Skip to content

CodeBook.md

Latest commit

 

History

History
56 lines (44 loc) · 2.88 KB

CodeBook.md

File metadata and controls

56 lines (44 loc) · 2.88 KB

#Overview The "raw" data is obtained from the project Human Activity Recognition Using Smartphones dataset.

The raw data is divided into training and test sets that have identical structure. During the processing each of these sets goes through the following conversion:

  1. values for the subject and activity are added for each measurement
  2. only the values representing mean and standard deviation are taken
  3. the variable descriptive names are used as the measurment column labels

After this conversion the test and training data sets are merged to create one data set, and mean values are calculated for each variable, aggregated by the subject and activity.

The variables of the resulting data set

  • subject - identifies the person performing the activity. Range from 1 to 30
  • activity - one of the 6 activities:
    • WALKING
    • WALKING_UPSTAIRS
    • WALKING_DOWNSTAIRS
    • SITTING
    • STANDING
    • LAYING
  • mean value for each of the variables described below, calculated for all the measurements for every person and activity.

The semantics of the variables are described in the original data set, and is as follows:
The features selected for this database come from the accelerometer and gyroscope 3-axial raw signals tAcc-XYZ and tGyro-XYZ. These time domain signals (prefix 't' to denote time) were captured at a constant rate of 50 Hz. Then they were filtered using a median filter and a 3rd order low pass Butterworth filter with a corner frequency of 20 Hz to remove noise. Similarly, the acceleration signal was then separated into body and gravity acceleration signals (tBodyAcc-XYZ and tGravityAcc-XYZ) using another low pass Butterworth filter with a corner frequency of 0.3 Hz.

Subsequently, the body linear acceleration and angular velocity were derived in time to obtain Jerk signals (tBodyAccJerk-XYZ and tBodyGyroJerk-XYZ). Also the magnitude of these three-dimensional signals were calculated using the Euclidean norm (tBodyAccMag, tGravityAccMag, tBodyAccJerkMag, tBodyGyroMag, tBodyGyroJerkMag).

Finally a Fast Fourier Transform (FFT) was applied to some of these signals producing fBodyAcc-XYZ, fBodyAccJerk-XYZ, fBodyGyro-XYZ, fBodyAccJerkMag, fBodyGyroMag, fBodyGyroJerkMag. (Note the 'f' to indicate frequency domain signals).

These signals were used to estimate variables of the feature vector for each pattern:
'-XYZ' is used to denote 3-axial signals in the X, Y and Z directions.

  • tBodyAcc-XYZ
  • tGravityAcc-XYZ
  • tBodyAccJerk-XYZ
  • tBodyGyro-XYZ
  • tBodyGyroJerk-XYZ
  • tBodyAccMag
  • tGravityAccMag
  • tBodyAccJerkMag
  • tBodyGyroMag
  • tBodyGyroJerkMag
  • fBodyAcc-XYZ
  • fBodyAccJerk-XYZ
  • fBodyGyro-XYZ
  • fBodyAccMag
  • fBodyAccJerkMag
  • fBodyGyroMag
  • fBodyGyroJerkMag

The set of variables that were estimated from these signals are:

  • mean: Mean value
  • std: Standard deviation