检索结果-内蒙古大学图书馆

Preference detection of the humanoid robot face based on EEG and eye movement

Neural Computing and Applications 2024年第19期36卷 11603-11621页

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, Aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI and Robotics Ministry of Education Shanghai Engineering Research Center of AI and Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

The face of a humanoid robot can affect the user experience, and the detection of face preference is particularly important. Preference detection belongs to a branch of emotion recognition that has received much attention from researchers. Most of the previous preference detection studies have been conducted based on a single modality. In this paper, we detect face preferences of humanoid robots based on electroencephalogram (EEG) signals and eye movement signals for single modality, canonical correlation analysis fusion modality, and bimodal deep autoencoder (BDAE) fusion modality, respectively. We validated the theory of frontal asymmetry by analyzing the preference patterns of EEG and found that participants had higher alpha wave energy for preference faces. In addition, hidden preferences extracted by EEG signals were better classified than preferences from participants' subjective feedback, and also, the classification performance of eye movement data was improved. Finally, experimental results showed that BDAE multimodal fusion using frontal alpha and beta power spectral densities and eye movement information as features performed best, with the highest average accuracy of 83.13% for the SVM and 71.09% for the KNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Advances in Intelligent Control of Magnetically Actuated Micro-robots

引用

Jiqiren/Robot 2023年第5期45卷 603-625页

作者： Xu, Tiantian Huang, Chenyang Liu, Jia Xu, Yanhua Lai, Zhengyu Wu, Xinyu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

Micro-robots wirelessly actuated by low-intensity electromagnetic fields can move in narrow environment and complete complex tasks, such as targeted drug delivery, micromanipulation, and environment detection. This paper introduces the advances of intelligent control of magnetically actuated micro-robots, mainly including the applications of intelligent control methods to the following areas: from rigid structure to flexible structure of magnetically actuated micro-robots, from single motion mode to multiple motion modes of magnetically actuated micro-robots, from open-loop control to closed-loop control of magnetically actuated micro-robots, from single individual and single swarm to multiple individuals of magnetically actuated micro-robots. Finally, the future development directions of magnetically actuated micro-robots are expected, including magnetic drives for larger workspace, micro-robots with more motion modes, medical micro-robots with flexible structures, autonomous navigation of micro-robots, and control of multiple magnetically actuated micro-robots. © 2023 Chinese Academy of Sciences. All rights reserved.

关键词： Controlled drug delivery

来源：评论

学校读者我要写书评

暂无评论

TRANSIENT DYNAMIC FINITE ELEMENT ANALYSIS AND RELIABILITY ASSESSMENT OF MINING EXCAVATORS GEAR TRANSMISSION system 13

TRANSIENT DYNAMIC FINITE ELEMENT ANALYSIS AND RELIABILITY AS...

引用

13th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2023

作者： Guo, Yunfei Qian, Zheng-Kun Huang, Hong-Zhong State Key Laboratory of Intelligent Mining Equipment Technology Taiyuan China Center for System Reliability and Safety University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781839539848

A transient dynamic finite element analysis and reliability assessment of mining excavators gear transmission system is conducted in this paper. Specifically, Transient dynamics method is used in mining excavator transmission gear contact finite element simulation analysis, studying the time-varying gear contact stress. Gear transmission three-dimension modeling was set up using UG software and imported into ANSYS for simulation analysis. According to the distribution of the motor power, and rotational speed, get the gear contact stress distribution, then depending on the materials of the gear tooth surface contact fatigue strength distribution, and get the gear contact fatigue reliability. © The Institution of Engineering & technology 2023.

关键词： Excavators

来源：评论

学校读者我要写书评

暂无评论

A bibliometric analysis of research on remote sensing-based monitoring of soil organic matter conducted between 2003 and 2023

Artificial Intelligence in Agriculture

引用

Artificial Intelligence in Agriculture 2025年第1期15卷 26-38页

作者： Xionghai Chen Fei Yuan Syed Tahir Ata-Ul-Karim Xiaojun Liu Yongchao Tian Yan Zhu Weixing Cao Qiang Cao National Engineering and Technology Center for Information Agriculture MOE Engineering and Research Center for Smart AgricultureMARA Key Laboratory for Crop System Analysis and Decision MakingJiangsu Key Laboratory for Information AgricultureCollaborative Innovation Centre for Modern Crop Production Co-sponsored by Province and MinistryNanjing Agricultural UniversityNanjing 210095China Department of Geography Minnesota State UniversityMankatoMN 56001USA Department of Agroecology Climate and WaterAarhus UniversityTjele 8830Denmark

