Are you Tian Yantao?

Claim your profile

Publications (5)0 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, three experiments were conducted about the extension/flexion movements of the index finger at two speeds 0.4Hz and 0.8Hz of the 10 subjects. AR coefficients of sEMG signals were used as the feature parameters fed into the fuzzy neural network. The motion direction identification, fixed finger joint angle recognition and trajectory forecast are implemented in this study. The experimental results are generally satisfactory: the accuracy rate of motion direction identification is 100% (0.4Hz) and 92.5% (0.8Hz); the accuracy rates of fixed finger joint angle recognition all reached 100% in 0.4Hz and 0.8Hz experiments; joint angle forecast achieved a good trajectory tracking. The results of this study show the feasibility of extraction finger joint angle information from sEMG.
    Industrial Electronics and Applications (ICIEA), 2013 8th IEEE Conference on; 01/2013
  • Zhang Li, Tian Yantao, Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In order to improve the accuracy rate of surface EMG (sEMG) pattern recognition, a modified Kohonen self-organizing competitive network is presented in this paper. Kohonen network has a simple algorithm and short time for clustering. There we adjust the structure of this network, and turn it into a supervised learning network by adding an output layer, then optimize the initial weight. The integrate EMG and power spectral density ratio of sEMG as the input of modified Kohonen network to identify the five kinds of movement patterns: extension of thumb, extension of wrist, flexion of wrist, side flexion of wrist and extension of palm. Experiments show that, compared with the traditional Kohonen network, the modified neural network classifier has the higher classification ability.
    Electronics, Communications and Control (ICECC), 2011 International Conference on; 01/2011
  • Shang Xiaojing, Tian Yantao, Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: The surface EMG (sEMG) is a biological electrical signal of neuromuscular activity distribution. From the point of the non-stationary and nonlinear, the independent component analysis method is firstly used to eliminate the power frequency interference in sEMG. Secondly, the low noise signal is processed by empirical mode decomposition (EMD), then use the decomposed signal to establish AR model. The model coefficients are used as signal features and PNN optimized by particle swarm optimization (PSO) is used to classify six types of forearm motions. The experimental results demonstrate the effectiveness of the proposed method.
    Electronics, Communications and Control (ICECC), 2011 International Conference on; 01/2011
  • Xu Zhuojun, Tian Yantao, Li Yang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we use ADAMS to design a model of intelligent prosthetic hand, which has the high humanoid shape, its weight and size are similar to adults hand The proposed model has 16 degrees of freedom (dofs), which are split into 14 dofs for the five fingers, and 2 dofs for the wrist. The model allows the execution of Activities of Daily Living (ADLs) like grasp, wrist turn and so on, in order to the research the control algorithm of the prosthetic hand, Integration of ADAMS with MATLAB for designing and developing prosthetic hand system is presented in this paper. The model can complete simple movements by proportional control algorithm.
    Electronics, Communications and Control (ICECC), 2011 International Conference on; 01/2011
  • Li Yang, Tian Yantao, Chen Yantao
    [Show abstract] [Hide abstract]
    ABSTRACT: For realizing seven hand gestures classification correctly, wavelet transform is used firstly to eliminate the noise in sEMG, because of its multi-resolution analysis characteristic. Then combine time domain features (such as EMG integral, variance, the third-order AR model coefficients) with frequency domain features (power-spectrum) as the inputs of neural network classifier to discriminate seven motion patterns. According to the shortcoming of traditional BP neural network algorithm which is easily trapped into local minimum, an improved one based on existing BP algorithm and simulated annealing algorithm is proposed in this paper. The experimental results indicate that the correct rate is above 90% by using the above algorithm. Comparing with traditional BP algorithm, the novel one has better recognition capability.
    Control Conference (CCC), 2010 29th Chinese; 08/2010