Diagnosis urine disease based on KNN algorithm and ANN

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    The Artificial Neural Networks (ANN) are commonly applied in several medical fields for undertaking diagnosis of diseases. ANN can be used for diagnosing the urine bladder as well as nephritis inflammation. This research paper mainly focuses on undertaking the diagnosis of urine disease on the basis of K-Nearest Neighbor Algorithm (KNN) and Artificial Neural Network (ANN). The Acute Inflammation Data Set was employed in the research methodology. The data was collected from the UCI Machine Learning Respiratory which would enhance the successful carrying out of the diagnosis. The collected data is distinguished into inputs as well as targets. The systems will represent the inputs to a neural network. The neural network targets will be recognized as 1’s for infected and as 0’s for non-infected. It is evident from the results that the artificial neural network could be significant for recognizing the infected person. The results which can be obtained from the application of ANN methodology on the basis of the selected signs and symptoms clearly indicates the network ability to comprehend the specific patterns which correspond to the person’s Symptoms-Nearest Neighbor algorithm normally unveils the satisfactory rate at which the diagnosis is done to ascertain the distinction between the infected as well as non-infected urinary system.


  • References


      [1] M.Sordo, "Introduction to Neural Networks in Healthcare," Open Clinical, [Online].

      [2] S. a. A.Kusiak, (2002), "Cancer gene search with data mining and genetic algorithms," Computers in Biology and Medicine.

      [3] T. L.Ozyilmaz, (2003), "Artificial neral networks for diagnosis of hepatitis disease." in Proceedings of the International Joint Conference on Neural Networks.

      [4] C. a. G. Heckerling, (2007)"Prediction of Urinary tract inflection based on the artificial neural networks and genetic algorithms." International Journal of Informatis, pp. 289-296. https://doi.org/10.1016/j.ijmedinf.2006.01.005.

      [5] Y. a. H.Chen, (2007)"Computer Aided-Diagnosis of uridynamic stress incontinence with vector -based perineal ultrasound using neural networks," Ultrasound in Obsterrics and Gynechology. pp. 1002-1006.

      [6] Moallen, Monadjemi, (2008), "Automatic Diagnosis of Particular Disease using a Fuzzy-Neural Approach.," International Review on Computers & Software, pp. 406-411.

      [7] P.J.G.Lisboa, (2002), "A review of evidence of health benefit from artificial neural networks in medical intervention", [Online].

      [8] M. H. Kadhem and A. M. Zeki, (2014), "Prediction of Urinary System Disease Diagnosis: A Comparative Study of Three Decision Tree Algorithms," 2014 International Conference on Computer Assisted System in Health, Kuala Lumpur, pp. 58-61. https://doi.org/10.1109/CASH.2014.25.

      [9] Jamie J. D'Costaa, Douglas G. Ward, Richard T. Bryan, (2016), "Urinary biomarkers for the diagnosis of urothelial bladder cancer", New Horizons in Translational Medicine, Vol. 3, pp. 221–223.

      [10] R. a. J. J.S.Snchez, (2007), "An analysis of how training datacomplexity affects the nearest neigbour classified." Patterns Analysis and Applications, p. 3.

      [11] J. B. Siddharth Jonathan and K.N. Shruthi, A Two Tier neural inter -Network Based Approach to Medical Diagnosis using K- Nearest Neighbor Classification for Diagnosis Pruning.

      [12] R. a. J. J.S.Snchez, (2007), "An analysis of how training datacomplexity affects the nearest neigbour classified.," Patterns Analysis and Applications, p. 3.

      [13] Saleh Alaliyat (2008) "Video - based Fall Detection in Elderly’s Houses " Master of Science in Media Technology Department of Computer Science and Media Technology, Gjøvik University College.


 

View

Download

Article ID: 21604
 
DOI: 10.14419/ijet.v7i4.21604




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.