An approach for incremental mining of clickstream patterns as a service application

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F23%3A63570701" target="_blank" >RIV/70883521:28140/23:63570701 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/document/10185132" target="_blank" >https://ieeexplore.ieee.org/document/10185132</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSC.2023.3294945" target="_blank" >10.1109/TSC.2023.3294945</a>

Result language

angličtina

Original language name

An approach for incremental mining of clickstream patterns as a service application

Original language description

Sequential pattern mining in general and one particular form, clickstream pattern mining, are data mining topics that have recently attracted attention due to their potential applications of discovering useful patterns. However, in order to provide them as real-world service applications, one issue that needs to be addressed is that traditional algorithms often view databases as static, although in practice databases often grow over time and invalidate parts of the previous results after updates, forcing the algorithms to rerun from scratch on the updated databases to obtain updated frequent patterns. This can be inefficient as a service application due to the cost in terms of resources, and the returning of results to users can take longer when the databases get bigger. The response time can be shortened if the algorithms update the results based on incremental changes in databases. Thus, we propose PF-CUP (pre-frequent clickstream mining using pseudo-IDList), an approach towards incremental clickstream pattern mining as a service. The algorithm is based on the pre-large concept to maintain and update results and a data structure called a pre-frequent hash table to maintain the information about patterns. The experiments completed on different databases show that the proposed algorithm is efficient in incremental clickstream pattern mining. IEEE

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE Transactions on Services Computing

ISSN

1939-1374

e-ISSN

1939-1374

Volume of the periodical

16

Issue of the periodical within the volume

6

Country of publishing house

US - UNITED STATES

Number of pages

14

Pages from-to

3892-3905

UT code for WoS article

001142484600005

EID of the result in the Scopus database

2-s2.0-85165246689