Infants and toddlers with developmental disabilities or delays use early intervention (EI) for rehabilitation services. Yet, EI quality is compromised for racially and ethnically diverse and socially disadvantaged families. A key lever to improve EI quality is family-centered care, an evidence-based approach that is grounded in family engagement for shared decision-making. This project is motivated by the need to give families a smart and connected option for engaging in the design of the EI service plan for their child. This effort will develop and evaluate an upgraded Participation and Environment Measure (PEM), an evidence-based electronic option for directing equitable family-centered EI service design. PEM upgrades will (a) increase content relevance for racially and ethnically diverse families, and (b) leverage modern artificial intelligence solutions to personalize the PEM user experience to a broader range of EI enrolled families. This upgraded PEM electronic option will be evaluated in a population of racially and ethnically diverse EI families, to assess for its capacity to improve EI quality and to appraise supports and barriers to its longer-term implementation within the broader EI service system. This project builds evidence for the first customized, culturally relevant electronic option to direct family-centered care during EI service design. The approaches and technologies developed may be applicable to similar service contexts. Additionally, this project increases opportunities for conducting interdisciplinary research at the intersection of computer science and rehabilitation science, building interprofessional capacity for research engagement among EI service providers and students training for pediatric rehabilitation careers, and sponsoring students from historically underrepresented groups in diverse research labs that value inclusive excellence.

This proposal develops key innovations to family-centered EI in two ways. First, for the PEM electronic option, the project will (a) increase content relevance for racially and ethnically diverse families, and (b) personalize the PEM user experience to a broader range of EI enrolled families. For the former, the project will establish cultural equivalencies of the original PEM assessment and critically examine its intervention content to ensure that families can voice concerns about racial climate and collect and share goal attainment strategies using community-preferred communication channels. For the latter, the team will incorporate an adaptive conversational agent into the PEM intervention to improve caregiver navigation and guidance, and we will develop methods to automatically customize its strategy exchange feature to individual caregiver needs. These innovations will result in fundamental advances to natural language processing research through the investigation of adaptive dialogue policies for task-oriented or mixed-initiative dialogue systems, generalized dialogue act schema, and lexicon-informed meaning representations. We will evaluate the upgraded PEM electronic option with racially and ethnically diverse and socially disadvantaged EI enrolled families, to assess for its capacity to improve caregiver and provider perceptions of family-centered EI service quality, improve parent engagement in EI service plan implementation, and increase the availability and relevance of participation-focused EI service plans. We will engage EI stakeholders to appraise supports and barriers to its longer-term implementation in EI. These advances will yield evidence for a customized, culturally-relevant electronic option to foster family-centered care in EI.

Communities are adversely affected by social harm events such as crime, traffic crashes, medical emergencies, and drug usages. This proposal aims to develop algorithms and software systems for the collection, analysis, and dynamic prediction of social harm events to facilitate appropriate government interventions to improve the quality of life in communities. The project has a significant community engagement component and software developed through the research will be used by the Indianapolis Metropolitan Police Department (IMPD), Indianapolis Emergency Medical Services (EMS), National Alliance of Mental Illness, the Indiana prosecutor's office, and individual citizens for sharing of social harm analytics and collaboration in social harm intervention. This objective will be achieved by: i) creating software systems for cross-agency social harm data integration, ii) developing mathematical models for capturing social harm event dynamics along with public trust and grievance towards police, and iii) conducting a field trial of the developed software system in Indianapolis. The methods developed in the project will also be applicable to other smart and connected communities across the country and could be used for data analytics integration and allocation of resources across government departments. Graduate students from both social science and computing disciplines will be trained in interdisciplinary research methods that span criminal justice, statistics, and computer science. Research interests in the domain of algorithms for heterogeneous data in smart cities will be encouraged through a workshop hosted by the investigators at Indiana University-Purdue University Indianapolis (IUPUI).