Soil organic matter(SOM)is a key metric for assessing soil quality and crop yield *** plays a vital role in maintaining the ecological balance environment and promoting sustainable farming *** review examines the evolving trends in remote sensing(RS)-based SOM monitoring by analyzing 739 scholarly publications from the Web of Science database from 2003 to 2023 using a bibliometric *** study reveals that research on RS-based SOM monitoring has entered a rapid growth phase since 2018,with China and the United states as the main contributors and an extensive international cooperation *** model construction,high frequency covariates such as soil pH,precipitation,temperature,and topography significantly improved the prediction *** preprocessing methods such as Standard Normal Variables(SNV),Principal Component Analysis(PCA),and Multiple Scattering Correction(MSC)enhanced data *** statistical models are gradually being replaced by nonlinear machine learning and deep learning methods(CNN,XGBoost,andStacking),which are particularly good at handling complex high-dimensional *** spectral libraries(OzSoil and AfSIS)excel in local accuracy,while global spectral libraries(ISRIC and LUCAS)are more suitable for cross-region modeling,and the migration learning technique effectively improves the model generalization ability in low data *** models(CNN-LSTM and GAN)have significant advantages in capturing the spatial and temporal dynamics of SOMs,and uncertainty quantification methods(Bayesian inference,Monte Carlo simulation)enhance the reliability of the models in multi-source data and data-scarce *** research should focus on further optimization of multi-source data fusion and uncertainty quantification to promote the development and applicability of RS-based SOM monitoring techniques for precision soil management and sustainable agriculture.

关键词： Data fusion Modeling methods Transfer learning Spatial mapping Spectral libraries

来源：评论

学校读者我要写书评

暂无评论

Ultraviolet photodetector of TiO2 film in different phase on various substrates

引用

Ceramics International 2025年第13期51卷 17190-17199页

作者： Qi, Jiawei Wu, Yanxia Zhang, Caili Yu, Shengwang Wang, Yongsheng Liu, Ying Hei, Hongjun College of Materials Science and Engineering Taiyuan University of Technology Taiyuan030024 China Lanzhou Institute of Chemical Physics Chinese Academy of Sciences Lanzhou730000 China Instrumental Analysis Center Taiyuan University of Technology Taiyuan034000 China State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China

TiO2 films were gained via annealed Ti films prepared by radio frequency (RF) magnetron sputtering with different sputtering power on various substrates, including Si, quartz glass and diamond. TiO2 films with different phases were obtained by adjusting the sputtering power of Ti target. The results showed that TiO2 films transferred from the anatase phase to the mixed phase then to the rutile phase with increasing sputtering power from 100 W to 300 W. The average transmittance of the samples in the visible light band exceeded 70 % and the adjustable Eg range of the prepared TiO2 film was 3.15–3.21 eV. Specially, the TiO2-based metal-semiconductor-metal (MSM) ultraviolet (UV) photodetector with the film prepared at 100 W (S1) on Si substrate exhibited the better photoelectric performance at 20 V bias, with photo-to-dark current ratio (PDCR), responsivity (R), external quantum efficiency (EQE), and specific detectivity (D∗) of 1.9 × 103, 75.9 mA/W, 15.9 % and 2.3 × 1011 Jones, respectively. Meanwhile, the performance of UV photodetectors with diamond substrate was almost better than that of Si substrate except for S1 due to wide band gap, high carrier mobility and high thermal conductivity of diamond. The performance of S1 on Si substrate was better than diamond substrate owing to the thermal expansion coefficient between anatase TiO2 and Si was closer to that between it and diamond. In addition, when Ti was deposited on Si (111) at room temperature, a strong chemical bond (Ti-Si) was formed between Ti and Si, so that Ti was more uniformly covered on the surface of Si (111) than on the surface of diamond. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Nanocrystals

