Volume 02, Issue 8
Published on: August 2026
ON-CNN WITH INTEGRATED RELU ACTIVATION FOR FPGA-BASED CNN ACCELERATION
Samudrala Vandana Dr Dr Anvesh Thatikonda
1M.TECH Student, Department Of ECE, SVS Group of Institutions, Hanmakonda, Telangana
2Associate Professor, Department Of ECE, SVS Group of Institutions, Hanmakonda, Telangana
2Associate Professor, Department Of ECE, SVS Group of Institutions, Hanmakonda, Telangana
Article Status
Plagiarism Passed
Peer Reviewed
Open Access
Available Documents
Abstract
Convolutional Neural Networks (CNNs) have become the foundation of modern artificial intelligence applications, including image classification, object detection, medical image analysis, and autonomous systems. However, the computational complexity and high memory requirements of CNN models present significant challenges for real-time deployment on resource-constrained hardware platforms. Field-Programmable Gate Arrays (FPGAs) offer a promising solution due to their inherent parallelism, configurability, and energy-efficient operation. This paper presents an Optimized Neural Convolutional Neural Network (ON-CNN) architecture with an integrated Rectified Linear Unit (ReLU) activation module for FPGA-based CNN acceleration. The proposed architecture combines convolution and activation operations within a unified processing pipeline, reducing intermediate memory accesses and minimizing processing latency. Dedicated parallel processing elements are employed to accelerate convolution computations, while the integrated ReLU unit performs real-time activation without additional clock cycles. The architecture is modeled using Verilog HDL and implemented on an FPGA platform to evaluate hardware resource utilization, throughput, latency, and power efficiency. Experimental results demonstrate that the proposed ON-CNN achieves improved computational performance and reduced resource overhead compared with conventional FPGA-based CNN accelerators. The integrated design enhances processing speed while maintaining classification accuracy, making it suitable for edge computing, embedded vision systems, intelligent surveillance, healthcare monitoring, and real-time artificial intelligence applications requiring low-power and high-performance inference.
Keywords: FPGA, Convolutional Neural Network (CNN), ON-CNN, ReLU Activation, Hardware Acceleration, Edge AI.
Keywords: FPGA, Convolutional Neural Network (CNN), ON-CNN, ReLU Activation, Hardware Acceleration, Edge AI.
How to Cite this Paper
Vandana, S. & Thatikonda, D. D. A. (2026). ON-CNN with Integrated ReLU Activation for FPGA-Based CNN Acceleration. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(8), 1-14. https://doi.org/10.55041/ijcope.v2i8.256
Vandana, Samudrala, and Dr Thatikonda. "ON-CNN with Integrated ReLU Activation for FPGA-Based CNN Acceleration." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 8, 2026, pp. 1-14. doi:https://doi.org/10.55041/ijcope.v2i8.256.
Vandana, Samudrala, and Dr Thatikonda. "ON-CNN with Integrated ReLU Activation for FPGA-Based CNN Acceleration." International Journal of Creative and Open Research in Engineering and Management 02, no. 8 (2026): 1-14. https://doi.org/https://doi.org/10.55041/ijcope.v2i8.256.
Search & Index
References
- Boutros, S. Nurvitadhi, C. de Prado, M. Blott, and K. Vissers, “FPGA-accelerated deep learning inference: Challenges and opportunities,” IEEE Micro, vol. 41, no. 5, pp. 46–54, 2021.
- Ma, H. Zhang, Y. Cao, J. Li, and Y. Chen, “Optimizing FPGA-based accelerator design for deep convolutional neural networks,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 29, no. 3, pp. 573–586, 2021.
- Zhang, J. Wang, C. Zhu, Y. Lin, and Y. Wang, “Efficient FPGA implementation of convolutional neural networks using optimized dataflow architecture,” IEEE Access, vol. 9, pp. 112034–112046, 2021.
- Alwani, H. Chen, M. Ferdman, and P. Milder, “Fused-layer CNN accelerators for FPGA platforms,” Integration, the VLSI Journal, vol. 81, pp. 34–46, 2021.
- Qiu, J. Wang, S. Yao, K. Guo, B. Li, and Y. Wang, “Deep learning acceleration with FPGA-based convolution engines,” Microprocessors and Microsystems, vol. 82, Art. no. 103909, 2021.
- Mittal, “A survey of FPGA-based accelerators for convolutional neural networks,” Journal of Systems Architecture, vol. 117, Art. no. 102149, 2021.
- Liu, H. Fan, and Y. Chen, “Resource-efficient FPGA architecture for real-time CNN inference,” Electronics, vol. 10, no. 18, pp. 1–18, 2021.
- Wang, Y. Li, and X. Huang, “High-throughput FPGA accelerator for convolutional neural networks using parallel processing elements,” IEEE Access, vol. 10, pp. 35812–35824, 2022.
- N. Whatmough, S. K. Lee, H. Zhou, and M. Mattina, “Energy-efficient FPGA implementations for deep neural network inference,” IEEE Transactions on Computers, vol. 71, no. 4, pp. 1018–1031, 2022.
- M. Rahman, M. A. Islam, and S. Hossain, “Low-latency FPGA architecture for CNN-based image classification,” AEU – International Journal of Electronics and Communications, vol. 148, Art. no. 154151, 2022.
- Li, T. Wang, and Y. Zhang, “Hardware-efficient ReLU implementation for FPGA-based deep learning accelerators,” Microelectronics Journal, vol. 125, Art. no. 105482, 2022.
- Chen, X. Liu, and H. Wu, “Integrated convolution and activation architecture for FPGA-based CNN acceleration,” Journal of Signal Processing Systems, vol. 94, no. 9, pp. 1121–1134, 2022.
- Kumar and A. Singh, “Parallel CNN accelerator design using FPGA for edge intelligence applications,” International Journal of Reconfigurable Computing, vol. 2022, pp. 1–12, 2022.
- Li, Q. Wang, and Z. Chen, “FPGA-based edge AI accelerator with optimized convolution and activation layers,” Electronics, vol. 11, no. 14, pp. 1–20, 2022.
- Roy, P. Banerjee, and A. Bhattacharya, “Performance analysis of FPGA-implemented convolutional neural networks for embedded vision systems,” Microprocessors and Microsystems, vol. 94, Art. no. 104641, 2023.
- Zhao, J. Sun, and Y. Liu, “Memory-efficient CNN accelerator architecture for FPGA-based inference systems,” IEEE Access, vol. 11, pp. 48216–48230, 2023.
- Gupta and R. Verma, “High-performance FPGA implementation of deep learning inference engines using pipelined convolution architectures,” Journal of Systems Architecture, vol. 141, Art. no. 102915, 2023.
- S. Rao, V. Prakash, and S. Kumar, “Resource-aware CNN accelerator with integrated activation processing for FPGA devices,” AEU – International Journal of Electronics and Communications, vol. 167, Art. no. 154758, 2023.
- Zhang, H. Yang, and L. Wang, “Low-power FPGA accelerator for real-time convolutional neural network inference,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 8, pp. 4128–4140, 2023.
- Zhou, C. Li, and M. Huang, “Scalable FPGA architecture for CNN acceleration in edge computing environments,” IEEE Access, vol. 12, pp. 12451–12466, 2024.
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Aug 27 2026
CCBYNC
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.