Urban Noise Computing for Event Discovery
Prajakta Joglekar, Vrushali Kulkarni
Department of Computer Engineering,
Maharashtra Institute of Technology, Pune,
Savitribai Phule Pune University, Maharashtra.
somanprajakta@gmail.com, vrushali.kulkarni@mitpune.edu.in
Abstract—Urban computing is a wide area for research, which
has picked up momentum after the introduction of Smart City
vision. Smart City initiative aims to improve the quality of life
of its citizens by building a strong and resilient framework for
the city. Noise pollution is one of the main problems affecting
citizens all over. Citizen science, when combined with Mobile
crowdsensing and Data mining can help researchers and town
planners to collect urban noise data at a massive spatio-temporal
scale, and analyse it to understand urban dynamics. This work is
an effort to use urban noise computing to detect anomalies and
interesting events happening in the city. The paper introduces
the readers to the basics of Urban noise computing. It covers a
comprehensive literature survey in the area of Urban noise com-
puting and Anomaly detection. This work also includes problem
statement, problem modelling and partial implementation details.
Index Terms—Anomaly detection, Event discovery, Mobile
crowdsensing, Smart city, Urban noise computing.
I. I NTRODUCTION
Urban computing is an interesting, multi-disciplinary area
of research which has gained momentum with the advent
of ’Smart Cities’ concept. In India, around 100 cities have
been selected for development under this initiative. Efforts
are being taken to improve the quality of life of the citizens
by providing smart and sustainable solutions. The pillars
of a Smart City include transport, healthcare, environment,
economy, governance and citizens.
Urbanization has given rise to job opportunities and higher
educational facilities. At the same time, it is facing many
challenges such as global warming, pollution, increased energy
consumption, traffic congestion and health issues related to
sedentary lifestyle of people. Urban noise problem or Noise
pollution is one such challenge which affects all the pillars of
a smart city directly or indirectly.
Noise pollution is one of the six major types of pollutions.
It is also one of the leading causes of ailments in humans
as well as the ecosystem. People suffer from high blood
pressure, hearing loss, stress and psychological disorders due
to continuous exposure to high noise levels [1]. The World
Health organization (WHO) has provided the guidelines of
community noise citing different health problems caused due
to different types of noise [2]. It is necessary for the citizens
and the government to measure urban noise, understand dif-
ferent causes that produce noise, model the noise situation in
the city and come up with abatement measures. According
to WHO, noise measurements may also be done to identify
emerging trends and patterns in the city. We hypothesize
that the study of urban noise can help us to understand the
urban dynamics and discover interesting events in the city.
Our research work is an effort to support this hypothesis. The
paper is organized as follows:
It first states the motivation behind this work. Concepts
related noise pollution are explained. The paper presents a
comprehensive Literature Survey in the area of Urban Noise
Computing as well as Event Detection in a city. It states
the observations and gap analysis and formulates the problem
statement. The proposed system is expressed using set theory
and data analysis. A suitable architecture is proposed for such
an Event Discovery system. The report also gives current
implementation status with partial results and concludes by
stating the future work.
II. MOTIVATION
Our city, Pune, has been selected as one of the cities under
’Smart Cities’ mission by the Indian Government. Lot of
efforts are being put in the direction of transportation, air
pollution problems, garbage management, developing cycle
tracks etc. to build a resilient environment[3]. Unfortunately,
there is no sound plan in place to curb noise pollution or
record ambient noise levels on regular basis. As per the
latest Environmental Status Report submitted by Pune Mu-
nicipal Corporation [4], noise levels in industrial, commercial,
residential as well as silence zones are said to exceed the
respective threshold values set by the Noise Pollution Control
Body. This has motivated us to select ”Urban Noise” as an
area of research.
Further, involvement of citizens is very important in urban
computing as they are the generators of myriads of data being
generated every day. We can exploit the capabilities of ’human
as a sensor’ to capture urban noise levels using smart phone.
This has motivated us to use ’Mobile Crowdsensing’ paradigm
in our work.
Finally, we believe that we can discover interesting events
in the city by modelling the urban noise data. Much work has
been done to detect anomalies and festive events using GPS
traces from taxi data, SMS and mobile call records, tweets
and USA’s 311 complaint data [5, 6, 7]. To the best of our
knowledge, no author has yet used the urban noise levels to
detect interesting events and anomalies in an urban region.
Sixth Post Graduate Conference for Computer Engineering (cPGCON 2017) Procedia
International Journal on Emerging Trends in Technology (IJETT)
IJETT | ISSN: 2455-0124( E) | 2350-0808 (P) | (IF: 0.456) | Volume 4 | Special Issue July - 2017 | 8224
Peer-review under responsibility of organizing committee of cPGCON 2017
© IJETT
www.ijett.in