Program

Visible to the public 

The full program is available now.

07:00 - 08:00 Continental Breakfast

07:00 - 08:30 Registration

Session 1

08:45 - 9:00 Opening Remarks

09:00 - 09:30 "Keynote: Smart and Connected Communities": David Corman

09:30 - 10:00 "Global Cities Team Challenge: Experience and Lessons" : Sokwoo Rhee

10:00 - 10:30 Coffee Break

Session 2 (Chair Sokwoo Rhee, NIST)

10:30 - 11:00 Toward Urban Vehicle Mobility Modeling in Japan

11:00 - 11:30 ASC: Actuation System for City-wide Crowdsensing With Ride-sharing Vehicular Platform

11:30 - 12:00 Towards Demand-Oriented Flexible Rerouting of Public Transit Under Uncertainty

12:00 - 13:30 Lunch

Session 3 (Chair Abhishek Dubey, Vanderbilt)

13:30-14:00 Studying the Effects of Weather and Roadway Geometrics on Daily Accident Occurrence using a Multilayer Perceptron Model

14:00-14:30 AutoVAPS: an IoT-Enabled Public Safety Service on Vehicles

14:30-15:00 Spatiotemporal Scenario Data-Driven Decision For the Path Planning of Multiple UASs

15:00 - 15:30 Coffee Break

Session 4 (Chair Yan Wan, UTA)

15:30-1600 A Testbed for a Smart Building: Design and Implementation

1600-16:30 Principles for Designed-In Security and Privacy for Smart Cities

16:30-17:00 Data Integration Platform for Smart and Connected Cities

The paper abstracts are available below.

A Testbed for a Smart Building: Design and Implementation
========================================================================

Authors
-------
1. Roja Eini (Virginia Commonwealth University)
2. Lauren Linkous (Virginia Commonwealth University)
3. Nasibeh Zohrabi (Virginia Commonwealth University)
4. Sherif Abdelwahed (Virginia Commonwealth University)

Abstract
--------
This paper addresses the design and implementation of a smart building prototype. The implementation utilizes Internet of Things (IoT) solutions to collect, analyze, and manage data from building systems in a smart city environment. The developed smart building prototype is capable of real-time interactions with the residents. The main objective is to adapt the building settings to the residents' needs and provide the maximum comfort level with minimum operational costs. For this purpose, building parameters are collected via a set of sensors and transferred to a database in real-time, which can be accessed, analyzed and visualized. Environment properties such as temperature, light, humidity, audio, video, surveillance, and access status are managed through a model-based controller. The developed testbed and control scheme are generic and modular. The prototype can also be utilized for testing cyber-physical systems' monitoring and management technologies.


Spatiotemporal Scenario Data-Driven Decision For the Path Planning of Multiple UASs
================================================================================================

Authors
-------
1. Chenyuan He (University of Texas at Arlington)
2. Yan Wan (University of Texas at Arlington)
3. Junfei Xie (Texas A&M University at Corpus Christi)

Abstract
--------
Modern systems operate in spaiotemporally evolving environments, and similar spatiotemporal scenarios are likely to be tied with similar decision solutions. This paper develops a spatiotemporal scenario data-driven decision solution for the path planning of multiple unmanned aircraft systems (UASs) in wind fields. The solution utilities offline operations, online operations and sptaiotemporal scenario data queries to provide an efficient path planning decision for multiple UASs. The solution features the use of similarity between spatiotemporal scenarios to retrieve offline decisions as the initial solution for online fine tuning, which significantly shortens the online decision time. A fast query algorithm that exploits the correlation of spatiotemporal scenarios is utilized in the decision framework to quickly retrieve the best offline decisions. The solution is demonstrated using
simulation studies, and can be utilized in other decision applications where spaiotemporal environments play a crucial role in the decision process and the allowed decision time window is short.


