement of 5G networks, billions of smart Internet of Things (IoT) devices along with an enormous amount of data are generated at the network edge. While still at an early age, it is expected that the evolving 6G network will adopt advanced artificial intelligence (ai) technologies to collect, transmit, and learn this valuable data for innovative applications and intelligent services. However, traditional machine learning (ML) approaches require centralizing the training data in the data center or cloud, raising serious user-privacy concerns. Federated learning, as an emerging distributed ai paradigm with privacy-preserving nature, is anticipated to be a key enabler for achieving ubiquitous ai in 6G networks. However, there are several system and statistical heterogeneity challenges for effective and efficient FL implementation in 6G networks. In this article, we investigate the optimization approaches that can effectively address the challenging heterogeneity issues from three aspects: incentive mechanism design, network resource management, and personalized model optimization. We also present some open problems and promising directions for future research. Copyright © 2023, The Authors. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

FishEye8K: A Benchmark and dataset for Fisheye Camera Object Detection

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Munkhjargal Gochoo Munkh-Erdene Otgonbold Erkhembayar Ganbold Jun-Wei Hsieh Ming-Ching Chang Ping-Yang Chen Byambaa Dorj Hamad Al Jassmi Ganzorig Batnasan Fady Alnajjar Mohammed Abduljabbar Fang-Pang Lin Department of Computer Science and Software Engineering United Arab Emirates University UAE Emirates Center for Mobility Research United Arab Emirates University UAE College of AI and Green Energy National Yang Ming Chiao Tung University Taiwan University at Albany — State University of New York NY USA Department of Computer Science National Yang Ming Chiao Tung University Taiwan Mongolian University of Science and Technology Mongolia National Center for High-Performance Computing Taiwan

With the advance of ai, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of State-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080×1080 and 1280×1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70:30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640×640 and 1280×1280, respectively. The dataset will be available on the GitHub link with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Passenger Waiting Time Prediction Based on Density Spatiotemporal Clustering and Time Series Feature Processing

Passenger Waiting Time Prediction Based on Density Spatiotem...

引用

International Conference on Electronic engineering and Informatics (EEI)

作者： Ruixi Huang Dawen Xia Jian Geng Wenyong Zhang Yang Hu Yantao Li Huaqing Li College of Data Science and Information Engineering Guizhou Minzu University Guiyang China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili China College of Big Data Engineering & College of Microelectronics and Artificial Intelligence Kaili University Kaili China Party School of the Anshun Municipal Committee of C.P.C Anshun China Department of Automotive Engineering Guizhou Traffic Technician and Transportation College Guiyang China College of Computer Science Chongqing University Chongqing China College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

Accurate passenger waiting time prediction addresses the taxi supply-demand imbalance in Intelligent Transport Systems (ITS). To capture the dependencies of passenger waiting time on urban taxi distribution, we propose a Density Spatiotemporal Clustering and Time Series Feature Processing (DSC-TSFP) method that discovers potential feature relationships of taxi GPS trajectory data. Specifically, a Multilevel Spatiotemporal Density-Based Spatial Clustering of applications with Noise (MST-DBSCAN) is proposed to cluster taxi GPS trajectory data to obtain waiting time series with spatiotemporal correlations. Furthermore, a time series processing module based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Normalization (CEEMDANN) is designed to enhance prediction accuracy by handling non-stationarity and numerical discrepancy, which solves the residual white noise problem in Intrinsic Modal Functions (IMFs) of EEMD and CEEMD. Next, a waiting time prediction module oriented to a Convolutional Long Short-Term Memory Network (ConvLSTM) is incorporated to compensate for the defects of spatially localized dependencies that LSTM cannot capture. Finally, a CEEMDANN-ConvLSTM model is constructed to predict the passenger waiting time by combining the time series processing and waiting time prediction module. Based on real-world taxi GPS trajectory data, experimental results demonstrate that DSC-TSFP outperforms comparable methods regarding prediction accuracy.

