中国科学院机构知识库网格系统: 检索

MLDA: Multi-Loss Domain Adaptor for Cross-Session and Cross-Emotion EEG-Based Individual Identification 期刊论文 OAI收割
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 卷号: 27, 期号: 12, 页码: 5767-5778
作者: Miao, Yifan; Jiang, Wanqing; Su, Nuo; Shan, Jun; Jiang, Tianzi

|

收藏 | 浏览/下载：36/0 | 提交时间：2024/03/26

Electroencephalography Feature extraction Task analysis Support vector machines Recording Motion pictures Brain modeling EEG biometric across mental states across time deep learning domain adaptation

A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals 期刊论文 OAI收割
JOURNAL OF ELECTROMYOGRAPHY AND KINESIOLOGY, 2018, 卷号: 42, 页码: 136-142
作者: Wu, Haifeng; Huang, Qing; Wang, Daqing; Gao, Lifu

|

收藏 | 浏览/下载：19/0 | 提交时间：2019/12/10

Convolutional neural network Mechanomyography Knee motion recognition Support vector machine

Classifying Discriminative Features for Blur Detection 期刊论文 OAI收割
ieee transactions on cybernetics, 2016, 卷号: 46, 期号: 10, 页码: 2220-2227
作者: Pang, Yanwei; Zhu, Hailong; Li, Xinyu; Li, Xuelong

收藏 | 浏览/下载：28/0 | 提交时间：2016/11/02

Blur detection classifier feature extraction motion blur support vector machine (SVM)

A hybrid ar-emd-svr model for the short-term prediction of nonlinear and non-stationary ship motion 期刊论文 iSwitch采集
Journal of zhejiang university-science a, 2015, 卷号: 16, 期号: 7, 页码: 562-576
作者: Duan, Wen-yang; Huang, Li-min; Han, Yang; Zhang, Ya-hui; Huang, Shuo

收藏 | 浏览/下载：50/0 | 提交时间：2019/05/09

Nonlinear and non-stationary ship motion Short-term prediction Empirical mode decomposition (emd) Support vector regression (svr) model Autoregressive (ar) model

Estimation of Lower Limb Periodic Motions from sEMG Using Least Squares Support Vector Regression 期刊论文 OAI收割
NEURAL PROCESSING LETTERS, 2015, 卷号: 41, 期号: 3, 页码: 371-388
作者: Li, Q. L.; Song, Y.; Hou, Z. G.

收藏 | 浏览/下载：19/0 | 提交时间：2015/09/21

sEMG LS-SVR Motion estimation Neural network Support vector machine Rehabilitation

Motion intention estimation of lower limbs based on sEMG supplement with acceleration signal 会议论文 OAI收割
27th Chinese Control and Decision Conference, CCDC 2015, Qingdao, China, May 23-25, 2015
作者: Zhao XG(赵新刚); Wang, Rui; Ye D(叶丹)

收藏 | 浏览/下载：21/0 | 提交时间：2015/11/18

sEMG Acceleration Signals Motion Intention Estimation Support Vector Machine (SVM)

Video steganalysis based on the constraints of motion vectors 会议论文 OAI收割
IEEE International Conference on Image Processing, Melbourne, Australia, Sep. 15-18, 2013
作者: Xikai Xu; Jing Dong; Wei Wang; Tieniu Tan; Wang, Wei

收藏 | 浏览/下载：20/0 | 提交时间：2016/01/21

Video steganalysis stegnography data hiding motion vector mutual constraints

Efficient human action recognition using accumulated motion image and support vector machines (EI CONFERENCE) 会议论文 OAI收割
International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2011, November 19, 2011 - November 23, 2011, Suzhou, China
作者: Zhang X.; Zhang J.; Zhang J.; Zhang X.; Zhang X.

收藏 | 浏览/下载：68/0 | 提交时间：2013/03/25

Vision-based human action recognition provides an advanced interface and research in this field of human action recognition has been actively carried out. This paper describes a scheme for recognizing human actions from a video sequences. The proposed method is an extension of the Motion History Image(MHI) method based on the ordinal measure of accumulated motion which is robust to variations of appearances. We define the accumulated motion image(AMI) using image differences firstly. Then the AMI of the video sequencesis resized to a MN regulation following the standard of training phases. Finally we employ Support Vector Machine(SVM) as a classifier to distinguish the current activity in target video sequences. In a word our proposed algorithm not only outperforms the state of art on public available KTH data set and Weizmann data set but also proves practical to some real world applications in addition this method is computationally simple and able to achieve a satisfactory accuracy.

Design of motion adjusting system for space camera based on ultrasonic motor (EI CONFERENCE) 会议论文 OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Space Exploration Technologies and Applications, May 24, 2011 - May 26, 2011, Beijing, China
作者: Sun Z.

收藏 | 浏览/下载：85/0 | 提交时间：2013/03/25

Drift angle is a transverse intersection angle of vector of image motion of the space camera. Adjusting the angle could reduce the influence on image quality. Ultrasonic motor (USM) is a new type of actuator using ultrasonic wave stimulated by piezoelectric ceramics. They have many advantages in comparison with conventional electromagnetic motors. In this paper some improvement was designed for control system of drift adjusting mechanism. Based on ultrasonic motor T-60 was designed the drift adjusting system which is composed of the drift adjusting mechanical frame the ultrasonic motor the driver of Ultrasonic Motor the photoelectric encoder and the drift adjusting controller. The TMS320F28335 DSP was adopted as the calculation and control processor photoelectric encoder was used as sensor of position closed loop system and the voltage driving circuit designed as generator of ultrasonic wave. It was built the mathematic model of drive circuit of the ultrasonic motor T-60 using matlab modules. In order to verify the validity of the drift adjusting system was introduced the source of the disturbance and made simulation analysis. It designed the control systems of motor drive for drift adjusting system with the improved PID control. The drift angle adjusting system has such advantages as the small space simple configuration high position control precision fine repeatability self locking property and low powers. It showed that the system could accomplish the mission of drift angle adjusting excellent. 2011 SPIE.

Three-sample rotation vector algorithm with angular rate input (EI CONFERENCE) 会议论文 OAI收割
2011 2nd International Conference on Mechanic Automation and Control Engineering, MACE 2011, July 15, 2011 - July 17, 2011, Inner Mongolia, China
作者: Zhang Y.

收藏 | 浏览/下载：22/0 | 提交时间：2013/03/25

In order to research the attitude algorithm with angular rate input under the conical motion a optimal threesample rotation vector algorithm based on single-step Newton backward interpolation is proposed. Using the principle of limited rigid body rotation and the characteristic of angular rate input three-sample rotation vector algorithm is derivated. To minimum attitude errors three-sample rotation vector algorithm is optimized. Three angular rate extraction methods of singlestep entire sample recursion multi-step entire sample and singlestep Newton backward interpolation are proposed. Under the condition of conical motion with semi-cone angle 3 and angular frequency 2rad/s simulation is done. The simulation results show that single-step Newton backward interpolation is superior to the other two methods and its maximum error peak is 0.01 error drift rate is 0.036/h. Experiments in three-axis flying turntable with the same parameters are carried out and the results show that error drift rates of three-channels are less than those of traditional quaternion which are 13.53% 12.08% and 23.68% lower respectively. It also verified that the new algorithm can perform a high accuracy under the conical motion. 2011 IEEE.