A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine

Lena Anyango Onyango; Anthony Gichuhi Waititu; Thomas Mageto; Mutua Kilai

doi:doi:10.11648/j.ijdsa.20220802.15

| Peer-Reviewed

A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine

Lena Anyango Onyango, Anthony Gichuhi Waititu, Thomas Mageto, Mutua Kilai

Published in International Journal of Data Science and Analysis (Volume 8, Issue 2)

Received: 8 March 2022 Accepted: 28 March 2022 Published: 22 April 2022

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Machine Learning Algorithms are employed in characterization, pattern recognition, and prediction. A hybrid model helps in reducing the computational complexity, improves accuracy, and results in an effective method for classification. The misclassification of the individual classifier is often excluded in a hybrid classifier. The objective of this research was to develop a hybrid classification model of Artificial Neural Network and non-linear kernel Support Vector Machine as an intelligent tool for achieving better classification performance and minimizing error rates. This study further evaluated the irreducibility and identifiability statistical properties of the ANN-SVM model. To achieve the hybridization of ANN and SVM, the research first obtained weights from the fitted Support Vector Machine model, and these weights were used as the initial weights in the Artificial Neural Network structure. The experiment was carried out in three distinct phases: selection of input features using the Boruta Wrapper Algorithm, classifier learning, and classifier combined effect and classification optimization. The study findings suggest that the hybrid ANN-SVM approach gives a higher performance accuracy of 89.7% and is more precise as compared to single ANN, SVM data mining algorithms. Therefore, the hybrid of ANN-SVM is the best binary classification system for classifying diabetes mellitus. The statistical software used for analysis was R.

Published in	International Journal of Data Science and Analysis (Volume 8, Issue 2)
DOI	10.11648/j.ijdsa.20220802.15
Page(s)	47-58
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Hybrid, Artificial Neural Network (ANN), Support Vector Machine (SVM), Classification

References

[1]	C. M. Amine, S. Meryem and S. Nesma, "Diagnosis of diabetes diseases using an artificial immune recognition system2 (AIRS2) with fuzzy k-nearest neighbor," Journal of medical systems, vol. 36, no. 5, pp. 2721-2729, 2012.
[2]	F. O. D, A. F. A and A. A., "Classification of cancer of the lungs using SVM and ANN," Int. J. Comput. Techno, vol. 15, no. 1, pp. 6418-6426, 2016.
[3]	T. T. K. M. M. Jahangir and X. S., "Diagnosis of cardiovascular diseases using artificial intelligence techniques: A review," International Journal of Computer Applications, vol. 183, no. 3, pp. 1-25, 2021.
[4]	A. Syahid, S. Ali and S. Roselina, "Hybrid artificial neural network with artificial bee colony algorithm for crime classification," in Computational Intelligence in Information Systems, Springer, 2015, pp. 31-40.
[5]	M. Sung-Hwan, L. Jumin and H. Ingoo, "Hybrid genetic algorithms and support vector machines for bankruptcy prediction," Expert systems with applications, vol. 31, no. 3, pp. 652-660, 2006.
[6]	C. Tanujit,. C. Swarup and C. Ashis Kumar, "A novel hybridization of classification trees and artificial neural networks for selection of students in a business school," Opsearch, vol. 55, no. 2, pp. 434-446, 2018.
[7]	C. Panayiotis,. C. Andreas and A. Andreas S, "A Hybrid Prediction Model Integrating Fuzzy Cognitive Maps with Support Vector Machines," in ICEIS (1), 2017, pp. 554-564.
[8]	C. R. Abrunhosa,. P. Leonardo Antonio Monteiro, B. Laura, B. d. B. and R. Am'alia Faria dos, "A comparative study between artificial neural network and support vector machine for acute coronary syndrome prognosis," Pesquisa Operacional, vol. 36, no. 2, pp. 321-343, 2016.
[9]	Y. B, W. YT, Y. JB and W. JY, "A comparison of the performance of ANN and SVM for the prediction of traffic accident duration," Neural Network World, vol. 26, no. 3, p. 271, 2016.
[10]	S. Amit Kumar, P. Sudesh Kumar and. A. Mohammed, "A comparative study between naive Bayes and neural network (MLP) classifier for spam email detection," Int. J. Comput. Appl, 2014.
[11]	Y. Bin, Y. Zhong-Zhen, C. Kang and Y. Bo, "Hybrid model for prediction of bus arrival times at next station," Journal of Advanced Transportation, vol. 44, no. 3, pp. 193-204, 2010.
[12]	A.-K. Ahmad and. H. Haneen, "Classifying Diabetes Disease Using Feedforward MLP Neural Networks," in Technological Innovations in Knowledge Management and Decision Support, 2019, pp. 127-149.
[13]	T. Divya and. A. Sonali, "A survey on Data Mining approaches for Healthcare," International Journal of Bio-Science and Bio-Technology, vol. 5, no. 5, pp. 241-266, 2013.
[14]	V. Vladimir, The nature of statistical learning theory, Springer science & business media, 2013.
[15]	R. Ms Jayshree S, M. Mr Prafulla L and P. Ms Dipali P, "A Review Paper on Classification of Stem Cell Transplant to Identify the High Survival Rate," International Journal on Recent and Innovation Trends in Computing and Communication, vol. 3, no. 4, pp. 1918-1920, 2015.
[16]	O. Fernando EB, F. A. A and J. C. G, "A new sequential covering strategy for inducing classification rules with ant colony algorithms," IEEE Transactions on Evolutionary Computation, vol. 17, no. 1, pp. 64-76, 2012.
[17]	V. V, "Statistical learning theory new york," NY: Wiley, 1988.
[18]	A. S. Lua,. S. Zyad and K. Basel, "Data mining: A preprocessing engine," Journal of Computer Science, vol. 2, no. 9, pp. 735-739, 2006.

