An energy efficient approach of deep learning based soft sensor for air quality management

Abstract

Monitoring environmental pollution is emerging as a recent study area especially in urban and highly polluted industrial areas. This field deploys many chemical analysis models and data driven models through soft sensors. But bio indicators are a more feasible, cost effective and precise monitoring model, which are rarely explored. This paper is based on growth monitoring of Cryptogams, a bio indicator which is capable of directly reflecting the pollution levels in the region of growth. A novel enhanced and energy efficient deformable active contour model is introduced to trace the development of transplanted Cryptogams at various sites with diverse pollution levels. The vegetative development of Cryptogams is monitored for duration of two weeks. The proposed energy efficient contour tracing model proves its superiority in precise tracing of the Cryptogam development, thus aiding in accurate pollution monitoring. The VGG 16 architecture built using deep convolutional neural network by constructing stacks of filters. VGG 16 architecture showed high performance when compared with other existing models. The accuracy is compared with the Ant colony optimization using GVF.