Next-gen Wireless Communication and Mobile Computing

In recent years, in addition to traditional in-vehicle systems such as car navigation, ETC, and GPS, various sensors—including LiDAR, millimeter-wave radar, and cameras—have been integrated into vehicles to enhance safe and secure driving by detecting pedestrians and objects around the vehicle. As a result, handling vast amounts of data from these sensors has become essential. In-vehicle networks used for transmitting this data must meet various communication quality requirements, including latency, bandwidth, and priority. Our research group is actively working on optimizing in-vehicle networks to address these challenges.

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). 

Wireless communication technologies such as LTE/4G, 5G, and Wi-Fi are essential for mobile computing and pervasive systems. Our research lab is dedicated to improving the performance of these wireless networks.

We are conducting research on position estimation of people and objects using wireless signals such as Wi-Fi, BLE, and RFID.