cilitate seamless interaction between humans and cyber-infrastructure. Worth emphasizing is that this line of work is fundamentally different from current research on human-in-the-loop cyber-physical systems that often focuses on applications in which control is centralized and fully or mostly automated while usually only a single human is involved (such as in assistive robots and intelligent prosthetics). The synthesis of approaches from social computing, citizen science, and data science to advance integration, management, and control of large and variable numbers of human agents in cyber-physical systems is potentially transformative, addressing a crucial bottleneck for the widespread adoption of similar methods in all kinds of socio-technical systems, including transportation networks, power grids, smart buildings, environmental control, and smart cities.

Finally, SONYC uses New York
City, the largest, densest, noisiest city
in North America, as its test site. The
city has long been at the forefront of
discussions about noise pollution,
has an exemplary noise codeb and,
in 311, the most comprehensive citi-
zen noise-reporting system. Beyond
noise, the city collects vast amounts
of data about everything from public
b http://www.nyc.gov/html/dep/html/noise/
index.shtml
lack temporal dynamics and make
modeling assumptions that often
render them too inaccurate to sup-
port mitigation or action planning. 1
Few of these initiatives involve act-
ing on the sensed or modeled data
to affect noise emissions, and even
fewer have included participation from
local governments. 15

SONYC (Sounds of New York City), our novel solution, as outlined in Figure 1, aims to address these limitations through an integrated cyber-physical systems’ approach to noise pollution.

First, it includes a low-cost, intelligent sensing platform capable of continuous, real-time, accurate, source-specific noise monitoring. It is scalable in terms of coverage and power consumption, does not suffer from the same biases as 311-style reporting, and goes well beyond SPL-based measurements of the acoustic environment. Second, SONYC adds new layers of cutting-edge data-science methods for large-scale noise analysis, including predictive noise modeling in off-net-work locations using spatial statistics and physical modeling, development of interactive 3D visualizations of noise activity across time and space to enable better understanding of noise patterns, and novel information-retrieval tools that exploit the topology of noise events to facilitate search and discovery. And third, it uses this sensing and analysis framework to improve mitigation in two ways—first by enabling optimized, data-driven planning and scheduling of inspections by the local government, thus making it more likely code violations will be detected and enforced; and second, by increasing the flow of information to those in a position to control emissions (such as building and con-struction-site managers, drivers, and neighbors) thus providing credible incentives for self-regulation. Because the system is constantly monitoring and analyzing noise pollution, it generates information that can be used to validate, and iteratively refine, any noise-mitigating strategy.

Consider a scenario in which a sys-
tem integrates information from the
sensor network and 311 to identify a
pattern of after-hours jackhammer
activity around a construction site.
This information triggers targeted in-
spections by the DEP that results in
an inspector issuing a violation. Sta-
tistical analysis can then be used by
researchers or city officials to validate
whether the action is short-lived in
time or whether its effect propagates
to neighboring construction sites or
distant ones by the same company. By
systematically monitoring interven-
tions, inspectors can understand how
often penalties need to be issued be-
fore the effect becomes long term. The
overarching goal is to understand how
to minimize the cost of interventions
while maximizing noise mitigation,
a classic resource-allocation prob-
lem that motivates much research in
smart-cities initiatives.

All this is made possible by formulating our solution in terms of a cyber-physical system. However, unlike most cyber-physical systems covered in the literature, the distributed and decentralized nature of the noise-pollution problem requires multiple socioeconomic incentives (such as fines and peer comparisons) to exercise indirect control over tens of thousands of subsystems contributing noise emissions. It also calls for developing and implementating a set of novel mechanisms for integrating humans in the cyber-physical system loop at scale and at multiple levels of the system’s management hierarchy, including extensive use of human-computer interaction (HCI) research in, say, citizen science and data visualization, to fa-

Figure 2. Acoustic sensing unit deployed on a New York City street.