Summary of Mssda: Multi-sub-source Adaptation For Diabetic Foot Neuropathy Recognition, by Yan Zhong et al.
MSSDA: Multi-Sub-Source Adaptation for Diabetic Foot Neuropathy Recognition
by Yan Zhong, Zhixin Yan, Yi Xie, Shibin Wu, Huaidong Zhang, Lin Shu, Peiru Zhou
First submitted to arxiv on: 21 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- 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 A novel dataset comprising continuous plantar pressure data is introduced, aiming to advance research on diabetic foot neuropathy (DFN), a critical factor leading to diabetic foot ulcers. The dataset includes 94 patients with DFN and 41 without DFN. A domain adaptation method is proposed to address the problem of dividing datasets by individuals, which can lead to significant domain discrepancies. The approach involves splitting the dataset based on convolutional feature statistics, selecting sub-source domains, and aligning distributions in specific feature spaces to minimize the domain gap. Comprehensive results validate the effectiveness of the method on both the new DFN recognition dataset and an existing dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Diabetic foot neuropathy is a serious problem that can lead to diabetic foot ulcers, which are very common and severe complications of diabetes. There isn’t enough data available to help researchers study this issue. To fix this, we collected a new dataset with continuous plantar pressure information from 135 people – 94 with DFN and 41 without. We also developed a way to adapt our model to different datasets so it can work better on new data. This method helps us avoid mistakes that happen when we divide the data by individual. Our results show that this approach works well for both our new dataset and another existing one. |
Keywords
» Artificial intelligence » Domain adaptation
