[Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation].

Aiming at the problem of low recognition accuracy of motor imagery electroencephalogram signal due to individual differences of subjects, an individual adaptive feature representation method of motor imagery electroencephalogram signal is proposed in this paper. Firstly, based on the individual differences and signal characteristics in different frequency bands, an adaptive channel selection method based on expansive relevant features with label F (ReliefF) was proposed. By extracting five time-frequency domain observation features of each frequency band signal, ReliefF algorithm was employed to evaluate the effectiveness of the frequency band signal in each channel, and then the corresponding signal channel was selected for each frequency band. Secondly, a feature representation method of common space pattern (CSP) based on fast correlation-based filter (FCBF) was proposed (CSP-FCBF). The features of electroencephalogram signal were extracted by CSP, and the best feature sets were obtained by using FCBF to optimize the features, so as to realize the effective state representation of motor imagery electroencephalogram signal. Finally, support vector machine (SVM) was adopted as a classifier to realize identification. Experimental results show that the proposed method in this research can effectively represent the states of motor imagery electroencephalogram signal, with an average identification accuracy of (83.0±5.5)% for four types of states, which is 6.6% higher than the traditional CSP feature representation method. The research results obtained in the feature representation of motor imagery electroencephalogram signal lay the foundation for the realization of adaptive electroencephalogram signal decoding and its application.

Follow the Smoke: Immersive Display of Motion Data With Synthesized Smoke.

With the development of motion capture and graphics technology, visual feedback becomes increasingly important for tasks such as motion training. In order to engage users with immersive visual feedback, we introduce smoke simulation to enhance the motion display. Boundary conditions in the smoke simulation are designed to produce smoke which follows and implies the corresponding complex human motion. We also synthesize multilayer smoke, which is shown to be useful for emphasizing the motion of specified limbs. We implement our technique in an HMD-based virtual reality (VR) system for Tai-Chi training. User study results show that synthesized smoke is useful for enhancing the motion display, and that the training process is generally preferred in terms of engagement.

Psychophysiological classification and experiment study for spontaneous EEG based on two novel mental tasks.

BACKGROUND: Study of imagination offers a perfect setting for study of a large variety of states of consciousness. OBJECTIVE: Here, we studied the characteristics of two electroencephalographic (EEG) patterns evoked by two different imaginary tasks and evaluated the binary classification performance. METHODS: Fifteen individuals (11 male and 4 female, age range of 22 to 33) participated in five sessions of 32-channel EEG recordings. Only by analyzing the subjects' output EEG signals from the central parieto-occipital region of PZ electrode, under the circumstances of consciousness of relaxation-meditation or tension-imagination, we carried out the experiment of feature extraction for spontaneous EEG, as the subjects were blindfolded but asked to open their eyes all the same. The Hilbert-Huang Transform (HHT) was utilized to obtain the Hilbert time-frequency amplitude spectrum, and then with the feature vector set extracted, a two-class Fisher linear discriminant analysis classifier was trained for classification of data epochs of those two tasks. RESULTS: The overall result was that about 90% (± 5%) of the epochs could be correctly classified to their originating task. CONCLUSION: This study not only brings new opportunities for consciousness studies, but also provides a new classification paradigm for achieving control of robots based on the brain-computer interface (BCI).