Summary of Leveraging Self-training and Variational Autoencoder For Agitation Detection in People with Dementia Using Wearable Sensors, by Abeer Badawi et al.
Leveraging Self-Training and Variational Autoencoder for Agitation Detection in People with Dementia Using Wearable Sensors
by Abeer Badawi, Somayya Elmoghazy, Samira Choudhury, Khalid Elgazzar, Amer Burhan
First submitted to arxiv on: 26 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 novel comprehensive approach presented in this study detects agitation and aggression (AA) in people with severe dementia (PwD) using physiological data from Empatica E4 wristbands. The research creates a diverse dataset of three distinct datasets gathered from 14 participants across multiple hospitals in Canada, which have not been extensively explored due to limited labeling. A semi-supervised block is proposed to learn the representation of features extracted using a variational autoencoder (VAE) and then classify events to detect AA. The approach combines self-training and VAE mechanism to improve model performance in classifying AA in PwD, achieving an accuracy of 90.16% with XGBoost classifier. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps us better understand dementia, a growing problem among older people that affects the quality of life for patients and caregivers. The researchers focus on agitation and aggression (AA), which can cause discomfort and even put patients or others at risk. They use wearable sensors and artificial intelligence to detect AA early enough for medical intervention. But most studies are limited by the availability of accurately labeled data. This study creates a new dataset and proposes a unique approach using self-training and VAE to detect AA in people with severe dementia. |
Keywords
» Artificial intelligence » Self training » Semi supervised » Variational autoencoder » Xgboost
