Time filter

Source Type

Wan C.,Jilin University | Tian Y.T.,Jilin University | Tian Y.T.,Key Laboratory of Bionic Engineering
Applied Mechanics and Materials | Year: 2014

Affective computing is an indispensable aspect in harmonious human-computer interaction and artificial intelligence. Making computers have the ability of generating emotions is a challenging task of affective computing. Affective Computing and Artificial Psychology are new research fields that involve computer and emotions, they have the same key research aspect, affective modeling. The paper introduces the basic affective elements, and the representation of affections in a computer. And then this paper will describe an emotion generation model for a multimodal virtual human. The relationship among the emotion, mood and personality are discussed, and the PAD emotion space is used to define the emotion and the mood. We obtain the strength information of each expression component through fuzzy recognition of facial expressions based on Ekman six expression classifications, and take this information as a signal motivating emotion under the intensity-based affective model. Finally, a 3D virtual Human emotional expression system with facial expressions is designed to show the emotion generation outputs. Experimental results demonstrate that the emotion generation intensity-based model works effectively and meets the basic principle of human emotion generation. © (2014) Trans Tech Publications, Switzerland.

Xu Z.J.,Jilin University | Tian Y.T.,Jilin University | Tian Y.T.,Key Laboratory of Bionic Engineering | Yang Z.M.,Jilin University | Li Y.,Jilin University
Applied Mechanics and Materials | Year: 2014

Finger joint angle pattern recognition is significant for the development of an intelligent bionic hand. It makes the intelligent prosthesis understand the user's intension more accurately and complete movements better. Surface electromyography signals have been widely used in intelligent bionics prosthesis research and rehabilitation medicine due to its advantages like high efficiency, convenient collection and non-invasive access. An improved grid-search method using a support vector machine has been proposed for the finger joint angle pattern recognition issue in surface electromyography signals. Pattern recognition for surface electromyography signals of index finger movement and metacarpophalangeal joint angle has been performed. Better classification performance was achieved through screening of feature vector combined with an improved grid-search support vector machine classification algorithm. © (2014) Trans Tech Publications, Switzerland.

Liang P.,Key Laboratory of Bionic Engineering | Wei J.,Dalian University
Applied Mechanics and Materials | Year: 2012

Using a weighed decomposition of the stiffness matrix and the weighed generalized inverse theory, a reanalysis method is presented for the topological modification of plane structures, and a set of formulae of elementary topology change are obtained. These formulae are explicit one and using them one can reanalyze the modified structures in topological optimal design. Finally an example is given to verify the valid of this method.

Li M.,Jilin University | Chen W.,Jilin University | Cui B.,Jilin University | Tian Y.,Jilin University | Tian Y.,Key Laboratory of Bionic Engineering
Open Biomedical Engineering Journal | Year: 2015

In this paper, in order to solve the existing problems of the low recognition rate and poor real-time performance in limb motor imagery, the integrated back-propagation neural network (IBPNN) was applied to the pattern recognition research of motor imagery EEG signals (imagining left-hand movement, imagining right-hand movement and imagining no movement). According to the motor imagery EEG data categories to be recognized, the IBPNN was designed to consist of 3 single three-layer back-propagation neural networks (BPNN), and every single neural network was dedicated to recognizing one kind of motor imagery. It simplified the complicated classification problems into three mutually independent two-class classifications by the IBPNN. The parallel computing characteristic of IBPNN not only improved the generation ability for network, but also shortened the operation time. The experimental results showed that, while comparing the single BPNN and Elman neural network, IBPNN was more competent in recognizing limb motor imagery EEG signals. Also among these three networks, IBPNN had the least number of iterations, the shortest operation time and the best consistency of actual output and expected output, and had lifted the success recognition rate above 97 percent while other single network is around 93 percent. © Li et al.; Licensee Bentham Open.

Huang H.,Key Laboratory of Bionic Engineering | Huang H.,Jilin University | Zhang Y.,Tianjin University of Science and Technology | Ren L.,Key Laboratory of Bionic Engineering | Ren L.,Jilin University
Journal of Bionic Engineering | Year: 2012

In order to improve the particle erosion resistance of engineering surfaces, this paper proposed a bionic sample which is inspired from the skin structure of desert lizard, Laudakin stoliczkana. The bionic sample consists of a hard shell (aluminum) and a soft core (silicone rubber) which form a two-layer composite structure. The sand blast tests indicated that the bionic sample has better particle erosion resistance. In steady erosion period, the weight loss per unit time of the bionic sample is about 10% smaller than the contrast sample. The anti-erosion mechanism of the bionic sample was studied by single particle impact test. The results show that, after the impact, the kinetic energy of the particle is reduced by 56.5% on the bionic sample which is higher than that on the contrast sample (31.2%). That means the bionic sample can partly convert the kinetic energy of the particle into the deformation energy of the silicone rubber layer, thus the erosion is reduced. © 2012 Jilin University.

Discover hidden collaborations