11.3 SEQUENTIAL PATTERN MINING-BASED APPROACHES

Sequential pattern mining [2, 25, 56] is an important topic in data mining and is often applied to basket data analysis and Web usage analysis. There are some interesting applications of sequential data mining to moving object databases. First, we briefly explain the notion of sequential pattern mining.

Suppose that there are four moving objects and their movement histories are given as images, images, images, and images, where A to E are location symbols and images represents a sequence. For example, images means the moving object visits locations A, B, and C in this order. An example of a sequential pattern is images meaning C is visited after A. Note that other places between A and C can be visited. For the above examples, this pattern matches h1, h3, and h4. Since there are two matches ...

Get Mobile Intelligence now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.