A current engineering challenge is to identify human activity (e.g., walking, in car, on bike, eating, smoking, falling) from smartphones and other wearable devices. More specifically, the embedded sensors (e.g., accelerometers and gyroscopes) produce a time series of position, velocity, and acceleration measurements. These time series are then processed to produce a set of features that can be used for activity recognition. The aim of this topic is to develop a supervised method to classify observations into human activities categories.
- matplotlib
- numpy
- sklearn
- pandas