Abstract
In the article a method for reducing the input data coming to the input of a neural network of the Multilayer Perceptron type is proposed. The data that was used for the analysis are related to one of the most malignant tumors - malignant melanoma. They refer to patients with malignant melanoma that were registered in Oncology Complex Center in Burgas town. The data and contain information about age, sex, marital status of the patient, date of diagnosis, name of the disease according to the International statistical classification of diseases and health problems. The InterCriteria Analysis (ICA) approach was used to analyze the relationships between these parameters.
A new improved structure and algorithm for increasing the learning speed of the Multilayer Perceptron (MLP) neural network are proposed. The algorithm is hybrid and includes determining the degrees of consonance and dissonance between the observed parameters. From the pairs of parameters (from ICA) with the highest consonance and with the lowest dissonance, one parameter is removed. For the purposes of MLP training, one of the values of the fuzzy pair of parameters is redundant because it does not carry additional information, and its removal reduces the number of neurons in the input layer of the neural network. In turn, this reduces the total error generated by each neuron. Another positive part is the faster learning of the neural network due to the lightweight architecture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aleksandrova, I., Bojinova, V., Dimova, P.: Panayiotopoulos syndrome – a clinical and EEG study of 40 patients. Comptes rendus de l’Académie bulgare des Sciences 70(3), 435–442 (2017)
Atanassov, K.: Index matrices: towards an augmented matrix calculus. Studies. In: Computational Intelligence Series, vol. 573. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10945-9
Atanassov, K.: On Intuitionistic Fuzzy Sets Theory. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29127-2
Atanassov, K., Mavrov, D., Atanassova, V.: Intercriteria decision making: a new approach for multicriteria decision making, based on index matrices and intuitionistic fuzzy sets. Issues Intuitionistic Fuzzy Sets Generalized Nets 11, 1–8 (2014)
Atanassov, K., Szmidt, E., Kacprzyk, J.: On intuitionistic fuzzy pairs. Notes Intuitionistic Fuzzy Sets 19(3), 1–13 (2013)
Garbe, C., Leiter, U.: Clinics in Dermatology, vol. 27, issue 1, pp. 3–9, January–February 2009. Elsevier. https://doi.org/10.1016/j.clindermatol.2008.09.001
Jekova, I., Vassilev, P., Stoyanov, T., Pencheva, T.: InterCriteria analysis: application for ECG data analysis. Mathematics 9(8), 854 (2021). https://doi.org/10.3390/math9080854
Hagan, M., Demuth, H., Beale, M.: Neural Network Design. PWS Publishing, Boston (1996)
Karimkhani, C., et al.: The global burden of melanoma: results from the Global Burden of Disease Study 2015. Br. J. Dermatol. 177(1), 134–140 (2017)
Markovic, S., et al.: Malignant melanoma in the 21st century, part 1: epidemiology, risk factors, screening, prevention, and diagnosis. In: Mayo Clinic Proceedings, pp. 364–380. Elsevier (2007)
Krumova, S., et al.: Intercriteria analysis of calorimetric data of blood serum proteome. BBA-Gen. Subjects 1861(2), 409–417 (2017)
Melanoma and other malignant neoplasms of skin (C43-C44), International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10)-WHO Version for 2019-covid-expanded. https://icd.who.int/browse10/2019/en#/C43-C44
Mladenov, V.l., et al.: Risk factors for the occurrence of early postoperative urological and surgical complications after kidney transplantation from a living and cadaveric donor. Comptes rendus de l’Académie bulgare des Sciences (2022). ISSN (online) 2367-5535
National Center of Public Health and Analyses, Annual information. http://ncpha.government.bg/index.php?lang=en
Peycheva, V., et al.: Impact of KCNQ2 mutations in Bulgarian patients with electroclinical syndromes with onset in the first year of life. Biotechnol. Biotechnol. Equip. 31(1), 138–142 (2017). Impact Factor (2015)
Sotirov, S., et al.: Application of the intuitionistic fuzzy InterCriteria analysis method with triples to a neural network preprocessing procedure. Computat. Intell. Neurosci. (2017). https://doi.org/10.1155/2017/2157852. 9 pages, Article ID 2157852
Sotirov, S., Atanassova, V., Sotirova, E., Bureva, V., Mavrov, D.: Application of the intuitionistic fuzzy InterCriteria analysis method to a neural network preprocessing procedure. In: 9th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), 30 June–03 July 2015, Gijon, Spain, pp. 1559–1564 (2015). https://doi.org/10.2991/ifsa-eusflat-15.2015.222
Sotirova, E., Vasilev, V., Bozova, G., Bozov, H., Sotirov, S.: Application of the InterCriteria analysis method to a dataset of malignant neoplasms of the digestive organs for the Burgas Region for 2014–2018. In: 2019 Big Data, Knowledge and Control Systems Engineering (BdKCSE), pp. 1–6 (2019). https://doi.org/10.1109/BdKCSE48644.2019.9010609
Sotirova, E., Bozova, G., Bozov, H., Sotirov, S., Vasilev, V.: Application of the InterCriteria analysis method to a data of malignant melanoma disease for the Burgas Region for 2014–2018. In: Atanassov, K.T., et al. (eds.) IWIFSGN 2019 2019. AISC, vol. 1308, pp. 166–174. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77716-6_15
Acknowledgment
The authors are grateful for the support provided by the Bulgarian National Science Fund under Grant Ref. No. KP-06-N22/1/2018 “Theoretical research and applications of InterCriteria Analysis”. The authors declare that there is no conflict of interest regarding the publication of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sotirov, S., Petrova, Y., Bozov, H., Sotirova, E. (2022). A Hybrid Algorithm for Multilayer Perceptron Design with Intuitionistic Fuzzy Logic Using Malignant Melanoma Disease Data. In: Kahraman, C., Tolga, A.C., Cevik Onar, S., Cebi, S., Oztaysi, B., Sari, I.U. (eds) Intelligent and Fuzzy Systems. INFUS 2022. Lecture Notes in Networks and Systems, vol 504. Springer, Cham. https://doi.org/10.1007/978-3-031-09173-5_77
Download citation
DOI: https://doi.org/10.1007/978-3-031-09173-5_77
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09172-8
Online ISBN: 978-3-031-09173-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)