Implementation of Lamp Control System by Reccurent Neural Network and Long-Short Term Memory

Abstract

Smart lamp is a technology that offers convenience for users in controlling the lamp. Previously, there had been research developing this system, but the controls offered were still based on Android that can’t support a multiple platform. This system uses the Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) algorithms. Besides that, this system also does a trial by using Internet of Things System for controlling and monitoring the lamps.From this research, the results of testing show that the average time required for the system to turn on and turn off Lamp I are 3.3 seconds and 3.28 seconds respectively with a minimum sound intensity of 60.6 dB. To turn on and turn off Lamp II in succession is 3.43 second and 3.61 second with a minimum sound intensity of 60.8 dB. Meanwhile, to turn on and turn off Lamp III in a row is 3.32 seconds and 3.39 seconds with a sound intensity of at least 61.32 dB. The three lamps can be controlled with the furthest distance is 1.2 meters.