In this paper an approach for personal biometric identification is presented based on extraction of ECG features and classification with RBFNN. We perform denoising and segmentation on the input signal, after which we realize dimensionality reduction and feature extraction based on PCA transform. The separability of the selected features is improved by applying LDA. The final stage of the proposed approach is classification and recognition of the extracted features with classifier score fusion.
In this paper an initial analysis is presented for the applicability of the Oculus Rift virtual reality display when used in newly proposed medical assistive system for motor disabled patients. The head-mounted display is used to give the patient a visual representation of the supposed spatial movements to be done along with a set of instructions for the sequence of basic steps. After each step from every exercise an evaluation is done for the degree of completeness by motion analyzing module and decision is made either for repetition or continuing to the next step. In timely manner overall estimation is done over the patient abilities to fulfill the entire program. The embedded sensors return valuable information for the head movement and position of the patient easing the synchronization of the forthcoming instructions. For a given variety of motor tasks the precision of the head set in terms of spatial motion over predetermined time intervals is tested. Positive results are observed and a variety of practical recommendations for using the Oculus Rift display are derived for more efficient usage.
1 March 2018 in Cybernetics and Information Technologies
Signals provided by the ElectroEncephaloGraphy (EEG) are widely used in Brain-Computer Interface (BCI) applications. They can be further analyzed and used for thinking activity recognition. In this paper we proposed an algorithm that is able to recognize five mental tasks using 6 channel EEG data. The main idea is to separate the raw EEG signals into several frames and compute their spectrums. Next, a second-order derivative of Gaussian is applied to extract features and an optimum Gaussian kernel parameters grid search is performed with the help of cross-validation. The extracted features are further reduced by Principal Component Analysis. The processed data is utilized to train SVM classifier which is used for mental tasks recognition afterwards. The performance of the algorithm is estimated on publically available dataset. In terms of 5 folds cross-validation we obtained an average of 82.7% recognition rate (accuracy). Additional experiments were conducted using leave-one-out cross-validation where 67.2% correct classification was reported. Comparison to several state-of-the art methods reveals the advantages of the proposed algorithm.
This paper consider the problem of face detection and tracking with an active camera. An algorithm using the mean-shift method for face detection has been presented. We propose an algorithm that provides automated control of a pan-tilt camera (PTC) to follow a personpsilas face and keep his image centered in the camera view. An error vector defined in the image plane and representing the face offset with respect to the center of the image is used for camera control. Adaptive feedback control design and stability analysis are performed via Lyapunov techniques. Simulation results are presented to illustrate the effectiveness of the proposed algorithms.
Face and ECG Based Multi-Modal Biometric Authentication | InTechOpen, Published on: 2011-08-09. Authors: Ognian Boumbarov, Yuliyan Velchev, Krasimir Tonchev, et
The eye's blinking is a significant indicator of the sleepiness. The existing systems of blink detection and sleepiness analysis require usually to fix camera on spectacle frame or a special helmet that is not convenient and can affect the obtained result. In this paper, the infrared camera-based contact-less system is proposed to evaluate the human's sleepiness. The infrared light switching is used to detect the pupil in each frame and, as a result, the blink event. The active pan-tilt unit is used to make possible free head movements. The algorithm is pointed out to process the camera frames in order to distinguish the involuntary blinks from voluntary ones. Preliminary experimental tests are shown with the intent to validate the proposed hardware and software system pointed out.