来源：评论

学校读者我要写书评

暂无评论

Reliable ferroelectricity down to cryogenic temperature in wakeup free Hf_(0.5)Zr_(0.5)O_(2)thin films by thermal atomic layer deposition

引用

Journal of Semiconductors 2024年第3期45卷 33-37页

作者： Shuyu Wu Rongrong Cao Hao Jiang Yu Li Xumeng Zhang Yang Yang Yan Wang Yingfen Wei Qi Liu State Key Laboratory of Fabrication Technologies for Integrated Circuits Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029China Frontier institute of Chip and System Fudan UniversityShanghai 200433China College of Electronic Science and Technology National University of Defense TechnologyChangsha 410073China University of Chinese Academy of Sciences Beijing 100049China

The performance and reliability of ferroelectric thin films at temperatures around a few Kelvin are critical for their application in *** this work,TiN/Hf_(0.5)Zr_(0.5)O_(2)/TiN capacitors that are free from the wake-up effect are investigated systematically from room temperature(300 K)to cryogenic temperature(30 K).We observe a consistent decrease in permittivity(εr)and a progressive increase in coercive electric field(Ec)as temperatures *** investigation reveals exceptional stability in the double remnant polarization(2P_(r))of our ferroelectric thin films across a wide temperature ***,at 30 K,a 2P_(r)of 36μC/cm^(2)under an applied electric field of 3.0 MV/cm is ***,we observed a reduced fatigue effect at 30 K in comparison to 300 *** stable ferroelectric properties and endurance characteristics demonstrate the feasibility of utilizing HfO_(2)based ferroelectric thin films for cryo-electronics applications.

关键词： hafnia-zirconia solid solution ferroelectricity cryogenic temperature wake-up effect

来源：评论

学校读者我要写书评

暂无评论

Continual learning fault diagnosis:A dual-branch adaptive aggregation residual network for fault diagnosis with machine increments

引用

Chinese Journal of Aeronautics 2023年第6期36卷 361-377页

作者： Bojian CHEN Changqing SHEN Juanjuan SHI Lin KONG Luyang TAN Dong WANG Zhongkui ZHU School of Rail Transportation Soochow UniversitySuzhou 215131China China Chang Guang Satellite Technology CO.LTD Changchun 130102China Department of Industrial Engineering and Management and in the State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200030China

As a data-driven approach, Deep Learning(DL)-based fault diagnosis methods need to collect the relatively comprehensive data on machine fault types to achieve satisfactory performance. A mechanical system may include multiple submachines in the real-world. During condition monitoring of a mechanical system, fault data are distributed in a continuous flow of constantly generated information and new faults will inevitably occur in unconsidered submachines, which are also called machine increments. Therefore, adequately collecting fault data in advance is difficult. Limited by the characteristics of DL, training existing models directly with new fault data of new submachines leads to catastrophic forgetting of old tasks, while the cost of collecting all known data to retrain the models is excessively high. DL-based fault diagnosis methods cannot learn continually and adaptively in dynamic environments. A new Continual Learning Fault Diagnosis method(CLFD) is proposed in this paper to solve a series of fault diagnosis tasks with machine increments. The stability–plasticity dilemma is an intrinsic issue in continual learning. The core of CLFD is the proposed Dual-branch Adaptive Aggregation Residual Network(DAARN).Two types of residual blocks are created in each block layer of DAARN: steady and dynamic blocks. The stability–plasticity dilemma is solved by assigning them with adaptive aggregation weights to balance stability and plasticity, and a bi-level optimization program is used to optimize adaptive aggregation weights and model parameters. In addition, a feature-level knowledge distillation loss function is proposed to further overcome catastrophic forgetting. CLFD is then applied to the fault diagnosis case with machine increments. Results demonstrate that CLFD outperforms other continual learning methods and has satisfactory robustness.

