Rancang Bangun Sistem Klasifikasi Biji Pinang Menggunakan Metode Nearest Mean Classifier Berbasis Android

Andika Firmansyah, Abdullah Abdullah, Samsudin Samsudin

Abstract


Abstrak

Pinang (areca catechu) merupakan tumbuhan yang memiliki nilai ekonomis. Buah pinang dikupas kulitnya diolah menjadi biji pinang kering dan selanjutnya dijual ke pengepul.  Budidaya pinang mudah dilakukan dan tidak butuh pemeliharaan ekstra dalam perawatannya, sehingga sebagian besar masyarakat di daerah ini senang menjadi petani pinang. Walau bagaimanapun juga penentuan harga biji pinang berdasarkan persentase kekeringan pinang menimbulkan masalah. Penentuan dilakukan sepihak oleh pihak pengepul, dimana dilakukan secara kasat mata sehingga kurang akurat, sehingga berpotensi merugikan pihak petani pinang. Oleh karena itu tujuan penelitian ini adalah membangun sebuah aplikasi sistem cerdas yang dapat membantu dalam mengidentifikasi persentase kekeringan biji pinang. Aplikasi ini berbasis android yang memanfaatkan kamera hand phone yang terdapat di perangkat pintar ponsel android. Penelitian ini akan mencari fitur yang tepat digunakan sebagai pembeda kekeringan antara biji pinang yang satu dengan yang lain. Penelitian ini juga akan mencari algoritma yang tepat untuk melakukan klasifikasi persentase kekeringan biji pinang tersebut. Berdasarkan hasil evaluasi diketahui tingkat akurasi metode Nearest Mean Classifier dalam menentukan kualitas biji pinang adalah sebesar 80 % dengan simpangan baku 7,6. Aplikasi ini diharapkan dapat membantu proses klasifikasi biji pinang dengan lebih cepat, tepat dan akurat dengan memuaskan kedua belah pihak pengepul dan petani. Aplikasi ini juga diharapkan dapat diterima untuk dijadikan alat ukur standar dalam penentuan persentase kekeringan biji pinang sehingga bermanfaat dalam rangka menentukan harga jual biji pinang.

Kata Kunci: android, sistem cerdas, klasifikasi, biji pinang

 

Abstract

Areca nut (areca catechu) is a plant that has economic value. The peeled areca nut is processed into dried areca nut and then sold to collectors. Cultivating areca nut is easy to do and does not require extra maintenance to maintain, so most people in this area are happy to be areca nut farmers. However, determining the price of areca nut based on the percentage of dryness of the areca nut creates problems. The collectors make the determination unilaterally, which is done in manual so that it is less accurate, so it has the potential to harm the areca nut farmers. Therefore, the aim of this research is to build a smart system application that can help identify the dry percentage of areca nuts. This application is based on android which utilizes a camera device on an android smartphone. This study identify the features that are appropriate to classify areca nuts. This research will also identify the right algorithm to classify the percentage of dryness of the areca nuts. Based on the results of the evaluation, it is known that the accuracy rate of the Nearest Mean Classifier method in determining the quality of areca nuts is 80% with a standard deviation of 7.6. This application is expected to help the classification process of areca nuts more quickly, precisely and accurately by satisfying both collectors and farmers. This application is also expected to be accepted as a standard measuring tool in determining the percentage of dryness of areca nuts so that it is useful in determining the selling price of areca nuts.

Keywords: android, areca nuts, classification, intelligent system


Full Text:

PDF

References


F. D. Korwa, J. Husain, T. Titah, and J. Supit, “Evaluasi Kesesuaian Lahan untuk Tanaman Pinang (Areca catechu) di Das Remu, Sorong, Papua Barat,” J. Cocos, vol. 7, no. 4, pp. 1–8, 2015.

R. Barlina, “Peluang Pemanfaatan Buah Pinang untuk Pangan Opportunity of Arecanut for Food Utilizing,” Bul. Palma, vol. 33, pp. 96–105, 2007.

I. D. G. P. Prabawa, “Ekstrak Biji Buah Pinang Sebagai Pewarna Alami pada Kain Sasiringan,” J. Ris. Ind. Has. Hutan, vol. 75, no. 2, pp. 31–38, 2015.

P. Hartono and Trismiyati, “Klasifikasi Biji Pinang Belah pada Pengembangan Mesin Sortir Pinang menggunakan Pengolahan Citra Digital,” J. Ris. Ind., vol. 10, no. 2, pp. 61–69, 2016.

