Detection of Meals and Physical Activity Events From Free-Living Data of People With Diabetes.
Mohammad Reza AskariMudassir RashidXiaoyu SunMert SevilAndrew ShahidehpourKeigo KawajiAli CinarPublished in: Journal of diabetes science and technology (2022)
The meal and exercise times detected by the RNN models can be used to warn people for entering meal and exercise information to hybrid closed-loop automated insulin delivery systems. Reliable accuracy for event detection necessitates powerful ML and large data sets. The use of additional sensors and algorithms for detecting these events and their characteristics provides a more accurate alternative.
Keyphrases
- physical activity
- type diabetes
- machine learning
- high intensity
- electronic health record
- loop mediated isothermal amplification
- deep learning
- big data
- glycemic control
- label free
- real time pcr
- cardiovascular disease
- resistance training
- body mass index
- high resolution
- healthcare
- high throughput
- metabolic syndrome
- artificial intelligence
- adipose tissue
- sleep quality
- social media
- insulin resistance
- low cost
- skeletal muscle