检索结果-内蒙古大学图书馆

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Filip Marciniak Wojciech Marciniak Tomasz Marciniak Faculty of Computing and Telecommunications Poznan University of Technology Poznań Poland DECYBEL Student Science Club Poznan University of Technology Poznań Poland Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Poznan University of Technology Poznań Poland

The paper analyzes the preparation of software for acoustic signal classification with machine learning techniques for microcontrollers. The design process was tested for three types of devices: Nordic Thingy:53, *** and Arduino Nano 33 BLE Sense Lite. The classifier training process was carried out using the Edge Impulse platform. Experimental studies were carried out for the process of classifying sound signals generated by the vacuum cleaner motor. The results of the training and the model test were presented for different configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biosignal-Based Attention Monitoring for Evaluating Train Driver Safety-Relevant Tasks

SSRN

引用

SSRN 2024年

作者： Kim, Jung Hwan Kim, Yeongjun Cho, Younggeol Kim, Tae Kyun Jang, Tongil Park, Chanwoo Kang, Seongkeun Advanced Instrumentation & Control Research Section Korea Atomic Energy Research Institute Daejeon Korea Republic of Department of Nuclear & Quantum Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of School of Computing Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Department of Railroad Electrical & Electronic Engineering Korea National University of Transportation Uiwang Korea Republic of System Safety Research Department Korea Railroad Research Institute Uiwang Korea Republic of

This study explores the impact of phone usage on train driver performance, a critical aspect influencing the safety of railroad operations. The persistent problem of phone distractions, which severely impair situational awareness and contribute to accidents, necessitates innovative solutions to enhance operational safety. Leveraging advancements in technology, this study introduces a novel approach combining electroencephalogram (EEG)-based analysis with deep learning algorithms to assess the effects of phone usage on the attention states of train drivers. Utilizing a full-type train simulator to replicate real-life scenarios, this study conducts an experimental design involving scenarios with and without phone engagement, aiming to provide a comprehensive assessment of phone usage on performance in critical situations. The deep learning model employed achieved an impressive classification accuracy of approximately 85.6% in distinguishing attention states among 25 participants, with high precision and recall values indicating its efficacy in detecting phone interaction. Moreover, findings reveal that phone usage leads to a 1.4 times increase in response time to situational awareness, significantly affecting driver performance. These findings highlight the significant impact of phone usage on train driver attention and underscore the potential of EEG-based analysis and deep learning in improving railroad safety measures. This study contributes to the growing body of safety literature by focusing on train drivers, offering fresh insights and practical implications for enhancing the safety and efficiency of railroad operations. © 2024, The Authors. All rights reserved.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Generating 3d Fish Skeleton Via Optimization Iterative Method and Fishskeletonnet

SSRN

引用

SSRN 2023年

作者： Shi, Min Zhao, Guo-Liang Sun, Bi-Lian Zhuo, Xin-Ru Zhu, Deng-Ming Li, Zhao-Xin School of Control and Computer Engineering North China Electric Power University Beijing102206 China Prospective Research Laboratory Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Agricultural Information Institute Chinese Academy of Agricultural Sciences Beijing100081 China

Simplified fish skeleton can help 3D fish modeling, and can quickly simulate the poses and motions of fish of different shapes, which is important for virtual reality in agriculture. Compared with the same characteristics of the human skeleton, the fish skeleton structure is not always consistent. Therefore, it is challenging to generate a realistic and simple fish skeleton. We present an iterative optimization method for generating a 3D fish skeleton model that accurately captures the complex structure of the fish skeleton. Our method differs from conventional methods that generate the skeleton based solely on the geometric shape of the 3D mesh. We analyze the biological features of the fish's actual motion to extract the skeleton of the main part and define the fish skeleton model. The model parameters, including the number and position of joints, are iteratively optimized using a sample dataset with different shapes and five common postures. Finally, we propose FishSkeletonNet to generate fish skeletons of different shapes and poses based on the above data as the dataset. We conduct experiments on the grass carp dataset to quantitatively and qualitatively evaluate the number and location of generated skeleton joints. The experimental results demonstrate that our method generates fish skeletons that are closer to the true structure of the fish skeleton and exhibit better biological plausibility compared to those generated by existing methods. © 2023, The Authors. All rights reserved.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Key technologies for electric vehicles

