Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

가상현실 기반 3차원 공간에 대한 감정분류 딥러닝 모델Emotion Classification DNN Model for Virtual Reality based 3D Space

Other Titles
Emotion Classification DNN Model for Virtual Reality based 3D Space
Authors
명지연전한종
Issue Date
Apr-2020
Publisher
대한건축학회
Keywords
Virtual Reality(VR); Emotion; Electroencephalography(EEG); Fast Fourier Transform(FFT); Deep Learning; 가상현실; 감정; 뇌파; FFT; 딥러닝
Citation
대한건축학회논문집, v.36, no.4, pp 41 - 49
Pages
9
Indexed
SCOPUS
KCI
Journal Title
대한건축학회논문집
Volume
36
Number
4
Start Page
41
End Page
49
URI
https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/145863
DOI
10.5659/JAIK_PD.2020.36.4.41
ISSN
2733-6239
2733-6247
Abstract
본 연구의 목적은 DNN (Deep Neural Networks) 모델을 사용하여 사용자의 감정, 특히 VR (Virtual-Reality) 기반의 3차원 디자인 대안에 대한 뇌파 (EEG) 기반의 감정을 분류하는 것이다. 사용자의 감정을 측정하기 위해 4 가지 유형의 VR 공간이 구축되었으며, 각 자극에 대한 뇌파가 측정되었다. EEG 데이터에 기초한 정량적 평가에 더하여, VR 자극 사이의 차이가 있는지를 정성적으로 확인하기 위한 설문이 수행되었다. 정규화 순위 분석 결과 계획 유형 간에 유의 한 차이가 확인되었다. 따라서 주관적 설문지의 값을 DNN 모델의 라벨링 데이터로, 수집된 EEG 데이터를 모델의 특징 값으로 사용했다.  모델 구축 및 훈련에는 Google Tensor Flow를 사용했다. 결과적으로 개발된 모델의 정확도는 98.9 %로 이전 연구보다 높다. 따라서 본 연구에서 제안한 모델을 활용하여 VR 기반 3차원 설계 대안에 대한 예비사용자의 감정파악이 가능해질 것으로 기대된다.
The purpose of this study was to investigate the use of the Deep Neural Networks(DNN) model to classify user’s emotions, in particular Electroencephalography(EEG) toward Virtual-Reality(VR) based 3D design alternatives. Four different types of VR Space were constructed to measure a user’s emotion and EEG was measured for each stimulus. In addition to the quantitative evaluation based on EEG data, a questionnaire was conducted to qualitatively check whether there is a difference between VR stimuli. As a result, there is a significant difference between plan types according to the normalized ranking method. Therefore, the value of the subjective questionnaire was used as labeling data and collected EEG data was used for a feature value in the DNN model. Google TensorFlow was used to build and train the model. The accuracy of the developed model was 98.9%, which is higher than in previous studies. This indicates that there is a possibility of VR and Fast Fourier Transform(FFT) processing would affect the accuracy of the model, which means that it is possible to classify a user’s emotions toward VR based 3D design alternatives by measuring the EEG with this model.
Files in This Item
Go to Link
Appears in
Collections
서울 공과대학 > 서울 건축학부 > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Jun, Han jong photo

Jun, Han jong
COLLEGE OF ENGINEERING (SCHOOL OF ARCHITECTURE)
Read more

Altmetrics

Total Views & Downloads

BROWSE