Original scientific paper SOM is a popular artificial neural network algorithm to perform rational clustering on many different data sets. There is a disadvantage of the SOM that can run on a predefined completed data set. Various problems are encountered on a time-stream data sets when clustering by using standard SOM since the time-stream data sets are generated dependent on time. In this study, the Sliding Window feature is included into standard SOM for clustering timestream data sets. Thus, the combination of SOM and Sliding Window (SOM + SW) gives more accurate results when clustering on time-stream data sets. To prove this, a set of internet usage data from a mobile operator in Turkey is taken to test. The taken data set from the mobile operator is clustered according to the classical SOM then the future data usages of subscribers are estimated. The same data set is applied on the SOM + SW to perform the same simulations. Keywords: clustering; mobile operators; self-organizing maps (SOM); sliding window; time-stream data sets Samoorganizirane mape s kliznim prozorom (SOM + SW)Izvorni znastveni članak SOM je popularan algoritam umjetne neuronske mreže za obavljanje racionalnog grupiranja na mnogim različitim skupovima podataka. Postoji nedostatak SOM-e koja se može izvoditi na unaprijed definiranom dovršenom skupu podataka. Na vremenskim tokovima skupova podataka pojavljuju se razni problemi prilikom grupiranja pomoću standardne SOM-e jer se vremenski tokovi podataka generiraju ovisno o vremenu. U ovoj studiji značajka kliznog prozora uključena je u standardnu SOM-u za grupiranje vremenskih tokova podataka. Stoga, kombinacija SOM i kliznog prozora (SOM + SW) daje točnije rezultate prilikom grupiranja podataka na vremenskom toku skupova podataka. Da bi se to dokazalo, testiran je skup podataka o uporabi interneta mobilnog operatora u Turskoj. Uzeti skup podataka mobilnog operatera grupiran je prema klasičnoj SOM-i, a zatim je procijenjena buduća uporaba podataka pretplatnika. Isti skup podataka primijenjen je na SOM + SW za izvođenje istih simulacija. Ključne riječi: grupiranje; klizni prozor; mobilni operateri; samoorganizirane mape (SOM); vremenski tok skupova podataka
One of the most important IT sectors that requires big data management is mobile data communication systems (MDCS) of GSM companies. In the charging mechanism of current MDCS, a subscriber “surfs” on the internet that creates data traffic and a counter subtracts the amount of data used by the user from the subscriber's quota. In other words, instant constant quota values are assigned to subscribers without concern for their previous amount of internet usage in current MDCS. Moreover, constant quota values cause constant charge calls in control traffic that are repeated for all new quota requests. Thus, performance degradation occurs because of the repetition of quota request calls and allocations. In this chapter, a dynamic quota calculation system (DQCS) is proposed for dynamic quota allocations and charging in MDCS using data mining approaches as two cascaded blocks. The first block is self-organizing map (SOM) clustering based on a sliding window (SW) methodology followed by the second block, which is the markov chain (MC); the overall system is denoted as “SOM/SW and MC.”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.