Implementation of Particle Swarm Optimization Feature Selection on Naïve Bayes for Thoracic Surgery Classification
Abstract
Thoracic surgery is among the operations that are most often performed on patients with lung cancer. Naive Bayes is one of the data mining classification techniques that may be used to handle thoracic surgery data. Therefore, the goal of this study is to assess the precision of all research models using Naive Bayes with and without Particle Swarm Optimization. This study's methodology includes the dataset used, the Naive Bayes algorithm theory, the particle swarm optimization algorithm, test validation using split validation, and performance assessment using the confusion matrix and AUC evaluation approaches. In this inquiry, secondary data are retrieved via the UCI Repository website. Thoracic surgery weight optimization accuracy is increased using particle swarm optimization. The test results of the Naive Bayes technique utilizing the thoracic surgery dataset showed the highest accuracy of 81.91% at a ratio of 80:20 and an AUC value of 0.620. The highest accuracy score is 93.62% with an AUC value of 0.773 at a ratio of 90:10, with three characteristics, namely PRE6, PRE14, and PRE17, having zero weight. This accuracy score was achieved when Particle Swarm Optimization was used to refine feature selection for attribute weighting. As a consequence, Naïve Bayes accuracy in thoracic surgery has increased as a result of attribute weighting on feature selection utilizing Particle Swarm Optimization. In turn, this research contributes to increasing the precision and efficiency with which thoracic surgical data are processed, which benefits lung cancer diagnosis in both speed and accuracy.
Downloads
References
[2] A. Bondzi-Simpson et al., “Ethiopia’s first minimally invasive surgery program: A novel approach in global surgical education,” JTCVS Open, vol. 13, no. C, pp. 459–467, 2023, doi: 10.1016/j.xjon.2022.11.015.
[3] X. Li, Y. Liu, Y. Zhou, Y. Gao, C. Duan, and C. Zhang, “Day surgery unit robotics thoracic surgery: feasibility and management,” J. Cancer Res. Clin. Oncol., vol. 1, no. 1, pp. 1–6, 2023, doi: 10.1007/s00432-023-04731-0.
[4] F. Fitriyani, “Metode Bagging Untuk Imbalance Class Pada Bedah Toraks Menggunakan Naive Bayes,” J. Kaji. Ilm., vol. 18, no. 3, p. 278, 2018, doi: 10.31599/jki.v18i3.281.
[5] M. A. Nematollahi et al., “Body composition predicts hypertension using machine learning methods: a cohort study,” Sci. Rep., vol. 13, no. 1, pp. 1–11, 2023, doi: 10.1038/s41598-023-34127-6.
[6] B. Shen, G. Coruzzi, and D. Shasha, “EnsInfer: a simple ensemble approach to network inference outperforms any single method,” BMC Bioinformatics, vol. 24, no. 1, pp. 1–13, 2023, doi: 10.1186/s12859-023-05231-1.
[7] R. Rachman and R. N. Handayani, “Klasifikasi Algoritma Naive Bayes Dalam Memprediksi Tingkat Kelancaran Pembayaran Sewa Teras UMKM,” J. Inform., vol. 8, no. 2, pp. 111–122, 2021, doi: 10.31294/ji.v8i2.10494.
[8] N. Ardiansyah, “Penerapan Teknik Data Mining Untuk Diagnosa Penyakit Appendicitis Di Rs Budi Asih Menggunakan Algoritmanaïve Bayes Classifier,” Sekolah Tinggi Teknologi Pelita Bangsa, 2018. [Online]. Available: https://ecampus.pelitabangsa.ac.id
[9] Roshan S and Rohini V, “Prediction of Post-Surgical Survival of Lung Cancer Patients After Thoracic Surgery Using Data Mining Techniques.,” Int. J. Adv. Res., vol. 5, no. 4, pp. 596–600, 2017, doi: 10.21474/ijar01/3852.
[10] W. Kanyongo and A. E. Ezugwu, “Feature selection and importance of predictors of non-communicable diseases medication adherence from machine learning research perspectives,” Informatics Med. Unlocked, vol. 38, no. March, p. 101232, 2023, doi: 10.1016/j.imu.2023.101232.
