Summary of Self-supervised Learning and Opportunistic Inference For Continuous Monitoring Of Freezing Of Gait in Parkinson’s Disease, by Shovito Barua Soumma et al.
Self-Supervised Learning and Opportunistic Inference for Continuous Monitoring of Freezing of Gait in Parkinson’s Disease
by Shovito Barua Soumma, Kartik Mangipudi, Daniel Peterson, Shyamal Mehta, Hassan Ghasemzadeh
First submitted to arxiv on: 27 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 This paper presents LIFT-PD, a self-supervised learning framework for real-time detection of Freezing of Gait (FoG) symptoms in Parkinson’s disease patients. The method combines pre-training on unlabeled data with a novel differential hopping windowing technique to learn from limited labeled instances. A model activation module minimizes power consumption by selectively activating the deep learning module only during active periods. Compared to supervised models, LIFT-PD achieves a 7.25% increase in precision and 4.4% improvement in accuracy using as low as 40% of the labeled training data. The model activation module also reduces inference time by up to 67%. This framework paves the way for practical, energy-efficient, and unobtrusive in-home monitoring of PD patients. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps people with Parkinson’s disease by making it easier to track their symptoms at home. Right now, there are limited technologies that can do this because they require a lot of power, data, and control. The authors created LIFT-PD, a new way to detect Freezing of Gait (FoG) symptoms using only a little bit of labeled data and less power. Their method is better than others at recognizing FoG and takes less time to make predictions. This breakthrough could lead to more comfortable and convenient monitoring for people with Parkinson’s disease. |
Keywords
» Artificial intelligence » Deep learning » Inference » Precision » Self supervised » Supervised
