초기설계 단계 사용자의 감정 인식을 위한 뇌파기반 딥러닝 분류모델

Abstract

본 논문의 목적은 건축 설계안에 대한 예비 사용자의 감성 반응을 파악할 수 있는 뇌파 기반 딥러닝 분류모델을 제안하는 것에 있다. 이에 본 논문에서는 Tensorflow를 사용하여 딥러닝 분류모델을 구축하였으며 실험을 통해 데이터를 생성하여 지도학습 방법으로 모델을 훈련하였다. 실험은 뇌파측정과 PANAS 설문지 작성으로 구성되었다. 그 후 머신러닝 모델과 딥러닝 모델의 정확도를 비교하였다. 제안된 모델은 향후 건축 계획 및 초기설계단계에서 의사결정참여자들의 설계안에 대한 감정을 파악하는데 활용될 수 있을 것으로 보인다. The purpose of this paper was to propose a model that recognizes potential users’ emotional response toward design by classifyingElectroencephalography(EEG). Studies in neuroscience and psychology have made an effort to recognize subjects’ emotional response byanalyzing EEG data. And this approach has been adopted in design since it is critical to monitor users’ subjective response in the preface ofdesign. Moreover, the building design process cannot be reversed after construction, recognizing clients’ affection toward design alternativesplays important role. An experiment was conducted to record subjects’ EEG data while they view their most/least liked images ofsmall-house designs selected by them among the eight given images. After the recording, a subjective questionnaire, PANAS, was distributedto the subjects in order to describe their own affection score in quantitative way. Google TensorFlow was used to build and train the model.Dataset for model training and testing consist of feature columns for recorded EEG data and labels for the questionnaire results. Aftertraining and testing, the measured accuracy of the model was 0.975 which was higher than the other machine learning based classificationmethods. The proposed model may suggest one quantitative way of evaluating design alternatives. In addition, this method may supportdesigner while designing the facilities for people like disabled or children who are not able to express their own feelings toward alternatives.