Empirical robustness evaluation of DNA-based clustering methods

Rohani Binti Abu Bakar, Junzo Watada

    Research output: Contribution to journalArticle

    Abstract

    DNA-based computation is one of the latest computation paradigms. Compared to conventional methods that obtain their end results via electronic processes, a DNA-based approach obtains its result from bio-chemical reactions. It is essential in this approach for all experimental processes to be performed without fault. However, some errors may occur while carrying out these bio-chemical experiments. Consequently, it is necessary to overcome their weaknesses. The aim of this study is to examine the robustness of DNA-based techniques in solving a clustering problem. In the broadest sense, robustness can be defined as being able to withstand stresses, pressures, or changes in procedure or circumstance. To examine the robustness of the approach, this research examined the impact of error or added noise on DNA-based procedure results. Comparative studies of different error sets are also provided here. Additionally, two well-known conventional clustering algorithms (Fuzzy C-means and k-means) were applied to the same error sets, to study the reliability and validity of results when comparing DNA-based clustering.

    Original languageEnglish
    Pages (from-to)1-12
    Number of pages12
    JournalInternational Journal of Intelligent Computing in Medical Sciences and Image Processing
    Volume4
    Issue number1
    DOIs
    Publication statusPublished - 2011

    Keywords

    • Clustering
    • Clustering robustness
    • DNA-based clustering
    • DNA-based computation
    • Fuzzy C-means
    • K-means

    ASJC Scopus subject areas

    • Radiology Nuclear Medicine and imaging
    • Computer Science(all)

    Fingerprint Dive into the research topics of 'Empirical robustness evaluation of DNA-based clustering methods'. Together they form a unique fingerprint.

  • Cite this