DATA MINING FOR ITS APPLICATIONS

Within the software industry the field of "Data Mining" is emerging as the next logical step in the progression for querying data warehouses beyond online analytical processing (OLAP). In contrast to OLAP, the goal of which is to inquire about known relationships among data, the objective of data mining is to seek out relationships among data that have heretofore remained undiscovered. The potential value of uncovering such previously unknown relationships are manifold, especially by those involved in planning decisions. The discovery of relationships among data may reveal, for example, a correlation among certain events and conditions. Knowledge of these relationships may then be used to gain insights regarding the conditions under which certain events occur, and to provide information for modifying those conditions, if it is desired to alter the likelihood of those events occurring. Data mining is, therefore, a method that can be used by planners that have massive amounts of heterogeneous raw data upon which they must base decision processes, but for which it is difficult to gain insight. A specific domain for which data mining is appropriate is Advanced Traffic Management Systems (ATMSs) since they generate large quantities of traffic data. This data typically includes lane speed, occupancy, incident, message sign, and other types of information. The data collected can provide a transportation planner and traffic engineer with significant insight into traffic patterns because the data is collected often and the data is time stamped. Traffic Engineers have historically used rubber tubes to count traffic. These "tubes" only provide the number of cars over a fixed period of time (typically measured in days). ATMS systems also provide much more detail (e.g. data at the lane level and in increments as small as 20 seconds). The amount of data being collected is enormous, thereby making it difficult for a typical Traffic Engineer to process, understand, and gain useful insights. For example, each day San Antonio TransGuide generates more than 30 Megabytes of data when recorded at 5 minute intervals, and it is estimated that the Houston TranStar system could generate more than 3 Gigabytes of data daily. This paper describes a research project that Southwest Research Institute (SwRI) has undertaken in order to explore the application of Data Mining to ITS applications. The goals of mining ITS data are to: (1) Investigate methods for mining ITS data for the purpose of discovering interesting relationships among data that can be used for planning in ITS domains; (2) Investigate methods for visualizing the relationships among different types of ITS data that will provide ITS planners with insights into these relationships; (3) Apply these methods to actual ITS data acquired from, for example, the San Antonio TransGuide system.