检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Peng, Ruimin Du, Zhenbang Zhao, Changming Luo, Jingwei Liu, Wenzhong Chen, Xinxing Wu, Dongrui Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China AI Platform Software Engineering Research Center Dongfeng Corporation Research & Development Institute Wuhan430072 China China Electronic System Technology Co. Ltd. Beijing100089 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China

Cross-subject electroencephalogram (EEG) based seizure subtype classification is very important in precise epilepsy diagnostics. Deep learning is a promising solution, due to its ability to automatically extract latent patterns. However, it usually requires a large amount of training data, which may not always be available in clinical practice. This paper proposes Multi-Branch Mutual-Distillation (MBMD) Transformer for cross-subject EEG-based seizure subtype classification, which can be effectively trained from small labeled data. MBMD Transformer replaces all even-numbered encoder blocks of the vanilla Vision Transformer by our designed multi-branch encoder blocks. A mutual-distillation strategy is proposed to transfer knowledge between the raw EEG data and its wavelets of different frequency bands. Experiments on two public EEG datasets demonstrated that our proposed MBMD Transformer outperformed several traditional machine learning and state-of-the-art deep learning approaches. To our knowledge, this is the first work on knowledge distillation for EEG-based seizure subtype classification. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Decoding split-frequency representation for cross-scale tracking

引用

Neural Networks 2025年 189卷 107587页

作者： Zhang, Yuanming Sun, Hao State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen518055 China

Learning tailored target representations for tracking is a promising direction in visual object tracking. Most state-of-the-art methods utilize autoencoders to generate representations by reconstructing the target's appearance. However, these reconstructions are often augmented to mimic scale jitter and alteration, neglecting physical scale observations such as those in aerial videos. This article addresses the challenge of representation learning for cross-scale tracking in generalized scenarios. Specifically, we incorporate target scale directly into the positional encoding, indicating scale through relative pixel density rather than the conventional metric of image resolution. This scale-aware encoding is then integrated into the proposed asymptotic hierarchy of decoders, designed to reconstruct representations by emphasizing the restoration of high- and low-frequency features at large and tiny scales. The reconstruction process is guided by supervised learning using split losses, enabling the generation of robust cross-scale representations for generic objects. Extensive experiments on six benchmarks — GOT-10k, LaSOT, TrackingNet, DTB70, UAV123, and TNL2K — validate the superior performance of our method. Additionally, our tracker achieves a remarkable speed of 123 frames per second on a Graphics Processing Unit, surpassing the previous best autoencoder-based tracker. The code and raw results will be made publicly available at: https://***/pellab/DSC. © 2025 Elsevier Ltd

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Forecasting Slow-Wave Sleep Deficiency Through Stress-Related Markers in Forehead EEG

Forecasting Slow-Wave Sleep Deficiency Through Stress-Relate...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Su, Cheng-Hua Ko, Li-Wei Jung, Tzyy-Ping Onton, Julie Tzou, Shey-Cherng Juang, Jia-Chi Hsu, Chung-Yao Institute of Bioinformatics and Systems Biology National Yang Ming Chiao Tung University Hsinchu300 Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Kaohsiung Medical University Drug Development and Value Creation Research Center Department of Biomedical Science and Environmental Biology Kaohsiung807 Taiwan Institute for Neural Computation Institute of Engineering in Medicine University of California San Diego La Jolla CA92093 United States College of Electrical Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Institute for Neural Computation University of California San Diego La Jolla CA92093 United States Kaohsiung Medical University Hospital Sleep Disorders Center Department of Neurology Kaohsiung807 Taiwan College of Medicine Kaohsiung Medical University Department of Neurology Kaohsiung807 Taiwan

