检索结果-内蒙古大学图书馆

International Conference on Computer and Communications (ICCC)

作者： Jinting Tan Hongliang Wang Xuerao Li Xiaoxing Zhang Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang Ligong University Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China

In the context of workshop-restricted environments, this paper presents an improved lightweight detection algorithm named YOLO-M3C to achieve safety helmet wearing detection on embedded devices in real-time while handling multiple video streams efficiently. YOLO-M3C introduces two key enhancements. Firstly, it replaces the backbone network of YOLOv5 with the more lightweight MobileNetV3 network for feature extraction. This improvement significantly reduces the network's parameter count, resulting in enhanced computational speed and a substantial decrease in computational resource requirements. Secondly, the attention mechanism CBAM is introduced to increase the model's focus on important features, leading to further improvements in detection accuracy. CBAM helps the model better comprehend crucial information in the images, thereby enhancing detection algorithm performance. Experimental results demonstrate that YOLO-M3C achieves increased average precision while shortening the training time by 15%. Additionally, the improved algorithm reduces the parameter count of the YOLOv5 model by 52%, effectively reducing model size and training time, while enhancing detection efficiency. The improved YOLOv5 algorithm can be effectively deployed on embedded devices in workshop environments, enabling efficient real-time processing of multiple video streams and reliable safety helmet wearing detection, thus meeting the real-time detection requirements in workshop settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Short-term Net Load Forecasting Method Based on Two-stage Feature Selection and LightGBM with Hyperparameter Auto-Tuning 59

A Short-term Net Load Forecasting Method Based on Two-stage ...

引用

59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023

作者： Lei, Shuya Liang, Xiao Wang, Xiaohui Ding, Jingyang Ge, Xinxin Wang, Fei Feng, Jia State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd Beijing102209 China North China Electric Power University Department of Electrical Engineering Baoding071003 China State Grid Zhejiang Electric Power Company Ltd Hangzhou310007 China

ISBN: (纸本)9798350396515

Reliable short-term net load forecasting (STNLF) is important for the stable operation of power systems and assists utilities in unit commitment and demand side management. With the increasing penetration of invisible behind-the-meter photovoltaic systems (BTM-PVs) installed close to customers, accurate STNLF is becoming more challenging. The intermittent of PV output is carried into the load due to the coupling of PV output and actual load, which makes the net load complex and difficult to forecast. In addition, the related influencing factors of BTM-PV also have a great impact on load characteristics based on the original features of load demand. To eliminate the redundant features is also one of the difficulties. This paper proposes a machine learning method to improve the accuracy of 24-hourahead net load forecasting, including PV-Load decoupling, feature selection and light gradient boosting machine (LightGBM) with Bayesian optimization. Firstly, the net load is decomposed into PV output and actual load using the data of small amount of observable PV customers. Then a two-step feature selection method is used to select key features for load demand and PV output, respectively, based on the forecasting accuracy of different feature combinations in the validation dataset. The selected features are used to train LightGBM model, and in order to fully maximize the performance of the forecasting model, the parameters of the model are optimized by Bayesian. Compared with other benchmark models, the proposed model has the best forecasting accuracy. The proposed framework is conducted on smart meter dataset in Ausgrid. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Ke, Zhifa Wen, Zaiwen Zhang, Junyu Center for Data Science Peking University China Beijing International Center for Mathematical Research Center for Machine Learning Research Changsha Institute for Computing and Digital Economy Beijing China Department of Industrial Systems Engineering and Management National University of Singapore Singapore

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general L-layer neural network. New proof techniques are developed and an improved new Õ(ϵ−1) sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an Õ(ϵ−1) complexity under the Markovian sampling, as opposed to the best known Õ(ϵ−2) complexity in the existing literature. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

Association Analysis of User Promiscuous Traffic Based on Convolutional Neural Network 4

Association Analysis of User Promiscuous Traffic Based on Co...

引用

4th IEEE advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2021

作者： Li, Yonglin Liu, Yan Zhengzhou University Zhong Yuan Network Security Research Institute Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781728185347

Analyzing user behavior from promiscuous network traffic, digging out user characteristics, and analyzing user behavior patterns are the main purposes of user association analysis. Existing methods start from the traffic generated by users and manually select the features that need to be extracted with the help of expert knowledge, the effect of the model depends to a certain extent on the quality of the selected features. This paper proposes a convolutional neural network-based user promiscuous traffic association analysis method Convolutional Neural Networks Based Association Analysis (CNNBAA). First, the traffic generated by users surfing the internet is preprocessed, such as segmentation, anonymization, and an interception, and then mapped into RGB map as the input data of Convolutional Neural Networks (CNN), and then use Residual Networks (ResNet) train the generated images to obtain a network model that can independently learn the characteristics of user online behavior. This method does not require manual selection of features and uses a convolutional neural network to learn features autonomously. We collected the network traffic in the true environment, constructed the experimental data set, and obtained the best traffic segmentation method and the best image conversion resolution through experiments. The experimental results show that the accuracy of the model is above 88%, which achieves the expected effect. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Time-Continuous Sliding Motion Image Registration Using Stationary Velocity Fields for Respiratory Motion Interpolation 10th

Time-Continuous Sliding Motion Image Registration Using Stat...

