Abstract-The main aim of this system is to predict and analyze gesture pattern from a user based on machine learning. The system is adopted in the rock-paper-scissors game which is suggested as always win at the game by predicting user gesture. Quantization and processing of user gesture from EMG sensor are implemented to generate training data in order that disciplining machine. As suggested procedure, an enormous amount of user gesture data will be collected and training model will be implemented with machine learning. By adopting the implemented system into the game, the research will verify that it is feasible to predict user gesture during playing game. The manner of a game is that computer shows the result when the user starts the rock-paper-scissors game in front of the monitor and the system always shows winning result that is the main purpose of it.

Abstract-In this paper, we propose a method to improve the recognition rate of gestures motion and scalability problem which can occur in gestures when operate drone using machine learning. For these purposes, the gestures data transmitted from the drone controller are used for machine learning on real time, and a new learning model is periodically created using the gestures data stored in the HDFS(Hadoop Distributed File System). The goal of our proposed system is to increase the recognition rate of the gestures motion when new learning model is created. In addition, it is possible to expect enhanced scalability through recognition of gestures motion, and that drone is able to recognize a new gestures motion which is not defined in the server.

Currently, vehicle related studies are activated due to the increase of vehicle. Thus, the technology using computer vision is being studied to identify the vehicle's information. It enables automatically identify the vehicle number. The image processing rate, however, is limited to the speed of data processing, and its inefficiency of processing is increase gradually. Therefore, in this paper we propose a method to enhance the efficiency of the processing using HDFS and distributed processing system.

Recently, a variety of businesses have appeared not only in the drone's military market but also in the consumer market and the service market. The reason for the rapid growth of the market is that it is possible to produce cheap drones using open source. Although there are lots of system for controlling drones, people still experience accidents due to inexperienced user who purchased drones. These accidents occur from the difference between the viewpoint of the user and the drones. Therefore, in this paper, we propose a User Centric Drone Controller (UCDC) to reduce accidents caused by clumsy manipulation.