ISBN: (纸本)9781665410205

Sleep quality is critical for human well-being. Lack of sleep and poor sleep quality impair daily cognitive functions and health. While stress has been recognized as a detrimental factor on sleep quality, the relationship between pre-sleep stress level, resting EEG and subsequent sleep structure remains to be explored. This study presents a novel approach that evaluates pre-sleep stress levels using a 2-channel EEG to predict slow-wave sleep (SWS) deficiency. We recorded forehead EEG immediately before sleep onset, then utilized power spectra and entropy analysis to extract stress-related neurological features, including beta/delta correlation, alpha asymmetry, fuzzy entropy (FuzzEn), and spectral entropy (SpEn). We found that individuals with SWS deficiency exhibited signs of stress, such as a robust beta/delta correlation, higher alpha asymmetry, and increased FuzzEn. Conversely, individuals with ample SWS displayed weak beta/delta correlation and reduced FuzzEn in EEG recordings. Finally, we tested the robustness of the selected neuro markers with two supervised learning models and found that the selected markers predict SWS deficiency with an accuracy above 70%. Our study demonstrated that stress-related neurological markers derived from pre-sleep EEG can effectively predict SWS deficiency. The proposed method can be integrated with a portable EEG device and sleep-improving interventions to develop a personalized sleep-improvement solution. © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

development of ROV Simulator based on Real Oceanographic Data

引用

IFAC-PapersOnLine 2023年第2期56卷 11590-11595页

作者： Ryusei KAMEWARI Yusuke FUJISHIMA Kuniaki KAWABATA Kenta SUZUKI Norimitsu SAKAGAMI Fumiaki TAKEMURA Satoru TAKAHASHI Graduate School of Science for Creative Emergence Kagawa University 2217-20 Hayashi-Machi Takamatsu Kagawa 761-0396 Japan Area of Mechanical Systems Engineering Faculty of Engineering and Design Kagawa University Kagawa Japan Sector of Fukushima Research and Development Japan Atomic Energy Agency Fukushima Japan Mechanical Engineering and Robotics Course Faculty of Advanced Science and Technology Ryukoku University Shiga Japan Department of Mechanical Systems Engineering National Institute of Technology Okinawa College Okinawa Japan

In recent years, demand for efficient oceanographic research for the development of marine resources has been increasing on a global scale. In general, research and operation training on underwater robotics in the ocean is very costly, and the climate and conditions of the ocean may make it impossible to conduct experiments. In this paper, we introduce an ocean simulator using real oceanographic data that can avoid these issues. First, we treat Choreonoid which is an integrated software for robots applied by National institute of Advanced Industrial Science and Technology (AIST), as the basis of the simulator software. Furthermore, to demonstrate its feasibility in a more realistic ocean environment, we introduce the seabed data obtained from oceanographic research and a function to reproduce ocean currents on the simulator. In this paper, self-localization experiment is conducted to demonstrate the effectiveness of the simulator for oceanographic research.

关键词： underwater robot oceanographic research Ocean simulator self-localization estimation

来源：评论

学校读者我要写书评

暂无评论

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

arXiv

引用

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Fault Detection in Inertial Measurement Unit and Global Navigation Satellite System of an Unmanned surface vehicle

Fault Detection in Inertial Measurement Unit and Global Navi...

引用

International Conference on control, Automation and systems ( ICCAS)

作者： Gyeongsub Song Nak Yong Ko Hyun Taek Choi Joono Sur Department of Control and Instrumentation Engineering Interdisciplinary Program in IT-Bio Convergence Systems Chosun University Gwangju Korea Department of Electronic Engineering Interdisciplinary Program in IT-Bio Convergence Systems Chosun University Gwangju Korea Autonomous & Intelligent Maritime Systems Research Division Korea Research Institute of Ships and Ocean Engineering Daejeon Korea Agency for Defense Development PM Research Institute for Advanced Defense Science and Technologies Daejeon Korea

This paper presents a method which detects faults in the measurement required for navigation of an unmanned surface vehicle. The measurement includes acceleration and angular rate by an inertial measurement unit (IMU), and the location by global navigation satellite system (GNSS). The method uses Kalman filter to estimate the state variables which represent the amount of faulty measurements. The method is tested by the experiment in which a boat equipped by commercial IMU and GNSS navigates in a sea trial. The result verifies that faults in acceleration and angular rate measurements are detected robustly and the GNSS position fault is detected when there is considerable location error.

