Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle
碩士 === 國立高雄第一科技大學 === 電機工程研究所碩士班 === 105 === BCI (Brain-computer interface), it is a communication system between the human brain and the detect device that through the electrodes to record weak brain signals is called electroencephalogram (EEG). In our research, the single-point brainwave device is...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/57000549899702526032 |
id |
ndltd-TW-105NKIT0442012 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105NKIT04420122017-08-28T04:24:54Z http://ndltd.ncl.edu.tw/handle/57000549899702526032 Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle 基於卷積神經網路深度學習策略下之腦波載具控制 TSAI,FENG-CHENG 蔡豐丞 碩士 國立高雄第一科技大學 電機工程研究所碩士班 105 BCI (Brain-computer interface), it is a communication system between the human brain and the detect device that through the electrodes to record weak brain signals is called electroencephalogram (EEG). In our research, the single-point brainwave device is used to catch eye-movement signals and the convolution neural network (CNN) is used to classify signals. After CNN recall, it can distinguish the movements from brain wave signals, and the vehicle will move driving by the comments. In other hand, our research design a vehicle based on remote control car. In order to increase reality, the video feedback model is added to send back stream video. About controlling, the speed and direction design the same as accelerate and steering wheel. During the vehicle move, its 6-axis posture will be sent back by posture model to the receiver. Finally, the experimental results prove that our approach is work. Huang,CHIN-I 黃勤鎰 2017 學位論文 ; thesis 102 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立高雄第一科技大學 === 電機工程研究所碩士班 === 105 === BCI (Brain-computer interface), it is a communication system between the human brain and the detect device that through the electrodes to record weak brain signals is called electroencephalogram (EEG). In our research, the single-point brainwave device is used to catch eye-movement signals and the convolution neural network (CNN) is used to classify signals. After CNN recall, it can distinguish the movements from brain wave signals, and the vehicle will move driving by the comments.
In other hand, our research design a vehicle based on remote control car. In order to increase reality, the video feedback model is added to send back stream video. About controlling, the speed and direction design the same as accelerate and steering wheel. During the vehicle move, its 6-axis posture will be sent back by posture model to the receiver.
Finally, the experimental results prove that our approach is work.
|
author2 |
Huang,CHIN-I |
author_facet |
Huang,CHIN-I TSAI,FENG-CHENG 蔡豐丞 |
author |
TSAI,FENG-CHENG 蔡豐丞 |
spellingShingle |
TSAI,FENG-CHENG 蔡豐丞 Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
author_sort |
TSAI,FENG-CHENG |
title |
Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
title_short |
Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
title_full |
Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
title_fullStr |
Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
title_full_unstemmed |
Based on Convolution Neural Network Deep Learning Strategy with Brain Wave Signal for Controlling Vehicle |
title_sort |
based on convolution neural network deep learning strategy with brain wave signal for controlling vehicle |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/57000549899702526032 |
work_keys_str_mv |
AT tsaifengcheng basedonconvolutionneuralnetworkdeeplearningstrategywithbrainwavesignalforcontrollingvehicle AT càifēngchéng basedonconvolutionneuralnetworkdeeplearningstrategywithbrainwavesignalforcontrollingvehicle AT tsaifengcheng jīyújuǎnjīshénjīngwǎnglùshēndùxuéxícèlüèxiàzhīnǎobōzàijùkòngzhì AT càifēngchéng jīyújuǎnjīshénjīngwǎnglùshēndùxuéxícèlüèxiàzhīnǎobōzàijùkòngzhì |
_version_ |
1718520251430207488 |