关键词： Catastrophic forgetting Continual learning Fault diagnosis Knowledge distillation Machine increments Stability-plasticity dilemma

来源：评论

学校读者我要写书评

暂无评论

Autonomous Navigation of Tracked Robot in Uneven Terrains 16th

Autonomous Navigation of Tracked Robot in Uneven Terrains

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： He, Gang Shi, Juntian Liu, Chao Guo, Weichao Sheng, Xinjun State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Meta Robotics Institute Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9789819965007

Since microdosing of chemical, biological, radiological, and nuclear (CBRN) contaminants is enough to cause great damage to humans, operating robots are widely used to handle CBRN-related tasks. However, how to improve the automation capabilities of these robots in uneven environments, such as autonomous navigation, is still a huge challenge. Current navigation methods usually set the scene as flat pavement, without considering the situation that the land slope exceeds a certain threshold. In order to explore ways of autonomous navigation in uneven environments, a 3D path planning and navigation method for the tracked robot is proposed in this paper, respecting applicable traversability constraints in uneven terrains. Firstly, a 3D graph-based map is built according to the occupancy map of the uneven environment. A set of spatial points, ensuring collision-avoidance of the robot, is randomly sampled in free space, and a vertex map is generated based on these vertices for robot traversing. Then, regarding the robot’s climbing and obstacle crossing ability as constraints, a path planning algorithm is used to search for the best path based on the Dijkstra algorithm. Finally, a fusion SLAM method based on LiDAR, IMU and RGB-D camera is used to achieve real-time localization, and the pure pursuit algorithm is used for navigation. The simulation results show that the proposed method can provide a safe and effective 3D path for the tracked robot and enable the robot’s autonomous navigation in uneven environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Experimental Demonstration of A CT-FeFET Array with Intrinsic Long-Short-Term Plasticity for Low-Cost Trajectory Prediction

Experimental Demonstration of A CT-FeFET Array with Intrinsi...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Li, Chao Yu, Jie Zhang, Xumeng Zhang, Zhaohao Zhu, Fangduo Ouyang, Siyuan Chen, Pei Cheng, Lingli Xu, Gaobo Zhang, Qingzhu Yin, Huaxiang Liu, Qi Liu, Ming State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200438 China Key Laboratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China Key Laboratory of Fabrication Technologies for Integrated Circuits Chinese Academy of Sciences Beijing100029 China

ISBN: (纸本)9798350365429

Trajectory prediction is a vital function in the auto-driving field, typically achieved with a long short-term memory network. Static IMC technology accelerates the computing of long-term parameters, while the execution of short-term parameters faces great buffer overhead. Inspired by the fused long-short-term synaptic plasticity in biology, here, we proposed a dynamic IMC strategy based on a charge-trapping FeFET array with intrinsic long-short-term plasticity. The long-term weights are stored in the ferroelectric domain, while the short-term weights are in-situ dynamically operated in a charge-trapping domain, eliminating the external caching process. We further demonstrated a dynamic IMC neuromorphic system built on this array for performing trajectory prediction of moving vehicles, achieving more than 1000× and 4× improvements than GPU in power consumption and memory overhead. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Iron Loss in Electrical Machine — Influencing Factors, Model, and Measurement

引用

Progress In Electromagnetics Research B 2024年 107卷 105-124页

作者： Yi, Jiawei Dong, Qinyuan Sun, Jianhua Sun, Lixia Li, Xiang Goh, Hui Hwang Zhao, Haisen Wu, Thomas Zhang, Dongdong The School of electrical engineering Guangxi University Nanning530004 China College of Chemistry and Chemical Engineering Guangxi University Nanning530004 China Guangxi Key Laboratory of Petrochemical Resources Processing and Process Strengthening Technology Guangxi University Nanning530004 China The State Key Laboratory of Alternate Electrical Supply System with Renewable Energy Sources North China Electric Power University 102206 China

Improving the efficiency of electrical machine is an important way to reduce carbon emissions. Accurate calculation and measurement of iron loss is an important part of improving efficiency of electrical machine. Therefore, how to accurately calculate and optimize the device structure to reduce iron loss has become a research focus. In this study, the influence of power supply, motor structure, ferromagnetic material, manufacturing processes, and multiphysics on the motor iron loss is discussed and summarized. Then, the classification and summary of the existing iron loss models are discussed, and shortcomings and the future research direction are suggested. In addition, several induction motor efficiency measurement standards are described, and the defects and improvement direction of efficiency measurement of converter-fed motor are discussed. The contents discussed and summarized in this study can be helpful to engineers engaged in high efficiency motor design and motor driving algorithm development. © (2023), (Electromagnetics Academy). All Rights Reserved.

关键词： Iron research

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：