[Tutorial] Introduction about the app: ADLs Recognition System

1. LogData Format

% LogFile created by the 'ADLs Recognition System' App for Android.
% Date of creation: 2018
% Developed by Bang Wu, Ph.D. candidate of IoT Lab at QMUL, UK (http://iot.eecs.qmul.ac.uk/)
% Version 1.0 2018
% The 'ADLs Recognition System' program stores information from Smartphone/Tablet internal sensors (Accelerometers, Gyroscopes, Magnetometers, Pressure, Ambient Light, Orientation, GPS/GNSS positio, WiFi RSS,...)
%
% LogFile Data format:
% Accelerometer data: 'ACCE;AppTimestamp(s);SensorTimestamp(s);Acc_X(m/s^2);Acc_Y(m/s^2);Acc_Z(m/s^2);'
% Gyroscope data:      'GYRO;AppTimestamp(s);SensorTimestamp(s);Gyr_X(rad/s);Gyr_Y(rad/s);Gyr_Z(rad/s);'
% Magnetometer data:  'MAGN;AppTimestamp(s);SensorTimestamp(s);Mag_X(uT);;Mag_Y(uT);Mag_Z(uT);'
% Pressure data:      'PRES;AppTimestamp(s);SensorTimestamp(s);Pres(mbar);'
% Light data:          'LIGH;AppTimestamp(s);SensorTimestamp(s);Light(lux);'
% Proximity data:      'PROX;AppTimestamp(s);SensorTimestamp(s);prox(?);'
% Humidity data:      'HUMI;AppTimestamp(s);SensorTimestamp(s);humi(Percentage);'
% Temperature data:    'TEMP;AppTimestamp(s);SensorTimestamp(s);temp(Celsius);'
% rotation vector data: 'AHRS;AppTimestamp(s);SensorTimestamp(s);x*sin(θ/2);y*sin(θ/2);z*sin(θ/2);cos(θ/2);Accuracy(radians)'
% Orientation data:    'ORIE;AppTimestamp(s);SensorTimestamp(s);Azimuth;Pitch;Roll;'
% GNSS/GPS data:      'GNSS;AppTimestamp(s);SensorTimeStamp(s);Latit(deg);Long(deg);Altitude(m);Bearing(deg);Accuracy(m);Speed(m/s);SatInView;SatInUse'
% WIFI data:          'WIFI;AppTimestamp(s);SensorTimeStamp(s);Name_SSID;MAC_BSSID;RSS(dBm);'
% stationary detect:    'STAT;AppTimestamp(s);SensorTimeStamp(s);status(int);'
% motion detect:        'MOTI;AppTimestamp(s);SensorTimeStamp(s);status(int);'
% step detector:        'STEP;AppTimestamp(s);SensorTimeStamp(s);status(int);'
%
% Note that there are two timestamps:
%  -'AppTimestamp' is set by the Android App as data is read. It is not representative of when data is actually captured by the sensor (but has a common time reference for all sensors)
%  -'SensorTimestamp' is set by the sensor itself (the delta_time=SensorTimestamp(k)-SensorTimestamp(k-1) between two consecutive samples is an accurate estimate of the sampling interval). This timestamp is better for integrating inertial data.