Cite This Article

Plain Text BibTeX RIS

APA Style

Lena Anyango Onyango, Anthony Gichuhi Waititu, Thomas Mageto, Mutua Kilai. (2022). A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. International Journal of Data Science and Analysis, 8(2), 47-58. https://doi.org/10.11648/j.ijdsa.20220802.15

Copy | Download

ACS Style

Lena Anyango Onyango; Anthony Gichuhi Waititu; Thomas Mageto; Mutua Kilai. A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. Int. J. Data Sci. Anal. 2022, 8(2), 47-58. doi: 10.11648/j.ijdsa.20220802.15

Copy | Download

AMA Style

Lena Anyango Onyango, Anthony Gichuhi Waititu, Thomas Mageto, Mutua Kilai. A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. Int J Data Sci Anal. 2022;8(2):47-58. doi: 10.11648/j.ijdsa.20220802.15

Copy | Download

@article{10.11648/j.ijdsa.20220802.15,
  author = {Lena Anyango Onyango and Anthony Gichuhi Waititu and Thomas Mageto and Mutua Kilai},
  title = {A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine},
  journal = {International Journal of Data Science and Analysis},
  volume = {8},
  number = {2},
  pages = {47-58},
  doi = {10.11648/j.ijdsa.20220802.15},
  url = {https://doi.org/10.11648/j.ijdsa.20220802.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijdsa.20220802.15},
  abstract = {Machine Learning Algorithms are employed in characterization, pattern recognition, and prediction. A hybrid model helps in reducing the computational complexity, improves accuracy, and results in an effective method for classification. The misclassification of the individual classifier is often excluded in a hybrid classifier. The objective of this research was to develop a hybrid classification model of Artificial Neural Network and non-linear kernel Support Vector Machine as an intelligent tool for achieving better classification performance and minimizing error rates. This study further evaluated the irreducibility and identifiability statistical properties of the ANN-SVM model. To achieve the hybridization of ANN and SVM, the research first obtained weights from the fitted Support Vector Machine model, and these weights were used as the initial weights in the Artificial Neural Network structure. The experiment was carried out in three distinct phases: selection of input features using the Boruta Wrapper Algorithm, classifier learning, and classifier combined effect and classification optimization. The study findings suggest that the hybrid ANN-SVM approach gives a higher performance accuracy of 89.7% and is more precise as compared to single ANN, SVM data mining algorithms. Therefore, the hybrid of ANN-SVM is the best binary classification system for classifying diabetes mellitus. The statistical software used for analysis was R.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine
AU  - Lena Anyango Onyango
AU  - Anthony Gichuhi Waititu
AU  - Thomas Mageto
AU  - Mutua Kilai
Y1  - 2022/04/22
PY  - 2022
N1  - https://doi.org/10.11648/j.ijdsa.20220802.15
DO  - 10.11648/j.ijdsa.20220802.15
T2  - International Journal of Data Science and Analysis
JF  - International Journal of Data Science and Analysis
JO  - International Journal of Data Science and Analysis
SP  - 47
EP  - 58
PB  - Science Publishing Group
SN  - 2575-1891
UR  - https://doi.org/10.11648/j.ijdsa.20220802.15
AB  - Machine Learning Algorithms are employed in characterization, pattern recognition, and prediction. A hybrid model helps in reducing the computational complexity, improves accuracy, and results in an effective method for classification. The misclassification of the individual classifier is often excluded in a hybrid classifier. The objective of this research was to develop a hybrid classification model of Artificial Neural Network and non-linear kernel Support Vector Machine as an intelligent tool for achieving better classification performance and minimizing error rates. This study further evaluated the irreducibility and identifiability statistical properties of the ANN-SVM model. To achieve the hybridization of ANN and SVM, the research first obtained weights from the fitted Support Vector Machine model, and these weights were used as the initial weights in the Artificial Neural Network structure. The experiment was carried out in three distinct phases: selection of input features using the Boruta Wrapper Algorithm, classifier learning, and classifier combined effect and classification optimization. The study findings suggest that the hybrid ANN-SVM approach gives a higher performance accuracy of 89.7% and is more precise as compared to single ANN, SVM data mining algorithms. Therefore, the hybrid of ANN-SVM is the best binary classification system for classifying diabetes mellitus. The statistical software used for analysis was R.
VL  - 8
IS  - 2
ER  -

