http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
알츠하이머 진단 및 중증도 예측을 위한 단일화된 딥러닝 아키텍처 연구
전효진(Hyo Jin Jon),정현택(Hyuntaek Jung),김룡빈(Longbin Jin),김은이(Eun Yi Kim) 대한전자공학회 2023 대한전자공학회 학술대회 Vol.2023 No.6
Alzheimers disease is a neurodegenerative disorder characterized by a long-term and progressive decline in cognitive abilities, which can be monitored simply through the MMSE test. In this paper, we propose a Weighted MSE-CE Loss with Bernoulli Penalty to simultaneously perform MMSE score prediction and Alzheimers disease detection. Additionally, by utilizing the VGGish feature which extracts acoustic characteristics on the ADReSSo dataset, we achieve an RMSE of 4.55 and an accuracy of 80.28% for each of the two tasks. This is the highest performance among models using only acoustic features for both tasks.