Acoustic analysis is one of the important branches of biometric recognition technology widely used now. The mainly aim of the technology is to recognize the identity of person and judge the content of speech or diagnose the illness automatically according to the features extracted from the speaker's waveforms. All these features are related with the characteristics of speaker's physiological, pathological and psychological action. Speaker recognition study has its 50-year old history already, but acoustic analysis in diagnosing disease has been founded since 1970s. This paper introduces the main concept and research background of this diagnosing system generally and discusses the problems generated during processing. At last the prospect for the applications of acoustic analysis is forecasted.
Humans ; Pattern Recognition, Physiological ; Signal Detection, Psychological ; Speech ; physiology ; Speech Acoustics ; Speech Disorders ; diagnosis ; physiopathology

Heart sound is a physiological parameter with individual characteristics generated by heart beat. To do the individual classification and recognition, in this paper, we present our study of using wavelet transform in the signal denoising, with the Mel-Frequency cepstrum coefficients (MFCC) as the feature parameters, and propose a research of reducing the dimensionality through principal components analysis (PCA). We have done the preliminary study to test the feasibility of biometric identification method using heart sound. The results showed that under the selected experimental conditions, the system could reach a 90% recognition rate. This study can provide a reference for further research.
Algorithms ; Artificial Intelligence ; Heart Sounds ; physiology ; Humans ; Individuality ; Pattern Recognition, Physiological ; physiology ; Principal Component Analysis ; Signal Processing, Computer-Assisted ; Wavelet Analysis

This study explored the possibility of using event-related potentials (ERP) for the measurement of picture-recognition memory and examined its correlation with the Chinese Wechsler Memory Scale-revised (WMS-RC) in patients with memory disorder caused by severe traumatic brain injury (sTBI). The subjects included 20 sTBI patients with memory disorder and 22 healthy individuals. Memory function was measured by using WMS-RC. Behavioral and ERP responses were recorded on-line during performance on a battery of picture recognition and the responses were analyzed off-line for recognition memory effects. Mean memory quotient (MQ) of patients with sTBI was significantly lower than that of the control group. Mean reaction time (RT) was significantly longer and the mean correctness rate (CR) of picture recognition was significantly lower in sTBI group than that of the controls. In controls, the main components of average ERP of picture recognition includes two positive-going waves, designated as P(170) and P(500), that appear 170 ms and 500 ms after stimulation when the subject could later successfully recall and recognize the pictures. P(500) amplitude of target stimulus was significantly higher than that of non-target stimulus. Compared to controls, P(500) responses of sTBI group were significantly delayed in latency (P<0.001) and lower in amplitude (P<0.001). P(500) latency showed significant negative correlation with MQ and the scores of "addition", "visual recognition", "picture recall", "visual reproduction" and "tactile memory" in WMS-RC. ERP of picture recognition provides a neurophysiological approach to directly assess memory impairment, and P(500) may serve as a helpful index for memory disorder caused by sTBI in forensic practice.
Brain Injuries/*complications ; Case-Control Studies ; Evoked Potentials/*physiology ; Memory Disorders/*etiology ; Memory Disorders/*physiopathology ; Pattern Recognition, Physiological/*physiology ; Wechsler Scales ; Young Adult

This is a research carried out to explore a pragmatic way of BCI based imaging movement, i. e. to extract the feature of EEG for reflecting different thinking by searching suitable methods of signal extraction and recognition algorithm processing, to boost the recognition rate of communication for BCI system, and finally to establish a substantial theory and experimental support for BCI application. In this paper, different mental tasks for imaging left-right hands movement from 6 subjects were studied in three different time sections (hint keying at 2s, 1s and 0s after appearance of arrow). Then we used wavelet analysis and Feed-forward Back-propagation Neural Network (BP-NN) method for processing and analyzing the experimental data of off-line. Delay time delta t2, delta t1 and delta t0 for all subjects in the three different time sections were analyzed. There was significant difference between delta to and delta t2 or delta t1 (P<0.05), but no significant difference was noted between delta t2 and delta t1 (P>0.05). The average results of recognition rate were 65%, 86.67% and 72%, respectively. There were obviously different features for imaging left-right hands movement about 0.5-1s before actual movement; these features displayed significant difference. We got higher recognition rate of communication under the hint keying at about 1s after the appearance of arrow. These showed the feasibility of using the feature signals extracted from the project as the external control signals for BCI system, and demon strated that the project provided new ideas and methods for feature extraction and classification of mental tasks for BCI.
Algorithms ; Brain ; physiology ; Electroencephalography ; methods ; Evoked Potentials, Motor ; physiology ; Hand ; physiology ; Humans ; Movement ; physiology ; Neural Networks (Computer) ; Pattern Recognition, Physiological ; Signal Processing, Computer-Assisted ; Thinking ; physiology ; User-Computer Interface