Miftahorrachman, “Diversitasi Genetik Tujuh Aksesi Plasma Nutfah Piang (Areca catechu L.) Asal Pulau Sumatera,” J. LITTRI, vol. 12, no. 1, pp. 27–31, 2006.

Balai Penelitian Tanaman Palma, “Prospek Pengembangan Tanaman Pinang,” Warta Penelitian dan Pengembangan Pertanian, vol. 34, no. 1, pp. 10–11, 2012.

S. K. Bhat, D. Ashwin, S. Mythri, and S. Bhat, “Arecanut ( Areca catechu L ) decreases Alzheimer’s disease symptoms: Compilation of research works,” J. Med. Plants Stud., vol. 5, no. 5, pp. 4–9, 2017.

E. Y. Kartika, “Penentuan kadar air dan kadar abu pada biskuit,” J. Kim. Anal., vol. 2, pp. 1–10, 2014.

N. H. Kario, “Analisis Usaha Panen Cengkeh di Kabupaten Minahasa Tenggara Propinsi Sulawesi Utara,” J. Agritech, vol. XVI, no. 2, pp. 146–156, 2014.

K. Huang, “Detection and classification of areca nuts with machine vision,” Comput. Math. with Appl., vol. 64, no. 5, pp. 739–746, 2012.

A. Danti and Suresha, “Segmentation and Classification of Raw Arecanuts Based on Three Sigma Control Limits,” Procedia Technol., vol. 4, September, pp. 215–219, 2012.

K. Kran, A. K. Govin, M. Bandi, and Shivasharanayya, “Design, Development and Testing of an Areca nut Dehusking Agri-machine,” Int. J. Eng. Res. Appl., vol. 4, no. 7, pp. 109–115, 2014.

M. N. Fauzi and Mahaputra, “Rncang Bangun Mesin Pemilah Biji Pinang (Sorting Betel Nut Machine Design Building),” J. Ris. Teknol. Ind., vol. 9, no. 2, pp. 157–166, 2015.

B. S. Ajith, B. C. Pramod, Y. D. Impha, H. S. Rakshith, K. Sudeep, and P. Padavu, “Modelling, Fabrication and Automation of Areca Nut Sorting Machine,” J. Mech. Eng. Autom., vol. 7, no. 4, pp. 99–102, 2017.

J. U. Bailoor, M. C. Sunny, K. R. Anchan, M. J. Tauro, and G. Shetty, “Segregation of Cashew Kernel and Areca Nut by Using Advanced Color Sorting Mechanism,” Int. J. Sci. Dev. Res., vol. 3, no. 5, pp. 566–572, 2018.

Abdullah, “Ant-based feature decomposition Method in constructing NMC and NBC ensembles,” Int. J. Comput. Trends Technol., vol. 30, no. 1, pp. 46–49, 2015.

S. Raschka, Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. 2018.

P. Thomas, H. Bril El Haouzi, M. C. Suhner, A. Thomas, E. Zimmermann, and M. Noyel, “Using a classifier ensemble for proactive quality monitoring and control: The impact of the choice of classifiers types, selection criterion, and fusion process,” Computers in Industry. 2018.




DOI: https://doi.org/10.32520/stmsi.v10i1.1207

Article Metrics

Abstract view : 996 times
PDF - 470 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
https://learning.modernland.co.id/api/toto/http://himatikauny.org/wp-includes/mahjong-ways-3/https://www.jst.hvu.edu.vn/akun-pro-kamboja/https://section.iaesonline.com/akun-pro-kamboja/https://journals.uol.edu.pk/sugar-rush/http://mysimpeg.gowakab.go.id/mysimpeg/aset/https://jurnal.jsa.ikippgriptk.ac.id/plugins/https://ppid.cimahikota.go.id/assets/demo/https://journals.zetech.ac.ke/scatter-hitam/https://silasa.sarolangunkab.go.id/swal/https://sipirus.sukabumikab.go.id/storage/uploads/-/sthai/https://sipirus.sukabumikab.go.id/storage/uploads/-/stoto/https://alwasilahlilhasanah.ac.id/starlight-princess-1000/https://www.remap.ugto.mx/pages/slot-luar-negeri-winrate-tertinggi/https://waper.serdangbedagaikab.go.id/storage/sgacor/https://waper.serdangbedagaikab.go.id/public/images/qrcode/slot-dana/https://siipbang.katingankab.go.id/storage_old/maxwin/https://waper.serdangbedagaikab.go.id/public/img/cover/10k/