Summary of Artificial Data Point Generation in Clustered Latent Space For Small Medical Datasets, by Yasaman Haghbin et al.
Artificial Data Point Generation in Clustered Latent Space for Small Medical Datasets
by Yasaman Haghbin, Hadi Moradi, Reshad Hosseini
First submitted to arxiv on: 26 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
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 Artificial Data Point Generation in Clustered Latent Space (AGCL) method aims to enhance classification performance on small medical datasets through synthetic data generation. By leveraging feature extraction, K-means clustering, and cluster evaluation based on a class separation metric, AGCL generates synthetic data points from clusters with distinct class representations. This novel approach was applied to Parkinson’s disease screening, utilizing facial expression data, and evaluated across multiple machine learning classifiers. Experimental results demonstrate that AGCL significantly improves classification accuracy compared to baseline methods GN and kNNMTD. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to create fake medical data that can help doctors better diagnose diseases like Parkinson’s. Right now, collecting lots of medical data is hard because it takes too much time and money. This makes machine learning models not very good at predicting things. The researchers came up with an idea called AGCL (Artificial Data Point Generation in Clustered Latent Space). It works by taking features from the real data, grouping them together based on what they look like, and then creating fake data that’s similar to the real data. They tested this method on facial expression data to see if it could help diagnose Parkinson’s disease. The results showed that AGCL was way better than just using the original data. |
Keywords
» Artificial intelligence » Classification » Clustering » Feature extraction » K means » Latent space » Machine learning » Synthetic data
