No abstract

No abstract

No abstract

The Convolutional Neural Network(CNN) can be divided into two stages: feature extraction and classification. The hyperparameters such as kernel size, number of channels, and stride in the feature extraction step affect the overall performance of CNN as well as determining the structure of CNN. In this paper, we propose a method to optimize the hyperparameter in CNN feature extraction stage using Parameter-Setting-Free Harmony Search (PSF-HS) algorithm. After setting the overall structure of CNN, hyperparameter was set as a variable and the hyperparameter was optimized by applying PSF-HS algorithm. The simulation was conducted using MATLAB, and CNN learned and tested using mnist data. We update the parameters for a total of 500 times, and it is confirmed that the structure with the highest accuracy among the CNN structures obtained by the proposed method classifies the mnist data with an accuracy of 99.28%.

Internet of things which helps communication between human and thing and between things by connecting networks on them is developing. Develops of Internet of things, network technique, and smart machine result interest on home network system. In this paper, we suggested a system with the home network to the dormitory using pressure sensors, infrared sensor, ultrasonic sensor, switch, arduino, raspberrypi, android application. Smart dormitory system based on the internet of things provide information whether public things in dormitory like laundry machine, computer, treadmill is being used now, and package is arrived through android application.

No abstract

No abstract

In this paper, the autonomous mobile robot control system for detecting fire was proposed using the wearable device based on EMG(Electromyogram) signal. Myo armband is used for detecting the user's EMG signal. The gesture was classified after sending the data of EMG signal to a computer using Bluetooth communication. Then the robot named 'uBrain' was implemented to move by received data from Bluetooth communication in our experiment. 'Move front', 'Turn right', 'Turn left', and 'Stop' are controllable commands for the robot. And if the robot cannot receive the Bluetooth signal from a user or if a user wants to change manual mode to autonomous mode, the robot was implemented to be in the autonomous mode. The robot flashes the LED when IR sensor detects the fire during moving.