Summary of Sleepfm: Multi-modal Representation Learning For Sleep Across Brain Activity, Ecg and Respiratory Signals, by Rahul Thapa et al.
SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
by Rahul Thapa, Bryan He, Magnus Ruud Kjaer, Hyatt Moore, Gauri Ganjoo, Emmanuel Mignot, James Zou
First submitted to arxiv on: 28 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces SleepFM, a multi-modal foundation model for sleep analysis. It curates a large polysomnography dataset from over 14,000 participants and uses it to develop the novel approach. The authors show that their method outperforms standard pairwise contrastive learning on downstream tasks such as sleep stage classification and sleep disordered breathing detection. Additionally, they demonstrate the effectiveness of the learned embeddings in retrieving corresponding recording clips across modalities. This work highlights the value of holistic multi-modal sleep modeling for capturing the richness of sleep recordings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a huge database of people’s sleep patterns by using special machines to record their brain, heart, and breathing activities while they sleep. It then uses this data to create a new way of analyzing sleep patterns, called SleepFM. The researchers show that this new approach is better than the old way at identifying different stages of sleep and detecting problems like sleep apnea. They also demonstrate that the new approach can be used to find matching recordings from other machines. This work shows how important it is to study sleep in a more complete and detailed way. |
Keywords
» Artificial intelligence » Classification » Multi modal