Copy | Download

Author Information

Lena Anyango Onyango

Department of Statistics and Actuarial Sciences, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya
Anthony Gichuhi Waititu

Department of Statistics and Actuarial Sciences, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya
Thomas Mageto

Department of Statistics and Actuarial Sciences, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya
Mutua Kilai

Department of Statistics and Actuarial Sciences, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Lena Anyango Onyango, Anthony Gichuhi Waititu, Thomas Mageto, Mutua Kilai. (2022). A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. International Journal of Data Science and Analysis, 8(2), 47-58. https://doi.org/10.11648/j.ijdsa.20220802.15

Copy | Download

ACS Style

Lena Anyango Onyango; Anthony Gichuhi Waititu; Thomas Mageto; Mutua Kilai. A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. Int. J. Data Sci. Anal. 2022, 8(2), 47-58. doi: 10.11648/j.ijdsa.20220802.15

Copy | Download

AMA Style

Lena Anyango Onyango, Anthony Gichuhi Waititu, Thomas Mageto, Mutua Kilai. A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine. Int J Data Sci Anal. 2022;8(2):47-58. doi: 10.11648/j.ijdsa.20220802.15

Copy | Download

@article{10.11648/j.ijdsa.20220802.15,
  author = {Lena Anyango Onyango and Anthony Gichuhi Waititu and Thomas Mageto and Mutua Kilai},
  title = {A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine},
  journal = {International Journal of Data Science and Analysis},
  volume = {8},
  number = {2},
  pages = {47-58},
  doi = {10.11648/j.ijdsa.20220802.15},
  url = {https://doi.org/10.11648/j.ijdsa.20220802.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijdsa.20220802.15},
  abstract = {Machine Learning Algorithms are employed in characterization, pattern recognition, and prediction. A hybrid model helps in reducing the computational complexity, improves accuracy, and results in an effective method for classification. The misclassification of the individual classifier is often excluded in a hybrid classifier. The objective of this research was to develop a hybrid classification model of Artificial Neural Network and non-linear kernel Support Vector Machine as an intelligent tool for achieving better classification performance and minimizing error rates. This study further evaluated the irreducibility and identifiability statistical properties of the ANN-SVM model. To achieve the hybridization of ANN and SVM, the research first obtained weights from the fitted Support Vector Machine model, and these weights were used as the initial weights in the Artificial Neural Network structure. The experiment was carried out in three distinct phases: selection of input features using the Boruta Wrapper Algorithm, classifier learning, and classifier combined effect and classification optimization. The study findings suggest that the hybrid ANN-SVM approach gives a higher performance accuracy of 89.7% and is more precise as compared to single ANN, SVM data mining algorithms. Therefore, the hybrid of ANN-SVM is the best binary classification system for classifying diabetes mellitus. The statistical software used for analysis was R.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - A Hybrid Classification Model of Artificial Neural Network and Non Linear Kernel Support Vector Machine
AU  - Lena Anyango Onyango
AU  - Anthony Gichuhi Waititu
AU  - Thomas Mageto
AU  - Mutua Kilai
Y1  - 2022/04/22
PY  - 2022
N1  - https://doi.org/10.11648/j.ijdsa.20220802.15
DO  - 10.11648/j.ijdsa.20220802.15
T2  - International Journal of Data Science and Analysis
JF  - International Journal of Data Science and Analysis
JO  - International Journal of Data Science and Analysis
SP  - 47
EP  - 58
PB  - Science Publishing Group
SN  - 2575-1891
UR  - https://doi.org/10.11648/j.ijdsa.20220802.15
AB  - Machine Learning Algorithms are employed in characterization, pattern recognition, and prediction. A hybrid model helps in reducing the computational complexity, improves accuracy, and results in an effective method for classification. The misclassification of the individual classifier is often excluded in a hybrid classifier. The objective of this research was to develop a hybrid classification model of Artificial Neural Network and non-linear kernel Support Vector Machine as an intelligent tool for achieving better classification performance and minimizing error rates. This study further evaluated the irreducibility and identifiability statistical properties of the ANN-SVM model. To achieve the hybridization of ANN and SVM, the research first obtained weights from the fitted Support Vector Machine model, and these weights were used as the initial weights in the Artificial Neural Network structure. The experiment was carried out in three distinct phases: selection of input features using the Boruta Wrapper Algorithm, classifier learning, and classifier combined effect and classification optimization. The study findings suggest that the hybrid ANN-SVM approach gives a higher performance accuracy of 89.7% and is more precise as compared to single ANN, SVM data mining algorithms. Therefore, the hybrid of ANN-SVM is the best binary classification system for classifying diabetes mellitus. The statistical software used for analysis was R.
VL  - 8
IS  - 2
ER  -

Copy | Download