A bio-inspired unsupervised algorithm for deploying [BoT

Abstract

The paper illustrates a novel concept & implementation technique for [Bio-Net]-of-Things (BoT). BoT discloses a method for bringing all the living systems online - so we have humans, IoT devices (inanimate) & bacteria, viruses, plants, crops, etc. all under one bracket of Internet. In this paper we are envisaging symbiotic intelligence for solving the problem of air pollution through BoT. We are facing the pollution menace from vehicles, industries, etc. to a greater extent, especially to the people who are living near roadsides in cities. Carbon monoxide, Nitrogen oxides (NOx), SO2 are the prominent air pollutants found in most cities. Out of these, NOx is one of the major pollutants emitted from vehicles. NOx gases react to form smog and acid rain, as well as being central to the formation of fine particles and ground level ozone, both of which are associated with adverse health effects. The paper demonstrates a setup that utilizes the photo catalytic effect of Titanium dioxide (TiO2) for reducing the effect of air pollution. The pollutants in the air are explicitly identified with the help of on-chip spectrometers and TiO2 is economically sprayed onto those target air pollutants. The cost effective usage of TiO2 is worked out by implementing an 'Unsupervised Particle Swarm Optimization' algorithm. The viability of the proposed IoT platform is confirmed by building a smart test-bed for executing the unsupervised algorithm. Experimental results show that BoT can be effectively deployed through this algorithmic middleware which can support 'n' no. of BoT devices. Thus a pioneering technique is disclosed for tackling the problem of air pollution.