Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Conference Object Citation - Scopus: 4Survey: Running and Comparing Stream Clustering Algorithms(CEUR Workshop Proceedings, 2018) Ahmed, Rowanda D.; Dalkılıç, Gökhan; Erten, MuratRecently, clustering data streams have become an incredibly important research area for knowledge discovery as applications produce more and more unstoppable streaming data. In this paper we introduce clustering, streams and data streaming clustering algorithms, as well as discussions of the most important stream clustering algorithms, considering their structure. As an additional contribution of our work and differently from review and survey papers in stream clustering, we offer the practical part of the most known stream clustering algorithms, namely: (i) CluStream; (ii) DenStream; (iii) D-Stream; and (iv) ClusTree, showing their experimental results along with some performance metrics computation of for each, depending on MOA framework.Conference Object Citation - WoS: 1Citation - Scopus: 2Fisher's Linear Discriminant Analysis Based Prediction Using Transient Features of Seismic Events in Coal Mines(Institute of Electrical and Electronics Engineers Inc., 2016) Köktürk Güzel, Başak Esin; Karaçalı, BilgeIdentification of seismic activity levels in coal mines is important to avoid accidents such as rockburst. Creating an early warning system that can save lives requires an automated way of predicting. This study proposes a prediction algorithm for the AAIA'16 Data Mining Challenge: Predicting Dangerous Seismic Events in Active Coal Mines that is based on transient activity features along with average indicators evaluated by a Fisher's linear discriminant analysis. Performance evaluation experiments on the training datasets revealed an accuracy level of around 0.9438 while the performance on the test dataset was at a level of 0.9297. These results suggest that the proposed approach achieves high accuracy in predicting danger seismic events while maintaining low complexity.Article Citation - Scopus: 1Annealing-Based Model-Free Expectation Maximisation for Multi-Colour Flow Cytometry Data Clustering(Inderscience Enterprises Ltd., 2016) Köktürk, Başak Esin; Karaçalı, BilgeThis paper proposes an optimised model-free expectation maximisation method for automated clustering of high-dimensional datasets. The method is based on a recursive binary division strategy that successively divides an original dataset into distinct clusters. Each binary division is carriedout using a model-free expectation maximisation scheme that exploits the posterior probability computation capability of the quasi-supervised learningalgorithm subjected to a line-search optimisation over the reference set size parameter analogous to a simulated annealing approach. The divisions arecontinued until a division cost exceeds an adaptively determined limit. Experiment results on synthetic as well as real multi-colour flow cytometrydatasets showed that the proposed method can accurately capture the prominent clusters without requiring any prior knowledge on the number of clusters ortheir distribution models.Conference Object A Data Coding and Screening System for Accident Risk Patterns: A Learning System(WITPress, 2011) Geçer Sargın, Feral; Geçer Sargın, Feral; Duvarcı, Yavuz; Duvarcı, Yavuz; İnan, E.; İnan, E.; Kumova, Bora İsmail; Kumova, Bora İsmail; Atay Kaya, İlgi; Atay Kaya, İlgiAccidents on urban roads can occur for many reasons, and the contributing factors together pose some complexity in the analysis of the casualties. In order to simplify the analysis and track changes from one accident to another for comparability, an authentic data coding and category analysis methods are developed, leading to data mining rules. To deal with a huge number of parameters, first, most qualitative data are converted into categorical codes (alpha-numeric), so that computing capacity would also be increased. Second, the whole data entry per accident are turned into ID codes, meaning each crash is possibly unique in attributes, called 'accident combination', reducing the large number of similar value accident records into smaller sets of data. This genetical code technique allows us to learn accident types with its solid attributes. The learning (output averages) provides a decision support mechanism for taking necessary cautions for similar combinations. The results can be analyzed by inputs, outputs (attributes), time (years) and the space (streets). According to Izmir's case results; sampled data and its accident combinations are obtained for 3 years (2005 - 2007) and their attributes are learned. © 2011 WIT Press.