Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.14617 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915882360373248 |
|---|---|
| author | Wei, Jianglan Zhang, Zhenyu Wang, Pengcheng Zeng, Mingjie Zeng, Zhigang |
| author_facet | Wei, Jianglan Zhang, Zhenyu Wang, Pengcheng Zeng, Mingjie Zeng, Zhigang |
| contents | Energy-efficient medical data classification is essential for modern disease screening, particularly in home and field healthcare where embedded devices are prevalent. While deep learning models achieve state-of-the-art accuracy, their substantial energy consumption and reliance on GPUs limit deployment on such platforms. We present HDC-X, a lightweight classification framework designed for low-power devices. HDC-X encodes data into high-dimensional hypervectors, aggregates them into multiple cluster-specific prototypes, and performs classification through similarity search in hyperspace. We evaluate HDC-X across three medical classification tasks; on heart sound classification, HDC-X is $350\times$ more energy-efficient than Bayesian ResNet with less than 1% accuracy difference. Moreover, HDC-X demonstrates exceptional robustness to noise, limited training data, and hardware error, supported by both theoretical analysis and empirical results, highlighting its potential for reliable deployment in real-world settings. Code is available at https://github.com/jianglanwei/HDC-X. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14617 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HDC-X: Efficient Medical Data Classification for Embedded Devices Wei, Jianglan Zhang, Zhenyu Wang, Pengcheng Zeng, Mingjie Zeng, Zhigang Machine Learning Energy-efficient medical data classification is essential for modern disease screening, particularly in home and field healthcare where embedded devices are prevalent. While deep learning models achieve state-of-the-art accuracy, their substantial energy consumption and reliance on GPUs limit deployment on such platforms. We present HDC-X, a lightweight classification framework designed for low-power devices. HDC-X encodes data into high-dimensional hypervectors, aggregates them into multiple cluster-specific prototypes, and performs classification through similarity search in hyperspace. We evaluate HDC-X across three medical classification tasks; on heart sound classification, HDC-X is $350\times$ more energy-efficient than Bayesian ResNet with less than 1% accuracy difference. Moreover, HDC-X demonstrates exceptional robustness to noise, limited training data, and hardware error, supported by both theoretical analysis and empirical results, highlighting its potential for reliable deployment in real-world settings. Code is available at https://github.com/jianglanwei/HDC-X. |
| title | HDC-X: Efficient Medical Data Classification for Embedded Devices |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.14617 |