引用

10th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2025

作者： Gildemeister, Ole Bostelmann, Johannes Schulz, Pia F. Oltmann, Andra Rostalski, Phillip Modersitzki, Jan Lellmann, Jan Institute of Mathematics and Image Computing University of Lübeck Lübeck Germany Fraunhofer Institute for Digital Medicine MEVIS Lübeck Germany Fraunhofer IMTE Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering Lübeck Germany Institute for Electrical Engineering in Medicine University of Lübeck Lübeck Germany

ISBN: (纸本)9783031923685

We propose an image registration model for computing a dense, piecewise diffeomorphic deformation map between 3D thorax images which incorporates sliding motion as often occurring in the pleural cavity. Our approach is based on stationary velocity fields and neural implicit representations, with a particular focus on facilitating motion interpolation. This allows for generating a time-continuous model of the respiratory cycle based on end-inspiration and end-expiration images. We investigate the effect of composing deformations in motion interpolation, using a hybrid technique to enforce domain alignment. We experimentally validate our approach for registration and motion interpolation between thoracic end-inspiration and end-expiration images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Fall detection in automated buses using in-vehicle camera -basic study using support vector machine-

Fall detection in automated buses using in-vehicle camera -b...

引用

Image Processing and Robotics (ICIP), International Conference on

作者： Kosei Ido Amey Ajit Dakare Yen Tran Naohisa Hashimoto Toru Kumagai Takahiro Miura Yanbin Wu Makoto Itami Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology(AIST) Tsukuba Japan Tokyo University of Science Tsukuba Japan University of Tsukuba Tsukuba Japan Human Augmentation Research Center National Institute of Advanced Industrial Science and Technology(AIST) Tsukuba Japan Department of Applied Electronics Faculty of Advanced Engineering Tokyo University of Science Tokyo Japan

ISBN: (数字)9798350374766

ISBN: (纸本)9798350374773

To enhance in-vehicle safety in automated buses, a system that can detect whether falls have occurred in the bus can support the remote human controllers in quickly responding to the running bus. In this study, we designed a fall detection system that utilizes Wong Kin Yiu’s yolov7 for extracting features from the video data. Then support vector machine was used for the discriminant task of whether a fall has occurred or not given an image as the input data. We tested our system with various settings, including full features versus reduced features, and raw images from the camera versus images that contain full views of the human inside the bus, all with multiple camera views. And finally, we confirmed that the 360-degree camera could detect human falls. Using several evaluation criteria, such as accuracy, precision, recall, and F1 scores, we showed how the detection ability of the system varied according to different settings of the test. The highest F1 score of 0.980 was achieved in the experiment. In addition, we found that if a full-body view of a human being could be achieved, the accuracy of the fall detections would be greatly improved. Finally, we discuss several potential directions for further research of this topic.

关键词： Support vector machines Machine learning algorithms Robot vision systems Cameras Feature extraction Vectors Safety

来源：评论

学校读者我要写书评

暂无评论

Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2024年 2卷 264-280页

作者： Liu, Ruonan Zhang, Quanhu Han, Te Yang, Boyuan Zhang, Weidong Yin, Shen Zhou, Donghua Shanghai Jiao Tong University Department of Automation Shanghai200240 China Tianjin University College of Intelligence and Computing Tianjin300350 China Beijing Institute of Technology Center for Energy and Environmental Policy Research Beijing100081 China Beijing Institute of Technology School of Management Beijing100081 China Beijing Laboratory for System Engineering of Carbon Neutrality Beijing100081 China Nanjing University Center for Advanced Control and Smart Operations Suzhou215163 China Hainan University School of Information and Communication Engineering Haikou570228 China Shanghai Jiaotong University Department of Automation Shanghai200240 China Norwegian University of Science and Technology Trondheim7491 Norway

Industrial Cyber-Physical Systems (ICPS) integrating disciplines such as computer science, communication technology, and engineering, have become a crucial component of modern manufacturing and industry. However, ICPS faces numerous challenges during long-term operation, including equipment faults, performance degradation, and security threats, etc. To achieve efficient maintenance and management, prognostics and health management (PHM) has been widely applied in the critical tasks of ICPS such as fault prediction, health monitoring, and maintenance decision-making. The emergence of large-scale foundation models (LFMs) like BERT and GPT marks a significant advancement in artificial intelligence (AI) technology, demonstrating substantial application potential in multiple fields. The accumulation of AI technology, rapid development of LFMs, and the abundance of industrial data and industrial process knowledge provide the foundational conditions for the construction and advancement of industrial LFMs. However, there is currently a lack of consensus on applying LFMs of PHM in ICPS, necessitating a systematic review and roadmap to clarify future development directions. To bridge this gap, this survey provides a comprehensive survey and understanding of the recent advances in LFMs of PHM in ICPS. It provides valuable references for decision makers and researchers in the industry, and helps to further improve the reliability, availability and safety of ICPS. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Benchmarking quantum optimization for the maximum-cut problem on a superconducting quantum computer

