Prediksi Harapan Hidup Pasca Operasi Toraks Pada Pasien Penderita Kanker Paru-paru Menggunakan Metode Genetic Algorithm Untuk Feature Selection Dan Naive Bayes Classifier
DOI:
https://doi.org/10.34818/eoe.v7i2.13129Abstract
Abstrak Penanganan dini yang dilakukan untuk menekan tingkat kematian pasien kanker paru-paru pasca operasi toraks, dengan mengumpulkan data berupa informasi tentang pasien pasca operasi toraks menimbulkan masalah baru yaitu data berdimensi tinggi yang memiliki banyak atribut dan tidak bisa menghasilkan informasi yang akurat. Oleh karena itu, diperlukan skema komputasi yang dapat mereduksi dimensi pada data tersebut. Dalam hal ini, proses reduksi bertujuan untuk meringankan beban komputasi pada klasifikasi, proses reduksi yang digunakan yaitu seleksi fitur Genetic Algorithm. Kemudian metode klasifikasi Naïve Bayes digunakan untuk melakukan proses klasifikasi harapan hidup pasca operasi toraks. Adapun akurasi terbaik yang dihasilkan dari seleksi fitur Genetic Algorithm dan Naïve Bayes Classifier yaitu 85,319%. Kata kunci : operasi toraks, genetic algorithm, naïve bayes Abstract Early treatment is carried out to reduce the death rate of lung cancer patients after thoracic surgery by collecting data in the form of information about postoperative thoracic patients, creating a new problem that is high-dimensional data that has many attributes and cannot produce accurate information. Therefore, a computational scheme is needed to reduce the dimensions of the data. In this case, the reduction process aims to ease the computational burden on classification, the reduction process used is the Genetic Algorithm for Feature Selection. Then the Naïve Bayes Classifier method is used to carry out the classification process of life expectancy after thoracic surgery. The best accuracy resulting from the selection of Genetic Algorithm and Naïve Bayes Classifier features is 85,319%. Keywords: thoracic surgery, genetic algorithm, naïve bayes
Downloads
References
[1] C. E. Niluh Gede Yasmin, Keperawatan Medikal Bedah: Klien Dengan Gangguan Sistem Pernapasan, Jakarta: Penerbit Buku Kedokteran EGC, 2002.
[2] M. Taradeh, M. Mafarja, A. A. Heidari, H. Faris, I. Aljarah, S. Mirjalili and H. Fujita, "An evolutionary gravitational search-based feature selection," Information Sciences, vol. 497, pp. 219-239, 2019.
[3] Suyanto, Soft Computing: Membangun Mesin Ber-IQ Tinggi, Bandung: Informatika, 2008.
[4] L. Marek, P. Konrad, R. Adam and K. Jerzy, "Thoracic Surgery Data Data Set," National Science Foundation, 13 November 2013. [Online]. Available: https://archive.ics.uci.edu/ml/datasets/Thoracic+Surgery+Data. [Accessed 15 July 2020].
[5] A. J. M, L. D. B and C. Priti, Knowledge Discovery Using Associative Classification for Heart Disease Prediction, Berlin: Springer, Berlin, Heidelberg, 2013.
[6] S. Raschka and V. Mirjalili, Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2, Birmingham: Packt Publishing Ltd, 2019.
[7] e. a. Maciej Zieba, "Boosted SVM for extracting rules from imbalanced data in applicationto prediction of the post-operative life expectancy in thelung cancer patients," Applied Soft Computing, 2013.
[8] J. S Akosa, "Predictive Accuracy: A Misleading Performance Measure for Highly Imbalanced Data," in Proceedings of the SAS Global Forum, 2017.
[9] J. E. Jackson, A User's Guide to Principal Components, John Wiley & Sons, 2005.
[10] S. Mirjalili, "Genetic algorithm," in Evolutionary algorithms and neural networks, Springer, 2019, pp. 43-55.
[11] Suyanto, Artificial Intelligence, Bandung: Informatika, 2014.
[12] Ding, Z. Ye, B. Kui and Weihong, "Feature selection based on hybridization of genetic algorithm and competitive swarm optimizer," Soft Computing, pp. 1-10, 2020.
[13] Suyanto, Evolutionary Computation, Bandung: Informatika Bandung, 2008.
[14] J. H. &. M. Kamber, Data Mining: Concepts and Techniques, San Francisco: Elsevier, 2006.
[15] H. j. Ali and T. Mohammad, "A non-parametric mixture of Gaussian naive Bayes," in Artificial Intelligence and Signal Processing Conference (AISP), 2017.
[16] Visa, R. Sofia, R. Brian, L. V. D. K. Anca and Esther, "Confusion Matrix-based Feature Selection.," MAICS, vol. 710, pp. 120-127, 2011.
[17] H. L. M. Dash, "Feature Selection for Classification," in Intelligent Data Analysis 1 (1997) 131–156, Singapore, 1997.
[18] W. Lee and H.-Y. Kim, "Genetic algorithm implementation in Python," in Fourth Annual ACIS International Conference on Computer and Information Science (ICIS'05), IEEE, 2005, pp. 8-11.
[19] C. Manuel, "manuel-calzolari/sklearn-genetic: sklearn-genetic," April 2019. [Online]. Available: https://doi.org/10.5281/zenodo.3348077.
[20] G. P. S. Luh, I. Made Adi Bhaskara and M. Sudarma, "Optimization of Feature Selection Using Genetic Algorithm with Naïve Bayes Classification for Home Improvement Recipients," International Journal of Engineering and Emerging Technology, vol. III, no. 1, 2018.



