检索结果-内蒙古大学图书馆

2024 4th International Conference on Mechatronics, Automation and Intelligent Control, MAIC 2024

作者： Chen, Yu Cai, Yuanli Liu, Jiaqi Deng, Yifan Lu, Jing Faculty of Electronic and Information Engineering Xi’an Jiaotong University Shanxi Xi’an China National Key Laboratory of Science and Technology on Test Physics and Numerical Mathematics Beijing China Shanghai Institute of Satellite Engineering Shanghai China

To address the challenges of single-sensor visual limitations and network congestion in tracking high-speed vehicles, a dynamic event-triggered cooperative cubature Kalman filtering algorithm is proposed. Initially, a dynamic event-triggered mechanism is developed based on measurement state information to reduce bandwidth consumption and enhance system responsiveness. Subsequently, within the framework of the cubature Kalman Filter, the covariance matrix and filtering gain matrix for each sensor’s distributed filter are derived using minimum mean square error approximation techniques. Finally, a cooperative filtering algorithm is designed using a weighted average consensus method and applied to tracking of hypersonic glide vehicles. Simulation results demonstrate that the proposed algorithm achieves higher accuracy compared to existing methods. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Myers-Briggs Type Indicator and the Big Five Model-How Our Personality Affects Language Use

Myers-Briggs Type Indicator and the Big Five Model-How Our P...

引用

2022 IEEE Asia-Pacific Conference on Computer science and Data engineering, CSDE 2022

作者： Radisavljevic, Dusan Batalo, Bojan Rzepka, Rafal Araki, Kenji Graduate School of Information Science and Technology Hokkaido University Sapporo Japan Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Hokkaido University Faculty of Information Science and Technology Sapporo Japan

ISBN: (纸本)9781665453059

Recently there has been an increasing interest in personality computing, a research field that mainly concerns itself with problems of personality perception, synthesis and recognition. In order to provide personality measure for these tasks, two models have been most commonly applied: the Myers-Briggs Type Indicator (MBTI) and the Big Five model (BF). Since some early scientific works have been critical of MBTI, the Big Five model has historically been more favoured by the scientific community. However, in recent years there has been an increasing number of researchers examining the possible application of MBTI in personality computing. Although the correlation between the set of measures offered by these two models has been proven to exist, works that directly compare the two, especially from the aspect of language usage, have been scarce. In this paper we examine the linguistic similarities between individuals labelled with MBTI types and Big Five dimensions by conducting an analysis using Linguistic Inquiry and Word Count (LIWC). Our study has further substantiated previous linguistic qualities of the Big Five model, while providing a novel insight into how MBTI types influence language use. Additionally, the results of our research have indicated existence of language use patterns shared by these two models. To the best of our knowledge, this is the first time a comparison of effects the two personality models have on language usage has been made. © 2022 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

AggFollower: Aggressiveness Informed Car-Following Modeling

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Chen, Xianda Yuan, Xinyi Zhu, Meixin Zheng, Xinhu Shen, Shaojie Wang, Xuesong Wang, Yinhai Wang, Fei-Yue Guangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong SAR China School of Transportation Engineering Tongji University Shanghai China Department of Civil and Environmental Engineering University of Washington Seattle WA USA State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior. IEEE

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Preliminary Exploration of Haptic-enabled Therapist-in-the-Loop Telerehabilitation System for Exoskeleton-assisted Upper Limb Training 20

Preliminary Exploration of Haptic-enabled Therapist-in-the-L...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Li, He Guo, Shuxiang Wang, Hanze Bu, Dongdong Beijing Institute of Technology The Key Laboratory of Convergence Biomedical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

Faced with the increase in upper limb hemiplegia caused by stroke, robotic exoskeleton-assisted home-based telerehabilitation has attracted increasing attention in recent years. Telerehabilitation is a viable alternative to traditional face-to-face rehabilitation training, which has many advantages. In this paper, a preliminary therapist-in-the-loop haptic-enable telerehabilitation system for upper limb training is presented. In the telerehabilitation system, a high-definition haptic device manipulated by the operator (served as the therapist) is the master side, and the designed upper limb rehabilitation exoskeleton worn by the subject (served as the stroke patient) is the slave side. The master-slave side realizes the operation and force data transmission through TCP/IP communication protocol. Through experiments, the angle error and time delay are analyzed, which proves the usability of the constructed system and lays the foundation for the subsequent research. © 2023 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Circuit Design Method for Reducing Static Current Consumption and Integrated Circuit Die Self-Heating in High-Temperature Transimpedance and Operational Amplifiers Based on Field-Effect Transistors

Circuit Design Method for Reducing Static Current Consumptio...

