Development of automatic cough monitoring, measurement and service system

2022 Fiscal Year Research-status Report

• Project/Area Number: 20K12080
• Research Institution: The University of Aizu
• Principal Investigator: MARKOV K 会津大学, コンピュータ理工学部, 教授 (80394998)
• Co-Investigator(Kenkyū-buntansha): 松井 知子 統計数理研究所, モデリング研究系, 教授 (10370090) ; 齋藤 純平 福島県立医科大学, 医学部, 講師 (50332929)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: cough recognition / cough monitoring / DNN audio analysis

Outline of Annual Research Achievements

During this year we built a high performance cough detection and monitoring system and successfully evaluated it using the data collected at FMU. There are 11 patients audio recordings in the dataset with highly irregular cough events time distribution. Out approach is to segment the input data into 10sec long segments and process each segment separately. Out model is based on fine tuned large audio model called HuBERT which can identify cough frames with high accuracy. In addition, we trained a special network which estimates the probability of each identified cough frame being the first, second, etc, in the couch event. This way, we can distinguish separate cough events even when they come right one after another within a long sequence of cough frames.

Current Status of Research Progress

3: Progress in research has been slightly delayed.

Reason

Currently, we are conducting experiments involving other openly available methods and models for cough event detection and monitoring in order to compare the performance of our system and the other state-of-the-art systems. To achieve statistically significant experimental results, we are performing a 4-fold cross validation experiments and so far our system has obtained more than 90% F1 score.

Strategy for Future Research Activity

After finishing the experiments, we plan to summarize the achievements of this project and publish them in a journal paper.

Causes of Carryover

The amount for the next fiscal year will be used for publication fees.