Mining minimal distinguishing subsequence patterns with gap constraints

Ji, Xiaonan; Bailey, James E.; Dong, Guozhu

doi:10.1007/s10115-006-0038-2

Cited by 101 publications

(82 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The classification, clustering and forecasting are the application of data mining where the aim is to analyse the data and make some information or prediction out of them. The application of classification task of data mining on AAs [46], [47], [48] and [50] is to ascertain each case (object, record, or instance ) to one class , out of a set of predefined classes , based on the values of some attributes for the case and this can be expresses as: IF< term1 AND term2 AND ……..> THEN<class>, Where each term is a triple <Attributes, operator, value>i.e.< gender=female> where value being a value belonging to the domain of attributes and the operator is the relational operator.…”

Section: Ant Algorithms and Data Miningmentioning

confidence: 99%

Bio-inspired Ant Algorithms: A review

Roy¹,

Chaudhuri²

2013

IJMECS

View full text Add to dashboard Cite

Abstract─ Ant Algorithms are techniques for optimizing which were coined in the early 1990"s by M. Dorigo. The techniques were inspired by the foraging behavior of real ants in the nature. The focus of ant algorithms is to find approximate optimized problem solutions using artificial ants and their indirect decentralized communications using synthetic pheromones. In this paper, at first ant algorithms are described in details, then transforms to computational optimization techniques: the ACO metaheuristics and developed ACO algorithms. A comparative study of ant algorithms also carried out, followed by past and present trends in AAs applications. Future prospect in AAs also covered in this paper. Finally a comparison between AAs with well-established machine learning techniques were focused, so that combining with machine learning techniques hybrid, robust, novel algorithms could be produces for outstanding result in future.

show abstract

Section: Ant Algorithms and Data Miningmentioning

confidence: 99%

Bio-inspired Ant Algorithms: A review

Roy¹,

Chaudhuri²

2013

IJMECS

View full text Add to dashboard Cite

show abstract

“…This algorithm applies both downward and upward closure properties as well as sampling to achieve faster and more efficient pruning. Last but not least, in ConSGapMiner (Ji, et al, 2007) a prefix-based framework is employed and a set of gap and length constraints are applied during the mining process for efficient pruning. The algorithm targets patterns that occur frequently in one class of sequences and are infrequent in sequences of other classes.…”

Section: Sequential Pattern Miningmentioning

confidence: 99%

Mining frequent arrangements of temporal intervals

et al. 2009

View full text Add to dashboard Cite

Abstract. The problem of discovering frequent arrangements of temporal intervals is studied. It is assumed that the database consists of sequences of events, where an event occurs during a time-interval. The goal is to mine temporal arrangements of event intervals that appear frequently in the database. The motivation of this work is the observation that in practice most events are not instantaneous but occur over a period of time and different events may occur concurrently. Thus, there are many practical applications that require mining such temporal correlations between intervals including the linguistic analysis of annotated data from American Sign Language as well as network and biological data. Three efficient methods to find frequent arrangements of temporal intervals are described; the first two are tree-based and use breadth and depth first search to mine the set of frequent arrangements, whereas the third one is prefix-based. The above methods apply efficient pruning techniques that include a set of constraints that add user-controlled focus into the mining process. Moreover, based on the extracted patterns a standard method for mining association rules is employed that applies different interestingness measures to evaluate the significance of the discovered patterns and rules. The performance of the proposed algorithms is evaluated and compared with other approaches on real (American Sign Language annotations and network data) and large synthetic datasets.

show abstract

“…To mine contrasting subsequences, an algorithm ConSGapM iner was proposed by Ji et al [14]. There are two steps of their algorithm: first, a DFS (Depth First Search) tree is built to enumerate all possible subsequence candidates; then, for each candidate, the bitset operations are applied to prune nodes which cannot fulfill the g-gap constraint.…”

Section: Related Workmentioning

confidence: 99%

“…Based on the Generalized Suffix Tree (GST) [11], emerging substrings can be extracted in linear time. Comparing with ConSGapM iner [14], this algorithm can only mine substrings, i.e. items have to be appearing immediately next to each other in the original sequence.…”

Section: Related Workmentioning

confidence: 99%

“…Discriminative subsequences are helpful in classification as well. Borrowing an example from Ji, Bailey and Dong, for instance, the subsequences "having horns", "faces worship", "stones price" and "ornaments price" appear several times in the Book of Revelation, but never in the Book of Genesis [14]. Biblical scholars might be interested in those subsequences and regard them as fingerprints associated with the Book of Revelation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Contrasting Sequence Groups by Emerging Sequences

Deng

Zaı̈ane

2009

Discovery Science

View full text Add to dashboard Cite

Abstract. Group comparison per se is a fundamental task in many scientific endeavours but is also the basis of any classifier. Contrast sets and emerging patterns contrast between groups of categorical data. Comparing groups of sequence data is a relevant task in many applications. We define Emerging Sequences (ESs) as subsequences that are frequent in sequences of one group and less frequent in the sequences of another, and thus distinguishing or contrasting sequences of different classes. There are two challenges to distinguish sequence classes: the extraction of ESs is not trivially efficient and only exact matches of sequences are considered. In our work we address those problems by a suffix tree-based framework and a sliding window matching mechanism for the distance metric between sequences. We propose a classifier for sequence data based on Emerging Sequences. Evaluating against two learning algorithms based on frequent subsequences and exact matching subsequences, the experiments on two datasets show that our similar ESs-based classification model outperforms the baseline approaches by up to 20% in prediction accuracy.

show abstract

Mining minimal distinguishing subsequence patterns with gap constraints

Abstract: Discovering contrasts between collections of data is an impor-

Cited by 101 publications

References 32 publications

Bio-inspired Ant Algorithms: A review

Bio-inspired Ant Algorithms: A review

Mining frequent arrangements of temporal intervals

Contrasting Sequence Groups by Emerging Sequences

Contact Info

Product

Resources

About