引用

Green Energy and Intelligent Transportation 2022年第2期1卷 135-137页

作者： Rui Xiong Jonghoon Kim Weixiang Shen Chen Lv Hailong Li Xiaoyong Zhu Wanzhong Zhao Bingzhao Gao Hongyan Guo Chengming Zhang Fengchun Sun Department of Vehicle Engineering School of Mechanical EngineeringBeijing Institute of TechnologyNo.5 South Zhongguancun StreetHaidian DistrictBeijing 100081China Energy Storage and Conversion Laboratory Department of Electrical EngineeringCollege of EngineeringChungnam National UniversityDaejeon34134South Korea School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyHawthornVictoria 3122Australia School of Mechanical and Aerospace Engineering Nanyang Technological University639798Singapore School of Business Society and Engineering Mälardalen UniversitySE 72123VäteråsSweden School of Electrical and Information Engineering Jiangsu UniversityZhenjiangChina Department of Vehicle Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina Clean Energy Automotive Engineering Center Tongji UniversityShanghai 201804China State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China Department of Electrical Engineering Harbin Institute of TechnologyHarbinChina

*** Electric vehicles(EVs)are playing an increasingly important role in decarbonizing the transportation *** constitute a promising solution to a set of global challenges such as climate change and air *** are an integration of a wide spectrum of techniques,such as battery monitoring,battery safety and vehicle energy *** this regard,the EV development still faces significant challenges,which necessitate innovations in EV *** this,Green Energy and Intelligent Transportation(GEITS)organizes a special issue of“Key Technologies for Electric Vehicles”that attempts to advance knowledge in the area of EVs and provides a platform for researchers and engineers to share recent research results and discuss critical challenges in this field.A wide spectrum of topics are discussed,including but not limited to the following.

关键词： battery Key challenges

来源：评论

学校读者我要写书评

暂无评论

Research on Attention-Based Predictive Model in Multi-Agent Reinforcement Learning

Research on Attention-Based Predictive Model in Multi-Agent ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Hong, Weixin Wu, Huaiyu Shen, Zhen Xiong, Gang Hu, Bin Dong, Xisong Wang, Fei-Yue The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China

ISBN: (纸本)9781665465335

Agent actions planning is a challenging problem in multi-agent reinforcement learning. Recent methods typically build their predictive models by full connection layers, but the shortage of utilizing action and observation information in complex multi-agent environment limits the performance of those methods. To address this issue, we propose a novel predictive model based on self-attention mechanism which can effectively use information in the environment. Specifically, we use the MADDPG algorithm to make a dataset where the input is the observations and actions and the output is the predicted observations and rewards. We also introduce the multi-head attention mechanism into the predictive model so that the predictive model can better combine different information for prediction. We perform extensive experiments to assess the proposed method and compare it with the representative baseline approach. Results demonstrate that our method outperforms competitors with higher accuracy in different tasks. Our implementation will be publicly available. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Gps/Bds Based Train Positioning Method Using Non-Differential Range Measurements

SSRN

引用

SSRN 2024年

作者： Jiang, Wei Zhou, ZiJian Wang, Jian Cai, BaiGen Rizos, Chris Liu, Dan The State Key Laboratory of Rail Traffic Control and Safety School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China Institute of Computing Technology China Academy of Railway Sciences Corporation Limited Beijing100081 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China The School of Civil and Environmental Engineering University of New South Wales Sydney2052 Australia

Compared with pseudorange measurement, carrier phase tracking is much less noisy, which can provide accurate positioning solutions. The existing carrier phase-based positioning methods rely on precise ephemeris or base station, which may cause poor real-time and increase complexity in the system. To simplify the calculation model and achieve accurate navigation solutions with a stand-alone receiver, a new GPS/BDS based real-time non-differential positioning method is proposed. Due to the need to estimate the ambiguity terms of carrier phase measurements, the dimension of the state is larger than that of the measurement, the system observability is evaluated via the observability degrees. Both the train test on Beijing- Shenyang high speed railway and simulation were carried out, and the results confirm that the multi-constellation method can improve the positioning accuracy compared with stand-alone cases. The position and velocity Root Mean Square of the proposed method are (0.9022 m, 0.9140 m, 1.1621 m) and (0.0818 m/s, 0.0958m/s, 0.0289m/s) in the north, east, down directions. The proposed method has improved positioning performance in terms of accuracy and observability compared with different combinations of measurement methods. © 2024, The Authors. All rights reserved.

关键词： Observability

来源：评论

学校读者我要写书评

暂无评论

Prototype Guided Personalized Federated Intrusion Detection System

Prototype Guided Personalized Federated Intrusion Detection ...

引用

Smart World Congress (SWC), IEEE

作者： Long Cheng Huiru Yan Hanlin Zhou Ying Wang Haichuan Tang Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China AI Lab of CRRC Academy Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.

关键词： Training Privacy Accuracy Federated learning Image edge detection Prototypes Intrusion detection Data models Ensemble learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Developing Educational Programs Using Russian IT Job Market Analysis

Developing Educational Programs Using Russian IT Job Market ...

