![]() ![]() The maximum accuracy was obtained, as expected, with Random Forest using all the 159 features. The features were extracted using the java programming language and the evaluation was done with WEKA. In the evaluation process we used the classi ers: Naive Bayes, K-Nearest Neighbor and Random Forest. We extracted features from the Magnitude of the Signal, the raw signal data, the vertical acceleration, the Horizontal acceleration, and the ltered Raw data. We have researched on a vector with 159 diferent features and on the vector subsets in order to improve the human activities recognition. Human activity recognition and monitoring involves a continuing analysis of large amounts of data so, any increase or decrease in accuracy results in a wide variation in the number of activities correctly classi ed and incorrectly classi ed, so it is very important to increase the rate of correct classication. The advances of this kind of technology are making possible the widespread and pervasiveness of sensing technology to take advantage of multiple sources of sensing to enrich users experience or to achieve proactive, context-aware applications and services. The recognition of human activities through sensors embedded in smart-phone devices, such as iPhone, is attracting researchers due to its relevance.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |