TY - GEN
T1 - Designing Multi-Class Classifiers for Sub-mA Microcontroller Platforms
AU - Sun, Qi Hui
AU - Lin, Mei Lan
AU - Tu, Chia Heng
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - With the prevalence of deep learning technology in various application domains, a recent trend is to deploy convolutional neural networks onto the sensors in the field enabling new smart applications, such as poaching detection, discovering endanger species, and estimating wildlife populations in environmental monitoring. Among the ultra-low-power hardware platforms with microcontrollers for the computations, the sub-mA platforms (i.e., lower-end ultra-low-power platforms) would be desired for monitoring in the field since they can achieve a longer lifetime given a fixed amount of power budget provided by the batteries. In this work, we propose a new approach to develop convolutional neural networks to run on such sub-mA platforms, usually with less than 10 KB memory for keeping the runtime data. The new approach combines the concepts of the One-vs-All (OVA) strategy and the transfer learning technology to build networks with small memory footprints. Our experimental results show our approach achieves the accuracy of 77.0% of a four-class classification problem for a poaching detection application as fast as 1.1 seconds.
AB - With the prevalence of deep learning technology in various application domains, a recent trend is to deploy convolutional neural networks onto the sensors in the field enabling new smart applications, such as poaching detection, discovering endanger species, and estimating wildlife populations in environmental monitoring. Among the ultra-low-power hardware platforms with microcontrollers for the computations, the sub-mA platforms (i.e., lower-end ultra-low-power platforms) would be desired for monitoring in the field since they can achieve a longer lifetime given a fixed amount of power budget provided by the batteries. In this work, we propose a new approach to develop convolutional neural networks to run on such sub-mA platforms, usually with less than 10 KB memory for keeping the runtime data. The new approach combines the concepts of the One-vs-All (OVA) strategy and the transfer learning technology to build networks with small memory footprints. Our experimental results show our approach achieves the accuracy of 77.0% of a four-class classification problem for a poaching detection application as fast as 1.1 seconds.
UR - http://www.scopus.com/inward/record.url?scp=85174906788&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174906788&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Taiwan58799.2023.10226987
DO - 10.1109/ICCE-Taiwan58799.2023.10226987
M3 - Conference contribution
AN - SCOPUS:85174906788
T3 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
SP - 131
EP - 132
BT - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023
Y2 - 17 July 2023 through 19 July 2023
ER -