From Crispness to Fuzziness: Three Algorithms for Soft Sequential Pattern Mining

Fiot, Céline; Laurent, Anne; Teisseire, Maguelonne

doi:10.1109/tfuzz.2007.894976

Cited by 28 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The novel algorithm is compared to two different algorithms. TotallyFuzzy [11] and Totally Fuzzy-FSW [38] are used for comparison. The number of frequent sequences is computed for minSupp{0.6, 0.7, 0.8, 0.9, 1.0} according to the primary condition given in Table 5.…”

Section: Experiments On a Real Datasetmentioning

confidence: 99%

Constraint Fuzzy Sequential Pattern Mining with TOPSIS Method

Zabihi¹,

Pedram²,

Ramezan³

2016

J. Math. Computer Sci.

View full text Add to dashboard Cite

To maintain profitability, many companies consider effective customer relationship management (CRM) to be one of the critical factors for success. The central objective of CRM is to maximize the lifetime value of a customer to a company and find positive customers. One of the methods that help this is sequential pattern mining. Sequential pattern mining is to discover all sub-sequences that are frequent. The classical sequential pattern mining algorithms do not allow processing of numerical data and require preprocessing of these data into a binary representation, which necessarily leads to a loss of information. Fuzzy sets are used to overcome this problem. In present fuzzy sequential pattern mining algorithms, there isn't any matter of itemset time and sequences are only found based on sequence of happening. In this paper, a novel algorithm about fuzzy sequential pattern mining is proposed with the time-gap constraints confine the time interval between two adjacent elements to a reasonable period while the sliding time window constraint permits elements of a pattern to span a set of transactions within a user-specified window and a fuzzy membership function is considered. Therefore, loss of useful sequences is prevented in the search process. The proposed algorithm searches for a goal sequence within the defined fuzzy sliding window and fuzzy gap functions.

show abstract

Section: Experiments On a Real Datasetmentioning

confidence: 99%

Constraint Fuzzy Sequential Pattern Mining with TOPSIS Method

Zabihi¹,

Pedram²,

Ramezan³

2016

J. Math. Computer Sci.

View full text Add to dashboard Cite

show abstract

“…The quantitative database is thus converted into a membership degree database, which is then mined for fuzzy sequential patterns. 2,3,14 The item and itemset concepts have been redefined relative to classical sequential patterns. A fuzzy item is the association of one item and one corresponding fuzzy set.…”

Section: Fuzzy Sequential Patternsmentioning

confidence: 99%

Evolution patterns and gradual trends

Fiot

Masséglia

Laurent

et al. 2009

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Nowadays, many databases record ordered or temporally annotated data, such as Web access logs or genomic sequences. Therefore, sequence mining has become an important research area. Among these data mining approaches, sequential patterns aim at describing frequent behaviors. In the access data of a commercial Web site, one may, for instance, discover that "35% of customers successively buy a PSP then a memory stick and PSP games". To provide more complete information, fuzzy sequential patterns were designed, including quantitative values within the mining task. Such patterns, considering the previous example, would be "35% of customers buy a PSP, then they buy few games many times, and then they buy a high-capacity memory stick once." However, symbolic or fuzzy sequential patterns, in their current form, do not allow to extract temporal tendencies that are typical of sequential data. By means of temporal tendency mining, one may discover in the same access data that "An increasing number of purchases of PSP games during a very short period is frequently followed by a purchase of a high-capacity memory stick a few days later." It would be easy to conclude that the users either quickly succeed in registering or make several attempts before they look at the help page within a few seconds. To the best of our knowledge, no method has been designed for discovering this kind of patterns. Therefore, we propose, in this paper, two approaches that extract pattern-expressing trends or evolution. First, we define evolution patterns that summarize the evolution of the quantities in the data. We explain how they can be obtained from a quantitative sequence database. Second, we define gradual trends in fuzzy sequential data. These trends describe variations in the fulfillment of fuzzy properties according to time. For both kinds of patterns, we developed algorithms that were implemented and tested on real data. C 2009 Wiley Periodicals, Inc.

show abstract

“…With fuzzy sets, there is a very extended way of considering fuzzy association rules as "if X is A then Y is B" in considering of various information of attributes, such as the type "if beer is lot then potato chips is lot" or "if age is old then salary is high" 5,8,11,16,20,21 . In the same manner, the notion of fuzzy sequential patterns 6,17,7,12,13 considers the sequential patterns 2 on quantitative attributes like "60% of young people purchase a lot of beers, then purchase many action movies later, then purchase few PC games", where the sequence represents "people is young, then beer is lot, then action movie is many, and then PC game is few". Different than many approaches that consider that fuzzy association rules as rules or fuzzy sequential patterns as sequences obtained from fuzzy transactions, i.e., fuzzy subsets of items containing like "age is old" and "salary is high", we proposed the notion of fuzzy recurrence rules 25 depicting the relation like "if DVD is often then CD is often" in sequence format.…”

Section: Related Workmentioning

confidence: 99%

Discovering Fuzzy Unexpected Sequences With Concept Hierarchies

Laurent

Poncelet

2009

Int. J. Unc. Fuzz. Knowl. Based Syst.

View full text Add to dashboard Cite

Sequential pattern mining is the method that has received much attention in sequence data mining research and applications, however, a drawback is that it does not profit from prior knowledge of domains. In our previous work, we proposed a belief-driven method with fuzzy set theory for discovering the unexpected sequences that contradict existing knowledge of data, including occurrence constraints and semantic contradictions. In this paper, we present a new approach that discovers unexpected sequences with determining semantic contradictions by using concept hierarchies associated with the data. We evaluate the effectiveness of our approach with experiments on Web usage analysis.

show abstract

From Crispness to Fuzziness: Three Algorithms for Soft Sequential Pattern Mining

Cited by 28 publications

References 19 publications

Constraint Fuzzy Sequential Pattern Mining with TOPSIS Method

Constraint Fuzzy Sequential Pattern Mining with TOPSIS Method

Evolution patterns and gradual trends

Discovering Fuzzy Unexpected Sequences With Concept Hierarchies

Contact Info

Product

Resources

About