A Two Stage Model on Prediction of Protein Stability Changes in Case of Uncertainty using Fuzzy K-Means Clustering and Fuzzy Artificial Neural Networks
Juliet Rozario1, B. Radha2
1Juliet Rozario, PG Research, Assistant Professor, Department of Computer Science, Nehru Arts and Science College, Coimbatore (Tamil Nadu), India.
2B. Radha, Assistant Professor, Department of Information Technology, Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
Manuscript received on 20 July 2019 | Revised Manuscript received on 03 August 2019 | Manuscript Published on 10 August 2019 | PP: 666-671 | Volume-8 Issue-2S3 July 2019 | Retrieval Number: B11230782S319/2019©BEIESP | DOI: 10.35940/ijrte.B1123.0782S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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: In both industrial applications and basic research the manipulation of protein stability is essential for knowing the principles which govern protein thermostability. This leads to hotspot in data mining based protein engineering and stability prediction. There are so many works related to the prediction of protein stability but they all lack in data preprocessing, presence of duplicates in the dataset and ability to handle uncertainty present in them. The main aim of this paper is to enhance the quality of the protein stability dataset and to increase the accuracy rate of prediction system. For deduplication process fuzzy K-means (FKM)based clustering is applied to cluster and match the duplicate records and eradicate them. To handle the uncertainty Fuzzy Artificial Neural Network (FANN) is used to perform prediction on protein stability. Simulation results proved the efficiency of FKM-FANN which yields excellent results comparing the existing methods.
Keywords: Protein Stability, Fuzzy K Means, Fuzzy Artificial Neural Network, Prediction And Deduplication.
Scope of the Article: Fuzzy Logics