Toward Urban Vehicle Mobility Modeling in Japan
===============================================================

Author
------
Hirozumi Yamaguchi (Osaka University)

Abstract
--------
Vehicle mobility data is significant for many types of smart city applications such as smart transportation, logistics, urban planning, and carbon dioxide emissions reduction. Particularly, microscopic mobility data, in which the location, direction, and speed of each vehicle are included, is promising for cyber-physical systems services and applications. Nevertheless, there are only limited datasets available to the public due to the difficulty of collecting the data from each real vehicle due to cost, privacy, and many other reasons. To address the issue, this position paper introduces our challenge of generating microscopic mobility data using traffic simulator as well as publicly available statistical and measured traffic data in Japan. We hope this approach contributes to those researchers and service designers to move beyond the limitation that comes from the microscopic mobility dataset unavailability.


ASC: Actuation System for City-wide Crowdsensing With Ride-sharing Vehicular Platform
================================================================================================

Authors
-------
1. Xinlei Chen (Carnegie Mellon University)
2. Susu Xu (Carnegie Mellon University)
3. Haohao Fu (University of California, Berkeley)
4. Carlee Joe-Wong (Carnegie Mellon University)
5. Lin Zhang (Tsinghua-UC Berkeley Shenzhen Institute)
6. Hae Young Noh (Carnegie Mellon University)
7. Pei Zhang (Carnegie Mellon University)

Abstract
--------
Vehicular mobile crowdsensing (MCS) enables a lot of smart city applications, such as smart transportation, environmental monitoring etc. Taxis provide a good platform for MCS due to their long operational time and city-scale coverage. However, taxis, as a non-dedicated sensing platform, does not guarantee high sensing coverage quality (large and balanced). This paper presents ASC, a system that actuates vehicular taxis fleets for optimal sensing coverage quality while matching ride requests with taxis. We propose a near-optimal algorithm that integrates 1) a mobility prediction model that guides the selection of taxis to actuate and 2) a ride request prediction model to help match ride request with taxis, lower incentive cost and improve taxi drivers' motivation. Extensive simulation and real-world experiments in a testbed with 230 actuated taxis show that our ASC can achieve up to $40\%$ improvement in sensing coverage quality improvement and up to $20\%$ better ride request matching rate than baselines approaches. In addition, to achieve a similar level of sensing coverage quality, our ASC only requires $10\%$ of the baseline budget.


Principles for Designed-In Security and Privacy for Smart Cities
================================================================================

Authors
-------
1. Corey Dickens (Dakota Consulting, Inc.)
2. Paul Boynton (NIST)
3. Sokwoo Rhee (NIST)

Abstract
--------
This paper presents the design and implementation of a process for an exploratory study that identifies a set of principles for designed-in security and privacy for smart city projects from among Global City Teams Challenge (GCTC) - Smart and Secure Cities and Communities Challenge (SC3) participants. The study was conducted based on information from the National Institute of Standards and Technology (NIST) GCTC Action Clusters database and interactions with the project teams. A research process was developed and implemented, comprising the following three steps:

(1) Investigate project descriptions created by the project leads on the NIST GCTC database and other public sources;
(2) Gather additional input from volunteer GCTC collaborators; and
(3) Identify a set of governing principles commonly shared by examples of GCTC projects.

Based on the outcomes of this process, a set of common principles has been identified that enable designed-in security and privacy considerations among the projects: specific technology usage, implementation of a cybersecurity management process and framework, and cybersecurity expertise and public-private partnerships. Characteristics of planning and implementation of security and privacy considerations from four example GCTC projects are described and analyzed in detail to illustrate the process.


Data Integration Platform for Smart and Connected Cities
========================================================================

Authors
-------
1. Austin Harris (University of Tennessee at Chattanooga)
2. Mina Sartipi (University of Tennessee at Chattanooga)

Abstract
--------
By exploiting IoT technologies and smart sensors, smart and connected cities acquire massive amounts of urban data critical for various urban operations, applications, and services. Data allows cities to identify the underlying urban rhythm in real time and understand the history of the urban transformation. Cities can use this data to determine the priorities and challenges that once addressed can improve the citizen's quality of life. Implementing reliable infrastructure to ingest data produced within these cities creates many challenges such as scalability, reliability, availability, and fault-tolerance. Using these challenges as design considerations, we propose a data integration architecture design that has been implemented on our urban testbed and is currently in use. Our contributions will accelerate further urban development initiatives by providing a integration platform that can easily be deployed within other testbeds.


