Paper Info
Title
Multiple model recognition for near-realistic exergaming
Abstract
Exergaming as a tool to combat obesity yields an interesting take on the problem of design and implementation of activity recognition systems for truly mobile games that achieve moderate levels of intensity. This work presents SoccAR, a mobile, sensor-based wearable exergaming system with fine-grain activity recognition. The system in this paper presents a recognition algorithm for the appropriate classification of 26 movements by extracting a large number of features and selecting the most important, as well as developing a multiple model strategy to better classify movements. This movement strategy allows for a trade off of detailed classification versus classification speed. A metric to define the accuracy in terms of the importance of particular movements is defined. The scheme presented develops a framework for more accurately classifying movements with a smaller number of features for a large, multiclass real-time environment. This results in a more accurate classification of movements, with an F-score in cross-validation of .937 using a PUK-kernel based SVM and multiple models, to .755 using only a single RBF-based model and 20 features.
Year
DOI
Venue
2015
10.1109/PERCOM.2015.7146520
2015 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Keywords
Field
DocType
multiple model recognition,near-realistic exergaming,activity recognition system,mobile games,SoccAR,sensor-based wearable exergaming system,fine-grain activity recognition,PUK-kernel based SVM,single RBF-based model
Activity recognition,Wearable computer,Computer science,Support vector machine,Artificial intelligence,Recognition algorithm,Machine learning,Multiple Models
Conference
ISSN
Citations 
PageRank 
2474-2503
2
0.39
References 
Authors
23
6
Name
Order
Citations
PageRank
Bobak Mortazavi1458.38
Mohammad Pourhomayoun28715.23
Suneil Nyamathi3152.29
Brandon Wu440.78
Sunghoon Ivan Lee56516.80
Majid Sarrafzadeh63103317.63