NANOSE & SNIFFPHONE, page-1072

great work Chapman,

re the importance of Brainchips role in this, I think the below PHD abstract that was previously shared on HC says it all

Neuronose: Anempirical study of neuromorphic approaches for the development of an artificialolfactory system

Electronic nose systems, .. have been researched extensively but havehad limited commercial success. ...

Although advances in computing techniques have enabled a variety ofalgorithms for preprocessing, feature extraction, and pattern-recognition,their short-comings in terms of computational resource requirement, processinglatency, and classification accuracy have largely limited the application ofe-nose systems to laboratory environments. Moving away from statisticalpattern-matching techniques, e-nose systems greatly benefited from applicationof conventional machine learning approaches for generation of meaningfulfeatures, application of dimensionality reduction, and more advancedpattern-recognition techniques. However, these improvements wereinsufficient to overcome the effects of their data-intensive structure andimplementation complexity that hindered their performance in real-worldapplications.

The emergence of neuromorphic engineering, a bio-inspired method thatmimics the neuro-biological architecture by encoding and processing informationusing sparse spike-based representation with minimal power consumption,delivered promising results for vision and auditory sensors.

“With increasing interest in developing low-power and robust chemicalsensors, the application of neuromorphic engineering concepts for electronicnoses has provided an impetus for research focusing on improving theseinstruments”.