Bio-signals compression using auto-encoder

Latest developments in wearable devices permits un-damageable and cheapest way for gathering of medical data such as bio-signals like ECG, Respiration, Blood pressure etc. Gathering analysis various biomarkers are considered to provide anticipatory healthcare through customized applications purpose. Wearable will rely on size, resources battery capacity; we need a novel algorithm robustly control memory the energy device. The rapid growth technology has led numerous auto encoders that guarantee results by extracting feature selection from time frequency domain an efficient way. main aim is train hidden layer reconstruct similar input. In previous works, accomplish compression all features were needed but our proposed framework using auto-encoder (BCAE) perform task taking only important compress it. By doing this it can reduce power consumption at source end hence increases life. performance result comparison done 3 parameters ratio, reconstruction error consumption. Our work outperforms with respect SURF method.