引用

2024 International Conference on Actual Problems of Electron Devices engineering, APEDE 2024

作者： Bugakova, Anna V. Frolov, Ilya V. Kleimenkin, Dmitriy V. Prokopenko, Nikolay N. Department of Scientific Research Department of Information Systems and Radio Engineering Don State Technical University Rostov-on-Don Russia Laboratory of Solid-State Electronics Opto- and Nanoelectronics Ulyanovsk Branch of the Kotelnikov Institute of Radioengineering and Elecronics of Russian Academy of Science Ulyanovsk Russia Department of Information Systems and Radio Engineering Don State Technical University Rostov-on-Don Russia

ISBN: (纸本)9798350393316

The circuit design method has been developed for halving the static current consumption of differential stages on field-effect transistors in transimpedance and operational amplifiers, which is recommended for use in micro-power analog microcircuits. An elementary thermal model of a high-temperature integrated circuit based on silicon-carbide (SiC), gallium-arsenide (GaAs) and silicon (Si) technologies under conditions of exposure to elevated temperatures is considered for the case when the integrated circuit die (chip) releases its self-power P0. The permissible values of the self-heating power P0 have been determined for SiC, GaAs and Si technological processes that ensure the operation of the integrated circuit die at a temperature not higher than a given limit value. © 2024 IEEE.

关键词： Gallium arsenide

来源：评论

学校读者我要写书评

暂无评论

African Vultures Based Feature Selection with Multi-modal Deep Learning for Automatic Seizure Prediction 2

African Vultures Based Feature Selection with Multi-modal De...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Nallur, Mounika Sandhya, M. Khan, Zabiha Mohan, B.R. Nayana, C.P. Rajashekhar, S.A. Murray State University Computer Information Systems United States East West Institute of Technology Department of Computer Science and Engineering Bengaluru India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India

ISBN: (纸本)9798350382952

The superiority of life for people with epilepsy can be greatly improved with the assistance of accurate seizure prediction and early warning. An automatic prediction model is required to procedure the EEG signals and account for the leads optimization problematic, as opposed to the majority of hand-designed prediction approaches. In this research, we put forth a fully automated model for seizure prediction using Channel and Spatial attention (CASA). The first step in the feature extraction practice is to pre-process the raw EEG signals. Large amounts of computation can be saved by adding more features to the system, but finding the right ones can be tricky. The African vulture optimization algorithm's (AVOA) strong capacity to break out of local optima is what makes this procedure possible. CASA saved the raw EEG data's temporal and geographical details. Automatic optimization of EEG full-lead data was completed with channel attention (CA), leading to an increase in the accuracy of predictions. The aforementioned adaptive learning of feature parameters was accomplished via spatial attention (SA). When all else fails, a fully associated layer is used to make the seizure forecast. The suggested algorithm is tested on the Freiburg EEG database, and the results reveal that the AVOA-based system performs admirably when it comes to predicting seizures. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

An Effective Anomalous Sound Detection Method Based on Representation Learning with Simulated Anomalies 48

An Effective Anomalous Sound Detection Method Based on Repre...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Han Song, Yan Zhuo, Zhu Zhou, Yu Li, Yu-Hong Xue, Hui McLoughlin, Ian Alibaba Group China University of Science and Technology of China National Engineering Laboratory for Speech and Language Information Processing Hefei China Singapore Institute of Technology Ict Cluster Singapore

ISBN: (纸本)9781728163277

In this paper, we propose an effective anomalous sound detection (ASD) method based on representation learning with simulated anomalies. Recently, ASD systems have used Outlier Exposure (OE) strategy to achieve promising performance in DCASE challenges. These exploit deep Convolutional Neural Networks (CNNs) to learn discriminative representations by treating the normal samples from different classes as pseudo anomalies. However, since the anomalous sounds occur only rarely, are diversely distributed and are unseen during training, the OE capability of representations learned from normal samples may be limited. To address this issue, we propose a statistics exchange (StEx) method, which constructs simulated anomalies to improve the effectiveness of representation learning via OE strategy. Specifically, the first and second order statistics are extracted from time or frequency axis of input spectrograms, and the simulated anomaly is then obtained by exchanging the statistics of spectrograms from different classes. Furthermore, an out-of-distribution (OOD) metric is introduced as an importance measure to qualitatively analyze OE capability, which enables appropriate simulated anomaly selection for ASD. Extensive experiments on the DCASE2021 challenge task2 development dataset verify the effectiveness of representation learning with simulated anomaly for OE based ASD. © 2023 IEEE.

