hars: Data on human activity recognition using smartphones

In diversityForest: Innovative Complex Split Procedures in Random Forests Through Candidate Split Sampling

Data on human activity recognition using smartphones

Description

This data set contains sensor data from 30 volunteers aged 19-48 years, performing six activities while wearing Samsung Galaxy S II smartphones on their waists. The sensors recorded 3-axial linear acceleration and angular velocity at 50Hz. The experiments were video-recorded to label the data manually. The outcome Activity is categorical with six classes that differentiate the six activities.
This is an updated version of the Human Activity Recognition Using Smartphones data set published in the UC Irvine Machine Learning Repository. This updated version published on OpenML includes both raw sensor signals and updated activity labels, with aggregated measurements for each individual and activity.

Format

A data frame with 180 observations (activities), 66 covariates and one 6-class outcome variable

Details

The classes of the outcome Activity are as follows: LAYING, SITTING, STANDING, WALKING, WALKING_DOWNSTAIRS, WALKING_UPSTAIRS.
The OpenML data set contained one additional variable Person that was removed because it has too many factors to use it as a covariate in prediction.

Source

• Updated version: OpenML: data.name: Smartphone-Based_Recognition_of_Human_Activities, data.id: 4153, link: https://www.openml.org/d/4153/ (Accessed: 29/08/2024)

• Original version: UC Irvine Machine Learning Repository, link: https://archive.ics.uci.edu/dataset/240/human+activity+recognition+using+smartphones/ (Accessed: 29/08/2024)

References

• Reyes-Ortiz, J.-L., Oneto, L., Samà, A., Parra, X., Anguita, D. (2016). Transition-aware human activity recognition using smartphones. Neurocomputing, 171:754-767, <\Sexpr[results=rd]{tools:::Rd_expr_doi("10.1016/j.neucom.2015.07.085")}>.

• Vanschoren, J., van Rijn, J. N., Bischl, B., Torgo, L. (2013). OpenML: networked science in machine learning. SIGKDD Explorations 15(2):49-60, <\Sexpr[results=rd]{tools:::Rd_expr_doi("10.1145/2641190.2641198")}>.

• Dua, D., Graff, C. (2019). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science. https://archive.ics.uci.edu/ml/.

Examples

# Load data:
data(hars)

# Numbers of observations per outcome class:
table(hars$Activity)

# Dimension of data:
dim(hars)

# First rows of (subset) data:
head(hars[,1:5])

diversityForest documentation built on June 8, 2025, 1:23 p.m.