Advertisement
Published in:
2018 | OriginalPaper | Chapter
Classification Method of Rubbing Haptic Information Using Convolutional Neural Network
Authors : Shotaro Agatsuma, Shinji Nakagawa, Tomoyoshi Ono, Satoshi Saga, Simona Vasilache, Shin Takahashi
Published in: Human Interface and the Management of Information. Interaction, Visualization, and Analytics
Publisher: Springer International Publishing
Abstract
In previous research, we proposed a method to collect accelerations in daily haptic behaviors using a ZigBee-based microcomputer. However, the method for classifying the collected data was not sufficiently implemented. We therefore propose applying collected data to classify rubbing haptic information. In this paper, we implemented a classification approach for haptic information collected by our method. We used a convolutional neural network (CNN) to classify the information. We performed a classification experiment in which the CNN classified 18 types of information, 93.2% on average. We also performed an experiment to classify rubbed objects in real-time. The CNN was able to classify five types of objects, about 67.7% on average.