MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115430 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering And Technology on September 26, 2026, for A Hardware-Accelerated Cnn Architecture For Real-Time Pneumonia Detection Using Pynq-Z2 Fpga.
Inventor includes Dr. Y. Padma Sai.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: ABSTRACT [0028] Convolutional Neural Network (CNN) is now widely used in medical applications. This work presents a high-performance hardware-software co- design pipeline for pneumonia disease detection based on a CNN on the Python productivity for ZYNQ(PYNQ-Z2) Field Programmable Gate Array(FPGA) board. This research leverages the parallel computation potential of FPGAs to accelerate computationally intensive convolutional layers in CNNs. A hardware-accelerated convolutional IP core was developed and instantiated as a Python overlay on the PYNQ board, thus enormously speeding up inference time. The CNN model trained on labeled chest X-ray images can identify pneumonia. Quantization and optimization are applied to the model to facilitate easy integration in an FPGA, where notable performance improvement in execution has been witnessed. Experimental findings have demonstrated that hardware-based acceleration performs better compared to pure software-based and can cut inference time by up to 4.2 times, with high diagnostic accuracy. It facilitates effective, reliable, and real-time detection of lung disease such as pneumonia.
Disclaimer: Curated by HT Syndication.
