Socially Informed Services Conflict Governance through Specification, Detection, Resolution and Prevention
Lead PI:
Desheng Zhang
Co-Pi:
Abstract

Smart services are deeply embedded in modern cities aiming to enhance various aspects of citizens' lives, including safety, wellness, and quality of life. Examples include intelligent traffic control and air quality control. Given these services, monitoring a city's safety and performance collectively is crucial, yet also challenging due to many potential conflicts among the number increasing of services deployed. Researchers have accumulated abundant knowledge on how to design these services independently. However, underlying expected or unexpected couplings among services due to complex interactions of social and physical activities are under-explored, which leads to potential service conflicts. Developing approaches of reducing conflicts is essential for ensuring social inclusion and equity of city services because when conflicts occur, their impacts are likely to be concentrated in some sub-communities (e.g., specific geographic locations, specific user groups like patients with respiratory illness, etc.) meaning that some citizens will experience lower quality services than others due to the diversity. Put differently, service conflicts contribute to a digital divide in service provision.

The key intellectual merit of the proposed project is the development of a socially aware conflict management theory and its deployment for smart cities, consisting of 5 sequential components as follows. (1) a novel, template-based requirements specification component/tool that integrates social and technical requirements to formally define a conflict; (2) a social diversity aware detection approach that utilizes machine learning and conflict correlations to detect conflicts in practice; (3) a multi-objective yet equity-centric resolution method that accounts for socially acceptable trade-offs, behavioral models, and control theory to resolve existing conflicts; (4) a participant-based conflict prevention solution that employs Game Theory and Reinforcement Learning in a scalable, decentralize fashion to prevent future conflicts; (5) a social intervention approach based on education outreach and professional training to disseminate the proposed technology to empower the community. The real-world implementation of this theory by working with the city partners in Newark NJ will show its effectiveness and broader impacts on a diverse set of stakeholders of conflict management from city operators, to service providers, to average citizens.

Desheng Zhang
Desheng is an Associate Professor of Computer Science at Rutgers University and a Visiting Professor at MIT. Previously, Desheng was offered the Senseable City Consortium Postdoctoral Fellowship from MIT, and awarded his Ph.D in Computer Science from University of Minnesota. Desheng is interested in bridging Cyber Physical Systems, Cyber Human Systems, Data Science and Machine Learning in Extreme-Scale Data-Intensive Urban Infrastructure from an Interdisciplinary perspective with extensive applications from transportation, to communication, and sharing economy. He is focused on the life cycle of data-driven systems, from mobile sensing, to cross-domain data fusion and prediction, decision making, visual data analytics, system optimization and deployment. He strategically positions his research on Real-Time Interactions of Cross-Domain Urban Platforms and their human users, i.e., on-demand delivery (e.g., UberEat, Doordash, Instacart) transportation (e.g., taxis, buses, trucks, subways, bikes, personal & electric vehicles), telecommunication (e.g., cellphones), payment (e.g., smartcards), social networks (e.g., check-in and app logs). He has been investigating platforms across 8 cities on 3 continents with 100 thousand app users, 500 thousand vehicles, 10 million phones, 16 million smartcards, and 100 million residents involved. His technical contributions have led to more than 100 papers in premium CS venues, e.g., IMWUT/UbiComp, MobiCom, SIGCOMM, KDD, SenSys, NSDI, ICDE, SIGSPATIAL, IPSN, ICCPS, BigData, RTSS, ICDCS. Desheng has been honored with 8 best paper/thesis/poster awards. During his free time, Desheng likes to travel. Here is a road map about cities he has been visited so far in US. During his free time, Desheng also likes to read non-fiction books. Here is a List of Six Recommended Books for 2020.
Performance Period: 10/01/2020 - 09/30/2024
Institution: Rutgers University New Brunswick
Sponsor: National Science Foundation
Award Number: 1952096