检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Wei Bai Xiaosu Wang Bo Liang Guoyuan Yang Hanyu Zhi Yinwei Qiao Institute of Computing Technology China Academy of Railway Sciences co. Ltd. Beijing China Postgraduate Department China Academy of Railway Sciences Beijing China School of Automation and Software Engineering Shanxi University Taiyuan China

The excessive length and high semantic complexity of station equipment fault handling report texts are addressed to the extent that effective text recognition is difficult to achieve. A station equipment fault handling dataset is formulated and a text recognition system for station fault reports based on the BERT-BiLSTM-CRF model is designed. The method first preprocesses the data using the BERT pre-trained language model to generate word vectors, which are then fed into BiLSTM to obtain the embedded contextual information, which is passed through the CRF model to obtain the global optimal solution, and finally outputs the textual results of the station equipment fault handling. The experimental results show that the model outperforms the other five comparative models by more than 2% in terms of precision, recall, and $F$ 1 value (checking accuracy) for intelligent recognition over the five entities predicted by the other five comparative models. This brings a new direction of thinking for the analysis of equipment troubleshooting texts in railway stations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analog One-Cycle Control Based Scheme for Battery Charging in Photovoltaic Systems

Analog One-Cycle Control Based Scheme for Battery Charging i...

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： João T. de Carvalho Neto Andrés O. Salazar Natal-East Side Campus Federal Institute of Education Science and Technology of Rio Grande do Norte Natal-RN Brazil Department of Computing Engineering and Automation Federal University of Rio Grande do Norte Natal-RN Brazil

In recent years, the use of photovoltaic systems has getting more attention because radiation is converted directly into electricity without the use of inverters. A major scientific challenge in this theme consists of clean energy storage systems, widely researched for charging electric vehicles (EVs). Batteries are one of the most common ways to store the generated energy directly from photovoltaic systems. Current literature proposes several challenges in charging batteries using photovoltaic systems, especially when it comes to increasing their lifetime, since sudden changes in irradiation cause voltage overshoots in the batteries. This article presents a control strategy based in One-Cycle Control to prevent damages in the batteries adapting its voltage to varying input voltages. The main purpose of this paper is to present applicability of One-Cycle Control based control scheme used for battery charging. The experimental results present the power and controller signal analysis in steady state conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-task Optimization Based Co-training for Electricity Consumption Prediction

arXiv

引用

arXiv 2022年

作者： Song, Hui Qin, A.K. Yan, Chenggang School of Engineering RMIT University Melbourne Australia Department of Computing Technologies Swinburne University of Technology Hawthorn Australia School of Automation Hangzhou Dianzi University Hangzhou China

Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving knowledge that could be extracted and shared among these tasks to augment the performance of solving each task. In this work, we propose a multi-task optimization (MTO) based co-training (MTO-CT) framework, where the models for solving different tasks are co-trained via an MTO paradigm in which solving each task may benefit from the knowledge gained from when solving some other tasks to help its solving process. MTO-CT leverages long short-term memory (LSTM) based model as the predictor where the knowledge is represented via connection weights and biases. In MTO-CT, an inter-task knowledge transfer module is designed to transfer knowledge between different tasks, where the most helpful source tasks are selected by using the probability matching and stochastic universal selection, and evolutionary operations like mutation and crossover are performed for reusing the knowledge from selected source tasks in a target task. We use electricity consumption data from five states in Australia to design two sets of tasks at different scales: a) one-step ahead prediction for each state (five tasks) and b) 6-step, 12-step, 18-step, and 24-step ahead prediction for each state (20 tasks). The performance of MTO-CT is evaluated on solving each of these two sets of tasks in comparison to solving each task in the set independently without knowledge sharing under the same settings, which demonstrates the superiority of MTO-CT in terms of prediction accuracy. Copyright © 2022, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficient Twin Migration in Vehicular Metaverses: Multi-Agent Split Deep Reinforcement Learning with Spatio-Temporal Trajectory Generation

引用

IEEE Transactions on Mobile computing 2025年

作者： Chen, Junlong Kang, Jiawen Xu, Minrui Wu, Fan Zhang, Hongliang Huang, Huawei Niyato, Dusit Mao, Shiwen Guangdong University of Technology School of Automation Guangzhou China Nanyang Technological University School of Computing and Data Science Singapore Singapore Central South University School of Computer Science and Engineering Changsha China Peking University School of Electronics Beijing China Sun Yat-Sen University School of Data and Computer Science Guangzhou China Auburn University Department of Electrical and Computer Engineering Auburn United States

