Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (6): 1245-1253.doi: 10.23919/JSEE.2020.000095

• SYSTEMS ENGINEERING • Previous Articles     Next Articles

Automatic fuzzy-DBSCAN algorithm for morphological and overlapping datasets

Aref YELGHI1,*(), Cemal KÖSE2(), Asef YELGHI3(), Amir SHAHKAR4()   

  1. 1 Department of Computer Engineering, Avrasya University, Trabzon 61250, Turkey
    2 Department of Computer Engineering, Karadeniz Technical University, Trabzon 61080, Turkey
    3 Department of Business Administration, Gazi University, Ankara 06560, Turkey
    4 Civil Engineering Department, Karadeniz Technical University, Trabzon 61080, Turkey
  • Received:2020-01-28 Online:2020-12-18 Published:2020-12-29
  • Contact: Aref YELGHI;;;
  • About author:|YELGHI Aref was born in 1986. He received his B.S. degree and M.S. degree in computer science from the Azad University Sari branch in 2008 and 2012 respectively. He obtained his Ph.D. degree in computer engineering from Karadeniz Technical University in 2018. His research interests include optimization, neural network and data mining. E-mail:||K?SE Cemal was born in 1964. He is a professor in the Department of Computer Engineering at Karadeniz Technical University. He received his Ph.D. degree from Faculty of Engineering, and Department of Computer Science, University of Bristol, in 1997. His research interests include signal and image processing, pattern recognition, and human computer interaction. E-mail:||YELGHI Asef was born in 1986. He received his B.S. degree in accounting, M.S. degree in capital markets and stock exchange from University of Marmara of Turkey in 2008 and 2014 respectively. He obtained his Ph.D. degree in bussines administration in University of Gazi of Turkey in 2020. Also since 2014, he has been pursuing his Ph.D. degree in banking at University of Marmara of Turkey. His research interests include exchange rate, bond marketing and data mining. E-mail:||SHAHKAR Amir was born in 1989. He received his B.S. degree in civil engineering in 2011 from Azad University of Tabriz. He received his M.S. degree in transportation engineering from Karadeniz Technical University, Trabzon, Turkey, in 2015. He started his Ph.D. learning in traffic engineering in 2016. Currently, he is a Ph.D. student in the Civil Engineering Department, Karadeniz Technical University, Trabzon. His research interests include analyzing traffic accidents through geographic information system (GIS), traffic simulation by Verkehr in Stadten simulations model (VISSIM), and optimizing traffic lights with adaptive neuro fuzzy inference system (ANFIS)-based metaheuristic algorithms. E-mail:


Clustering is one of the unsupervised learning problems. It is a procedure which partitions data objects into groups. Many algorithms could not overcome the problems of morphology, overlapping and the large number of clusters at the same time. Many scientific communities have used the clustering algorithm from the perspective of density, which is one of the best methods in clustering. This study proposes a density-based spatial clustering of applications with noise (DBSCAN) algorithm based on the selected high-density areas by automatic fuzzy-DBSCAN (AFD) which works with the initialization of two parameters. AFD, by using fuzzy and DBSCAN features, is modeled by the selection of high-density areas and generates two parameters for merging and separating automatically. The two generated parameters provide a state of sub-cluster rules in the Cartesian coordinate system for the dataset. The model overcomes the problems of clustering such as morphology, overlapping, and the number of clusters in a dataset simultaneously. In the experiments, all algorithms are performed on eight data sets with 30 times of running. Three of them are related to overlapping real datasets and the rest are morphologic and synthetic datasets. It is demonstrated that the AFD algorithm outperforms other recently developed clustering algorithms.

Key words: clustering, density-based spatial clustering of applications with noise (DBSCAN), fuzzy, overlapping, data mining