Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal Jurnal Inotera Vocatech : Vocational Education and Technology Journal
Nica Astrianda
Universitas Teuku Umar
Civil Engineering, Building, Construction & Architecture Computer Science & IT Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Clustering of Palm Oil Production Results with K-Means Algorithm in West Aceh Regency Sanusi; Ilham Juliwardi; Muhammad Ardiansyah; Nica Astrianda; Ana Elviajakfar
Jurnal Inotera Vol. 7 No. 1 (2022): January-June 2022
Publisher : LPPM Politeknik Aceh Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31572/inotera.Vol7.Iss1.2022.ID168

Abstract

The area and production of oil palm in West Aceh continues to experience a significant increase, because along with the expansion of oil palm plantations in the local area, it is very influential on employment and improving the economy of the community. This study aims to group the results of oil palm production and planted area by applying the data mining technique method with the K-Means Clustering algorithm. The data used in this study in the form of area and palm oil production results were obtained from the West Aceh catalog (BAPPEDA) and the Central Statistics Agency from 2005 to 2020 in 12 sub-districts of West Aceh Regency. The results of the study showed that the high cluster (cluster 1) contained 1 sub-district, namely Kaway XVI, the medium cluster (cluster 0) there were 7 sub-districts namely Bubon, Johan Pahlawan, Panten Reu, Samatiga, Sungai Mas, Woyla Barat, and Woyla Barat, while the cluster low (cluster 2), there are 4 sub-districts, namely Arongan Lambalek, Meureubo, Pante Ceureumen, and Woyla.
Klasifikasi Kematangan Buah Tomat Dengan Variasi Model Warna Menggunakan Support Vector Machine Nica Astrianda
VOCATECH: Vocational Education and Technology Journal Vol 1, No 2 (2020): April
Publisher : Akademi Komunitas Negeri Aceh Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38038/vocatech.v1i2.27

Abstract

Abstract Tomato ripeness classification has been done manually through direct visual observation. However, manual classification is highly influenced by operator subjectivity so that on certain conditions, the classification process is not consistent. The development of information technology allows the identification of the ripeness level of tomatoes based on the characteristics of color with the help of computers. In this study Tomato fruit is classified by histogram color image input obtained from the capture result. This is done by changing all the colors in the image of the RGB color model (Red, Green, Blue) into several different color models ie HSV color model (Hue, Saturation, Value), CIElab color model and YCBCR color model. The obtained color model will be used as training data using SVM (Support Vector Machine) so that the system is able to classify the ripeness of tomato fruit later. The image processing process of this research is done using matlab. After being analyzed manually using 20 data as training, 54 data as data testing got success rate classification of tomato fruit ripeness using Support Vector Machine is 100% by using CIElab color model. Keywords: Support Vector Machine; CIElab; HSV; YCbCr; Ripeness of Tomato ____________________________ Abstrak Klasifikasi kematangan tomat telah dilakukan secara manual melalui pengamatan visual langsung. Namun, klasifikasi manual sangat dipengaruhi oleh subjektivitas operator sehingga pada kondisi tertentu, proses klasifikasi tidak konsisten. Perkembangan teknologi informasi memungkinkan identifikasi tingkat kematangan tomat berdasarkan karakteristik warna dengan bantuan komputer. Dalam penelitian ini buah tomat diklasifikasikan berdasarkan input gambar berwarna histogram yang diperoleh dari hasil tangkapan. Hal ini dilakukan dengan mengubah semua warna pada gambar model warna RGB (Red, Green, Blue) menjadi beberapa model warna yang berbeda yaitu model warna HSV (Hue, Saturation, Value), model warna CIElab dan model warna YCBCR. Model warna yang diperoleh akan digunakan sebagai data pelatihan menggunakan SVM (Support Vector Machine) sehingga sistem mampu mengklasifikasikan kematangan buah tomat. Proses pengolahan citra pada penelitian ini dilakukan dengan menggunakan matlab. Setelah dianalisis secara manual menggunakan 20 data sebagai data pelatihan, 54 data sebagai data pengujian mendapatkan klasifikasi tingkat keberhasilan kematangan buah tomat menggunakan Support Vector Machine adalah 100% dengan menggunakan model warna CIElab. Kata Kunci: Support Vector Machine; CIElab; HSV; YCbCr; Kematangan Tomat. __________________________
KLASIFIKASI KEMATANGAN TOMAT DENGAN MODEL WARNA YANG BERBEDA MENGGUNAKAN LINEAR DISKRIMINAN ANALISIS (LDA) Nica Astrianda; Hayatun Maghfirah; Fatma Susilawati Mohamad
VOCATECH: Vocational Education and Technology Journal Vol 3, No 2 (2022): April
Publisher : Akademi Komunitas Negeri Aceh Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38038/vocatech.v3i2.75

Abstract

AbstractQuality of fruits depend heavily on the right time of plucking plus the right stage of ripeness to ensure its highest quality before selling. Tomatoes are one of the fruits that have a relatively fast maturity process. So that the classification of  tomato maturity has an  important role to reduce the risk of spoilage of tomato. Color is one of the attributes that can be used to identify the ripeness of tomato and it is one of the most distinctive characteristic of the fruits and vegetables that grow in tropical climates. In this study, the goal is to classify tomatoes maturity using color based predominant images. Linear Discriminant Analysis (LDA) is used to classify the ripeness classes based on three color models (HSV, YCbCr and CIElab). Comparisons are made between these color models for system accuracy and running time. For the highest accuracy of 95% achieved with a running time of 3,425 seconds with the CIElab color model, and a low of 67% with a running time of 3,526 seconds using the YcbCr color model, and 85% with the fastest system running time of 3,253 seconds obtained by the HSV color model.Keywords:Keywords: Linear Discriminant Analysis, HSV, YCbCr, CIELab, ripeness,  Tomatoes __________________________ AbstrakKualitas buah sangat bergantung pada waktu yang tepat untuk memetik ditambah tahap kematangan yang tepat untuk memastikan kualitas tertinggi sebelum dijual. Tomat adalah salah satu buah yang memiliki proses kematangan yang relatif cepat. Sehingga klasifikasi kematangan tomat memiliki peran penting untuk mengurangi resiko pembusukan tomat. Warna adalah salah satu atribut yang dapat digunakan untuk mengidentifikasi kematangan tomat dan itu adalah salah satu karakteristik yang paling khas dari buah-buahan dan sayuran yang tumbuh di iklim tropis. Dalam penelitian ini, tujuannya adalah untuk mengklasifikasikan kematangan tomat menggunakan gambar dominan berbasis warna. Linear Discriminant Analysis (LDA) digunakan untuk mengklasifikasikan Tingkat kematangan berdasarkan  tiga model warna berbeda yaitu  HSV, YCbCr dan CIElab. Perbandingan dibuat antara model warna ini untuk akurasi dan running time sistem. Untuk akurasi  tertinggi 95% dicapai dengan running time 3.425 detik dengan menggunakan model warna CIElab, dan terendah 67% dengan running time 3.526 detik menggunakan model warna YcbCr, dan 85% dengan running time sistem tercepat 3.253 detik diperoleh oleh model warna HSV.Kata Kunci:Kata kunci: Analisis Diskriminan Linier, HSV, YCbCr, CIELab, kematangan, Tomat 
Co-Authors Ana Elvia Jakfar Fatma Susilawati Mohamad Hayatun Maghfirah Ilham Juliwardi Muhammad Ardiansyah Sanusi