Vehicle Twins (VTs) as digital representations of vehicles can provide users with immersive experiences in vehicular metaverse applications, e.g., Augmented Reality (AR) navigation and embodied intelligence. VT migration is an effective way that migrates the VT when the locations of physical entities keep changing to maintain seamless immersive VT services. However, an efficient VT migration is challenging due to the rapid movement of vehicles, dynamic workloads of Roadside Units (RSUs), and heterogeneous resources of the RSUs. To achieve efficient migration decisions and a minimum latency for the VT migration, we propose a multi-agent split Deep Reinforcement Learning (DRL) framework combined with spatio-temporal trajectory generation. In this framework, multiple split DRL agents utilize split architecture to efficiently determine VT migration decisions. Furthermore, we propose a spatio-temporal trajectory generation algorithm based on trajectory datasets and road network data to simulate vehicle trajectories, enhancing the generalization of the proposed scheme for managing VT migration in dynamic network environments. Finally, experimental results demonstrate that the proposed scheme not only enhances the Quality of Experience (QoE) by 29% but also reduces the computational parameter count by approximately 25% while maintaining similar performances, enhancing users' immersive experiences in vehicular metaverses. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comprehensive electrical models for a wireless sensor network device

引用

Heliyon 2024年第23期10卷 e40415页

作者： León Ávila, Bernardo Yaser García Vázquez, Carlos Alberto Pérez Baluja, Osmel Cotfas, Daniel Tudor Cotfas, Petru Adrian Transilvania University of Brașov Department of Electronics and Computers Faculty of Electrical Engineering and Computer Science Brasov 500036 Romania University of Sancti Spiritus “José Martí Pérez” Department of Computer Engineering Faculty of Business and Technical Sciences Comandante Manuel Fajardo s/n Olivos 1 Sancti Spíritus 60100 Cuba Technological University of Havana Department of Automation and Computing Faculty of Automation and Biomedical Engineering Street 114 No. 11901 between Ciclovía and Rotonda Havana 19390 Cuba

This paper proposes a novel circuit model of a Wireless Sensor Network (WSN) device. The model is designed to accurately represent the behavior of a WSN device operating in a duty cycle, capturing the essential characteristics of its components, including the microcontroller, sensor, transceiver, and power supply. The proposed model incorporates static and dynamic power consumption aspects, reflecting the energy usage patterns during various operational states such as sensing, processing, and communication. The model's accuracy is validated through a comparative analysis with a LTspice® implementation and a real mote implemented for this study. Simulation results closely match the empirical data, demonstrating the model's effectiveness in predicting the mote's behavior. This approach provides a valuable tool for optimizing power consumption and extending the lifetime of WSN deployments within a simulation environment, offering significant insights for designers and researchers in this field. © 2024 The Authors

关键词： Electric model SPICE model Wireless sensor network node

来源：评论

学校读者我要写书评

暂无评论

Numerical Analysis of Internal Defect Detection in Aluminum Alloy Pipes Aims to Provid Data Support for AI Models

Numerical Analysis of Internal Defect Detection in Aluminum ...

引用

Advanced Information, Mechanical engineering, Robotics and automation (AIMERA), IEEE International Conference on

作者： Pengshihan Bai Shang Wang Jianqiao Long Kexin Zheng Jing Ma Nandu Li Steve Bruce School of Metallurgical and Ecological Engineering University of Science and Technology Beijing Beijing China School of Automotive Engineering Beijing Polytechnic Beijing China School of Computing Newcastle University UK Dezhou Natural Resources Bureau Shandong China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China Department of Research & Development SEH Automation Pte Ltd Singapore

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

The online effective detection of internal defects in metals has long faced many challenges. The rapid development of Artificial Intelligence (AI) technology has provided possibilities for improving defect detection techniques. However, AI algorithms rely heavily on large amounts of data, which are difficult to obtain through traditional experimental methods. To address this issue, this study proposes a method for the internal defect detection of aluminum alloy pipes and provides data support for AI models and algorithms. We established a "pinch roller-pressure roller-aluminum alloy pipes" model and obtained the variation rules of Mises stress, constraint reaction force caused by the change of internal defect position through numerical calculation. The results show that the position change of the internal defect has a clear functional relationship with the constraint reaction force of roller-A. When the defect is located near the lower part of roller-B, the constraint reaction force of roller-A reaches the maximum value (978.8 N). This study provides empirical evidence for establishing an online defectdetection AI models. It clarifies the evolution pattern of constraint forces related to crack location. These findings provide data support for developing efficient and accurate defect online detection systems based on AI to address the limitations of traditional methods.