Social harm data resides within a disconnected set of community databases and current methodologies for modeling social harm neglect space-time dynamics altogether or focus on a small related subset of event types. Furthermore, interventions are designated in spatial locations for several weeks or months at a time, failing to account for the daily changes in risk of social harm events where crime, traffic crashes, and medical emergencies cluster in different times and locations in communities. Current policing interventions that focus on spatial risk (i.e., hotspots) are often too narrow and seek only to optimize crime reductions. In order to address some of these limitations, this project will develop: i) software systems for heterogeneous social harm data integration, ii) new marked point processes for modeling heterogeneous social harm event dynamics including trust and grievances towards police, iii) optimal control methods for space-time point processes that are lacking in current point process research, and iv) near real time software-human systems for deploying hourly interventions to dynamically changing risk. During phases one and two, the project team will work collaboratively with IMPD's community policing unit and leverage this unit's relationships with local neighborhood watch, faith-based, juvenile diversion, and volunteer groups that are predominantly comprised of minority community members serving largely minority neighborhoods. This collaboration will facilitate broad community buy-in for phase three and enable communication with and recruitment of community groups disproportionately exposed to social harm risk. The last phase of the project will include a randomized controlled trial of heterogeneous data driven policing in Indianapolis in collaboration with IMPD, Indianapolis EMS, Indianapolis Mayor's Office, National Alliance of Mental Illness, Marion County Prosecutor's Office, the Indy Public Safety Foundation, and the general public who will be encouraged to download a version of the application through a press release prior to the trial launch. In the trial, the extent to which police in partnership with community stakeholders can respond to dynamic, heterogeneous social harm hotspots will be investigated and the impact across four types of social harm (crime, traffic crashes, EMS calls for service, and community trust in police within high risk communities) will be measured.

This activity is in response to the NSF Dear Colleague Letter: Supporting Transition of Research into Cities through the US ASEAN (Association of Southeast Asian Nations Cities) Smart Cities Partnership (NSF 20-024), in collaboration with the US Department of State. This research seeks to integrate innovations in smart and connected communities with creative gardens within the city alleys of Makassar City, Indonesia via a synergistic collaboration between US and Indonesian teams and a close partnership with Makassar City. Makassar is striving to become a livable world class city for a fast-growing, diverse population of 1.7 million people. The ongoing “Garden Alley” project in the city aims to improve the “livability” of the city, measured by factors including air-quality, heat index, food security, and social interactions. To date, Makassar has implemented 40 gardens within 15 of the city’s sub-districts, covering a sizable portion of the city’s alleys. The goal of this research is to catalyze the transformation of Makassar City’s garden alleys into smart environments by deploying a sensor network at representative green allies and conventional allies to collect data related to air quality, microclimates, and other factors, to analyze the heterogeneous data using machine learning techniques, and to then share the data and its insights with city representatives and specific communities within the city.

This transformative research will provide the foundational science and knowledge that are needed to design, optimize, and deploy S&CC technologies within the ASEAN region and beyond. This interdisciplinary research will yield several major innovations: 1) New low-cost, durable, and mobile sensor networks will be designed for air quality and microclimate monitoring in the hot and humid climate in southeast Asian cities. 2) Suitable machine learning techniques will be employed to exploit the multi-dimensional and heterogeneous data collected from both existing infrastructures and new mobile test platforms in Makassar and create intelligent spatio-temporal operational maps of Makassar’s alleys that can be used for various design, planning, and operational decisions by the city. 3) Data-driven city-scale smart operating schemes involving feedback loops will be explored through close engagement with the Indonesian partners. The developed solutions will be highly dynamic yet robust and have the potential to be scaled, as well as transferred to other cities. Additionally, this project will initiate a new collaboration between the US and Indonesia, improving the quality of life in an emerging southeast Asian city, but with potentially broad applicability, and provide a broad range of dissemination activities, involvement of students in international activities, as well as active engagement with local communities and researchers in Indonesia.
 

Uncertainties during global pandemics, such as the novel Coronavirus disease (COVID-19), can generate fear and anxiety, resulting in panic-buying and overreactive consumer behavior. Information from a multitude of sources may further exacerbate the situation, leading to shortages of critical disease prevention products for emergency managers and those in dire need. The consumer response may also vary based on population demographics and community interactions. This project aims to understand the relationships between consumer panic-buying, reports on infected cases, and local population demographics in a large and densely populated urban epicenter of the virus. Fundamental understanding of community factors and the role of reports on consumer behavior in emergencies will enable effective and timely decisions on resource planning and disbursement, preventing unexpected shortages of critical supplies in large and diverse urban centers. In addition, the quantitative methodologies developed in this project bridge the disciplines of engineering, computer science, social and health science, creating a new interdisciplinary paradigm that provides a holistic view towards emergency preparedness and disaster management in urban centers.

