A 15-Gbps BiCMOS XNOR gate for fast recognition of COVID-19 in binarized neural networks

The COVID-19 pandemic is spreading around the world causing more than 177 million cases and over 3.8 deaths according to European Centre for Disease Prevention Control. virus has devastating effects on economies, health, well-being of worldwide population. Due high increase in daily cases, available number test kits under-developed countries scarce. Hence, it vital implement an effective screening method patients using chest radiography since equipment already exists. With presence automatic detection systems, any abnormalities that characterizes can be identified. Several artificial-intelligence algorithms have been proposed detect virus. However, neural networks training considered time-consuming. Since computations are spent floating-point multiplications, computational power required. Multipliers consume most space among all arithmetic operators deep networks. This paper proposes a 15 Gbps high-speed bipolar-complementary-metal-oxide-semiconductor (BiCMOS) exclusive-nor (XNOR) gate replace multipliers binarized implemented BiCMOS-based field-programmable arrays (FPGAs). will significantly improve response time identifying CT scans X-rays.