引用

2021 Ural Symposium on Biomedical engineering, Radioelectronics and Information Technology, USBEREIT 2021

作者： Sozykin, Andrey Koshelev, Anton Bersenev, Alexander Shadrin, Denis Aksenov, Alexander Kuklin, Evgeniy N.N. Krasovskii Institute of Mathematics and Mechanics Department of Computing Systems Ekaterinburg Russia Engineering School of IT Telecom. and Control Systems Ural Federal University Ekaterinburg Russia Institute of Natural Sciences and Mathematics Ural Federal University Ekaterinburg Russia

ISBN: (纸本)9781728176918

The paper presents an approach to developing new educational programs for information technologies (IT) specialists using job market analysis. We developed a set of innovative software tools for collecting data from job sites and analyzing the data using machine learning algorithms. The tools were used to create a dataset of job advertisements from popular Russian job site HeadHunter for a period from 2006 until 2020. Both tools and dataset are freely available on the Internet. In order to develop the educational programs, we analyzed the demand for IT professions and programming languages, as well as joint occurrence of skills in job descriptions. To demonstrate the possibilities of our approach, two educational programs were created: A JavaScript-based program for Web Development and a Python-based program for Data Science. Developing the educational programs based on the requirements of the job market allows graduates to increase their employability. During the programs, students not only study the foundation of the profession such as programming languages, but also acquire a complete set of skills required to work in demanded positions. © 2021 IEEE.

关键词： Employment

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud computing: An Algorithm-Level Review

arXiv

引用

arXiv 2025年

作者： Gu, Yan Liu, Zhaoze Dai, Shuhong Liu, Cong Wang, Ying Wang, Shen Theodoropoulos, Georgios Cheng, Long The School of Control and Computer Engineering North China Electric Power University Beijing China The School of Computer Science and Technology Shandong University of Technology China The Institute of Computing Technology Chinese Academy of Sciences Beijing China The School of Computer Science University College Dublin Ireland Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud operations are job scheduling and resource management, which are critical for optimizing system performance and ensuring timely and cost-effective service delivery. However, the dynamic and heterogeneous nature of cloud environments presents significant challenges for these tasks, as workloads and resource availability can fluctuate unpredictably. Traditional approaches, including heuristic and meta-heuristic algorithms, often struggle to adapt to these real-time changes due to their reliance on static models or predefined rules. Deep Reinforcement Learning (DRL) has emerged as a promising solution to these challenges by enabling systems to learn and adapt policies based on continuous observations of the environment, facilitating intelligent and responsive decision-making. This survey provides a comprehensive review of DRL-based algorithms for job scheduling and resource management in cloud computing, analyzing their methodologies, performance metrics, and practical applications. We also highlight emerging trends and future research directions, offering valuable insights into leveraging DRL to advance both job scheduling and resource management in cloud computing. © 2025, CC BY.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Estimating infinitesimal generators of stochastic systems with formal error bounds: A data-driven approach 24

Estimating infinitesimal generators of stochastic systems wi...

引用

24th ACM International Conference on Hybrid Systems Computation and control, HSCC 2021, held as part of the 14th Cyber Physical Systems and Internet-of-Things Week, CPS-IoT Week 2021

作者： Lavaei, Abolfazl Nejati, Ameneh Soudjani, Sadegh Zamani, Majid Institute for Dynamic Systems and Control Eth Zurich Switzerland Department of Electrical Engineering Technical University of Munich Germany School of Computing Newcastle University United Kingdom Department of Computer Science University of Colorado Boulder United States

ISBN: (纸本)9781450383394

In this work, we propose a data-driven technique for a formal estimation of infinitesimal generators of continuous-time stochastic systems with unknown dynamics. In the proposed framework, we first approximate the infinitesimal generator of the solution process via a set of data collected from solution processes of unknown systems. We then put some proper assumptions on dynamics of systems and quantify the closeness between the infinitesimal generator and its approximation while providing a priori guaranteed confidence bound. We show that both the time discretization and the number of data play significant roles in providing a reasonable closeness precision. Motivations and Related Works. Infinitesimal generator of a stochastic process (i.e., a partial differential operator that encodes a great deal of information about the process) plays a principal role in many analysis frameworks including: (i) stability analysis of continuous-time stochastic systems via Lyapunov functions [1], (ii) establishing similarity relations between two continuous-time stochastic systems via stochastic simulation functions [2], (iii) constructing finite abstractions of continuous-time stochastic control systems [3], and (iv) safety analysis of continuous-time stochastic systems via barrier certificates [4], to name a few. In the relevant literature, only [5] studies the estimation of infinitesimal generators, whose approach is based on the assumption of knowing the precise model and discretizing both time and state. To the best of our knowledge, our work is the first to propose a method for estimating the infinitesimal generator of stochastic systems with unknown dynamics while providing formal guarantees. The complete version of this work can be found in [6]. © 2021 Owner/Author.

关键词： Stochastic systems

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：