Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
6 The term Big Data represents a fundamental change in what data is collected and how it is collected, analyzed, and used to uncover trends and relationships. The ability to merge multiple, diverse, and comprehensive datasets and then mine the data to uncover or derive useful information on heretofore unknown or unanticipated trends and relationships could provide significant opportunities to advance the state of the practice in TIM policies, strate- gies, practices, and resource management. For example Big Data could: â¢ Include non-traditional datasets to allow for the establishment of additional TIM perfor- mance measures, as well as the identification of TIM performance trends and the factors that impact performance; â¢ Bolster context-aware decision-making, such as aiding in resource allocation, on-scene actions, and scene management; â¢ Move TIM beyond intuitive operations, enabling prediction of when, where, and under what conditions problems are most likely to occur; and â¢ Help agencies build a more compelling and clear business case for their TIM programs, a fundamental step in securing continuous funding and supporting the long-term health and viability of these critical programs. Big data involves a large volume of data, but it is not just about the volume of data. Four other âVsâ of Big Data also are important: â¢ Velocity refers to the speed/frequency at which the data is available. â¢ Variety refers to the diversity of the datasets available. â¢ Veracity refers to the legitimacy or trustworthiness of the data. â¢ Value refers to the worth of the data to its users. Above all, Big Data must provide information that is of value to its users. One way to con- ceptualize the value of data, including Big Data, is through a value chain. Figure 1-1 illustrates a straightforward Big Data value chain from a presentation at a 2014 data symposium hosted by the Florida Department of Transportation (Florida DOT) (Kanniyappan and McQueen 2014). The figure represents the cascading benefits that can be derived from Big Data, ranging from data analysis to insight gains to better decision-making and, finally, to better design, planning, and operations. In their presentation, Kanniyappan and McQueen stated that, âBig Data may be as important to business and society as the Internet since more data leads to more accurate analysis.â Not all the Vs need to be present for data to qualify as Big Data. In fact, for TIM, the most important of the Vs may be the variety of the available datasets. Given the multi-disciplinary nature of TIM and the wide range of responder organizations and rolesânot to mention the roadway, environmental, and human factors involved in traffic incidentsâhaving access to C H A P T E R 1 Introduction
Introduction 7 diverse, associated datasets could be key in identifying ways to improve TIM. Many opportuni- ties exist to improve TIM using Big Data, and numerous data sources exist from which to draw. Traditional data sources for measuring and assessing TIM performance are transportation datasets like those generated at traffic management centers (TMCs) and by safety service patrol (SSP) programs. Some datasets generated by law enforcement, such as those associated with computer-aided dispatch (CAD) systems and crash reports, also are used to examine TIM per- formance. Yet-to-be-tapped data sources offer many additional opportunities to gain insights into where and how TIM could be improved, as well as when, where, and under what conditions traffic incidents are likely to occur so that the appropriate response can be pre-staged and/or immediately put into place. Moreover, leveraging Big Data that is associated with the connected and automated vehicle future may enable TIM operations that expedite incident detection and response while improving on-scene safety. Central to the concept of leveraging Big Data is the promise that analytics can illuminate critical actions that may result in significant improvements. 1.1 Objective The objectives of NCHRP Project 17-75 were to conduct research to illuminate Big Data concepts, applications, and analyses; describe current and emerging sources of data that could improve TIM; describe potential opportunities for TIM agencies to leverage Big Data; identify potential challenges associated with the use of Big Data; and develop guidelines to help advance the state of the practice for TIM agencies. 1.2 Overview of Research and Organization of Report To meet the objectives of this research project, an approach was laid out that included the following activities: â¢ Assess research, practices, and innovative approaches through a review of the literature. â¢ Organize and conduct a responder workshop to inform the development of an incident response and clearance ontology, and to identify areas in which improvements to TIM are needed. â¢ Identify Big Data opportunities for TIM based on the current state of the practice and responder needs. â¢ Conduct a comprehensive assessment of a wide variety of TIM-relevant data sources to determine the openness, maturity, and readiness for Big Data applications. â¢ Create an incident response and clearance ontology. â¢ Develop guidelines that help to advance TIM agencies toward the application of Big Data. Source: Kanniyappan and McQueen (2014) Figure 1-1. The Big Data value chain.
8 Leveraging Big Data to Improve Traffic Incident Management This report describes the research approach in more detail and presents the findings asso- ciated with each of the research activities. The remaining chapters of the report are organized as follows: â¢ Chapter 2: State of the Practice of TIM: This chapter provides a high-level overview of the state of the practice in TIM procedures, training, data collection, and the use of data for measuring and monitoring TIM performance, and makes the business case for TIM. Examples are provided for agencies/organizations that are leaders in using data to assess and improve TIM. â¢ Chapter 3: State of the Practice of Big Data: This chapter provides a brief introduction to and history of Big Data, addresses the state of the practice, and provides a cross-industry overview of Big Data, including storage and analytics tools. â¢ Chapter 4: Big Data and TIM: This chapter explores Big Data opportunities for TIM by presenting specific examples that stem from applications representing the current state of the practice in TIM data collection and analysis. Each example begins with a summary of the traditional data collection and analysis approach. The summary is followed by presentation of a potential Big Data approach/opportunity to address the same problem or research question. Each example concludes with a discussion that contrasts the differing data needs and analytical approaches used in the traditional and Big Data approaches and highlights the possibilities and potential benefits afforded by Big Data. â¢ Chapter 5: Assessment of Data Sources for TIM: This chapter presents the approach and findings from a comprehensive assessment of 31 data sources in six categorized data domains that are relevant to TIM. The findings include a description of each data source, its potential application for TIM, the costs of accessing the data, and challenges associated with the data sources. The data sources also are assessed using two data maturity models, including an overall assessment of data readiness and openness. Detailed data assessment tables for each data source are presented in Appendix A. â¢ Chapter 6: Big Data Guidelines for TIM Agencies: This chapter presents the Big Data pyramid, a convenient visual guide for the application of data science. Based on the find- ings from this research, guidelines also are provided to support moving the TIM community (and state transportation agencies in general) toward the application of Big Data. â¢ Chapter 7: Summary and Next Steps: This chapter summarizes the findings of the research, sets forth potential next steps for the research findings, and addresses recommendations, needs, and priorities for additional related research. â¢ Appendix A: Data Source Assessment Tables: This appendix contains the detailed data assessment tables for 31 data sources, each including information on the organization that collects, maintains, and owns the data; how the data is collected; data structure; data size; data storage and management; data accessibility; data sensitivity; data openness; data challenges; and data costs. â¢ Appendix B: Incident Response and Clearance Ontology (IRCO): This appendix explains the concept of an ontology, and the value in creating ontologies. The approach and steps taken to develop an incident response and clearance ontology (IRCO) are established for application to TIM.