Supervised Contrastive Learning Framework and Hardware Implementation of Learned ResNet for Real-time Respiratory Sound Classification

Jinhai Hu, Cong Sheng Leow, Shuailin Tao, Wang Ling Goh, Yuan Gao

IEEE Transactions on Biomedical Circuits and Systems (TBioCAS), 2024

Representation Learning · Model Implementation

Overview

A supervised contrastive learning framework that combines augmentation and model optimization for classification with scarce and imbalanced data. The study also examines the trade-off between inference efficiency and classification quality in a hardware implementation.