2020 BRN Discussion, page-163

The following isextracted from the e-nose paper by Adam Osserian, Peter van der Made and otherspublished last year. It is worth reading and comparing just how far ahead theyare by comparison with the researchers in the 2019 paper which I have provided alink to who claim to have achieved state of the art odour recognition and ontop of that no rats were harmed in the implementation of the AKIDA simulation.

https://www.mdpi.com/1424-8220/19/22/4831/htm

5. Conclusions

In this paper, wepresented the development of an SNN-based solution for real-time classificationof electronic olfactory data. The SNN was implemented using Brainchip’s AkidaDevelopment Environment, which provides an emulation of the Akida NSoC’sfunctionalities on a Python-based software platform. The highlights of thisimplementation included the development of a novel AER-based encoder for olfactiondata, implementation of unsupervised STDP for training the SNN, highly accuratereal-time classification results, and preliminary results that lay a foundationfor applying the Akida SNN for reliable early classification results.

One of the mostsignificant contributions of this study is the development of AERO, anAER-based data-to-spike encoder for olfaction data. The operating principle ofAERO is based on discretizing the sensor responses and encoding theiractivation levels along with sensor ID and temporal data. For thisimplementation, normalized relative resistance features were extracted fromsensor responses and provided as an input to the AERO encoder. Parameters, suchas frequency of event-generation, the number of time points for encoding, anddiscretization levels, can be configured based on the input data and processingrequirements. The development of AERO has opened several avenues for futureresearch, such as encoding multi-dimensional data using different features andinterfacing of electronic nose systems with AER-based neuromorphic hardware forprocessing.

The SNN was testedusing the benchmark dataset [20] under four different scenarios of increasing complexity. In general, under each scenario, the classification performance of the SNN was between 90% and 100%, and the processing latency was between 2.5 and 3 s, which includes data-to-spike encoding, learning, classification, and other software-based latencies introduced due to looping and conditional statements. This processing latency would, of course, be dramatically reduced once the classifier is implemented on the Akida NSoC hardware without the overhead of software emulation. Taken together, these classification results show that the SNN-based classifier can deliver highly accurate results with minimal processing latency. Moreover, the ability to transfer the SNN implementation to the Akida NSoC can be leveraged to develop low-power electronic nose systems with minimal computational cost and memory requirements. Intrinsically, in most cases, neuromorphic approaches have proven to outperform traditional processing methods that suffer from limited accuracy, high computational and power requirements, and substantial latency to provide classification results [32]. When evaluated against other neuromorphic and traditional approaches based on the same dataset [21, 24,33,34], the results revealed that the SNN classifier developed in this study achieved comparable and, in most cases, better classification performance with minimal computation requirements and latency for both learning and processing. More importantly, the Akida SNN was able to identify patterns from a highly multi-dimensional dataset and classify the dataset based on the four chemical groups of the compounds.

Future researchbased on these results will focus on the development of a robust SNN-basedclassifier on the Akida NSoC and its implementation in a real-worldapplication. The efficacy of AERO when combined with rate coding methods, suchas [35] and rank-order encoding [2,31,36], will also be investigated. This implementation also lays the foundation for the application of both the AERO encoder and an SNN to study neuromorphic gustation and the fusion of olfaction and gustation for the development of a comprehensive analytical tool for chemical sensing.

https://www.mdpi.com/1424-8220/19/5/993?utm_source=TrendMD&utm_medium=cpc&utm_campaign=Sensors__TrendMD_0