SISTEM KLASIFIKASI TINGKAT KEMATANGAN BUAH KOPI MENGGUNAKAN METODE K-NEAREST NEIGHBOR

Rahmi Hidayati; Fadhilah Dhia Azzahra; Kartika Sari

doi:10.33365/jtst.v6i2.431

Rahmi Hidayati Universitas Tanjungpura
Fadhilah Dhia Azzahra Universitas Tanjungpura
Kartika Sari Universitas Tanjungpura

DOI: https://doi.org/10.33365/jtst.v6i2.431

Keywords: Ripeness, Coffee Fruit, K-NN, Classification, TCS3200

Abstract

Coffee fruit is an agricultural product with high economic value and is one of the main plantation commodities in many tropical countries. In its utilization, coffee fruit can be processed into beverages, medicines, and beauty products. To produce high-quality processed products, the sorting of coffee fruit is essential. This research developed a system to classify the ripeness of coffee fruit. The coffee fruit has verying of ripeness, indicated different colors. The sensor used is the TCS3200 color sensor to detect the color of the coffee fruit, and the K-Nearest Neighbor (K-NN) method is implemented for classification. Data from the TCS3200 sensor is used as training and testing data for K-NN classification. In this study, a total of 120 training data and 45 testing data were used. The results of this research classify the ripeness of coffee fruit into three categories: unripe, ripe, and overripe. Based on testing results using a confusion matrix with different K values, the highest accuracy achieved was 88.9% with K=3.

References

[1] S. A. Sembiring, P. Marbun, and kemala sari Lubis, “Kajian Jumlah Biji Basah Dan Berat Bji Basah Kopi Robusta (Coffea Robusta Lindl.) pada Beberapa Ketinggian, Kemiringan Lereng Dan Jenis Tanah Di Kecamatan Silima Pungga-Pungga Kabupaten Dairi,” J. Agroekoteknologi, vol. 4, no. 1, pp. 1857–1864, 2016.
[2] A. Ahyuna and H. Herlinda, “Pembuatan Alat Pemisah Buah Kopi Otomatis Berdasarkan Warna Menggunakan Sensor Warna Tcs230 Berbasis Mikrokontroler,” J. Ilm. Matrik, vol. 22, no. 2, pp. 139–146, 2020, doi: 10.33557/jurnalmatrik.v22i2.940.
[3] T. Iflah and D. N. Rokhmah, “Faktor Yang Mempengaruhi Mutu Dan Citarasa Kopi,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 10, pp. 10294–10299, 2019.
[4] S. Srikandi, A. W. Kristanti, and R. Sutamihardja, “Tingkat Kematangan Biji Kopi Arabica (Coffea arabica L.) Dalam Menghasilkan Kadar Kafein,” J. Sains Nat., vol. 9, no. 1, p. 22, 2019, doi: 10.31938/jsn.v9i1.189.
[5] J. W. G. Putra, Pengenalan Konsep Pembelajaran Mesin dan Deep Learning, vol. 4. 2020. [Online]. Available: https://www.researchgate.net/publication/323700644
[6] P. P. Anchalia and K. Roy, “The k-nearest neighbor algorithm using MapReduce paradigm,” Proc. - Int. Conf. Intell. Syst. Model. Simulation, ISMS, vol. 2015-September, pp. 513–518, 2015, doi: 10.1109/ISMS.2014.94.
[7] Marisa Fitri et al., “Pengukuran Tingkat Kematangan Kopi Arabika Menggunakan Algoritma K-Nearest Neighbour,” JIMP J. Inform. Merdeka Pasuruan, vol. vol.6 no.3, no. 3, pp. 4–8, 2021.
[8] D. Ennis, “The Effects of Caffeine on Health: The Benefits Outweigh the Risks,” Perspectives (Montclair)., vol. 6, no. 1, pp. 1–5, 2014.
[9] Malabay, “Pemanfaatan Flowchart Untuk Kebutuhan Deskripsi Proses Bisnis,” J. Ilmu Komput., vol. 12, no. 1, pp. 21–26, 2016, [Online]. Available: https://digilib.esaunggul.ac.id/pemanfaatan-flowchart-untuk-kebutuhan-deskripsi-proses-bisnis-9347.html
[10] Mustika et al., Data Mining dan Aplikasinya. 2021. [Online]. Available: https://repository.penerbitwidina.com/uk/publications/351768/data-mining-dan-aplikasinya
[11] N. N. Dzikrulloh and B. D. Setiawan, “Penerapan Metode K – Nearest Neighbor ( KNN ) dan Metode Weighted Product ( WP ) Dalam Penerimaan Calon Guru Dan Karyawan Tata Usaha Baru Berwawasan Teknologi ( Studi Kasus : Sekolah Menengah Kejuruan Muhammadiyah 2 Kediri ),” Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 1, no. 5, pp. 378–385, 2017.
[12] A. Iskandar, M. Muhajirin, and L. Lisah, “Sistem Keamanan Pintu Berbasis Arduino Mega,” J. Inform. Upgris, vol. 3, no. 2, pp. 99–104, 2017, doi: 10.26877/jiu.v3i2.1803.
[13] I. F. Rahmad, “Pendeteksi Kesegaran Buah Menggunakan Sensor Warna dan Kelembaban,” Jurikom), vol. 6, no. 5, pp. 550–558, 2019, [Online]. Available: http://ejurnal.stmik-budidarma.ac.id/index.php/jurikom%7CPage550
[14] A. R. Wiguna, “Analisis Cara Kerja Sensor Ultrasonic Dan Motor Servo Menggunakan Mikrokontroler Arduino Uno Untuk Pengusir Hama Disawah Smart Room View project Fuzzy Inference System View project,” Univ. Bandar Lampung, 2020, [Online]. Available: https://www.researchgate.net/publication/347690066
[15] A. N. Putra, “Sistem Otomasi Pengering Pakaian Berbasis Mikrokontroller Arduino,” J. Saintek, vol. 13, no. 2, pp. 126–131, 2016.
[16] M. Yusup, P. A. Sunarya, and K. Aprilyanto, “Rancang Bangun Sistem Monitoring Pengukuran Volume Air Berbasis IoT Menggunakan Arduino Wemos,” J. CERITA, vol. 6, no. 2, pp. 147–153, 2020, doi: 10.33050/cerita.v6i2.1136.