A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data
In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/22/4831 |
| _version_ | 1798025378380382208 |
|---|---|
| author | Anup Vanarse Adam Osseiran Alexander Rassau Peter van der Made |
| author_facet | Anup Vanarse Adam Osseiran Alexander Rassau Peter van der Made |
| author_sort | Anup Vanarse |
| collection | DOAJ |
| description | In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking neural network (SNN)-based classifier, implemented in a chip-emulation-based development environment, that can be seamlessly deployed on a neuromorphic system-on-a-chip (NSoC). Under three different scenarios of increasing complexity, the SNN was determined to be able to classify real-valued sensor data with greater than 90% accuracy and with a maximum latency of 3 s on the software-based platform. Highlights of this work included the design and implementation of a novel encoder for artificial olfactory systems, implementation of unsupervised spike-timing-dependent plasticity (STDP) for learning, and a foundational study on early classification capability using the SNN-based classifier. |
| first_indexed | 2024-04-11T18:17:51Z |
| format | Article |
| id | doaj.art-a675c514f17c4858bab2173e108ef140 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:17:51Z |
| publishDate | 2019-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a675c514f17c4858bab2173e108ef1402022-12-22T04:09:51ZengMDPI AGSensors1424-82202019-11-011922483110.3390/s19224831s19224831A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose DataAnup Vanarse0Adam Osseiran1Alexander Rassau2Peter van der Made3School of Engineering, Edith Cowan University, 6027 Perth, AustraliaSchool of Engineering, Edith Cowan University, 6027 Perth, AustraliaSchool of Engineering, Edith Cowan University, 6027 Perth, AustraliaBrainchip Inc., Aliso Viejo, CA 92656, USAIn several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking neural network (SNN)-based classifier, implemented in a chip-emulation-based development environment, that can be seamlessly deployed on a neuromorphic system-on-a-chip (NSoC). Under three different scenarios of increasing complexity, the SNN was determined to be able to classify real-valued sensor data with greater than 90% accuracy and with a maximum latency of 3 s on the software-based platform. Highlights of this work included the design and implementation of a novel encoder for artificial olfactory systems, implementation of unsupervised spike-timing-dependent plasticity (STDP) for learning, and a foundational study on early classification capability using the SNN-based classifier.https://www.mdpi.com/1424-8220/19/22/4831snn-based classificationneuromorphic olfactionbio-inspired electronic nose systems |
| spellingShingle | Anup Vanarse Adam Osseiran Alexander Rassau Peter van der Made A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data Sensors snn-based classification neuromorphic olfaction bio-inspired electronic nose systems |
| title | A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data |
| title_full | A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data |
| title_fullStr | A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data |
| title_full_unstemmed | A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data |
| title_short | A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data |
| title_sort | hardware deployable neuromorphic solution for encoding and classification of electronic nose data |
| topic | snn-based classification neuromorphic olfaction bio-inspired electronic nose systems |
| url | https://www.mdpi.com/1424-8220/19/22/4831 |
| work_keys_str_mv | AT anupvanarse ahardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT adamosseiran ahardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT alexanderrassau ahardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT petervandermade ahardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT anupvanarse hardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT adamosseiran hardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT alexanderrassau hardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata AT petervandermade hardwaredeployableneuromorphicsolutionforencodingandclassificationofelectronicnosedata |