Comparison of K-Nearest Neighbors Method and Naïve Bayes Method in Classifying the Quality of Oil Palm Seed Varieties

Suhaiba Nasyira Hariono; Nurdin; Lidya Rosnita

doi:10.31572/inotera.Vol10.Iss2.2025.ID539

Suhaiba Nasyira Hariono Departement of Informatics, Universitas Malikussaleh
Nurdin Universitas Malikussaleh
Lidya Rosnita Departement of Informatics, Universitas Malikussaleh

DOI: https://doi.org/10.31572/inotera.Vol10.Iss2.2025.ID539

Keywords: Oil Palm Seeds, Classification, Quality, K-Nearest Neighbors, Naïve Bayes

Abstract

Rapid advances in technology and science have driven significant transformations in various sectors, including the palm oil industry. As one of the nation's strategic commodities, the success of the palm oil industry is greatly influenced by the quality of the seeds used. The selection of high-quality seeds from the initial nursery stage pre-nursery to the main nursery stage is a critical factor in supporting productivity, harvest quality, and resistance to pests and diseases. However, the seed selection process often faces challenges such as genetic variation among individuals and differences in adaptive capacity to the environment, leading to inconsistent growth performance. This study aims to classify the quality of oil palm seedlings using the K-Nearest Neighbors and Naïve Bayes classification algorithms based on seedling growth observation data at PTPN IV Pabatu Plantation, Serdang Bedagai District. The criteria used in the classification process include seedling age, seedling height, stem diameter, number of leaves, leaf length, and pest infestation per seedling. Based on the test results, the K-Nearest Neighbors method achieved an accuracy of 94%, precision of 89.47%, and recall of 94.44%. Meanwhile, the Naïve Bayes method achieved an accuracy of 82%, precision of 92.85%, and recall of 78.78%. These results indicate that the K-Nearest Neighbors algorithm performs better in classifying the quality of oil palm seedlings compared to the Naïve Bayes algorithm. Thus, this data mining-based classification approach can serve as a strategic solution to enhance the accuracy of seedling selection in an objective and efficient manner

Downloads

Download data is not yet available.

References

Sunarko, Budi Daya dan Pengelolaan Kebun Kelapa Sawit dengan Sistem Kemitraan (Partnership System in Managing Palm Oil Plantation). AgroMedia Pustaka, 2009.

Badan Pusat Statistik, “Produksi Perkebunan Besar Tahunan Menurut Jenis Tanaman (Ribu Ton),” BADAN PUSAT STATISTIK, 2024. [Online]. Available: https://www.bps.go.id/id/ statistics-table/2/OTQjMg==/produksi-perkebunan-besar-tahunan-menurut-jenis-tanaman--ribu-ton-.html.

S. Thakur, S. Ratnam, and A. Singh, “Perkebunan Kelapa Sawit Indonesia Dalam Perspektif Pembangunan Berkelanjutan,” Palm Oil Agribus. Strateg. Policy Inst., vol. 4, no. 12, pp. 50–55, 2024.

E. Hambali and M. Rivai, “The Potential of Palm Oil Waste Biomass in Indonesia in 2020 and 2030,” IOP Conf. Ser. Earth Environ. Sci., vol. 65, no. 1, 2017.

N. Nur, Asmawati, and N. Syahra, “Perbandingan Metode k-NN dan Naïve Bayes dalam Klasifikasi Penentuan Calon Pendonor Darah,” J. Comput. Inf. Syst. ( J-CIS ), vol. 1, no. 1, pp. 21–28, Aug. 2021.

N. Puspitasari, R. Rosmasari, F. W. Pratama, and H. Sulastri, “Quality Classification of Palm Oil Varieties Using Naive Bayes Classifier,” Digit. Zo. J. Teknol. Inf. dan Komun., vol. 13, no. 1, pp. 11–23, May 2022.

N. Nurdin, “Analisa Data Mining Dalam Memprediksi Masyarakat Kurang Mampu Menggunakan Metode K-Nearest Neighbor,” J. Inform. dan Tek. Elektro Terap., vol. 12, no. 2, pp. 1090–1098, 2024.

Zunan Setiawan, Muhammad Fajar, and Arif Mudi Priyatno, Buku Ajar Data Mining. Jakarta, Indonesia: SonPedia Publishing, 2023.

A. Muzakir, A. Desiani, and A. Amran, “Klasifikasi Penyakit Kanker Prostat Menggunakan Algoritma Naïve Bayes dan K-Nearest Neighbor,” Komputika J. Sist. Komput., vol. 12, no. 1, pp. 73–79, 2023.

A. Garavand, C. Salehnasab, A. Behmanesh, and Aslani, “Efficient Model for Coronary Artery Disease Diagnosis: A Comparative Study of Several Machine Learning Algorithms,” J. Healthc. Eng., vol. 22, no. 1, p. 9, 2022.

S. Saumina, Y. Afrillia, and N. Nurdin, “Klasifikasi Usaha Mikro Kecil dan Menengah Menggunakan Metode K-Nearest Neighbors di Kota Lhokseumawe,” Jurnal Sistem Informasi Kaputama (JSIK), vol. 9, no. 2, 2025.

A. A. Fikhri, and N. Nurdin, “Implementasi Algoritma K-Nearest Neighbor Pada Sistem Pemantau Suhu Dan Kelembapan Ruang Server Menggunakan Protokol Mqtt Berbasis Iot,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, 2024.

O. Peretz, M. Koren, and O. Koren, “Naive Bayes classifier – An ensemble procedure for recall and precision enrichment,” Eng. Appl. Artif. Intell., vol. 136, Oct. 2024.

N. Nurdin, S. Abadi, and Y. Afrillia “Classification System for Soil Types Suitable for Food Crops using Naïve Bayes Method,” Sist. J. Sist. Inf., vol. 13, no. 3, hal. 1102–1113, 2025.

Moch. Rizky Yuliansyah, M. B, and A. Franz, “Perbandingan Metode K-Nearest Neighbors dan Naïve Bayes Classifier Pada Klasifikasi Status Gizi Balita di Puskesmas Muara Jawa Kota Samarinda,” Adopsi Teknol. dan Sist. Inf., vol. 1, no. 1, pp. 08–20, 2022.

M. Qamal, I. Sahputra, N. Nurdin, M. Maryana, and M. Mukarramah, Sistem Pendukung Keputusan Penentuan Penerimaan Bantuan PKH Menggunakan Metode Naïve Bayes, TECHSI: J. Tek. Inform., vol. 14, no. 1, p. 21, 2023, doi: 10.29103/techsi.v14i1.6960.

Nurdin and D. Astika, “Penerapan Data Mining Untuk Menganalisis Penjualan Barang Dengan Menggunakan Metode Apriori Pada Supermarket Sejahtera Lhokseumawe,” TECHSI - J. Tek. Inform., vol. 7, no. 1, pp. 132–155, 2019.

Isman, Andani Ahmad, and Abdul Latief, “Perbandingan Metode KNN Dan LBPH Pada Klasifikasi Daun Herbal,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 3, pp. 557–564, 2021.

B. Valentino Jayadi, T. Handhayani, and M. Dolok Lauro, “Perbandingan Knn Dan Svm Untuk Klasifikasi Kualitas Udara Di Jakarta,” J. Ilmu Komput. dan Sist. Inf., vol. 11, no. 2, pp. 11–17, 2023.