Summary of Multimodal Physical Activity Forecasting in Free-living Clinical Settings: Hunting Opportunities For Just-in-time Interventions, by Abdullah Mamun et al.
Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions
by Abdullah Mamun, Krista S. Leonard, Megan E. Petrov, Matthew P. Buman, Hassan Ghasemzadeh
First submitted to arxiv on: 12 Oct 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 A machine learning system called MoveSense is developed to forecast patients’ activity behavior, enabling early and personalized interventions in real-world clinical settings. The researchers conduct two clinical studies involving prediabetic veterans and patients with obstructive sleep apnea to gather multimodal behavioral data using wearable devices. They develop long short-term memory (LSTM) network models that forecast the number of step counts up to 24 hours in advance, examining activity and engagement modalities. Additionally, goal-based forecasting models predict whether a person’s next-day steps will be over a certain threshold. The results show that multimodal LSTM with early fusion outperforms linear regression and ARIMA on both datasets, achieving lower mean absolute errors and higher accuracy for goal-based forecasting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MoveSense is a new system that helps doctors predict how active patients will be in the future. It uses data from special devices that track people’s movements and behavior. The researchers tested MoveSense with two groups of patients: those at risk of developing diabetes, and those who have sleep apnea. They found that MoveSense was much better at predicting activity levels than other methods. This could help doctors design personalized plans to get patients more active and healthy. |
Keywords
» Artificial intelligence » Linear regression » Lstm » Machine learning
