Human Activity Recognition (HAR) is a research field aimed at identify the action carried out by one subject. This is done by exploitation of on body sensors. Applications are numerous, in the field of health care to monitor elderly or diseased persons or in the domain of sport and fitness. Recent smartphones incorporate accelerometers, gyroscopes and have great processing abilities and are perfectly suited for such developments.
Experimental design: The experiments have been carried out with a group of 30 volunteers within an age bracket of 19-48 years. Each person performed six activities (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING) wearing a smartphone (Samsung Galaxy S II) on the waist. Using its embedded accelerometer and gyroscope, we captured 3-axial linear acceleration (expressed in g) and 3-axial angular velocity (expressed in radian/sec) at a constant rate of 50Hz. The experiments have been video-recorded to label the data manually. The obtained dataset has been randomly partitioned into two sets, where 70% of the volunteers was selected for generating the training data and 30% the test data.
The sensor signals (accelerometer and gyroscope) were pre-processed by applying noise filters and then sampled in fixed-width sliding windows of 2.56 sec and 50% overlap (128 readings/window). The sensor acceleration signal, which has gravitational and body motion components, was separated using a Butterworth low-pass filter into body acceleration and gravity. The gravitational force is assumed to have only low frequency components, therefore a filter with 0.3 Hz cutoff frequency was used. From each window, a vector of features was obtained by calculating variables from the time and frequency domain.
Processed data: Data were processed in R. Data were initially split in several tables (one for the subjects id, one for the activities, another for the data themselves) and had to be reunited. For the purpose of this class, both dataset, test and train, where merged in one dataset. In the same way and in a goal of simplification, only the measurements on the mean and standard deviation for each measurement where selected. And lastly, for each subject and each activity (which was performed several times) an average was retained.