Analisis Performa Metode K- Nearest Neighbor (KNN) dan Crossvalidation pada Data Penyakit Cardiovascular
Abstract
Secara global, penyebab kematian nomor satu setiap tahunnya adalah penyakit Cardiovascular. Penyakit cardiovascular adalah penyakit yang disebabkan gangguan fungsi jantung dan pembuluh darah, seperti Penyakit Jantung Koroner, Penyakit Gagal jantung atau Payah Jantung, Hipertensi dan Stroke. (Kemenkes RI, 2014). Tujuan dari penelitian ini adalah mengukur performa (akurasi, presisi, recall dan f-measure) metode knn dan crossvalidation pada dataset cardiovascular. dataset yang digunakan sebanyak 1000 record terdiri dari 11 atribut (age, gender, height, dsb) data pasien cardiovascular dan non cardiovascular, dataset tersebut diperoleh dari UCI Machine Learning Repository yang dikelola oleh Hungarian Institute of Cardiology Budapest: Andras Janosi, M.D., University Hospital, Zurich, Switzerland. Tahapan yang dilakukan yaitu: membagi rasio simulasi dataset (20:80, 50:50, 80:20), penerapan crossvalidation (k-fold=10) dan klasifikasi menggunakan metode K-NN (k=2 hingga K=900), Hasil penelitian dari simulasi rasio dataset 50:50 memperoleh nilai akurasi 82%, presisi 82%, recall 82% dan f-measure 80% pada nilai K=13. Kemudian hasil penelitian dari simulasi rasio dataset 20:80 memperoleh nilai akurasi 87%, presisi 87%, recall 97% dan f-measure 92% pada nilai K=3. Dan hasil penelitian dari simulasi rasio dataset 80:20 memperoleh nilai akurasi 91%, presisi 92%, recall 60% dan f-measure 72% pada nilai K=5.
Downloads
References
H. Azis, “Klasifikasi Penyakit Jantung Menggunakan Metode K-Nearest Neighbor,” Indones. J. Data Sci., pp. 1–4, 2018, doi: https://doi.org/10.33096/ijodas.v1i1.3.
S. H. A. Aini, Y. A. Sari, and A. Arwan, “Seleksi Fitur Information Gain untuk Klasifikasi Penyakit Jantung Menggunakan Kombinasi Metode K-Nearest Neighbor dan Naïve Bayes,” J. Pengemb. Teknol. Inf. dan Ilmu Komput. Univ. Brawijaya, vol. 2, 2018.
K. RI, “Situasi Kesehatan Jantung,” Pus. data dan Inf. Kementeri. Kesehat. RI, 2014.
M. M. Baharuddin, T. Hasanuddin, and H. Azis, “Analisis Performa Metode K-Nearest Neighbor untuk Identifikasi Jenis Kaca,” Ilk. J. Ilm, vol. 11, pp. 269–274, 2019.
H. Azis, F. T. Admojo, and E. Susanti, “Analisis Perbandingan Performa Metode Klasifikasi pada Dataset Multiclass Citra Busur Panah,” Techno.Com, vol. 19, no. 3, 2020.
F. T. Admojo and Ahsanawati, “Klasifikasi Aroma Alkohol Menggunakan Metode KNN,” Indones. J. Data Sci., vol. 1, no. 2, pp. 34–38, 2020.
M. Lestari, “Penerapan Algoritma Klasifikasi Nearest Neighbor (K-NN) Untuk Mendeteksi Penyakit Jantung,” Fakt. Exacta, vol. 7, no. September 2010, pp. 366–371, 2014.
H. Leidiana, “Penerapan Algoritma K-Nearest Neighbor Untuk Penentuan Resiko Kredit Kepemilikan Kendaraan Bemotor,” J. Penelit. Ilmu Komputer, Syst. Embed. Log., vol. 1, 2013.
C. A. U. Hassan, M. S. Khan, and M. A. Shah, “Comparison of Machine Learning Algorithms in Data classification,” Int. Conf. Autom. Comput., 2018.
S. Sahar, “Analisis Perbandingan Metode K-Nearest Neighbor dan Naïve Bayes Clasiffier Pada Dataset Penyakit Jantung,” Indones. J. Data Sci., vol. 1, no. 3, pp. 79–86, 2020, doi: 10.33096/ijodas.v1i3.20.
L. B. C. Tanujayaa, B. Susanto, and A. Saragiha, “Perbandingan Metode Regresi Logistik dan Random Forest untuk Klasifikasi Fitur Mode Audio Spotify,” Indones. J. data Sci., vol. 1, no. 3, pp. 68–78, 2020.
D. Cahyanti, A. Rahmayani, and S. Ainy, “Analisis performa metode Knn pada Dataset pasien pengidap Kanker Payudara,” Indones. J. Data Sci., vol. 1, no. 2, pp. 39–43, 2020.
Sugiarti and Mirnawati, “Implementasi Algoritma Goverment Standard ( GOST ) dalam Pengamanan File Dokumen,” Indones. J. Data Sci., vol. 1, no. 2, pp. 52–56, 2020.
Harlinda and Nasir, “Perancangan sistem pendukung keputusan dalam pengalokasian dana bantuan sosial di kabupaten pinrang dengan menggunakan metode AHP,” Indones. J. Data Sci., vol. 1, no. 2, pp. 44–51, 2020.
A. Prasetya Wibawa, W. Lestar, A. Bella Putra Utama, I. Tri Saputra, and Z. Nabila Izdihar, “Multilayer Perceptron untuk Prediksi Sessions pada Sebuah Website Journal Elektronik,” Indones. J. Data Sci., vol. 1, no. 3, pp. 57–67, 2020, doi: 10.33096/ijodas.v1i3.15.
M. M. Baharuddin, T. Hasanuddin, and H. Azis, “Analisis Performa Metode K-Nearest Neighbor untuk Identifikasi Jenis Kaca,” Ilk. J. Ilm., vol. 11, no. 28, pp. 269–274, 2019.
L. Nurhayati and H. Azis, “Perancangan Sistem Pendukung Keputusan Untuk Proses Kenaikan Jabatan Struktural Pada Biro Kepegawaian,” Semin. Nas. Teknol. Inf. dan Multimed., pp. 6–7, 2016.
Copyright (c) 2021 Indonesian Journal of Data and Science
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
License and Copyright Agreement
In submitting the manuscript to the journal, the authors certify that:
- They are authorized by their co-authors to enter into these arrangements.
- The work described has not been formally published before, except in the form of an abstract or as part of a published lecture, review, thesis, or overlay journal.
- The work is not under consideration for publication elsewhere.
- The work has been approved by all the author(s) and by the responsible authorities – tacitly or explicitly – of the institutes where the work has been carried out.
- They secure the right to reproduce any material that has already been published or copyrighted elsewhere.
- They agree to the following license and copyright agreement.
Copyright
Authors who publish with Indonesian Journal of Data and Science 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-NonCommercial 4.0 International License. (CC BY-NC 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.