Human Activity Recognition Using Smartphones Dataset
Human Activity Recognition Using Smartphones Dataset Version 2.0
A tidy data set based on the data sourced from https://d396qusza40orc.cloudfront.net/getdata%2Fprojectfiles%2FUCI%20HAR%20Dataset.zip
- The output of this data set is a summary level average for each of the 30 Subjects and each of the 6 activities.
- Subject identifier was combined included in the data
- Activity names replaced the numeric values in the original data set.
- The features were selected by chosing only data that has "mean" or "std" standard deviation value.
See CodeBook.txt for details of how the data was assembled, selected, and description of fields.
================= The script first merges the files containing training data and test data, subject identiers, activity data, and activity reference data.
In addition to merging, column headers were applied, loaded from features.txt
The data then selected the fields needed, putting into a data.frame named "tidydata". Only means and Standard Deviation columns were selected in addition to Subject and Activity.
The tidydata was summarized by grouping by Subject and Activity, and getting the mean value of each remaining feature. This was stored in a data.table named "summarydata".
SummaryData was then persisted to a "Pipe-delimited" text file "summarydata.txt".
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
Additional vectors obtained by averaging the signals in a signal window sample. These are used on the angle() variable:
gravityMean tBodyAccMean tBodyAccJerkMean tBodyGyroMean tBodyGyroJerkMean
The complete list of variables of each feature vector is available in 'CodeBook.txt'
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.
Check the README.txt file for further details about this dataset.
A video of the experiment including an example of the 6 recorded activities with one of the participants can be seen in the following link: [Web Link]
For each record in the dataset 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.
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
This dataset is distributed AS-IS and no responsibility implied or explicit can be addressed to the authors or their institutions for its use or misuse. Any commercial use is prohibited.
Jorge L. Reyes-Ortiz, Alessandro Ghio, Luca Oneto, Davide Anguita. November 2012.