Towards Demand-Oriented Flexible Rerouting of Public Transit Under Uncertainty
==============================================================================================

Authors
-------
1. Saideep Nannapaneni (Wichita State University)
2. Abhishek Dubey (Vanderbilt University)

Abstract
--------
This paper proposes a flexible rerouting strategy for the public transit to accommodate the spatio-temporal variation in the travel demand. Transit routes are typically static in nature, i.e., the buses serve well-defined routes; this results in people living in away from the bus routes choose alternate transit modes such as private automotive vehicles resulting in ever-increasing traffic congestion. In the flex-transit mode, we reroute the buses to accommodate high travel demand areas away from the static routes considering its spatio-temporal variation. We perform clustering to identify several flex stops; these are stops not on the static routes, but with high travel demand around them. We divide the bus stops on the static routes into critical and non-critical bus stops; critical bus stops refer to transfer points, where people change bus routes to reach their destinations. In the existing static scheduling process, some slack time is provided at the end of each trip to account for any travel delays. Thus, the additional travel time incurred due to taking flexible routes is constrained to be less than the available slack time. We use the percent increase in travel demand to analyze the effectiveness of the rerouting process. The proposed methodology is demonstrated using real-world travel data for Route 7 operated by the Nashville Metropolitan Transit Authority (MTA).


AutoVAPS: an IoT-Enabled Public Safety Service on Vehicles
==========================================================================

Authors
-------
1. Liangkai Liu (Wayne State University)
2. Xingzhou Zhang (Wayne State University)
3. Qingyang Zhang (Anhui University)
4. Andrew Weinert (MIT Lincoln Laboratory)
5. Yifan Wang (Wayne State University)
6. Weisong Shi (Wayne State University)

Abstract
--------
With the rapid development of Internet-of-Things, sensors and devices are connected enabling a variety of applications. One of the most attractive applications is Video Analysis for Public Safety (VAPS), which has got massive attention from both research community and industry. However, there are still challenges in the system design and implementation of the VAPS service, especially in the mobile environment. For example, law enforcement officers are equipped with body camera when they are on duty, how to connect body-worn cameras with the law enforcement vehicle and enable the law enforcement vehicle to perform near real-time video analysis for the officer are still open questions. Inspired by the promising edge computing technology, we propose IoT-Enabled public safety services called AutoVAPS which can integrate body-worn cameras and other sensors on the vehicle for public safety. In AutoVAPS, we propose a reference architecture that including the data layer for data management, the model layer for edge intelligence, and the access layer for privacy-preserving data sharing and access. Object detection is implemented as a case study of AutoVAPS. Early results illustrated the applicability and challenges of AutoVAPS.


Studying the Effects of Weather and Roadway Geometrics on Daily Accident Occurrence using a Multilayer Perceptron Model
================================================================================================

Authors
-------
1. Jeremiah Roland (University of Tennessee at Chattanooga)
2. Peter Way (University of Tennessee at Chattanooga)
3. Mina Sartipi (University of Tennessee at Chattanooga)

Abstract
--------
One of the most common, yet dangerous, events that people face each day is driving. From unpredictable weather to hazardous roadways, there is a seemingly endless number of factors at play that can lead to vehicular accidents. Therefore, attempting to predict these accidents is a timely topic in today's research spectrum. The data used in this research consists of historical accident records from Hamilton County, Tennessee beginning in 2016 and continues to be updated daily, as well as the associated weather occurrences and roadway geometrics. To enhance heterogeneity a procedure was performed that generated non-accident traffic data based on our actual traffic accident data. This procedure is called negative sampling. These different data sets were combined and placed through a Multilayer Perceptron (MLP) machine learning model. The end results displayed a high collective correlation between accident occurrence and the various features considered in our proposed model, allowing us to predict with 77.5% accuracy where and when an accident will occur.