Data
Smartphone-Based_Recognition_of_Human_Activities

Smartphone-Based_Recognition_of_Human_Activities

active ARFF Publicly available Visibility: public Uploaded 01-12-2015 by Joaquin Vanschoren
0 likes downloaded by 9 people , 9 total downloads 0 issues 0 downvotes
  • sport study_7 study_88 study_93
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Jorge L. Reyes-Ortiz, Davide Anguita, Luca Oneto and Xavier Parra. Preprocessed by Mikhail Evchenko Source: [UCI](http://archive.ics.uci.edu/ml/datasets/Smartphone-Based+Recognition+of+Human+Activities+and+Postural+Transitions) Please cite: Jorge-L. Reyes-Ortiz, Luca Oneto, Albert Sama, Xavier Parra, Davide Anguita. Transition-Aware Human Activity Recognition Using Smartphones. Neurocomputing. Springer 2015. Transition-Aware Human Activity Recognition The experiments were carried out with a group of 30 volunteers within an age bracket of 19-48 years. They performed a protocol of activities composed of six basic activities: three static postures (standing, sitting, lying) and three dynamic activities (walking, walking downstairs and walking upstairs). The experiment also included postural transitions that occurred between the static postures. These are: stand-to-sit, sit-to-stand, sit-to-lie, lie-to-sit, stand-to-lie, and lie-to-stand. All the participants were wearing a smartphone (Samsung Galaxy S II) on the waist during the experiment execution. We captured 3-axial linear acceleration and 3-axial angular velocity at a constant rate of 50Hz using the embedded accelerometer and gyroscope of the device. The experiments were video-recorded to label the data manually. 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 561 features was obtained by calculating variables from the time and frequency domain. See 'features_info.txt' for more details. This dataset is an updated version of the UCI Human Activity Recognition Using smartphones Dataset that can be found at: [Web Link] This version provides the original raw inertial signals from the smartphone sensors, instead of the ones pre-processed into windows which were provided in version 1. This change was done in order to be able to make online tests with the raw data. Moreover, the activity labels were updated in order to include postural transitions that were not part of the previous version of the dataset. Note: From the original UCI data, the data was aggregated for each person and activity type (mean). Train and test sets are joined. ### Attribute Information - Raw triaxial signals from the accelerometer and gyroscope of all the trials with participants. - The labels of all the performed activities.

68 features

Activity (target)nominal6 unique values
0 missing
Person (ignore)nominal30 unique values
0 missing
tBodyAcc-mean()-Xnumeric180 unique values
0 missing
tBodyAcc-mean()-Ynumeric180 unique values
0 missing
tBodyAcc-mean()-Znumeric180 unique values
0 missing
tBodyAcc-std()-Xnumeric180 unique values
0 missing
tBodyAcc-std()-Ynumeric180 unique values
0 missing
tBodyAcc-std()-Znumeric180 unique values
0 missing
tGravityAcc-mean()-Xnumeric180 unique values
0 missing
tGravityAcc-mean()-Ynumeric180 unique values
0 missing
tGravityAcc-mean()-Znumeric180 unique values
0 missing
tGravityAcc-std()-Xnumeric180 unique values
0 missing
tGravityAcc-std()-Ynumeric180 unique values
0 missing
tGravityAcc-std()-Znumeric180 unique values
0 missing
tBodyAccJerk-mean()-Xnumeric180 unique values
0 missing
tBodyAccJerk-mean()-Ynumeric180 unique values
0 missing
tBodyAccJerk-mean()-Znumeric180 unique values
0 missing
tBodyAccJerk-std()-Xnumeric180 unique values
0 missing
tBodyAccJerk-std()-Ynumeric180 unique values
0 missing
tBodyAccJerk-std()-Znumeric180 unique values
0 missing
tBodyGyro-mean()-Xnumeric180 unique values
0 missing
tBodyGyro-mean()-Ynumeric180 unique values
0 missing
tBodyGyro-mean()-Znumeric180 unique values
0 missing
tBodyGyro-std()-Xnumeric180 unique values
0 missing
tBodyGyro-std()-Ynumeric180 unique values
0 missing
tBodyGyro-std()-Znumeric180 unique values
0 missing
tBodyGyroJerk-mean()-Xnumeric180 unique values
0 missing
tBodyGyroJerk-mean()-Ynumeric180 unique values
0 missing
tBodyGyroJerk-mean()-Znumeric180 unique values
0 missing
tBodyGyroJerk-std()-Xnumeric180 unique values
0 missing
tBodyGyroJerk-std()-Ynumeric180 unique values
0 missing
tBodyGyroJerk-std()-Znumeric180 unique values
0 missing
tBodyAccMag-mean()numeric180 unique values
0 missing
tBodyAccMag-std()numeric180 unique values
0 missing
tGravityAccMag-mean()numeric180 unique values
0 missing
tGravityAccMag-std()numeric180 unique values
0 missing
tBodyAccJerkMag-mean()numeric180 unique values
0 missing
tBodyAccJerkMag-std()numeric180 unique values
0 missing
tBodyGyroMag-mean()numeric180 unique values
0 missing
tBodyGyroMag-std()numeric180 unique values
0 missing
tBodyGyroJerkMag-mean()numeric180 unique values
0 missing
tBodyGyroJerkMag-std()numeric180 unique values
0 missing
fBodyAcc-mean()-Xnumeric180 unique values
0 missing
fBodyAcc-mean()-Ynumeric180 unique values
0 missing
fBodyAcc-mean()-Znumeric180 unique values
0 missing
fBodyAcc-std()-Xnumeric180 unique values
0 missing
fBodyAcc-std()-Ynumeric180 unique values
0 missing
fBodyAcc-std()-Znumeric180 unique values
0 missing
fBodyAccJerk-mean()-Xnumeric180 unique values
0 missing
fBodyAccJerk-mean()-Ynumeric180 unique values
0 missing
fBodyAccJerk-mean()-Znumeric180 unique values
0 missing
fBodyAccJerk-std()-Xnumeric180 unique values
0 missing
fBodyAccJerk-std()-Ynumeric180 unique values
0 missing
fBodyAccJerk-std()-Znumeric180 unique values
0 missing
fBodyGyro-mean()-Xnumeric180 unique values
0 missing
fBodyGyro-mean()-Ynumeric180 unique values
0 missing
fBodyGyro-mean()-Znumeric180 unique values
0 missing
fBodyGyro-std()-Xnumeric180 unique values
0 missing
fBodyGyro-std()-Ynumeric180 unique values
0 missing
fBodyGyro-std()-Znumeric180 unique values
0 missing
fBodyAccMag-mean()numeric180 unique values
0 missing
fBodyAccMag-std()numeric180 unique values
0 missing
fBodyBodyAccJerkMag-mean()numeric180 unique values
0 missing
fBodyBodyAccJerkMag-std()numeric180 unique values
0 missing
fBodyBodyGyroMag-mean()numeric180 unique values
0 missing
fBodyBodyGyroMag-std()numeric180 unique values
0 missing
fBodyBodyGyroJerkMag-mean()numeric180 unique values
0 missing
fBodyBodyGyroJerkMag-std()numeric180 unique values
0 missing

