Towards Framing an Integrated Model for Optimization and Clustering (IMOC) High-Dimensional Non-Linear DNA Data Processing using ACO and DENCLUE
R.Nandhakumar1, Antony Selvadoss Thanamani2
1R.Nandhakumar, Assistant Professor, Department of Computer Science, Nallamuthu Gounder Mahalingam College, Pollachi, India.
2Antony Selvadoss Thanamani, Associate Professor & Head, Department of Computer Science, Nallamuthu Gounder Mahalingam College, Pollachi, India
Manuscript received on September 18, 2019. | Revised Manuscript received on October 05, 2019. | Manuscript published on October 30, 2019. | PP: 603-608 | Volume-9 Issue-1, October 2019 | Retrieval Number: A9753109119/2019©BEIESP | DOI: 10.35940/ijeat.A9753.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Gene Expression data contains important information about the biological reactions that are carried out in creatures that are based on the surroundings. For understanding those processes in a better manner, the hidden expressions from the high-dimensional non-linear data are to be processed effectively. Moreover, the intricacy of biological data increases the challenges in High-dimensional non-linear gene data processing. For handling the complications, incorporation of clustering techniques is employed for identifying the patterns appropriately. Furthermore, this makes clarity in gene functions, regulations, inherent expressions, categories from noisy data input. In this paper, an Integrated Model for Optimization and Clustering (IMOC) is developed for efficient gene data processing for cancer detection application. Two efficient algorithms are integrated in this work, Ant Colony Optimization for effectively determine the features of gene data and Density based Clustering (DENCLUE) is for clustering the DNA data based on the determined features. For evaluating the proposed model, the benchmark datasets such as DNA Microarray Data of Leukemia and DNA Microarray Data of Colon Cancer are used. Further, the results show that the proposed model outperforms the existing models in accuracy and efficiency rates.
Keywords: Gene Expression Data, DNA microarray data, Ant Colony Optimization, Density Based Clustering, Integrated Model.