citizens will necessarily be sparse in
space and time. In order to perform
meaningful analyses and help inform
decisions by city agencies, it is essential for the system to compensate for
this sparseness. Several open datasets are available that could, directly
or indirectly, provide information
on the noise levels in the city; for
example, locations of restaurants,
night clubs, and tourist attractions
indicate areas where sources of social noise are likely, while social media data streams can be used to understand the temporal dynamics of
crowd behavior. Likewise, multiple
data streams associated with taxi,
bus, and aircraft traffic can provide indirect information on traf-fic-based noise levels. We plan to
develop noise models that use spatiotemporal covariance to predict
unseen acoustic responses through
a combination of sensor and open
data. We will also explore combinations of data-driven modeling, applying physical models that exploit
the three-dimensional geometry of
the city, sound type and localization
cues from sensors and 311, and basic
principles of sound propagation. We
expect that through a combination
of techniques from data mining, statistics, and acoustics, as well as our
own expertise developing models
suitable for GPU implementation
using ray-casting queries in the context of computer graphics, we will
be able to create accurate, dynamic,
three-dimensional urban noise maps
in real time.
Citizen science and civic participa-
tion. The role of humans in SONYC is
not limited to annotating sound. In
addition to the fixed sensors located
in various parts of the city, we will be
designing a SONYC mobile platform
aimed at enabling ordinary citizens
to record and annotate sounds in
situ, view existing data contributed
and analyzed by others, and contact
city authorities about noise-related
concerns. A mobile platform will
allow them to leverage slices taken
from this rich dataset to describe
and support these concerns with
evidence as they approach city au-
thorities, regulators, and policymak-
ers. Citizens will not only be more
informed and engaged with their envi-
time using the same tools from oper-
ations research that optimize routes
for delivery trucks and taxis. Worth
noting is that, even though our pre-
liminary study focused on validating
311 complaints, SONYC can be used
to gain insight beyond complaint
data, allowing researchers and city
officials to understand the extent and
type of unreported noise events, iden-
tify biases in complaint behavior, and
accurately measure the level of noise
pollution in the local environment.
Looking Forward
The SONYC project is currently in
the third of five years of its research
and development agenda. Its initial
focus was on developing and deploy-
ing intelligent sensing infrastructure
but has progressively shifted toward
analytics and mitigation in collabo-
ration with city agencies and other
stakeholders. Here are some areas we
intend to address in future work:
Low-power mesh sensor network. To
support deployment of sensors at
significant distances from Wi-Fi or
other communication infrastruc-
ture and at locations lacking ready
access to electrical power, we are de-
veloping a second generation of the
sensor node to be mesh-enabled and
battery/solar powered. Each sensor
node will serve as a router in a low-
power multi-hop wireless network in
the 915MHz band, using FCC-compat-
ible cognitive radio techniques over
relatively long links and energy-effi-
cient multi-channel routing for com-
municating to and from infrastruc-
ture-connected base stations. The
sensor design will further reduce pow-
er consumption for multi-label noise
classification by leveraging heteroge-
neous processors for duty-cycled/
event-driven hierarchical computing.
Specifically, the design of the sensor
node will be based on a low-power sys-
tem-on-chip—the Ineda i7d—for
which we are redesigning “mote-scale”
computation techniques originally
developed for single microcontroller
devices to support heterogeneous
processor-specific operating sys-
tems via hardware virtualization.
Modeling. The combination of
noise data collected by sensors and
d http://inedasystems.com/wearables.php
The dedicated
computing core
opens the possibility
for edge computing,
particularly for
in-situ machine
listening intended
to automatically
and robustly identify
the presence
of common
sound sources.