The main focus of this RAPID project is to develop a multi-network framework that captures the linkages and inter-dependencies between networks that govern information spreading, panic spreading, and disease spreading in urban populations. Fundamental understanding of the relationships between various factors such as consumer buying behavior, socio-economic community characteristics, and the extent of available health information enables the assessment of potential outcomes such as shortages of critical disease prevention supplies. Data and crowdsourced information from the COVID-19 experience of selected NYC neighborhoods is used as a case study for validation studies. An accurate understanding of the multi-faceted consumer behavior enables decision analytics for effective planning and targeted disbursement of critical supplies for mitigating the effects of panic-buying. The identification of underlying complex and interdependent network structures provides insights into the design of equitable and effective strategies for resource planning and allocation to tackle the vicious panic cycle in emergencies, thus promoting urban resilience.
 

This goal of this project is to optimize processes for remote delivery of meals to persons in need. The COVID-19 pandemic has fundamentally disrupted processes of food delivery to economically depressed and vulnerable segments of the US population. With the closing of schools and the advent of social distancing practices, over 13 million low-income students who have historically relied on their school to provide daily meals are now without important nutritional support, and centralized school summer meal distribution programs are no longer viable. Similarly, low-income adults and seniors that depend on centralized distribution of meals at shelters and food banks are now being forced to cope with virus mitigation procedures that severely limit their access. Both short and long term solutions to food security for all in this new normal depend on greater reliance on remote food delivery, and although vehicle routing and pickup/delivery problems have been studied for close to 50 years, the constraints imposed by contemporary public health and social distancing concerns present new optimization challenges. This research will contribute new problem formulations and solutions to these important classes of remote food delivery problems, and through existing relationships with the Allegheny County Department of Human Services, Southwestern Pennsylvania United Way, Allies for Children and the Greater Pittsburgh Food Bank, the project will apply research results to inform their ongoing pilot food delivery efforts. More broadly, these results will stimulate future research on these problems and influence remote food delivery problems nationwide.

To realize these results and impact, this project aims to develop new algorithms and heuristics that address the unique constraints and objectives presented by these geographically-dispersed food delivery problems, to provide a theoretical basis for more efficient operational practice. With respect to school bus student meal delivery, algorithms and heuristics for solving several problems will be developed and analyzed. First, the project will consider the coupled problem of assigning stops to students requiring meals and generating efficient routes to accommodate these students within a global meal time window, while enforcing social distance constraints on number of students that can be assigned to any one bus stop. Second, the research will investigate an extended formulation that additionally allows the use of smaller passenger vehicles or vans, to better service students that have difficult access to bus stops and/or long walk times. To ensure relevance, the project will utilize demand and bus route data from selected school districts in Allegheny County, PA to evaluate performance. Finally, with respect to remote distribution of food to low-income seniors, the algorithms and heuristics developed for student meal delivery will be extended and adapted to this more capacity constrained setting, where food must be moved exclusively in smaller volunteer passenger vehicles. Data obtained from the Greater Food Bank of Pittsburgh will be used to evaluate these extended research results. All data sets used and solutions results obtained will be made available to stimulate future research in this area.
 

The spread of COVID-19 has broad implications both for human health and economies around the world. This Smart and Connected Communities project will monitor the spread of COVID-19 by collecting real-time information on active COVID-19 cases, understand how transportation has driven the spread of the virus, and quantify how travel restrictions have limited the spread of the virus. The data collection will gather and store real-time information on the spread of COVID-19 and a timeline of travel restrictions for three sets of communities. This data will then be employed to model how the virus propagates between communities via transportation using various network-dependent epidemic models. Finally, using the collected data and the calibrated epidemic models, analysis will be conducted to understand how effective the different modifications of the transportation network structure, such as travel restrictions in each set of communities, are at slowing the spread of COVID-19, while factoring in the economic effects. Understanding how the transportation network between communities acts as a propagator of the virus, and how control actions taken by local and national governments to limit or block travel within and between regions slow the spread of the virus will provide the framework for the development of mitigation strategies for the COVID-19 pandemic, as well as other possible outbreaks in the future. These strategies will limit the loss of human life and reduce the economic impacts of the virus. The methods developed as a result of this work will also be beneficial in the future for battling subsequent outbreaks.

