| Autor: |
Iris A.M. Huijben, Arthur A. Nijdam, Lieke W.A. Hermans, Sebastiaan Overeem, Merel M. Van Gilst, Ruud J.G. Van Sloun |
| Přispěvatelé: |
Eindhoven MedTech Innovation Center, Biomedical Diagnostics Lab, Signal Processing Systems, Electrical Engineering, Biomedical Engineering, EAISI Health |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2022, 2945-2948 |
| Popis: |
Nowadays, high amounts of data can be acquired in various applications, spurring the need for interpretable data representations that provide actionable insights. Algorithms that yield such representations ideally require as little a priori knowledge about the data or corresponding annotations as possible. To this end, we here investigate the use of Kohonen's Self-Organizing Map (SOM) in combination with data-driven low-dimensional embeddings obtained through self-supervised Contrastive Predictive Coding. We compare our approach to embeddings found with an auto-encoder and, moreover, investigate three ways to deal with node selection during SOM optimization. As a challenging experiment we analyze nocturnal sleep recordings of healthy subjects, and conclude that - for this noisy real-life data - contrastive learning yields a better low-dimensional embedding for the purpose of SOM training, compared to an auto-encoder. In addition, we show that a stochastic temperature-annealed SOM-training outperforms both a deterministic and a non-temperature-annealed stochastic approach. Clinical relevance - The hypnogram has for decades been the clinical standard in sleep medicine despite the fact that it is a highly simplified representation of a polysomnography recording. We propose a sensor-agnostic algorithm that is able to reveal more intricate patterns in sleep recordings which might teach us about sleep structure and sleep disorders. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
