黄东敏（2022级硕士生，王文锦课题组）

题目：Machine Learning-based Acoustic Analysis of Infants and Young Children

报告摘要：

       Community-Acquired Pneumonia (CAP) is a significant cause of child mortality globally, due to the lack of ubiquitous monitoring methods. Clinically, the wireless stethoscope can be a promising solution as lung sounds with crackles and tachypnea are considered as the typical symptoms. Therefore, we carried out a multi-center clinical trial in four China hospitals to investigate the feasibility of using a wireless stethoscope for children CAP diagnosis and prognosis. To process the lung sounds, two machine learning-based methods are proposed by us to deal with two major challenges: (1) Comprehensive assessment; (2) Differences between children. For the former, the strategy of fusing the left and right lung sound features is adopted to provide a more comprehensive assessment of lung condition. For the latter, an adversarial training approach is proposed to mine the subject-independent but task-dependent representation to eliminate differences between individuals. The experimental results show the feasibility and effectiveness of wireless stethoscope in CAP, and point out the direction of improvement.

报告时间：5月23日，18:20-18:40

张立远（2022级硕士生，罗智课题组）