Advancement in the field of telemedicine facilitated to transmit large volumes of biomedical images through internet. Transmission speed is important even it when compromises on the visually redundant information in the image. To resolve the informational loss convolutional encoders are used at the transmitter’s end for coding the pixel intensities, Viterbi decoders are the most widely used decoder at the receiver’s end to extract the message bits from the convolutional coded data. However, with respect to the increase in number of errors, the speed of the decoder decreases. Hence extensive research has been carried out in this area to develop high speed computationally less complex Viterbi decoders. Recent research focuses on the modifications of Add Compare Select Unit (ACSU), Path Metric Unit (PMU) and Branch Metric Unit (BMU) of the conventional Viterbi decoder. In this paper, a novel approach is proposed for the design of coder-decoder using soft computing techniques. Predicted message bits from the proposed ANFIS are exactly equal to that obtained from the conventional Viterbi decoders followed by an experimental simulation and assessment over a set of test biomedical images in MATLAB simulation environment. Speed of the proposed system is independent on the number of error bits in the code. Performance of the proposed system is much better than BPN based approach in terms of accuracy and sensitivity. The experimental results demonstrated that the execution of the approach is both efficient and effectual, minimizing the response time by reducing the network transfer.

Username
Password