KNN-Based ML Model for the Symbol Prediction in TCM Trellis Coded Modulation TCM Decoder

Machine Learning is a booming technology today. In machine learning set of training, data to be provided the model for training and that predicts output. models are trained using computer program known as ML algorithms.The new learning-based Transition Metric Unit (TMU) 4D- 8PSK Trellis coded Modulation TCM Decoder presented in this work. The classic Viterbi decoder's branch metric unit, or TMU, takes on complex structure. (TCM) combination 8 PSK modulations Error Correcting Code (ECC). TMU one units decoder, which essentially decoder. Similar how first Branch determined straightforward decoder performs BM computation via unit. becomes challenging uses more dynamic power result enormous constraint length vast number encoder states.In proposed algorithm innovative KNN (K nearest neighbours) based developed. It supervised input output both model, also called labels, when will come give its previous experience data.Here we symbol prediction at receiver end learning. Using innovation, paper perceives optimization further reduce H/W requirements low latency results less consumption.