62 properties

180
Number of instances (rows) of the dataset.
68
Number of attributes (columns) of the dataset.
6
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
66
Number of numeric attributes.
2
Number of nominal attributes.
6
The maximum number of distinct values among attributes of the nominal type.
-1.83
Minimum skewness among attributes of the numeric type.
2.94
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
4.86
Maximum skewness among attributes of the numeric type.
0.01
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
0.67
Third quartile of skewness among attributes of the numeric type.
0.5
Maximum standard deviation of attributes of the numeric type.
16.67
Percentage of instances belonging to the least frequent class.
-1.24
First quartile of kurtosis among attributes of the numeric type.
0.42
Third quartile of standard deviation of attributes of the numeric type.
Average entropy of the attributes.
30
Number of instances belonging to the least frequent class.
-0.67
First quartile of means among attributes of the numeric type.
0
Standard deviation of the number of distinct values among attributes of the nominal type.
0.96
Mean kurtosis among attributes of the numeric type.
0
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
-0.48
Mean of means among attributes of the numeric type.
0.34
First quartile of skewness among attributes of the numeric type.
0.97
Average class difference between consecutive instances.
Average mutual information between the nominal attributes and the target attribute.
0.26
First quartile of standard deviation of attributes of the numeric type.
2.58
Entropy of the target attribute values.
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
Second quartile (Median) of entropy among attributes.
0.38
Number of attributes divided by the number of instances.
6
Average number of distinct values among the attributes of the nominal type.
-0.79
Second quartile (Median) of kurtosis among attributes of the numeric type.
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
0.49
Mean skewness among attributes of the numeric type.
-0.59
Second quartile (Median) of means among attributes of the numeric type.
16.67
Percentage of instances belonging to the most frequent class.
0.29
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
30
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
0.46
Second quartile (Median) of skewness among attributes of the numeric type.
Maximum entropy among attributes.
-1.6
Minimum kurtosis among attributes of the numeric type.
0
Percentage of binary attributes.
0.34
Second quartile (Median) of standard deviation of attributes of the numeric type.
43.74
Maximum kurtosis among attributes of the numeric type.
-0.96
Minimum of means among attributes of the numeric type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
0.7
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
0
Percentage of missing values.
1.34
Third quartile of kurtosis among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.
6
The minimal number of distinct values among attributes of the nominal type.
97.06
Percentage of numeric attributes.
-0.48
Third quartile of means among attributes of the numeric type.

4 tasks

83 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: Activity
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task