关键词： anomalous sound detection out-of-distribution representation learning statistics exchange

来源：评论

学校读者我要写书评

暂无评论

Sweat colorimetric detection system based on OpenMV

Sweat colorimetric detection system based on OpenMV

引用

Machine Learning and Computer Application (ICMLCA), International Conference on

作者： Yuanyuan Meng Yanxia Chen Chennong Li Yandi Liu Lei Qin Beijing Sensor Key Laboratory Beijing Information Science & Technology University Beijing China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798331530334

ISBN: (纸本)9798331530341

The demand for real-time sweat biosensing is increasing in daily health monitoring. Colorimetric detection, as a simple and intuitive method, plays an important role in sweat biosensing. However, achieving an instant and effective colorimetric detection remains a challenge in real-time sweat biosensing for daily health monitoring. Herein, we design a sweat colorimetric detection system based on OpenMV. The colorimetric detection system is capable of sensitively capturing images and quickly recognizing color changes. The colorimetric detection system based on OpenMV provides a simple and effective technology to realize real-time sweat detection and shows great potential as a colorimetric detection system platform for color recognition and image processing. We believe that our colorimetric detection system will have great potential applications and offer effective means for the design of smart biosensors and have great potential in the development of portable and intelligent sweat analysis equipment.

关键词： Image recognition Image color analysis Machine learning Computer applications Sensor systems and applications Real-time systems Biosensors Data mining Monitoring

来源：评论

学校读者我要写书评

暂无评论

A novel sliding mode guidance law with finite-time convergent theory against maneuvering targets 1

A novel sliding mode guidance law with finite-time convergen...

引用

1st Aerospace Frontiers Conference, AFC 2024

作者： Sizhuo, Wang Defu, Lin Hongyan, Li Jiang, Wang School of Aerospace Engineering Beijing Institute of Technology Beijing100081 China School of Electronic Information Engineering Beihang University Beijing100191 China Joint Laboratory on Intelligent Unmanned Systems China-UAE Belt and Road Beijing100191 China

ISBN: (纸本)9781510681613

This paper proposes a novel sliding mode guidance law with finite-time convergent theory against maneuvering targets with impact angle constraint and autopilot lag. To mitigate the external disturbance stemming from the target maneuver, an adaptive sliding mode disturbance observer(ASMDO) is used to estimate the target maneuver precisely. During the process of guidance law design, a fixed-time control theory is used during the reaching stage to guarantee the system state convergence time upper bound is relative to the flight time of the missile which can ensure that the stable time of the system state is less than the flight time to avoid large miss distance. Furthermore, the autopilot lag is approximated as a second-order link to be more practical in engineering. After the guidance commands are designed, a controller based on dynamic surface control is designed to track the designed acceleration commands. The Lyapunov method is applied to demonstrate the stability of the guidance law. Numerical simulations prove the effectiveness and progressiveness of the proposed guidance law. © 2024 SPIE.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Neighborhood Modularization‑based Artificial Bee Colony Algorithm for Disassembly Planning with Operation Attributes

引用

Chinese Journal of Mechanical engineering 2022年第6期35卷 165-177页

作者： Hongfei Guo Linsheng Zhang Yaping Ren Leilei Meng Zhongwei Zhou Jianqing Li GBA and B&R International Joint Research Center for Smart Logistics School of Intelligent Systems Science and EngineeringInstitute of Physical InternetJinan University(Zhuhai Campus)Zhuhai 519070China School of Computer Science Liaocheng UniversityLiaocheng 252059China Faculty of Information Technology Macao University of Science and TechnologyMacao 999078China

The recycling and remanufacturing of end-of-life products are significant for environmental protection and resource *** is an essential process of remanufacturing end-of-life *** disassembly plans help improve disassembly efficiency and reduce disassembly *** paper studies a disassembly planning problem with operation attributes,in which an integrated decision of the disassembly sequence,disassembly directions,and disassembly tools are ***,a mathematical model is formulated with the objective of minimizing the penalty cost caused by the changing of operation ***,a neighborhood modularization-based artificial bee colony algorithm is developed,which contains a modular optimized ***,two case studies with different scales and complexities are used to verify the performance of the proposed approach,and experimental results show that the proposed algorithm outperforms the two existing methods within an acceptable computational time.

关键词： End-of-life products Disassembly planning Artificial bee colony Neighborhood modularization

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：