Open Access Open Access  Restricted Access Subscription Access

The Multiple Time Series Clinical Data Processing with Modified Artificial Bee Colony Algorithm and Artificial Neural Network


Affiliations
1 Department of Computer Science and Engineering, Hindusthan Institute of Technology,Coimbatore, Tamilnadu, India
 

Objectives: The main objective of this research is to discover patient acuity or severity of illness for immediate practical use for clinicians by evaluating the use of multivariate time series modelling along with multiple models.

Methods/Statistical analysis: As large-scale multivariate time series data become increasingly common in application domains, such as health care and traffic analysis, researchers are challenged to build efficient tools to analyze it and provide useful insights. In many situations, analyzing a time-series in isolation is reasonable. And also this scenario is used to increase the prediction accuracy and reducing the time complexity using optimization algorithm.

Findings: The various research works has been analyzed and evaluated. From the analysis, the multiple measurements support vector machine (MMSVM), multiple measurements random forest regression (MMRF) and improved particle swarm optimization (IPSO) algorithm, modified artificial bee colony algorithm (MABCA) to solve the multiple time series problems by maximizing the optimal feature information which found to be superior for higher performance in terms of accuracy, precision and recall. The proposed MABCA with transductive support vector machine (TSVM) and artificial neural network (ANN) is used to improve the classification performance.

Application/Improvements: The findings of this work prove that the graph search based method provides better result than other approaches.


Keywords

Data Mining, Multiple Measurements, Support Vector Machine (SVM), Particle Swarm Optimization (PSO), Modified Artificial Bee Colony Algorithm (MABCA) and Artificial Neural Network (ANN).
User
Notifications

  • N. Anwar, E. Huntz, W. Kolch, A. Pitti. Semantic Data Integration for Francisellatularensisnovicida Proteomic and Genomic Data. 2010; 21(5), pp.321-345.
  • I. Batal, H. Valizadegan, G. F. Cooper, M. Hauskrecht. A pattern mining approach for classifying multivariate temporal data.In Proceedings IEEE International Conference Bioinformatics and Biomedical. 2011; 20(3), pp. 358-365.
  • L. Breiman. Random forests, Mach. Learning.2001; 45(1), pp. 5-32.
  • Damian Bargiel, S. Herrmann. Multi-temporal land-cover classification of agricultural areas in two European regions with high resolution spotlight terraSAR-X data.2011; 3(5), pp. 859-877.
  • M. Campos, J. Palma, R. Marın, Temporal data mining with temporal constraints artificial intelligence in medicine. 2007; 2(4), pp. 67-76.
  • S. Dowdy, S. Wearden, D. Chilko. Statistics for Research’, 3rd (edn). New York, NY, USA: Wiley. 2004; 42(6), pp. 625-640.
  • T. Exarchos, M. Tsipouras, C. Papaloukas, D. Fotiadis. An optimized sequential pattern matching methodology for sequence classification.2009; 19(2), pp. 249-264.
  • S. P. Gardner. Ontologies and Semantic Data Integration. Drug Discovery Today, 2005; 10(14), pp.1001-1007.
  • S. Gupta, D. Kumar, A. Sharma. Data Mining Classification Techniques Applied For Breast Cancer Diagnosis And Prognosis. 2011; 11(7), pp.125-135.
  • J. Han, M Kamber. Data Mining: Concepts and Techniques. 2nd ed. San Francisco, CA, USA: Morgan Kaufmann. 2006; 20(12), pp.325-365.
  • M. .A Hern´andez, S. J. Stolfo. Real-world data is dirty: Data cleansing and the merge/purge problem,’ Data Mining Knowledge Discovery, 1998; 2(1), pp. 9-37.
  • Joseph Sexton, D. L. Urban, M. J. Donohue, C. Song. Long-term land cover dynamics by multi-temporal classification across the Landsat- 5 record. Remote Sensing Environment, 2005; 128(4), pp. 246-258.
  • C.H. Lee, J C Chen, Tseng V S. A novel data mining mechanism considering bio-signal and environmental data with applications on asthma monitoring. Computer Methods Programs Biomedicine, 2011; 101(1), pp. 44-61.
  • M. Lee, H. Lu, T. Ling, Y. Ko. Cleansing data for mining and warehousing,’ in Database and Expert Systems Applications.1999; 46(6), pp.750-807.
  • M. Lenzerini, Data integration: A theoretical perspective, In Proceedings 21st Symposium on Principles of Database Systems, Madison, WI, USA, 2002; 35(7), pp. 233-246.
  • Y. Sam Sung Zhao, Li, Peng Sun. A Fast Filtering Schema for Large Database Cleansing, 2002; 26(8), pp.520-530.
  • J. Soni, D. Ansari, S. Sharma. Predictive Data Mining for Medical Diagnosis:An Overview of Heart Disease Prediction, 2011; 47(2), pp.640-650.
  • M. Stacey,C. McGregor. ‘Temporal abstraction in intelligent clinical data analysis: A survey,’ Artificial Intelligence in Medicine, 2007; 39(1), pp. 1-24.
  • R. Saranya, K. Balamurugan,M. Karuppasamy. Artificial Bee Colony Algorithm Based Congestion Management in Restructured Power System. Indian Journal of Science and Technology, 2015; 8(S7), 171-178.
  • A. Dhivya, S. N. Sivanandan. Hybrid Fuzzy Jordan Network for Robust and Efficient Intrusion Detection System. Indian Journal of Science and Technology, 2015; 8(34), pp. 1-10.

Abstract Views: 255

PDF Views: 0




  • The Multiple Time Series Clinical Data Processing with Modified Artificial Bee Colony Algorithm and Artificial Neural Network

Abstract Views: 255  |  PDF Views: 0

Authors

M. Priyanga
Department of Computer Science and Engineering, Hindusthan Institute of Technology,Coimbatore, Tamilnadu, India
K. Sasi Kala Rani
Department of Computer Science and Engineering, Hindusthan Institute of Technology,Coimbatore, Tamilnadu, India
M. Pavithra
Department of Computer Science and Engineering, Hindusthan Institute of Technology,Coimbatore, Tamilnadu, India
S. Yamunadevi
Department of Computer Science and Engineering, Hindusthan Institute of Technology,Coimbatore, Tamilnadu, India

Abstract


Objectives: The main objective of this research is to discover patient acuity or severity of illness for immediate practical use for clinicians by evaluating the use of multivariate time series modelling along with multiple models.

Methods/Statistical analysis: As large-scale multivariate time series data become increasingly common in application domains, such as health care and traffic analysis, researchers are challenged to build efficient tools to analyze it and provide useful insights. In many situations, analyzing a time-series in isolation is reasonable. And also this scenario is used to increase the prediction accuracy and reducing the time complexity using optimization algorithm.

Findings: The various research works has been analyzed and evaluated. From the analysis, the multiple measurements support vector machine (MMSVM), multiple measurements random forest regression (MMRF) and improved particle swarm optimization (IPSO) algorithm, modified artificial bee colony algorithm (MABCA) to solve the multiple time series problems by maximizing the optimal feature information which found to be superior for higher performance in terms of accuracy, precision and recall. The proposed MABCA with transductive support vector machine (TSVM) and artificial neural network (ANN) is used to improve the classification performance.

Application/Improvements: The findings of this work prove that the graph search based method provides better result than other approaches.


Keywords


Data Mining, Multiple Measurements, Support Vector Machine (SVM), Particle Swarm Optimization (PSO), Modified Artificial Bee Colony Algorithm (MABCA) and Artificial Neural Network (ANN).

References