关键词： Force Metals Production Aluminum alloys Data models Numerical models Artificial intelligence Stress Monitoring Defect detection

来源：评论

学校读者我要写书评

暂无评论

GSLB: the graph structure learning benchmark 23

GSLB: the graph structure learning benchmark

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhixun Li Liang Wang Xin Sun Yifan Luo Yanqiao Zhu Dingshuo Chen Yingtao Luo Xiangxin Zhou Qiang Liu Shu Wu Jeffrey Xu Yu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Department of Automation University of Science and Technology of China Department of Automation University of Science and Technology of China School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science University of California Los Angeles Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review of Inference Time Prediction Approaches of DNN: Emphasis on Service robots with cloud-edge-device architecture

Review of Inference Time Prediction Approaches of DNN: Empha...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Tian Xiang Qiwei Meng Ji Zhang Beibei Zhang Wei Song Anhuan Xie Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong HKSAR China Research Center for Intelligent Computing Software Research Institute of Intelligent Computing Zhejiang Laboratory Hangzhou China Electrical and Computer Engineering Dalhousie University Halifax Canada

In recent years, the global robot market has witnessed substantial growth, particularly in the domain of service robots. Despite their expanding presence, service robots encounter limitations when operating autonomously in unstructured environments, primarily due to their constrained computational capacities. As a solution, the fusion of cloud and edge computing resources becomes imperative to expedite task inference and enhance scenario perception capabilities. The integration of cloud-edge-device models holds significant promise in bolstering the operational efficiency of robots. This entails the dynamic partitioning of intricate robotic tasks, executed collaboratively across cloud, edge, and device resources. In this landscape, deep neural network (DNN) models play a pivotal role in facilitating a wide array of robotic tasks. The inference time for each layer of a DNN model in actual deployment, emerges as a critical determinant in the model’s partitioning strategy. It also serves as an important metric influencing the model’s suitability for a specific hardware platform. This article presents an overview of recent advancements in predicting inference and training time of DNN models, summarizes the related methods, and finally discusses the challenges in this field and the research that can be studied in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Activity Mining in Multi-Occupancy Contexts Based on Nearby Interaction Under a Fuzzy Approach

SSRN

引用

SSRN 2023年

作者： Polo-Rodríguez, Aurora Cavallo, Filippo Nugent, Chris Medina-Quero, Javier Department of Computer Science University of Jaén Jaén23071 Spain Department of Industrial Engineering University of Florence Florence50121 Italy School of Computing Ulster University Northern Ireland BelfastBT48 7JL United Kingdom Department of Computer Engineering Automation and Robotics University of Granada Granada18071 Spain

Multioccupation encompasses real-life environments in which people interact in the same common space. Recognising activities in this context for each inhabitant has been challenging and complex. This work presents a fuzzy knowledge-based system for mining human activities in multi-occupancy contexts based on nearby interaction based on the Ultra-wideband. First, interest zone spatial location is modelled using a straightforward fuzzy logic approach, enabling discriminating short-term event interactions. Second, linguistic protoforms use fuzzy rules to describe long-term events for mining human activities in a multi-occupancy context. A data set with multimodal sensors has been collected and labelled to exhibit the application of the approach. The results show an encouraging performance (0.9 precision) in the discrimination of multiple occupations. © 2023, The Authors. All rights reserved.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

Atmospheror: Towards an Olfactory Interactive System for Enhancing Social Presence and Interaction in Synchronous Online Classes

Atmospheror: Towards an Olfactory Interactive System for Enh...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in computing Systems, CHI EA 2023

作者： Lu, Qi Zhang, Yuewei Zhang, Yuxin Ma, Shao-En Zhang, Yunfan Qin, Yuou Gao, Peizhong Zhang, Qiwei Xu, Yingqing The Future Laboratory Academy of Arts & Design Tsinghua University Beijing China The Future Laboratory Industiral Engineering Tsinghua University Beijing China The Future Laboratory School of Software Tsinghua University Beijing China The Future Laboratory Tsinghua University Beijing China The Future Laboratory Department of Automation Tsinghua University Beijing China College of Design and Innovation Tongji University Shanghai China Creative Computing Institute University of the Arts London London United Kingdom

ISBN: (纸本)9781450394222

Synchronous online classes have become increasingly common in recent years. However, students and instructors often face challenges when giving and receiving reactions and feedback. Existing solutions include audio and visual cues, which often act as distractions. A potential alternative is olfactory cues. This paper proposes Atmospheror, an interactive system that supports interaction and feedback between students and instructors through an ambient olfactory display. We performed a pilot study with two instructors and 13 students to evaluate the effectiveness of Atmospheror and its design and implementation, applying both quantitative and qualitative methods. Preliminary results indicate that Atmospheror can promote students' concentration and increase interactivity in online classes. User interviews provided suggestions for future enhancements of the selection and treatment of odor, hardware implementation, and interface system mechanisms. © 2023 Owner/Author.

关键词： Students

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：