Ballistocardiography is a revamped technology for cardiac function monitoring. Detecting individual heart beats
in BCG remains a challenging task due to various artifacts and low signal-to-noise ratio, which are not well addressed by conventional approaches using intuitive or simple-form principles. Instead, we propose to employ deep learning networks to capture the characteristics of variational BCG waveforms within and across individual subjects. Particularly, we design a neural network that combines Convolutional-Neural-Network
(CNN) and Extreme Learning Machine (ELM). We test the new learning method on a real BCG data set and compare it with a state-of-the-art method. We demonstrate how advanced machine learning technology can learn and detect BCG waveforms robustly.