aulraj M P

Fractal feature based detection of muscular and ocular artifacts in EEG signals

Electroencephalogram (EEG) is used to measure the bioelectric potential on the brain scalp. The recorded EEG signal can have different types of artifacts and the interpretation of a noisy EEG signal is difficult. In this research work, a simple method is proposed to minimize the artifacts present in the EEG signals recorded while perceiving a pure tone. The recorded EEG signal can contain artifacts, such as movement artifacts, muscle contraction artifacts and saturation artifacts. In the proposed method, fractal dimension based features with different interval length and time-domain based energy features were extracted from the EEG signals with and without simulated noise. Using the extracted features, neural network models were developed to classify the EEG signal as a normal or a noisy signal. Further, the performance of the model is also evaluated in terms of classification rate. From the results, it is observed that the neural network model developed with the combined fractal dimension features of interval length 2,3,4,5 and 6 with frame size 128 has the highest classification accuracy of 95.5%.

A machine learning approach for distinguishing hearing perception level using auditory evoked potentials

An auditory loss is one of the most common disabilities present in newborns and infants in the world. A conventional hearing screening tests applicability is limited as it requires a feedback response from the subject under test. To overcome such problems, the primary focus of this study is to develop an intelligent hearing ability level assessment system using auditory evoked potential signals (AEP). AEP signal is a non-invasive tool that can reflect the stimulated interactions with neurons along the stations of the auditory pathway. The AEP responses of fourteen normal hearing subjects to auditory stimuli (20 dB, 30 dB, 40 dB, 50 dB and 60 dB) were derived from electroencephalogram (EEG) recordings. Higuchis fractal method is applied to extract the fractal features from the recorded AEP signals. The extracted fractal features were then associated to different hearing perception levels of the subjects. Feed-forward and feedback neural networks are employed to distinguish the different hearing perception levels. The performance of the proposed intelligent hearing ability level assessment found to exceed 85% accuracy. This study indicates that AEP responses to the auditory stimuli to the normal hearing persons can predict the higher order auditory stimuli followed by the lower order auditory stimuli and consequently the state of auditory development of subjects.

EEG based estimation of hearing frequency perception by artificial neural networks

Auditory evoked potentials are a type of EEG signal emanated from the scalp of the brain by an acoustical stimulus. In this paper, auditory evoked potential (AEP) signals emanated while hearing the click-sound stimuli excited at three different frequencies were recorded. Spatio-temporal features of four distinct bands were extracted from the recorded AEP signal. The extracted features were then associated to the hearing frequency perception response of an individual and neural network models for left and right ears were developed. The maximum classification accuracy of the developed neural network model in discriminating the hearing frequency perception response of a person has been observed as 94.5 per cent.

Classification of Moving Vehicles using Multi-Classifier with Time-Domain Approach

The hearing impaired is afraid of walking along a street and living a life alone. Since, it is difficult for hearing impaired to hear and judge sound information and they often encounter risky situations while they are in outdoors. The sound produced by moving vehicle in outdoor situation cannot be moderated wisely by profoundly hearing impaired community. They also cannot distinguish the type and the distance of any moving vehicle approaching from their behind. In this paper, a simple system that identifies the type and distance of a moving vehicle using artificial neural network has been proposed. The noise emanated from a moving vehicle along the roadside was recorded together with its type and position. Using time-domain approach, simple feature extraction algorithm for extracting the feature from the noise emanated by the moving vehicle has been developed. Simple time-domain features such as energy and zerocrossing rates are applied for getting the important signatures from the sound. The extracted features were associated with the type and zone of the moving vehicle and a multi-classifier system (MCS) based on neural network model has been developed. The developed MCS is tested for its validity. General Terms Pattern Recognition, Moving Vehicle, Multilayer Perceptron