english | português | español

Groupware@LES ilustração, seta para a direita Projects ilustração, seta para a direita Human Activity Recognition

Human Activity Recognition

Human Activity Recognition - HAR - has emerged as a key research area in the last years and is gaining increasing attention by the pervasive computing research community (see picture below, that illustrates the increasing number of publications in HAR with wearable accelerometers), especially for the development of context-aware systems. There are many potential applications for HAR, like: elderly monitoring, life log systems for monitoring energy expenditure and for supporting weight-loss programs, and digital assistants for weight lifting exercises.

HAR: IEEE publications (2006-2011) based on wearable accelerometers' data
HAR: IEEE publications (2006-2011) based on wearable accelerometers' data



Systematic-like approach for reviewing literature

In order to enable you to replicate the literature review we made for this research, all publications assessed in this paper are available here, in RIS format. In this research, the bibliographic management and publishing solution used was the EndNote X5(tm). The library in EndNote format is also available for download.




HAR Dataset for benchmarking

We propose a dataset with 5 classes (sitting-down, standing-up, standing, walking, and sitting) collected on 8 hours of activities of 4 healthy subjects. We also established a baseline performance index. You can download the dataset here (please, drop us a line (wugulino inf puc-rio br) about your research and how we can contribute to your benchmarking).



This dataset is licensed under the Creative Commons (CC BY-SA)


Important: you are free to use this dataset for any purpose. This dataset is licensed under the Creative Commons license (CC BY-SA). The CC BY-SA license means you can remix, tweak, and build upon this work even for commercial purposes, as long as you credit the authors of the original work and you license your new creations under the identical terms we are licensing to you. This license is often compared to "copyleft" free and open source software licenses. All new works based on this dataset will carry the same license, so any derivatives will also allow commercial use.


Detailed Accuracy
Correctly Classified Instances 164662 99.4144 %
Incorrectly Classified Instances 970 0.5856 %
Root mean squared error 0.0463
Relative absolute error 0.7938 %
Relative absolute error 0.7938 %

Detailed Accuracy by Class
TP Rate FP Rate Precision Recall F-Measure ROC Area Class
0.999 0 1 0.999 0.999 1 Sitting
0.971 0.002 0.969 0.971 0.970 0.999 Sitting down
0.999 0.001 0.998 0.999 0.999 1 Standing
0.962 0.003 0.969 0.962 0.965 0.999 Standing up
0.998 0.001 0.998 0.998 0.998 1 Walking
0.994 0.001 0.994 0.994 0.994 1 Weighted Avg.



Please, cite this publication to refer this dataset and literature review


Ugulino, W.; Cardador, D.; Vega, K.; Velloso, E.; Milidiu, R.; Fuks, H. Wearable Computing: Accelerometers' Data Classification of Body Postures and Movements. Proceedings of 21st Brazilian Symposium on Artificial Intelligence. Advances in Artificial Intelligence - SBIA 2012. In: Lecture Notes in Computer Science. , pp. 52-61. Curitiba, PR: Springer Berlin / Heidelberg, 2012. ISBN 978-3-642-34458-9. DOI: 10.1007/978-3-642-34459-6_6.
Cited by 2 (Google Scholar)

DocumentoDocumento ApresentaçãoApresentação




Other HAR Related Publications


Weight Lifting Exercises Dataset



On-body sensing schema




This human activity recognition research has traditionally focused on discriminating between different activities, i.e. to predict "which" activity was performed at a specific point in time (like with the Daily Living Activities dataset above). The approach we propose for the Weight Lifting Exercises dataset is to investigate "how (well)" an activity was performed by the wearer. The "how (well)" investigation has only received little attention so far, even though it potentially provides useful information for a large variety of applications,such as sports training.

In this work (see the paper) we first define quality of execution and investigate three aspects that pertain to qualitative activity recognition: the problem of specifying correct execution, the automatic and robust detection of execution mistakes, and how to provide feedback on the quality of execution to the user. We tried out an on-body sensing approach (dataset here), but also an "ambient sensing approach" (by using Microsoft Kinect - dataset still unavailable)

Six young health participants were asked to perform one set of 10 repetitions of the Unilateral Dumbbell Biceps Curl in five different fashions: exactly according to the specification (Class A), throwing the elbows to the front (Class B), lifting the dumbbell only halfway (Class C), lowering the dumbbell only halfway (Class D) and throwing the hips to the front (Class E).

Class A corresponds to the specified execution of the exercise, while the other 4 classes correspond to common mistakes. Participants were supervised by an experienced weight lifter to make sure the execution complied to the manner they were supposed to simulate. The exercises were performed by six male participants aged between 20-28 years, with little weight lifting experience. We made sure that all participants could easily simulate the mistakes in a safe and controlled manner by using a relatively light dumbbell (1.25kg).

Download the WLE dataset here



This dataset is licensed under the Creative Commons (CC BY-SA)


Important: you are free to use this dataset for any purpose. This dataset is licensed under the Creative Commons license (CC BY-SA). The CC BY-SA license means you can remix, tweak, and build upon this work even for commercial purposes, as long as you credit the authors of the original work and you license your new creations under the identical terms we are licensing to you. This license is often compared to "copyleft" free and open source software licenses. All new works based on this dataset will carry the same license, so any derivatives will also allow commercial use.


Please, cite this paper to refer the WLE dataset


Velloso, E.; Bulling, A.; Gellersen, H.; Ugulino, W.; Fuks, H. Qualitative Activity Recognition of Weight Lifting Exercises. Proceedings of 4th International Conference in Cooperation with SIGCHI (Augmented Human '13) . Stuttgart, Germany: ACM SIGCHI, 2013.

DocumentoDocumento


Collaborators:


- Wallace Ugulino (wugulino inf puc-rio br)
- Eduardo Velloso
- Hugo Fuks