Article Per Year (5 Year)
p-Index From 2020 - 2025
1.573
P-Index
This Author published in this journals
All Journal Jurnal Info Sains : Informatika dan Sains Journal of Artificial Intelligence and Digital Business Journal of Computer Science and Research Jurnal Ilmiah Multidisiplin Indonesia Journal of Data Mining and Information Systems Multidisiplin Pengabdian Kepada Masyarakat (M-PKM) Journal of Data Science, Technology, and Artificial Intelligence Jurnal Sistem Informasi dan Teknologi Jaringan
Harefa, Ade May Luky
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Library & Information Science Nursing Physics

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Color Space Influence on Photosynthetic Pigment Measurement Accuracy Using CNN in Color Constancy Harefa, Ade May Luky; Insandi, Arief Muhazir
JDMIS: Journal of Data Mining and Information Systems Vol. 3 No. 1 (2025): February 2025
Publisher : Yayasan Pendidikan Penelitian Pengabdian Algero

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/jdmis.v3i1.4064

Abstract

This study aims to design a plant pigment measurement system using digital images and deep learning, incorporating various color spaces including RGB, HSV, LAB, and YCbCr. The proposed method serves as a faster, more cost-effective, and accurate alternative to traditional methods such as spectrophotometric analysis and HPLC. Experimental results indicate that the choice of color space and inpaint preprocessing settings significantly impacts the accuracy of the CNN P3Net model. The combination of RGB+YCbCr with inpaint and RGB+LAB without inpaint yielded the lowest validation MAE values. The study also demonstrates that color constancy phenomena influence model accuracy, with color spaces that account for this phenomenon, such as RGB+YCbCr with inpaint, providing better accuracy than those that do not.
Design and Build an Android-Based Mobile Application for Online Badminton Court Booking Priskila Parimanam; Harefa, Ade May Luky
Journal of Data Science, Technology, and Artificial Intelligence Vol. 1 No. 1 (2024): July 2024
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63703/ditech.v1i1.1

Abstract

In this digital era, the utilization of mobile technology is increasingly crucial to provide easier and faster services for users. In the design phase, a needs analysis and literature study were conducted regarding online booking applications and badminton court systems that already exist at the Sekip Badminton Center. The user interface design was created to allow users to easily book badminton courts according to their preferred time and location. This application incorporates essential features, including user authentication system, court availability calendar, time options, court type selection, and secure payment processing to enhance user convenience and experience. This research focuses on the development of an Android-based application. Quality testing processes were carried out to ensure the application functions well, is free from errors, and provides accurate results. The result of this research is a mobile application that assists users in quickly and efficiently booking badminton courts. The application improves accessibility and effectiveness in court booking, contributing positively to the development of the sports industry, particularly in the field of badminton courts.
Application of Linear Regression Method in Predicting Veil Sales (Case Study: Fauzan Kerudung Shop) Fitri Amalini; Harefa, Ade May Luky
Journal of Data Science, Technology, and Artificial Intelligence Vol. 1 No. 1 (2024): July 2024
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63703/ditech.v1i1.4

Abstract

The sales prediction system can support business transactions, especially those engaged in the trading sector, as an operational process that forecasts products to be sold in the future. One of the stores involved in the trading business is Toko Kerudung Fauzan. This kerchief store relies solely on estimates to determine the quantity of goods to be purchased from suppliers. This reliance on estimates has led to difficulties for the store owner in predicting future sales without performing calculations to maintain inventory levels in the store. Therefore, there is a significant need for a prediction system to determine kerchief sales in the future. The method employed for sales prediction is the Linear Regression Method. The number of data samples used consists of sales data collected from January to December 2022. Consequently, it can be stated that the decision to predict sales in 2023 shows a decline. 
Pengembangan Sistem Informasi Pengelolaan Jadwal dan Ruangan berbasis Website Adhitya Pratama, Yudhistira; Pratama, Yudhistira Adhitya; Nababan, Adli Abdillah; Maulana, Ade; Dulianto, Des; Harefa, Ade May Luky
Jurnal Sistem Informasi dan Teknologi Jaringan Vol 5 No 2 (2024): September
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63703/sisfotekjar.v5i2.42

