大規模行動認識のための並列分散処理に向けて(Distributed Parallel Processing for Large-scale Activity Recognition)
Hirotaka Hokazono, Yuichi Hattori, Sozo Inoue,
Recently, smartphones equipped with sensors, such as gyroscopes and accelerometers are widely spread. Accordingly, the sensor has made it easy to obtain data on human behavior. In order to recognize actions a number of training data are required, and therefore machine learning for recognition of the actions requires a lot of time. In this paper, we discuss how to locate data for distributed parallel processing for large-scale activity recognition.