A new approach based on discrete hidden Markov model using Rocchio algorithm for the diagnosis of the brain diseases

Transcranial Doppler (TCD) study of the adult intracerebral circulation has gained an important popularity in last 10 years, since it is a non-invasive, easy to apply and reliable technique. In this study, an implementation on biomedical system has been developed for classification of signals gathered from middle cerebral arteries in the temporal area via TCD for 24 healthy and 82 ill people which have one of the four different brain patients such as; cerebral aneurysm, brain hemorrhage, cerebral oedema and brain tumor. Basically, the system is composed of feature extraction and classification parts. In the feature extraction stage, the Linear Predictive Coding (LPC) Analysis and Cepstral Analysis were applied in order to extract the cepstral and delta-cepstral coefficients in frame level as feature vectors. In the classification stage a new Discrete Hidden Markov Model (DHMM) based approach was proposed for the diagnosis of brain diseases. This proposed method was developed via Rocchio algorithm. Therefore, to calculate DHMM parameters regulated according to maximum likelihood (ML) approach, both training samples of related class and other classes were included in calculation. Thus, DHMM model parameters presenting one class were suggested to represent the training samples related to that class better as well as not to represent the training samples related to other classes. The performance of the proposed DHMM with Rocchio approach was compared with some methods such as DHMM, Artificial Neural Network (ANN), neuro-fuzzy approaches and obtained better classification performance than these methods.