Gamification for High-quality Dataset in Mobile Activity Recognition

Nattaya Mairittha, Sozo Inoue,
EAI International Conference on Mobile Computing, Applications and Services (MobiCASE) poster
(Not Available)
(Not Available)
216-222
2018-03-01
Osaka
http://mobicase.org/2018/show/home
This paper presents a gamification concept for getting high- quality user-annotated datasets in the context of mobile activity recogni- tion. The‘novel’idea behind this concept is that users are motivated by getting feedback about the quality of their labeling activity as rewards or gamification element. For that, the collected sensor data and labels are used as training data for a machine learning algorithm for determining the dataset quality based on the resulting accuracy. By using the pro- posed method, the results show that the gamification elements increase the quantity (the proposed method is greater than the naive by at least 305) and‘ quality ’(the accuracy of the proposed data outperformed the original data by at least 4.3%) of the labels. Besides, the cheating de- tection algorithm could detect cheating with the accuracy of more than 70% that is fascinating work.

Data Files