Recently, modern people are experiencing various types of trauma and have difficulty in controlling their emotions and stabilizing. It is essential to visit a hospital to diagnose trauma but lots of people often miss diagnosis and treatment because of being unaware of it. In this paper, we propose a method for screening trauma based on audio data using convolutional neural networks. Among the six basic emotions, four emotions were used for screening trauma: fear, sad, neutral, and happy. It was assumed that when fear and sad emotions appeared in the audio, the probability of trauma was high and when neutral and happy emotions appeared, the probability was low. To extract the features from audio, the audio was converted into spectrogram images through pre-processing and used to train convolutional neural networks. As a result, VGG-13 model showed the highest performance(98.96%) for screening trauma among others.
한국어
최근 현대인들은 다양한 원인으로 인해 트라우마 증상을 겪고 있다. 트라우마를 겪으면 감정 조절에 문 제가 생기며 불안해하고 안정감을 찾기 어려워한다. 이런 트라우마를 진단하기 위해서 병원을 방문하는 것이 필수 적이지만 사회적 편견과 자신이 가지고 있는 트라우마에 대해 인지하지 못해 진단 및 치료를 놓치는 경우가 많다. 이를 위해 본 논문에서는 합성곱 신경망 모델을 통해 음성을 기반으로 트라우마를 초기 진단하는 방법을 연구하 였다. 기본 감정 6가지 중 fear, sad, neutral, happy 4가지 감정을 트라우마 초기 진단에 활용하였다. 음성에서 fear 와 sad 감정이 나타나면 트라우마일 확률이 높고, neutral과 happy 감정이 나타나면 트라우마가 아닐 확률이 높 다고 가정하였다. 음성의 특징을 추출하기 위해 전처리 과정을 거쳐 푸리에변환 한 spectrogram 이미지로 만들고 학습하였다. 그 결과, VGG-13 모델에서 98.96%로 높은 정확도를 나타내 트라우마 진단에 좋은 결과를 얻을 수 있었다.
목차
요약 Abstract Ⅰ. 서론 Ⅱ. 본론 2.1 트라우마 감정 정의 2.2 데이터 2.3 알고리즘 Ⅲ. 실험 결과 3.1 모델 학습 Ⅳ. 결론 REFERENCES
Ever since next generation convergence technology became one of the most important industries in the nation, computing professionals have encountered a growing number of challenges. Along with scholars and colleagues in related fields, they have gathered in avariety of forums and meetings over the last few decades to share their knowledge, experiences and the outcome of their research. These exchanges have led to the founding of the International Next-generation Convergence technology (INCA) on December 1, 2015. INCA was registered as an incorporated association under the Ministry of Information and Communications. The main purpose of the organization is to improve our society by achieving the highest capability possible in next generation convergence technology.
간행물
간행물명
차세대융합기술학회논문지 [The Journal of Next-generation Convergence Technology Association]