<![CDATA[Human activity recognition is one of the popular topics on both academic and commercial researchers. Some researchers have tried to classify human activity recognition but the result is unsatisfactory. Moreover, there is another problem with high dimensional human activity recognition dataset. The high dimensional of data set takes a longer computational time and makes the classification model be overfitting. One method that can be used to solve those problems is the classification using the Decision Tree C4.5 algorithm and Information Gain as selection feature method. Decision Tree C4.5 algorithm is a suitable method for continuous dataset and Information Gain is one of the filter methods in feature selection that can work well on high-dimensional dataset. This research also conducted various tests on some parameters such as the optimal number of features and the maximum depth tree that be used. Based on the test that has been done obtained the accuracy of 81% with 90% of the total number of all features (561 features) and 10 for the maximum depth for the tree.]]>
Copyrights © 2019
