Journal
SENSORS
Volume 22, Issue 8, Pages -Publisher
MDPI
DOI: 10.3390/s22083039
Keywords
electronic nose; gas sensor array; sixth-generation wireless communication technology (6G); 6G-IoT; zero-padding; spatial augmentation; convolutional neural networks; machine learning; artificial intelligence; pattern recognition
Funding
- NCC Laboratory, Department of Electronics Engineering, IIT (BHU), India [IS/ST/EC-13-14/02]
- I-DAPT HUB Foundation, IIT(BHU), India [R&D/SA/I-DAPT IIT(BHU)/ECE/21-22/02/290]
- European Union's Horizon 2020 Research and Innovation Program under Marie Skodowska-Curie Grant [847577]
- Science Foundation Ireland (SFI) [16/RC/3918]
- European Regional Development Fund
- Deanship of Scientific Research at Taif University, Kingdom of Saudi Arabia [TURSP-2020/265]
Ask authors/readers for more resources
Ultra-low-power and lightweight artificial intelligence models are important in 6G-IoT ecosystems. The paper demonstrates high performance in a gas sensor system utilizing Convolutional Neural Network (CNN) with a reduced number of sensor elements. Redundant sensor elements are identified and removed, resulting in reduced power consumption without significant performance deviation. Specialized data pre-processing and CNN compensate for performance variation. The experiment achieves successful classification and quantification of hazardous gases with improved power efficiency.
Ultra-low-power is a key performance indicator in 6G-IoT ecosystems. Sensor nodes in this eco-system are also capable of running light-weight artificial intelligence (AI) models. In this work, we have achieved high performance in a gas sensor system using Convolutional Neural Network (CNN) with a smaller number of gas sensor elements. We have identified redundant gas sensor elements in a gas sensor array and removed them to reduce the power consumption without significant deviation in the node's performance. The inevitable variation in the performance due to removing redundant sensor elements has been compensated using specialized data pre-processing (zero-padded virtual sensors and spatial augmentation) and CNN. The experiment is demonstrated to classify and quantify the four hazardous gases, viz., acetone, carbon tetrachloride, ethyl methyl ketone, and xylene. The performance of the unoptimized gas sensor array has been taken as a baseline to compare the performance of the optimized gas sensor array. Our proposed approach reduces the power consumption from 10 Watts to 5 Watts; classification performance sustained to 100 percent while quantification performance compensated up to a mean squared error (MSE) of 1.12 x 10(-2). Thus, our power-efficient optimization paves the way to computation on edge, even in the resource-constrained 6G-IoT paradigm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available