关键词： Accuracy Time series analysis White noise Predictive models Trajectory Spatiotemporal phenomena Informatics Public transportation Long short term memory Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for geoscience:Progress,challenges,and perspectives

引用

The Innovation 2024年第5期5卷 136-160,135页

作者： Tianjie Zhao Sheng Wang Chaojun Ouyang Min Chen Chenying Liu Jin Zhang Long Yu Fei Wang Yong Xie Jun Li Fang Wang Sabine Grunwald Bryan MWong Fan Zhang Zhen Qian Yongjun Xu Chengqing Yu Wei Han Tao Sun Zezhi Shao Tangwen Qian Zhao Chen Jiangyuan Zeng Huai Zhang Husi Letu Bing Zhang Li Wang Lei Luo Chong Shi Hongjun Su Hongsheng Zhang Shuai Yin Ni Huang Wei Zhao Nan Li Chaolei Zheng Yang Zhou Changping Huang Defeng Feng Qingsong Xu Yan Wu Danfeng Hong Zhenyu Wang Yinyi Lin Tangtang Zhang Prashant Kumar Antonio Plaza Jocelyn Chanussot Jiabao Zhang Jiancheng Shi Lizhe Wang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Computer Science China University of GeosciencesWuhan 430078China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China Data Science in Earth Observation Technical University of Munich80333 MunichGermany The National Key Laboratory of Water Disaster Prevention Yangtze Institute for Conservation and DevelopmentHohai UniversityNanjing 210098China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China Soil Water and Ecosystem Sciences DepartmentUniversity of FloridaPO Box 110290GainesvilleFLUSA Materials Science Engineering Program Cooperating Faculty Member in the Department of Chemistry and Department of Physics Astronomy University of CaliforniaCaliforniaRiversideCA 92521USA Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China Key Laboratory of Computational Geodynamics University of Chinese Academy of SciencesBeijing 100049China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China College of Geography and Remote Sensing Hohai UniversityNanjing 211100China Department of Geography The University of Hong KongHong Kong 999077SARChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China School of Environmental Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China Collaborative Inno

This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(ai)and data collection *** models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical ***,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world *** contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical *** techniques have shown promise in addressing Earth science-related ***,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of ai models hinder their seamless integration into *** integration of physics-based and data-driven methodologies into hybrid models presents an alternative *** models,which incorporate domain knowledge to guide ai methodologies,demonstrate enhanced efficiency and performance with reduced training data *** review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced ai techniques and *** examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of ai in *** paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.

关键词： Earth utilizing landscape

来源：评论

学校读者我要写书评

暂无评论

BioAR: Bio-Laboratory Automation Meets Augmented Reality 14th

BioAR: Bio-Laboratory Automation Meets Augmented Reality

引用

14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021

作者： Zou, Zheng Liu, Shi-Jian College of Computer and Cyber Security Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China Fujian Provincial Engineering Technology Research Center for Public Service Big Data Mining and Application Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China Digital Fujian Institute of Big Data Security Technology Fujian Normal University No. 8 Xuefu South Road Fujian Shangjie Minhou Fuzhou China College of Computer Science and Mathematics Fujian University of Technology No. 3 Xueyuan Road University Town Fujian Minhou Fuzhou China

ISBN: (纸本)9789811684296

Modern laboratory is benefiting from science and engineering by adopting automated systems into labor-intensive lab routines. In this paper, a computer-aided system that involves augmented reality (AR) to promote the automatic levels of the bio-laboratory is introduced. The motivation of this work lies in the idea of offering visual guidance for users to pick a tube manually from the rack after the retrieval. Because it is difficult for people to tell the target tube from the others since they look almost the same. Design issues and implementation details are given after a careful analysis of the system requirements. The BioAR system is tested out and successfully applied to a bio-laboratory with tube related operations, whose performance is approved by the technicians. A video demo of the proposed system can be found at https://***/video/BV1FX4y157WB/. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality

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：