Biomimetic olfactory processor with on-chip one-shot incremental learning for odor identification

Electronic noses (E-noses) mimic the mammalian olfactory system and have been used to detect gases in public safety, disease diagnosis, food safety and so on. However, existing E-noses lack of adaptive learning ability, making them susceptible to sensor drift caused by environmental changes, leading to a progressive decline in recognition accuracy over time. Moreover, unlike mammalian olfactory systems with robust learning abilities and adaptation, current E-noses cannot continuously and rapidly learn new odors profiles or compensate for environmental perturbations. To address the limitations, we propose a novel biomimetic olfactory processor ANP-OB which achieves rapid learning capabilities by mimicking the mammalian olfactory bulb. The ANP-OB is able to remember a new gas after learning it only once, and does not forget previously learned gases. With one-shot incremental learning, ANP-OB achieves a recognition accuracy of 99.8% in a 10-class gas recognition task under 60% noise. Furthermore, its power consumption is less than 50 μW with event-driven asynchronous circuits, making it the lowest-power olfactory processor to our knowledge.