引用

Physical Review Applied 2025年第1期23卷 014045-014045页

作者： Maxime Dupont Bhuvanesh Sundar Bram Evert David E. Bernal Neira Zedong Peng Stephen Jeffrey Mark J. Hodson Rigetti Computing 775 Heinz Avenue Berkeley California 94710 USA Davidson School of Chemical Engineering Purdue University West Lafayette Indiana 47907 USA Universities Space Research Association (USRA) Research Institute for Advanced Computer Science Mountain View California 94043 USA Quantum AI Laboratory NASA Ames Research Center Moffett Field California 94035 USA

Achieving high-quality solutions faster than classical solvers on computationally hard problems is a challenge for quantum optimization to deliver utility. Using a superconducting quantum computer, we experimentally investigate the performance of a hybrid quantum-classical algorithm inspired by semidefinite programming approaches for solving the maximum-cut problem on 3-regular graphs up to several thousand variables. We leverage the structure of the input problems to address sizes beyond what current quantum machines can naively handle. We attain an average approximation ratio of 99% over a random ensemble of thousands of problem instances. We benchmark the quantum solver against similarly high-performing classical heuristics, including the gurobi optimizer, simulated annealing, and the Burer-Monteiro algorithm. A run-time analysis shows that the quantum solver on large-scale problems is competitive against gurobi but short of others on a projected 100-qubit quantum computer. We explore multiple leads to close the gap and discuss prospects for a practical quantum speedup.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Contextual adaptative interfaces for industry 4.0 17th

Contextual adaptative interfaces for industry 4.0

引用

17th International Symposium on Distributed computing and Artificial Intelligence, DCAI 2020

作者： Canito, Alda Mota, Daniel Marreiros, Goreti Corchado, Juan M. Martins, Constantino GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Institute of Engineering Polytechnic of Porto Porto Portugal Department of Computer Science University of Salamanca Salamanca Spain

ISBN: (纸本)9783030538286

Information technologies are intrinsically connected to the manufacturing processes, with more data generated each second. To efficiently operate machines, users must sort out information that is relevant to them in specific moments and contexts. In this paper, we propose an architecture that combines context – e.g. location, type of order, available assets, previous actions – with information established through user stereotypes. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Cochlear implant/MXene-based electroacoustic stimulation modulates the growth and maturation of spiral ganglion neurons

引用

Engineered Regeneration 2024年第4期5卷 443-451页

作者： Yangnan Hu Hao Wei Menghui Liao Shanying Han Xin Gao Yusong Wang Shan Zhou Dongyu Xu Xugang Zhuang Ye Yang Hong Cheng Bin Zhang Qingyue Cui Jieyu Qi Lei Tian Wenyan Li Xia Gao Renjie Chai State Key Laboratory of Digital Medical Engineering Department of Otolaryngology Head and Neck SurgeryZhongda HospitalSchool of Life Sciences and TechnologyAdvanced Institute for Life and HealthJiangsu Province High-Tech Key Laboratory for Bio-Medical ResearchSoutheast UniversityNanjing210096China Co-Innovation Center of Neuroregeneration Nantong UniversityNantong 226001China Department of Otolaryngology Head and Neck Surgery Nanjing Drum Tower HospitalAffiliated Hospital of Medical SchoolNanjing UniversityJiangsu Provincial Key Medical Discipline(Laboratory)Nanjing 210008China Department of Otolaryngology Head and Neck Surgery Sichuan Provincial People’s HospitalUniversity of Electronic Science and Technology of ChinaChengdu 610072China Department of Otolaryngology-Head and Neck Surgery Shandong Provincial ENT HospitalShandong UniversityJinanShandongChina State Key Laboratory of Digital Medical Engineering Department of Otolaryngology Head and Neck SurgeryZhongda HospitalSchool of MedicineAdvanced Institute for Life and HealthSoutheast UniversityNanjing210096China ENT institute and Department of Otorhinolaryngology Eye&ENT HospitalState Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain ScienceFudan UniversityShanghai200031China Department of Neurology Aerospace Center HospitalSchool of Life ScienceBeijing Institute of TechnologyBeijing 100081China Institute for Stem Cell and Regeneration Chinese Academy of ScienceBeijingChina Southeast University Shenzhen Research Institute Shenzhen 518063China

Cochlear implantation(CI)offers a dependable treatment for sensorineural hearing loss,with precision electroa-coustic stimulation parameters showing great potential in improving auditory outcomes in CI ***,we report the attachment of MXene into CI systems which effectively mimic the neural electrode interface due to MXene’s excellent electrical conductivity and ***-frequency short-term biphasic electrical pulses emitted by the MXenes-based CI promoted the outgrowth of spiral ganglion neuron(SGN)neurites and growth cones,substantially boosting the calcium activity in *** study lays a theoretical foundation for the precision medicine approaches in CI patient care,and informs the selection of materials for cochlear implant electrode materials in the future.

关键词： Cochlear implant MXene Electroacoustic stimulation Cellular response

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：