Density based clustering using mathematical morphology

Download

index.pdf

Date

2007

Author

Erdem, Coşku

Metadata

Show full item record

Item Usage Stats

122
views

49
downloads

Improvements in technology, enables us to store large amounts of data in warehouses. In parallel, the need for processing this vast amount of raw data and translating it into interpretable information also increases. A commonly used solution method for the described problem in data mining is clustering. We propose "Density Based Clustering Using Mathematical Morphology" (DBCM) algorithm as an effective clustering method for extracting arbitrary shaped clusters of noisy numerical data in a reasonable time. This algorithm is predicated on the analogy between images and data warehouses. It applies grayscale morphology which is an image processing technique on multidimensional data. In this study we evaluated the performance of the proposed algorithm on both synthetic and real data and observed that the algorithm produces successful and interpretable results with appropriate parameters. In addition, we computed the computational complexity to be linear on number of data points for low dimensional data and exponential on number of dimensions for high dimensional data mainly due to the morphology operations.

Subject Keywords

Information Technology.

URI

http://etd.lib.metu.edu.tr/upload/12608264/index.pdf
https://hdl.handle.net/11511/16715

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

A complex event processing framework implementation using heterogeneous devices in smart environments Kaya, Muammer Özge; Eren, Pekin Erhan; Department of Information Systems (2012) Significant developments in microprocessor and sensor technology make wirelessly connected small computing devices widely available; hence they are being used frequently to collect data from the environment. In this study, we construct a framework in order to extract high level information in an environment containing such pervasive computing devices. In the framework, raw data originating from wireless sensors are collected using an event driven system and converted to simple events for transmission over a...
Adoption and utilization of information systems in an emerging Turkish industrial rown : a case study on Gaziantep Salihoğlu, Yasemin; Bilgen, Semih; Department of Information Systems (2003) This thesis analyzes factors motivating and inhibiting the adoption of information systems in enterprises in Gaziantep by a scale generated on Rogers̕ theory of diffusion of innovation. These factors are grouped into four as administrative, technological, environmental, and organizational characteristics in the scale built. Structured interview method was used while collecting the data. It was interviewed with 20 firms, operating in various sectors in Gaziantep. Results of the study showed that, within the ...
ITMEM-Information Technology Management Enhancement Model: assessment of information technology use in organizations Sezgin, Emre; Özkan Yıldırım, Sevgi; Department of Information Systems (2010) This study proposes a new model for the assessment of information technology (IT) use in public and private companies, which is called ITMEM- Information Technology Management Enhancement Model. This model aims to assist decision making processes in information technology management. For this purpose, a tool is developed to explore strengths and weaknesses of a company in IT use. The model was developed upon a three-folded structure including (1) academic studies in technology management, (2) best practices...
Attack tree based information technology security metric integrating enterprise objectives with vulnerabilities Karabey, Buğra; Baykal, Nazife; Department of Information Systems (2011) Security is one of the key concerns in the domain of Information Technology systems. Maintaining the confidentiality, integrity and availability of such systems, mandates a rigorous prior analysis of the security risks that confront these systems. In order to analyze, mitigate and recover from these risks a metrics based methodology is essential in prioritizing the response strategies to these risks and also this approach is required for resource allocation schedules to mitigate such risks. In addition to t...
Analysis of electronic signature in Turkey from the legal and economic perspectives and the awareness level in the country İskender, Gökhan; Koçyiğit, Altan; Department of Information Systems (2006) As in the case of other information technologies, the best way of obtaining efficient results from electronic signature application is integrating it to the legal and economic systems and increasing the awareness level of technology in the society. This thesis performs the legal and economic analyses of electronic signature in Turkey and measures the awareness level in the society. The analyses performed in the thesis show that electronic signature is not legally established in Turkey even the legal base is...

Citation Formats

C. Erdem, “Density based clustering using mathematical morphology,” M.S. - Master of Science, Middle East Technical University, 2007.