Archive for the ‘Shape’ Category

SAXually Explicit Images: Data Mining Large Shape Databases

Monday, April 2nd, 2012

SAXually Explicit Images: Data Mining Large Shape Databases by Eamonn Keogh.

ABSTRACT

The problem of indexing large collections of time series and images has received much attention in the last decade, however we argue that there is potentially great untapped utility in data mining such collections. Consider the following two concrete examples of problems in data mining.

Motif Discovery (duplication detection): Given a large repository of time series or images, find approximately repeated patterns/images.

Discord Discovery: Given a large repository of time series or images, find the most unusual time series/image.

As we will show, both these problems have applications in fields as diverse as anthropology, crime…

Ancient history in the view of some, this is a Google talk from 2006!

But, it is quite well done and I enjoyed the unexpected application of time series representation to shape data for purposes of evaluating matches. It is one of those insights that will stay with you and that seems obvious after they say it.

I think topic map authors (semantic investigators generally) need to report such insights for the benefit of others.

The Shape of Things – SHAPES 1.0

Wednesday, December 14th, 2011

The Shape of Things – SHAPES 1.0

Proceedings of the First Interdisciplinary Workshop on SHAPES, Karlsruhe, Germany, September 27, 2011. Edited by: Janna Hastings, Oliver Kutz, Mehul Bhatt, Stefano Borgo

If you have ever thought of “shape” as being a simple issue, consider the abstract from “Shape is a Non-Quantifiable Physical Dimension” by Ingvar Johansson:

In the natural-scientific community it is often taken for granted that, sooner or later, all basic physical property dimensions can be quantified and turned into a kind-of-quantity; meaning that all their possible determinate properties can be put in a one-to-one correspondence with the real numbers. By using some transfinite mathematics, the paper shows this tacit assumption to be wrong. Shape is a very basic property dimension; but, since it can be proved that there are more possible kinds of determinate shapes than real numbers, shape cannot be quantified. There will never be a shape scale the way we have length and temperature scales. This is the most important conclusion, but more is implied by the proof. Since every n-dimensional manifold has the same cardinality as the real number line, all shapes cannot even be represented in a three-dimensional manifold the way perceivable colors are represented in so-called color solids.

If shape, which exists in metric space has these issues, that casts a great deal of doubt on mapping semantics, which exists in non-metric space, in a “…one-to-one correspondence with real numbers.”

Don’t you think?

We can make simplifying assumptions about semantics and make such mappings, but we need to be aware that is what is happening.