Identification of moderate to chronic diabetic neuropathic conditions of simulated median nerve response using prony´s method

Using a portable electroneurograph, the evoked response of the median nerve has been recorded from patients with moderate to chronic diabetic neuropathic conditions. The evoked responses are again simulated and the features of these signals are extracted using Prony´s feature extraction method. The poles and resonance frequencies of the evoked responses are used as features. A multilayer feed forward neural network classifier is applied to these features for the classification of different neuropathic conditions. Identification of moderate to chronic diabetic neuropathic conditions at different stages is the primary significance of this technique which helps the doctor for better diagnosis and to go for advanced treatment.