In the area of recognition and classification of children activities, numerous works have been proposed that make use of different\ndata sources. In most of them, sensors embedded in childrenâ??s garments are used. In this work, the use of environmental sound\ndata is proposed to generate a recognition and classification of children activities model through automatic learning techniques,\noptimized for application on mobile devices. Initially, the use of a genetic algorithm for a feature selection is presented, reducing\nthe original size of the dataset used, an important aspect when working with the limited resources of a mobile device. For the\nevaluation of this process, five different classification methods are applied, k-nearest neighbor (k-NN), nearest centroid (NC),\nartificial neural networks (ANNs), random forest (RF), and recursive partitioning trees (Rpart). Finally, a comparison of the\nmodels obtained, based on the accuracy, is performed, in order to identify the classification method that presents the best\nperformance in the development of a model that allows the identification of children activity based on audio signals. According to\nthe results, the best performance is presented by the five-feature model developed through RF, obtaining an accuracy of 0.92,\nwhich allows to conclude that it is possible to automatically classify children activity based on a reduced set of features with\nsignificant accuracy.
Loading....