This project will apply network modeling techniques to understand how different control actions on the transportation network influence the spread of the virus between communities. The understanding gained herein will inform decision makers during this and future outbreaks as to which transportation-related mitigation strategies are best to use in different situations and at what point in the outbreak to use them in order to minimize both the spread of virus as well as the economic impact. The research will draw on and contribute to wide-ranging and fundamental results in statistical data analysis, mathematical modeling and analysis of epidemic processes, mathematical programming, network analysis, and control theory. The resulting study of problems will contribute to advancement of mathematical modeling and analysis of infectious diseases, and mitigation optimization algorithms and heuristics.
 

The vision of a smart city is underpinned by its ability to collect, manage, and use data. However, data access remains a fundamental challenge across city agencies, public institutions, and community stakeholders. This project is championing a paradigm shift in data sharing by implementing a new data access framework that allows users to share access to data in-situ instead of sending copies of data around. This project builds on the new data access paradigm to deploy a city Data Access Network (City-DAN) to support city managers get timely access to important data for fast decision and response. City-DAN is piloted first in Ho Chi Minh City, Vietnam and then scaled to other ASEAN cities. This activity is in response to NSF Dear Colleague Letter Supporting Transition of Research into Cities through the US ASEAN ((Association of Southeast Asian Nations Cities) Smart Cities Partnership in collaboration with NSF and the US State Department. The research team (University of Virginia) is working closely with stakeholders in Ho Chi Minh City including city managers, departments, and community organizers as well as Vietnam National University – International University to transition technology into practice.

The proposed distributed, peer-to-peer data access framework represents an ambitious vision of the next generation data ecosystem. This project establishes a foundational data platform to underpin smart cities by addressing issues of data integrity, provenance, control, and timely access. This project takes advantage of the unique deployment opportunity to pursue a vibrant research agenda on grid computing. Specific research areas include advanced cyber infrastructure, cybersecurity, networking, and persistent identifiers. This project will especially focus on identity and access management (IAM) in the context of unreliable infrastructure and weak level-of-assurance (identify proofing) baselines. The project will examine new approaches for enhancing reliability while balancing with transparency and QoS. Lessons learned also can be adopted to advance the smart and connected community research community in the US and other countries.
 

This activity is in response to NSF Dear Colleague Letter Supporting Transition of Research into Cities through the US ASEAN (Association of Southeast Asian Nations Cities) Smart Cities Partnership in collaboration with NSF and the US State Department. Ho Chi Minh City (HCMC), an ASEAN city in Vietnam, is well-known for its traffic congestion and high density of vehicles, cars, buses, trucks, and a swarm of motorbikes (7.3 million motorbikes for more than 8.4 million residents) that overwhelm city streets. Large-scale development projects have exacerbated urban conditions, making traffic congestion more severe. Additionally, traffic congestion is one of the leading contributors to noise and dust pollution in the city. Altogether, traffic congestion poses major barriers to urban quality of life, but the solutions are complex. There are two main problems with traffic in HCMC. First, HCMC, like other dense urban areas, needs significant financial and technical resources to solve its traffic and infrastructure problems. Second, given that traffic monitoring is carried out by a limited number of staff who watch traffic activities from thousands of camera feeds on multiple screens, there are limits to the number and effectiveness of responses that personnel are able to offer in response to real-time traffic problems.

The goal of this project is to use visual crowd AI sensing for the HCMC planning simulator. The project will make use of the city camera system (crowd-AI sensing) for traffic analysis in real-time. It seeks to detect “anomaly events” such as traffic violations, traffic jams, and accidents, with reduced intervention from monitoring staff, allowing staff, in turn, to better respond to traffic problems as they arise. A city planning simulator will be developed upon the analyzed traffic data. The simulator will be used to support metropolitan transportation planning. Project findings will not only address specific urban challenges and the innovative technical solutions needed to solve them in HCMC, but also will provide models use in other contexts, including U.S. cities where traffic, congestion, and urban infrastructure challenges can benefit from AI.

The project will be validated by professionals in HCMC who can evaluate its effectiveness for detecting anomaly events with reduced human observation, who are better able to respond to traffic problems as a result of implementing aspects of the project, and who can make use of the project data for traffic analysis.