Towards Smart City: Sensing Air Quality in City based on Opportunistic Crowd-sensing Joy Dutta, Chandreyee Chowdhury, Sarbani Roy, Asif Iqbal Middya, Firoj Gazi Department of Computer Science and Engineering, Jadavpur University, Kolkata-700032, India joy.dutta.in@ieee.org, {chandreyee, sarbani.roy}@cse.jdvu.ac.in, asif.md.ju@gmail.com, firojgazi123@gmail.com ABSTRACT Cities are expanding and more and more citizens are exposed to air pollutants both indoors and outdoors. This may have adverse effects on citizens’ health. In this paper, we present AirSense, an opportunistic crowd-sensing based air quality monitoring system, aimed at collecting and aggregating sensor data to monitor air pollution in the vicinity (building/neighbourhood) and the city. We introduce a light weight, low power and low cost air quality monitoring device (AQMD) and demonstrate how AQMD and smartphones in a crowd collaboratively gather and share data of interest to the cloud. In cloud, collected data are analyzed and an aggregate view is generated from data collected from various sensors and from different users for providing an air pollution heat map of the city. Unlike previous works, both micro and macro level air quality monitoring is possible with Airsense. End user can view his/her pollution footprint for the whole day, the neighborhood (local) air quality and AQImap (air quality index map) of the city on his/her smartphone. The system is implemented and the prototype is also evaluated. Categories and Subject Descriptors C.3 [Special-Purpose And Application-Based Systems] General Terms Crowd-sensing, sensors, cloud, air pollution. Keywords Air quality; Opportunistic crowd-sensing; Sensing device 1. INTRODUCTION Presently, air pollution is a global concern as it may cause many chronic and fatal diseases. Especially in developing countries, rapid urbanization is happening, without paying attention to the environment. As urban areas have high density of population, maintaining air quality is becoming more and more challenging. People are unknowingly exposed to harmful gases making them prone to many deadly diseases. Not only prolonged exposure to polluted air, some gasses if inhaled even for a short time can cause serious illness.The effect is even more severe in young and elder adults. However, in reality, there are inadequate air quality measurement stations [2] in a city of a developing country. The reason behind this is the appreciable cost of building and maintaining such a station. On the other hand, air quality readings taken from these stations are highly reliable and accurate as measured using carefully calibrated professional equipment. U- Air system proposed in [2] analyzes readings reported by a few air quality monitoring stations and a variety of data sources including meteorology, traffic flow etc.observed in the city. It uses artificial neural network to find spatial correlation of air pollution in different parts of the city.Some effort is being made for designing portable sensors, that can be attached to public vehicles[4] so that data can be collected on the move. This little bit saves the maintenance effort. But, these air quality monitoring systems are able to view the effects on a macro scale. Moreover, indoor air quality monitoring, (for example in factory or laboratory) are important as a person stays most of his/her time indoor. Nowadays, a few devices are being made that can be placed at specific locations indoor to detect air quality. These again provides a macro scale view of indoor air pollution. For home, it may suffice but for factories and/or laboratories, these may prove to be inadequate. More importantly, individual’s pollution footprint cannot be measured and its associated health hazards cannot be assessed with these macro scale devices. Few research efforts are being made in this direction that uses low cost portable sensing devices that interfaces with smartphones to be carried by citizens. The devices sense data with or without user intervention and send it to cloud through the Internet. The avantage of these group of crowd-sensing based air pollution monitoring applications is ease of maintenance and low cost of procuring these devices. Some relevant air quality monitoring solutions based on participatory sensing approach have been described in [3-6]. In participatory sensing the user decides when to sense and send data depending on a number of factors including incentive, remaining energy of the device etc. In [7], wearable sensors are used to sense air quality that is pushed to the cloud through the smartphone. In [9-10] efforts are being made where devices are carried by citizens for sensing and the data collected by citizens can be shared through social media to spread awareness. However, these works mainly focus on outdoor air quality monitoring mainly of public places in the city. However, most citizens stay indoor or in campuses most of their time in a day. Consequently, the main objective of this work is to design and develop a system called AirSense for air quality monitoring of our neighborhood both indoor and outdoor. The proposed system will encourage the citizens to participate in a crowd-sensing initiative, which could be a backbone of any smart city. The nature of the crowd-sensing used in this work is categorized as opportunistic sensing [1] where, user involvement is minimal, which generally ensures reliable data at regular intervals. Nowadays, smartphones and tablets are increasingly becoming an essential part of human life as the most effective and convenient communication tools not bounded by time and space. Hence, a portable Air Quality Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org. ICDCN '17, January 04-07, 2017, Hyderabad, India © 2017 ACM .ISBN 978-1-4503-4839-3/17/01…$15.00 DOI: http://dx.doi.org/10.1145/3007748.3018286