关键词： Accelerometers Global navigation satellite system Sea surface Measurement units Sea measurements Inertial navigation Sensors

来源：评论

学校读者我要写书评

暂无评论

Double deep Q-learning for anti-saturation attack problem of warship group 1

Double deep Q-learning for anti-saturation attack problem of...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Li, Wei Xiong, Gang Tao, Hao Han, Yunjun Wang, Fang Dong, Xisong Shen, Zhen Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan430064 China Shandong University Jinan China

ISBN: (纸本)9781665433372

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios. © 2021 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Study and prediction of the 2022 global monkeypox epidemic

引用

Journal of Biosafety and Biosecurity 2022年第2期4卷 158-162页

作者： Fengying Wei Zhihang Peng Zhen Jin Jinjie Wang Ximing Xu Xinyan Zhang Jun Xu Zixiong Ren Yao Bai Xiaoli Wang Bulai Lu Zhaojun Wang Jianguo Xu Senzhong Huang School of Mathematics and Statistics Fuzhou UniversityFuzhou 350116FujianChina Department of Biostatistics School of Public HealthNanjing Medical UniversityNanjing 211166JiangsuChina Complex Systems Research Center Key Discipline of Computer Science and Technology of“Double-First-Class”Project of Shanxi ProvinceShanxi UniversityTaiyuan 030006ShanxiChina Nankai Institute of Economics Binhai Development InstituteNankai UniversityTianjin 300071China Children’s Hospital of Chongqing Medical University Chongqing 400010China Jinzhou Center for Disease Control and Prevention Jinzhou 121000LiaoningChina School of Statistics and Data Science Nankai UniversityTianjin 300071China Xi’an Center for Disease Control and Prevention Xi’an 710061ShaanxiChina Beijing Center for Disease Control and Prevention Beijing 100013BeijingChina Suzhou Center for Disease Control and Prevention Suzhou 215004JiangsuChina State Key Laboratory of Communicable Disease Prevention and Control National Institute for Communicable Disease Control and PreventionChinese Center for Disease Control and PreventionBeijing 102206China School of Statistics and Data Science ZhiYing Research Center for Health DataNankai UniversityTianjin 300071China Institute of Public Health Nankai UniversityTianjin 300071China

The World Health Organization(WHO)declared monkeypox as a public health emergency of international concern(PHEIC)on July 23,2022,their highest level of *** raised concerns about the management of the global monkeypox outbreak,as well as the scientific analysis and accurate prediction of the future course of the *** study used EpiSIX(an analysis and prediction system for epidemics based on a general SEIR model)to analyze the monkeypox epidemic and to forecast the major tendencies based on data from the USA CDC(https://***)and the WHO(https://***/health-topics/monkeypox).The global outbreak of monkeypox started in the UK on May 2,2022,which marked the beginning of an epidemic *** of October 28,2022,the cumulative number of reported cases worldwide was 77,115,with 36 *** simulations predict that the global monkeypox epidemic will enter a low epidemic status on March 1,2023 with the cumulative number of confirmed cases ranging from 85,000 to 124,000,and the total number of deaths ranging from 60 to *** analysis revealed that the basic reproduction number(R0)of monkeypox virus(MPXV)is near to 3.1 and the percentage of asymptomatic individuals is 13.1%–14.5%,both of which are similar to the data for *** vaccination efficiency against susceptibility(VEs)of individuals who have had monkeypox is~79%,and the vaccination efficiency against infectiousness(VEi)of individuals who have had monkeypox is~76%–82%.The mean incubation period for monkeypox is 8 *** total,94.7%of infected individuals develop symptoms within 20 days and recover within 2 weeks after the confirmation of *** results using EpiSIX showed that ring vaccination was remarkably effective against *** findings confirmed that a 20-day isolation for close contacts is necessary.

