Abstract
This paper presents the design of a patch electrode and a data-driven recognition algorithm for early-stage skin cancer detection. The skin and cancerous tissues exhibit skin depths of 0.35-0.87 mm and 0.45-1.1 mm, respectively, within the 15-40 GHz frequency range, meeting skin cancer detection requirements. A dataset was constructed by dividing the skin into 7×7 grids and randomly populating it with cancerous tissue. The dataset was augmented using geometric symmetry and used to train a deep residual network for cancer tissue recognition, achieving an accuracy of 95.3%. This study provides a promising pathway toward accurate, low-cost hardware and algorithms for early-stage skin cancer detection.
| Original language | English |
|---|---|
| Title of host publication | 2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781733467711 |
| DOIs | |
| State | Published - 2025 |
| Event | 2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 - Huangshan, China Duration: 8 Aug 2025 → 11 Aug 2025 |
Publication series
| Name | 2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 - Proceedings |
|---|
Conference
| Conference | 2025 International Applied Computational Electromagnetics Society Symposium, ACES-China 2025 |
|---|---|
| Country/Territory | China |
| City | Huangshan |
| Period | 8/08/25 → 11/08/25 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 3 Good Health and Well-being
Keywords
- ResNet
- automated modelling
- biological dielectric property
- millimeter wave
Fingerprint
Dive into the research topics of 'The Design of a Patch Electrode and Data-Driven Recognition Algorithm for Early-Stage Skin Cancer Detection'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver