Skip to content

Latest commit

 

History

History
119 lines (108 loc) · 4.22 KB

CodeBook.md

File metadata and controls

119 lines (108 loc) · 4.22 KB
Raw

Feature Selection

May 23, 2015

Based on experiments published in Human Activity Recognition Using Smartphones

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

The complete list of feature is:

  1. tBodyAcc_mean_X
  2. tBodyAcc_mean_Y
  3. tBodyAcc_mean_Z
  4. tBodyAcc_std_X
  5. tBodyAcc_std_Y
  6. tBodyAcc_std_Z
  7. tGravityAcc_mean_X
  8. tGravityAcc_mean_Y
  9. tGravityAcc_mean_Z
  10. tGravityAcc_std_X
  11. tGravityAcc_std_Y
  12. tGravityAcc_std_Z
  13. tBodyAccJerk_mean_X
  14. tBodyAccJerk_mean_Y
  15. tBodyAccJerk_mean_Z
  16. tBodyAccJerk_std_X
  17. tBodyAccJerk_std_Y
  18. tBodyAccJerk_std_Z
  19. tBodyGyro_mean_X
  20. tBodyGyro_mean_Y
  21. tBodyGyro_mean_Z
  22. tBodyGyro_std_X
  23. tBodyGyro_std_Y
  24. tBodyGyro_std_Z
  25. tBodyGyroJerk_mean_X
  26. tBodyGyroJerk_mean_Y
  27. tBodyGyroJerk_mean_Z
  28. tBodyGyroJerk_std_X
  29. tBodyGyroJerk_std_Y
  30. tBodyGyroJerk_std_Z
  31. tBodyAccMag_mean
  32. tBodyAccMag_std
  33. tGravityAccMag_mean
  34. tGravityAccMag_std
  35. tBodyAccJerkMag_mean
  36. tBodyAccJerkMag_std
  37. tBodyGyroMag_mean
  38. tBodyGyroMag_std
  39. tBodyGyroJerkMag_mean
  40. tBodyGyroJerkMag_std
  41. fBodyAcc_mean_X
  42. fBodyAcc_mean_Y
  43. fBodyAcc_mean_Z
  44. fBodyAcc_std_X
  45. fBodyAcc_std_Y
  46. fBodyAcc_std_Z
  47. fBodyAcc_meanFreq_X
  48. fBodyAcc_meanFreq_Y
  49. fBodyAcc_meanFreq_Z
  50. fBodyAccJerk_mean_X
  51. fBodyAccJerk_mean_Y
  52. fBodyAccJerk_mean_Z
  53. fBodyAccJerk_std_X
  54. fBodyAccJerk_std_Y
  55. fBodyAccJerk_std_Z
  56. fBodyAccJerk_meanFreq_X
  57. fBodyAccJerk_meanFreq_Y
  58. fBodyAccJerk_meanFreq_Z
  59. fBodyGyro_mean_X
  60. fBodyGyro_mean_Y
  61. fBodyGyro_mean_Z
  62. fBodyGyro_std_X
  63. fBodyGyro_std_Y
  64. fBodyGyro_std_Z
  65. fBodyGyro_meanFreq_X
  66. fBodyGyro_meanFreq_Y
  67. fBodyGyro_meanFreq_Z
  68. fBodyAccMag_mean
  69. fBodyAccMag_std
  70. fBodyAccMag_meanFreq
  71. fBodyBodyAccJerkMag_mean
  72. fBodyBodyAccJerkMag_std
  73. fBodyBodyAccJerkMag_meanFreq
  74. fBodyBodyGyroMag_mean
  75. fBodyBodyGyroMag_std
  76. fBodyBodyGyroMag_meanFreq
  77. fBodyBodyGyroJerkMag_mean
  78. fBodyBodyGyroJerkMag_std
  79. fBodyBodyGyroJerkMag_meanFreq