关键词： Monkeypox Epidemic Prediction Tendency

来源：评论

学校读者我要写书评

暂无评论

Severe self-injurious behaviors in an autistic child with sensory seeking, depressive disorder and anxiety disorder: A focus on the therapeutic interventions

引用

Neuropsychiatrie de l'Enfance et de l'Adolescence 2023年第6期71卷 295-300页

作者： Dao, V. Guetta, M. Giannitelli, M. Doulou, F. Leullier, M. Ghattassi, Z. Cravero, C. Cohen, D. Department of Child and Adolescent Psychiatry Reference Centre for Rare Psychiatric Diseases Pitié-Salpêtrière Hospital Sorbonne Université AP–HP 47-83 boulevard de l'Hôpital Paris 75013 France Clinical research group (GRC) 15 Psychiatric disorders and development (PSYDEV) Sorbonne University 47-83 boulevard de l'Hôpital Paris 75013 France Interdepartmental Mobile Unit for Complex Situations in Autism (UMI 75-92) Elan Retrouvé Foundation 6 rue Gager-Gabillot Paris 75015 France CNRS UMR 7222 Institute for Intelligent Systems and Robotics Sorbonne University 4 place Jussieu Paris 75005 France

We report the case of a 12-year-old boy with nonverbal autism, intellectual disability, and hypermobility spectrum disorder. The patient was hospitalized in a French multidisciplinary neurobehavioral inpatient unit due to extreme self-harming behaviors. This major self-aggression led to a multi-fractured nose and to a growing risk of life-threatening traumatic injuries (risk of cervical fracture and spinal cord injury caused by forceful headbanging). These challenging behaviors required for a time the day-to-day skills of at least four caregivers and resulted in a rare escalation of restraint measures and in exceptional adaptations by our psychoeducational team. Clinical improvement was obtained after managing all causes of somatic pain and discomfort, as well as stabilizing the patient's mood and anxiety. We offered both sensorimotor developmental approaches with proprioceptive compressive garment and therapeutic body wrap, as well as protective equipment and specific psychoeducational interventions adapted to his severe self-injurious behaviors and to his developmental abilities. © 2023 Elsevier Masson SAS

关键词： Autism Intellectual disability Psychoeducational interventions Self-injurious behavior Sensory-seeking behavior

来源：评论

学校读者我要写书评

暂无评论

Robust Output Feedback Adaptive control of Nuclear Reactor

Robust Output Feedback Adaptive Control of Nuclear Reactor

引用

control Conference (ICC), 2019 Sixth Indian

作者： Peddireddy M S Reddy S. R. Shimjith A. P. Tiwari Soumitra Kar Homi Bhabha National Institute Mumbai India Reactor Control Division Bhabha Atomic Research Centre Mumbai Human Resource Development Division Reactor Bhabha Atomic Research Centre Mumbai Security Electronics and Software Systems Division Bhabha Atomic Research Centre Mumbai

This paper presents an output feedback Robust Model Reference Adaptive control (RMRAC) for control of a Pressurized Water Reactor (PWR). The main advantage of the proposed method is that it does not need explicit model parameter information. The nonlinear model for reactor core dynamics is considered based on normalized point kinetics equations, with one equivalent delayed neutron group and temperature feedback from lumped fuel and coolant temperatures. The nonlinear equations are linearized and recast as a transfer function model to perform control studies. The ideal controller gains are computed by assuming that the numerator and denominator coefficients are known at nominal power. Thereafter, adaptive laws are designed to handle parametric uncertainties and external disturbances over the operating power levels. The impact of external disturbances in output power is minimized with the help of over parametrized controller structure. Additionally, $\sigma$ modification is considered to make the adaptive laws robust. The stability of signals is verified through Lyapunov analysis and Barbalat's Lemma. The efficacy of the proposed controller is compared with the standard MRAC and the state feedback assisted controller (SFAC) through simulations.

关键词： Adaptation models Uncertainty Computational modeling Transfer functions Mathematical models Inductors Adaptive control

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：