Paper biological risk detection through deep learning and fuzzy system

<span lang="EN-US">Given the recent events worldwide due to viral diseases that affect human health, automatic monitoring systems are one of strong points research has gained strength, where detection biohazardous waste a sanitary nature is highlighted related stands out. It essential in this field generate developments aimed at saving lives, robotic can operate as assistants various fields. In work an artificial intelligence algorithm based on two stages presented, recognition paper debris using ResNet-50, chosen for its object localization capacity, and other fuzzy inference system generation alarm states biological risk by such debris, logic helps establish model non-predictive exposed. A biohazard described, oriented assistive robot residential environment. The training parameters network, which achieve 100% accuracy with confidence levels between 82% very small direct view, presented. Timing cycles established validation exposure time waste, through system, alarms generated, allows establishing average reliability 98%.</span>