Record Details
A statistical inference framework for finding recurring patterns in large data with applications to energy management
ScholarsArchive at Oregon State University
| Field | Value |
|---|---|
| Title | A statistical inference framework for finding recurring patterns in large data with applications to energy management |
| Names |
You, Zeyu
(creator) Raich, Raviv (advisor) |
| Date Issued | 2014-07-02 (iso8601) |
| Note | Graduation date: 2014 |
| Abstract | We consider the problem of finding unknown patterns that are recurring across multiple sets. For example, finding multiple objects that are present in multiple images or a short DNA code that is repeated across multiple DNA sequences. We first consider a simple problem of finding a single unknown pattern in multiple data sets. For time series data, the problem can also be formulated as a blind joint delay estimation. The non-convex nature of the problem presents a few challenges. Here, we introduce a novel algorithm to estimate the unknown pattern, which is guaranteed to yield an error within a factor of two of that of the optimal solution. Using mixture modeling, we propose a natural extension to the approach that allows the detection of multiple templates placed across multiple sets. Applications to home energy management are considered. |
| Genre | Thesis/Dissertation |
| Topic | recurring pattern recognition |
| Identifier | http://hdl.handle.net/1957/50023 |
