top of page


Time series forecasting


Scout for data sets which include time histories for sound or vibration (eg. ECG, turbine bearing, seismic). Pick parameters of interest and perform FFT to look at data in the frequency domain to understand temporal changes in frequencies, their magnitudes and phases to find patterns and perform classification. One example could be acquire fetal sound data in pregnant (instead of multiple ultrasounds) to predict amniotic fluid levels, potential health concerns etc.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page