We consider the problem of finding pairs of short patterns such that, in a given input sequence of length n, the distance between each pair’s patterns is at least α. The problem was introduced in [1] and is motivated by the optimization of multiplexed nested PCR. We study algorithms for the following two cases; the special case when the two patterns in the pair are required to have the same len...

Transformation-based learning (TBL) and frequent pattern discovery (FPD) are two popular research paradigms, one from the domain of empirical natural language processing , the second from the eld of data mining. This paper describes how Eric Brill's original TBL algorithm can be improved via incorporation of FPD techniques. The algorithm B-Warmr is presented that upgrades TBL to rst-order logic...

This paper presents how to mine formulation rules from a named organization corpus. The TEIRESIAS algorithm, which is widely used in bioinformatics domain, is adopted. The experimental results based on MET2 test bed show that the approach of regarding the morpheme of a keyword as a cluster is the best, the approach of regarding all the keywords as the same cluster is the next, and the approach ...

____________________________________ vi List of Figures ___________________________________ x List of Tables __________________________________ xiv

Unsupervised Pattern Discovery for Multimedia Sequences Lexing Xie This thesis investigates the problem of discovering patterns from multimedia sequences. The problem is of interest as capturing and storing large amounts of multimedia data has become commonplace, yet our capability to process, interpret, and use these rich corpora has notably lagged behind. Patterns refer to the the recurrent a...

Large-Scale Pattern Discovery in Music Thierry Bertin-Mahieux This work focuses on extracting patterns in musical data from very large collections. The problem is split in two parts. First, we build such a large collection, the Million Song Dataset, to provide researchers access to commercial-size datasets. Second, we use this collection to study cover song recognition which involves finding ha...

We present a data mining system, EasyMiner which has been developed for interactive mining of interesting patterns in time-oriented databases. This system implements a wide spectrum of data mining functions, including generalisation, characterisation, classification, association and relevant analysis. By enhancing several interesting data mining techniques, including attribute induction and ass...

Human listeners are able to recognize structure in music through the perception of repetition and other relationships within a piece of music. This work aims to automate the task of music analysis. Music is “explained” in terms of embedded relationships, especially repetition of segments or phrases. The steps in this process are the transcription of audio into a representation with a similarity...

We present a method for modeling user navigation on a web site using grammatical inference of stochastic regular grammars. With this method we achieve better models than the previously used first order Markov chains, in terms of predictive accuracy and utility of recommendations. In order to obtain comparable results, we apply the same grammatical inference algorithms on Markov chains, modeled ...

This note reports on a novel method of detection of haplotype blocks in the human genome. It is based upon pattern discovery using technology being patented by Cira Discovery Sciences, Inc. It is intended as a demonstration of our pattern discovery technology in the context of genomic variation (SNP) data. Actual applications in genomic analyses will take advantage of technological advances tha...