Blog posts

2025

Wearable EDA Quality Model improves SOTA

less than 1 minute read

Published:

Electrodermal activity (EDA) is a key indicator of sympathetic nervous system activation and a reliable marker of emotional arousal or stress. However, motion artifacts and connectivity issues often degrade EDA signal quality. To enable meaningful interpretation, it is essential to distinguish between high- and low-quality EDA signals. We propose an EDA signal quality index system leveraging unsupervised pre-training—a strategy widely used in natural language processing models such as GPT. Our approach achieve approximately $8\%$ in ROCAUC improvement compared to SOTA, while requiring only half the training epochs. This demonstrates that even with limited labeled data and a lightweight model, pre-training can significantly enhance EDA quality assessment, making it practical for real-time, wearable health applications.

2024

Multi-task learning and Multi-Modal learning

2 minute read

Published:

Multi-task Learning solves multiple tasks at one time, while exploiting commonalities and differences across tasks. Multi-modal Learning integrates and processes multiple types of data in one framework.

2023

2022

Predict unit-level LoS using time-series modelling

3 minute read

Published:

We propose to a dynamic, real-time, lightweight, end-to-end next day median ED-LoS prediction algorithm using time-series LSTM modelling. Similar method can be extended to unit-level KPI prediction.

Challenges in data labels

less than 1 minute read

Published:

I here list some different challenges in data labels that I encountered in the past and ways to model them.

2021

2020