Signal Classification Using Deep Learning
Hiromitsu Nishizaki, Koji Makino · 2019
Internet-of-Things (IoT) devices have rapidly become important in understanding conditions in an environment. The sensed data from an IoT (or sensor) device generally form a time sequential signal where the values vary with time. This study describes time sequential signal processing using a recurrent-based neural network and particularly focuses on two sorts of signal classification tasks: a sound classification and a tennis swing motion classification. We will introduce these classification tasks and their evaluation results using recurrent neural networks. The experimental results show that the recurrent neural networks could well classify the signals. Moreover, the bi-directional analysis is critical to achieving high-performance classification.