Utama, Nafi Ananda
Program Studi Agroteknologi, Fakultas Pertanian, Universitas Muhammadiyah Yogyakarta, Jl. Lingkar Selatan, Kasihan, Bantul, Yogyakarta 55183, Indonesia, Telp. 0274 387656.

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

Analysis of Cross Validation on Classification of Mangosteen Maturity Stages using Support Vector Machine Prabasari, Indira; Zuhri, Afrizal; Riyadi, Slamet; Hariadi, Tony K; Utama, Nafi Ananda
Emerging Information Science and Technology Vol 5, No 1 (2024): May
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/eist.v5i1.22359

Abstract

This study explores the efficacy of the Support Vector Machine (SVM) method in classifying mangosteen fruit images based on six ripeness levels. Employing SVM enables nonlinear data classification and simultaneous utilization of multiple feature extractions, resulting in enhanced accuracy. Analysis reveals that models integrating three feature extractions outperform those with only two. With ample training data and optimized parameters, SVM achieves detection accuracy exceeding 90%. However, algorithmic enhancements are necessary to compute RGB color index values for all pixels on mangosteen skin surfaces, possibly through circular-shaped windows approximating the fruit's contour. Moreover, comparative assessments of RGB color system calculations against alternative systems such as HSI are crucial for selecting the most suitable color model in alignment with human perception.
Classification of Mangosteen Surface Quality Using Principal Component Analysis Riyadi, Slamet; Ayu Ratiwi, Amelia Mutiara; Damarjati, Cahya; Hariadi, Tony K.; Prabasari, Indira; Utama, Nafi Ananda
Emerging Information Science and Technology Vol. 1 No. 1: February 2020
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/eist.115

Abstract

Mangosteen (Garcinia mangostana L) is one of the primary contributor for Indonesia export. For export commodity, the fruit should comply the quality requirement including its surface. Presently, the surface is evaluated by human visual to classify between defect and non- defect surface. This conventional method is less accurate and takes time, especially in high volume harvest. In order to overcome this problem, this research proposed images processing based classification method using principal component analysis (PCA). The method involved pre-processing task, PCA decomposition, and statistical features extraction and classification task using linear discriminant analysis. The method has been tested on 120 images by applying 4-fold cross validation method and achieve classification accuracy of 96.67%, 90.00%, 90.00% and 100.00% for fold-1, fold-2, fold-3 and fold-4, respectively. In conclusion, the proposed method succeeded to classify between defect and non-defect mangosteen surface with 94.16% accuracy.
Implementation of the Smart & Green Building Concept in the UMY Student Dormitory Building Sukamta, Sukamta; Jamal, Agus; Utama, Nafi Ananda; Suryanto, Rudy; Subandono, Bagus; Budiyanto, Gunawan; Suryanto, Arwan
Berdikari: Jurnal Inovasi dan Penerapan Ipteks Vol. 13 No. 2: August 2025
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/berdikari.v13i2.28064

Abstract

The design of student housing in the modern era is not only required to provide functional comfort but also to address the challenges of energy efficiency and environmental sustainability. Universitas Muhammadiyah Yogyakarta (UMY) responds to these needs through the development of a Student Dormitory that adopts the principles of smart and green building. The purpose of this community engagement program is to evaluate the implementation of intelligent and environmentally friendly building concepts from technical, functional, and operational economic perspectives. This program employs a case study method with a descriptive qualitative approach, based on the analysis of building technical documents and a review of relevant national and international scientific literature. The findings show that the integration of digital access control systems (smart access), energy-efficient VRV (Variable Refrigerant Volume) cooling, harmonic filters, solar water heaters, and the use of Panasap Blue Glass has significantly contributed to reducing energy consumption by up to 40%. In addition to enhancing residents’ comfort and security, these technologies also demonstrate potential investment payback within 5 to 7 years. The implications extend beyond cost and operational efficiency, contributing directly to the achievement of the Sustainable Development Goals (SDGs). Furthermore, this program is grounded on the principle of sustainability, emphasizing the long-term utilization of eco-friendly technologies, the principle of benefit, ensuring tangible advantages for students, the university, and the wider community through improved quality of life and reduced carbon footprint; and the principle of economic viability, guaranteeing operational cost efficiency and financial sustainability of the project. The strategic objectives of this community engagement initiative are (1) to establish UMY’s Student Dormitory as a model of environmentally conscious student housing in tropical regions, (2) to promote knowledge and technology transfer on smart and green buildings to other universities, (3) to strengthen UMY’s reputation as a modern campus aligned with the SDGs agenda, and (4) to create an energy-efficient housing ecosystem that contributes to long-term cost savings and improved residents’ well-being. In conclusion, the study indicates that UMY’s student housing model, based on smart and green building principles, is feasible to adopt as a reference for dormitory development in other higher education institutions, particularly in tropical areas