[11] R. Sanjaya and Fitriyani, “Prediksi Bedah Toraks Menggunakan Seleksi Fitur Forward Selection dan K-Nearest Neighbor,” J. Edukasi dan Penelit. Inform., vol. 5, no. 3, pp. 316–320, 2019, [Online]. Available: https://pdfs.semanticscholar.org
[12] D. M. Br.Tarigan, D. P. Rini, and Samsuryadi, “Seleksi Fitur pada Klasifikasi Penyakit Gula Darah Menggunakan Particle Swarm Optimization (PSO) pada Algoritma C4.5,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 3, pp. 569–575, 2020, [Online]. Available: http://jurnal.iaii.or.id/index.php/RESTI/article/view/1881/264
[13] M. Asfi and N. Fitrianingsih, “Implementasi Algoritma Naive Bayes Classifier sebagai Sistem Rekomendasi Pembimbing Skripsi,” Infotekjar J. Nas. Inform. Dan Teknol. Jaringan-, vol. 5, no. 1, pp. 1–7, 2020, [Online]. Available: https://jurnal.uisu.ac.id/index.php/infotekjar/article/download/2536/pdf
[14] E. Priyanti, “Peningkatan Algoritma Naïve Bayes Menggunakan Algoritma Genetika Pada Klasifikasi Bakteri,” J. Swabumi, vol. 9, no. 2, pp. 85–88, 2021, [Online]. Available: https://ejournal.bsi.ac.id/ejurnal/index.php/swabumi/article/download/11217/pdf
[15] K. D. Nugroho and U. Sucipto, “Studi Fenomenologi: Dampak Pengabaian Gejala Kanker Bagi Klien Dan Keluarga Phenomenology Study: The Impact Of Cancer Symptoms For Clients And Families,” J. Keperawatan Malang, vol. 5, no. 1, pp. 46–54, 2020, [Online]. Available: http://jurnal.stikespantiwaluya.ac.id/
[16] E. Marfianti, “Peningkatan Pengetahuan Kanker Payudara dan Ketrampilan Periksa Payudara Sendiri (SADARI) untuk Deteksi Dini Kanker Payudara di Semutan Jatimulyo Dlingo,” JAMALI - J. Abdimas Madani Dan Lestari, Vol. 3, No. 1, Pp. 25–31, 2021, [Online]. Available: Https://Journal.uii.ac.id/jamali
[17] F. A. Rizki, M. Hartoyo, and Sudiarto, “Health Education Using The Leaflet Media Reduce Anxiety Levels In Pre Operation Patients,” Jendela Nurs. J., vol. 3, no. 1, pp. 49–57, 2019, [Online]. Available: https://ejournal.poltekkes-smg.ac.id/ojs/index.php/jnj/about/submissions#authorGuidelines
[18] A. Mustopa, Hermanto, Anna, E. B. Pratama, A. Hendini, and D. Risdiansyah, “Analysis of User Reviews for the PeduliLindungi Application on Google Play Using the Support Vector Machine and Naive Bayes Algorithm Based on Particle Swarm Optimization,” in International Conference on Informatics and Computing (ICIC), Gorontalo, 2020, pp. 1–7. doi: 10.1109/ICIC50835.2020.9288655.
[19] Y. J. Zhang, H. Zhang, and R. Gupta, “A new hybrid method with data ‑ characteristic ‑ driven analysis for artificial intelligence and robotics index return forecasting,” Financ. Innov., vol. 10, no. 4, pp. 1–23, 2023, doi: 10.1186/s40854-023-00483-5.
[20] D. Valero-carreras, J. Alcaraz, and M. Landete, “Computers and Operations Research Comparing two SVM models through different metrics based on the confusion matrix,” Comput. Oper. Res., vol. 152, no. December 2022, p. 106131, 2023, doi: 10.1016/j.cor.2022.106131.
[21] S. S. Zakariaee, A. I. Abdi, N. Naderi, and M. Babashahi, “Prognostic significance of chest CT severity score in mortality prediction of COVID ‑ 19 patients , a machine learning study,” Egypt. J. Radiol. Nucl. Med., 2023, doi: 10.1186/s43055-023-01022-z.
[22] F. Gorunescu, Data Mining: Concepts, Models and Techniques. Heidelberg: Springer Berlin, 2011. [Online]. Available: https://doi.org/10.1007/978-3-642-19721-5
[23] F. Alghifari and D. Juardi, “Penerapan Data Mining Pada Penjualan Makanan Dan Minuman Menggunakan Metode Algoritma Naïve Bayes,” J. Ilm. Inform., vol. 9, no. 2, pp. 1–7, 2021, [Online]. Available: https://ejournal.upbatam.ac.id/index.php/jif/article/view/3755/2062
Copyright (c) 2023 Shalehah, Muhammad Itqan Mazdadi, Andi Farmadi, Dwi Kartini, Muliadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
