Summary of Freezing Of Gait Detection Using Gramian Angular Fields and Federated Learning From Wearable Sensors, by Shovito Barua Soumma et al.
Freezing of Gait Detection Using Gramian Angular Fields and Federated Learning from Wearable Sensors
by Shovito Barua Soumma, S M Raihanul Alam, Rudmila Rahman, Umme Niraj Mahi, Abdullah Mamun, Sayyed Mostafa Mostafavi, Hassan Ghasemzadeh
First submitted to arxiv on: 18 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 proposed FOGSense system aims to improve the detection of freezing of gait (FOG) in Parkinson’s disease patients. Traditional methods are limited by their reliance on controlled settings and failure to capture temporal and spatial gait patterns. The novel approach uses Gramian Angular Field transformations and federated deep learning to detect FOG in uncontrolled, free-living conditions. Evaluation using the ‘tdcsfog’ dataset shows improved accuracy compared to single-axis accelerometers, reduced failure points compared to multi-sensor systems, and robustness to missing values. The federated architecture enables personalized model adaptation and efficient smartphone synchronization during off-peak hours, making it suitable for long-term monitoring as symptoms evolve. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FOGSense is a new system that helps doctors detect freezing of gait in people with Parkinson’s disease. This symptom makes it hard for people to walk or move properly. The problem with current detection methods is that they don’t work well outside of controlled settings and can’t capture all the patterns of how someone walks. FOGSense uses special math and computer learning techniques to detect freezing of gait in real-life situations. It does a better job than other systems at detecting this symptom, and it can even learn and adapt to individual people’s walking styles over time. |
Keywords
* Artificial intelligence * Deep learning
