Our final (tidy) data set contains means of all 66 features containing mean() or std() by subject and activity, for a total of 180 rows and 68 columns. The final data set is written as a .txt file called "course3project.txt". Specific variables are described below:
- subject - subject ID (1-30)
- activity - one of 6 activities (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING)
The remaining 66 columns reflect means across a specific subject and activity. Note that the measurements are standardized on a -1 to 1 scale and thus unitless. Here is a guide to these variable names:
- "time" refers to the time domain of the signal
- "frequency" refers to the frequency domain of the signal from a FFT
- "Body" refers to the Body component of the accelerometer readings
- "Gravity" refers to the Gravity component of the accelerometer readings
- "Mean" refers to original data that was a calculated signal average in a window sample
- "SD" refers to original data that was a calculated standard deviation of signals in a window sample
- "axis" refers to the direction of the signal (X, Y, or Z direction)
- "Jerk" refers to a measure derived from body linear acceleration and angular velocity
- "Magnitude" refers to signal magnitude based on Euclidean norm
- timeBodyAccelerometer-Mean-Xaxis
- timeBodyAccelerometer-Mean-Yaxis
- timeBodyAccelerometer-Mean-Zaxis
- timeBodyAccelerometer-SD-Xaxis
- timeBodyAccelerometer-SD-Yaxis
- timeBodyAccelerometer-SD-Zaxis
- timeGravityAccelerometer-Mean-Xaxis
- timeGravityAccelerometer-Mean-Yaxis
- timeGravityAccelerometer-Mean-Zaxis
- timeGravityAccelerometer-SD-Xaxis
- timeGravityAccelerometer-SD-Yaxis
- timeGravityAccelerometer-SD-Zaxis
- timeBodyAccelerometerJerk-Mean-Xaxis
- timeBodyAccelerometerJerk-Mean-Yaxis
- timeBodyAccelerometerJerk-Mean-Zaxis
- timeBodyAccelerometerJerk-SD-Xaxis
- timeBodyAccelerometerJerk-SD-Yaxis
- timeBodyAccelerometerJerk-SD-Zaxis
- timeBodyGyroscope-Mean-Xaxis
- timeBodyGyroscope-Mean-Yaxis
- timeBodyGyroscope-Mean-Zaxis
- timeBodyGyroscope-SD-Xaxis
- timeBodyGyroscope-SD-Yaxis
- timeBodyGyroscope-SD-Zaxis
- timeBodyGyroscopeJerk-Mean-Xaxis
- timeBodyGyroscopeJerk-Mean-Yaxis
- timeBodyGyroscopeJerk-Mean-Zaxis
- timeBodyGyroscopeJerk-SD-Xaxis
- timeBodyGyroscopeJerk-SD-Yaxis
- timeBodyGyroscopeJerk-SD-Zaxis
- timeBodyAccelerometerMagnitude-Mean
- timeBodyAccelerometerMagnitude-SD
- timeGravityAccelerometerMagnitude-Mean
- timeGravityAccelerometerMagnitude-SD
- timeBodyAccelerometerJerkMagnitude-Mean
- timeBodyAccelerometerJerkMagnitude-SD
- timeBodyGyroscopeMagnitude-Mean
- timeBodyGyroscopeMagnitude-SD
- timeBodyGyroscopeJerkMagnitude-Mean
- timeBodyGyroscopeJerkMagnitude-SD
- frequencyBodyAccelerometer-Mean-Xaxis
- frequencyBodyAccelerometer-Mean-Yaxis
- frequencyBodyAccelerometer-Mean-Zaxis
- frequencyBodyAccelerometer-SD-Xaxis
- frequencyBodyAccelerometer-SD-Yaxis
- frequencyBodyAccelerometer-SD-Zaxis
- frequencyBodyAccelerometerJerk-Mean-Xaxis
- frequencyBodyAccelerometerJerk-Mean-Yaxis
- frequencyBodyAccelerometerJerk-Mean-Zaxis
- frequencyBodyAccelerometerJerk-SD-Xaxis
- frequencyBodyAccelerometerJerk-SD-Yaxis
- frequencyBodyAccelerometerJerk-SD-Zaxis
- frequencyBodyGyroscope-Mean-Xaxis
- frequencyBodyGyroscope-Mean-Yaxis
- frequencyBodyGyroscope-Mean-Zaxis
- frequencyBodyGyroscope-SD-Xaxis
- frequencyBodyGyroscope-SD-Yaxis
- frequencyBodyGyroscope-SD-Zaxis
- frequencyBodyAccelerometerMagnitude-Mean
- frequencyBodyAccelerometerMagnitude-SD
- frequencyBodyBodyAccelerometerJerkMagnitude-Mean
- frequencyBodyBodyAccelerometerJerkMagnitude-SD
- frequencyBodyBodyGyroscopeMagnitude-Mean
- frequencyBodyBodyGyroscopeMagnitude-SD
- frequencyBodyBodyGyroscopeJerkMagnitude-Mean
- frequencyBodyBodyGyroscopeJerkMagnitude-SD
Data for this project was obtained from: https://d396qusza40orc.cloudfront.net/getdata%2Fprojectfiles%2FUCI%20HAR%20Dataset.zip
Here is an excerpt from their README.txt describing the experiment used to collect data:
Human Activity Recognition Using Smartphones Dataset Version 1.0
Jorge L. Reyes-Ortiz, Davide Anguita, Alessandro Ghio, Luca Oneto. Smartlab - Non Linear Complex Systems Laboratory DITEN - Università degli Studi di Genova. Via Opera Pia 11A, I-16145, Genoa, Italy. activityrecognition@smartlab.ws www.smartlab.ws
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 and 3-axial angular velocity 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. See 'features_info.txt' for more details.
For each record it is provided:
- Triaxial acceleration from the accelerometer (total acceleration) and the estimated body acceleration.
- Triaxial Angular velocity from the gyroscope.
- A 561-feature vector with time and frequency domain variables.
- Its activity label.
- An identifier of the subject who carried out the experiment.
Notes:
- Features are normalized and bounded within [-1,1].
- Each feature vector is a row on the text file.
License: Use of this dataset in publications must be acknowledged by referencing the following publication [1]
[1] Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra and Jorge L. Reyes-Ortiz. Human Activity Recognition on Smartphones using a Multiclass Hardware-Friendly Support Vector Machine. International Workshop of Ambient Assisted Living (IWAAL 2012). Vitoria-Gasteiz, Spain. Dec 2012