FPGA-Based Deep Learning Accelerators for Healthcare Applications: Current Trends and Optimization Strategies with Intel oneAPI
- DOI
- 10.2991/978-94-6463-754-0_60How to use a DOI?
- Keywords
- FPGA; Deep Learning; Healthcare; Intel oneAPI; Healthcare; Optimization Techniques
- Abstract
The potential for improving healthcare applications has been demonstrated by the combination of deep learning with Field-Programmable Gate Array (FPGA) technology. This work presents an extensive analysis of FPGA-based deep learning accelerators, focusing on their implementation using Intel Arria 10 FPGAs. To enhance performance metrics, we investigate a number of optimization strategies, such as quantization and trimming. According to experimental data, our modified FPGA model reduces latency from 50 ms to 15 ms while achieving an accuracy of 93.2% for medical picture categorization. Furthermore, the Recurrent Neural Network (RNN) models outperform conventional CPU-based implementations in genomic data processing, demonstrating a 45-s processing time. The results show that FPGA designs with Intel One API support may significantly improve the efficacy and efficiency of deep learning applications used in the medical field.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - S. Karthik AU - K. Priyadarsini AU - J. Jeba Sonia PY - 2025 DA - 2025/06/30 TI - FPGA-Based Deep Learning Accelerators for Healthcare Applications: Current Trends and Optimization Strategies with Intel oneAPI BT - Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025) PB - Atlantis Press SP - 689 EP - 701 SN - 2589-4943 UR - https://doi.org/10.2991/978-94-6463-754-0_60 DO - 10.2991/978-94-6463-754-0_60 ID - Karthik2025 ER -