Next-gen Wireless Communication and Mobile Computing
We are pursuing location estimation using the electromagnetic properties of wireless communication, and methods for building distributed machine learning systems.
Edge Computing・Distributed Systems
In recent years, due to the trend of aggregating data processing in the cloud, some IoT tools, such as Microsoft and Google TensorFlow, are supporting edge computing functions that can introduce decision functions trained by machine learning, etc., to IoT devices. However, most of these existing tools and approaches aim to reduce the amount of data to be sent to the cloud by transferring some or all of the learned decision functions from the cloud to edge devices. In the learning phase, it is still necessary to aggregate all the data to a cloud server or a home gateway with learning functions. In this research, we propose a new method for deep learning and data processing in WSN (Wireless Sensor Network).
LTE/4G, 5G, Wi-Fi