Abstract

The rapid development of information technology has significantly impacted various aspects of life, including management and administration. Efficient scheduling and room management remain a major challenge for educational, governmental, and private institutions. Manual processes are often time-consuming, prone to errors, and lack flexibility in responding to dynamic changes. This research aims to design and develop a web-based information system for scheduling and room management to address these challenges effectively. The system provides features such as building and room management, schedule management, and user account handling, enhancing accessibility and reducing overlapping schedules and allocation errors. The development process involves system requirement analysis and modeling using Use Case and Entity Relationship Diagrams. The resulting system simplifies real-time monitoring, automates manual processes, and improves institutional operational efficiency. Testing through black-box methods confirmed the system's functionality and user-friendliness, ensuring reliable implementation for users. This study contributes to technological advancement by offering a practical solution to operational inefficiencies while laying the groundwork for further enhancements in system functionality and user interface design.
Implementasi Metode ELECTRE Dalam Menentukan Perekrutan Calon Model Sijabat, Petti Indrayati; Harefa, Ade May Luky; Nazara, Melfance
Jurnal Sistem Informasi dan Teknologi Jaringan Vol 6 No 1 (2025): Maret
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini membahas pengembangan sistem pendukung keputusan untuk perekrutan calon model di PT. Rama Indonesia menggunakan metode ELECTRE. Proses seleksi yang sebelumnya dilakukan secara manual sering kali mengalami kendala subjektivitas dan birokrasi yang berbelit. Oleh karena itu, penelitian ini bertujuan untuk membangun sistem yang lebih objektif dan efisien dalam menyeleksi calon model berdasarkan lima kriteria utama, yaitu Hasil Tes Wawancara, Kemampuan Berpose, Kesehatan dan Kebugaran, Portofolio, serta Keterampilan Khusus. Analisis dilakukan terhadap 10 alternatif calon model dengan menerapkan metode ELECTRE untuk menentukan peringkat berdasarkan bobot kriteria yang telah ditentukan. Hasil evaluasi menunjukkan bahwa lima kandidat berhasil memenuhi batas minimal passing grade 75%, yaitu Arifa Valkenburg (89%), Putri Mendriani (83%), Anisa Putri Ganesh (80%), Nurul (85%), dan Dinda (89%), sementara lima kandidat lainnya tidak memenuhi kriteria kelulusan. Implementasi sistem ini memungkinkan PT. Rama Indonesia untuk melakukan proses seleksi dengan lebih akurat, transparan, dan cepat. Dengan demikian, metode ELECTRE terbukti efektif dalam membantu pengambilan keputusan perekrutan calon model.
DIGITALISASI PROSES PENJUALAN MELALUI WEB BASED POINT OF SALE PADA WARUNG DEK GAM KUPHI Nababan, Adli Abdillah; Hasugian, Paska Marto; Miftahul Jannah; Harefa, Ade May Luky
Multidisiplin Pengabdian Kepada Masyarakat Vol. 4 No. 01 (2025): Multidisiplin Pengabdian Kepada Masyarakat, Maret-Juni 2025
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan efisiensi operasional dan akurasi pencatatan transaksi penjualan pada Warung Dek Gam Kuphi melalui penerapan sistem Point of Sale (POS) berbasis web. Warung tradisional pada umumnya masih melakukan pencatatan secara manual sehingga rentan terhadap kesalahan, kehilangan data, serta tidak mampu menyajikan laporan penjualan yang cepat dan akurat. Dalam kegiatan ini, tim pelaksana merancang dan mengimplementasikan sistem POS berbasis web yang dapat diakses melalui perangkat komputer maupun smartphone. Proses pelatihan dan pendampingan kepada mitra juga dilakukan secara langsung agar mitra memahami cara penggunaan sistem secara menyeluruh. Hasil kegiatan menunjukkan bahwa mitra dapat dengan mudah mengoperasikan sistem tersebut dan merasa terbantu dalam pencatatan penjualan, pengelolaan stok barang, serta pelaporan keuangan harian. Kegiatan ini memberikan dampak positif dalam mendorong digitalisasi usaha mikro, khususnya di sektor perdagangan kecil. Kedepan, sistem ini dapat dikembangkan lebih lanjut dengan integrasi metode pembayaran digital dan fitur analisis penjualan untuk mendukung pengambilan keputusan bisnis yang lebih baik.
Analysis of the Monte Carlo Method in Simulation of Snake and Ladder Game Using R Programming Afif Yasri; Ramlan Marbun; Harefa, Ade May Luky; Muhammad Syahputra Novelan
Jurnal Info Sains : Informatika dan Sains Vol. 15 No. 01 (2025): Informatika dan Sains , 2025
Publisher : SEAN Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study applies the Monte Carlo method to simulate the classic board game "Snakes and Ladders" using the R programming language. The research aims to explore how randomness and probability influence the number of moves needed to complete the game and to provide a statistical overview of game outcomes. A simulation of 10,000 iterations was conducted, where each iteration represents one complete game play, starting from position 1 and ending exactly at position 100. The results show that players require an average of 51.41 moves to finish the game, with a minimum of 8 and a maximum of 394 moves. These results illustrate the highly variable nature of the game due to random dice rolls and the presence of snakes and ladders that can significantly alter a player's position. Visualization techniques such as histograms, density plots, boxplots, and line graphs were used to represent the distribution and variability of moves. The findings demonstrate the effectiveness of Monte Carlo simulations in analyzing stochastic systems, where outcomes are driven by random variables. This research contributes to the understanding of probabilistic modeling and can serve as a simple yet insightful example of applying computational methods to real-world scenarios.
TaniMarket: An E-Commerce Platform for Empowering Local Agricultural MSMEs Miftahul Jannah; Nababan, Adli Abdillah; Medhian Ahmadi Putra; Jijon Raphita Sagala; Harefa, Ade May Luky
Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID) Vol. 4 No. 05 (2025): Jurnal Ilmiah Multidisplin Indonesia (JIM-ID), June 2025
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The development of information technology provides a great opportunity for Micro, Small, and Medium Enterprises (MSMEs) to market their products digitally, including in the agricultural sector. However, there are still many agricultural MSME actors who have not utilized this technology optimally. This research aims to build a webbased information system called TaniMarket, which can be used as a means of marketing agricultural products by MSME actors. Application development is carried out using the Waterfall method, which includes the stages of needs analysis, system design, implementation, testing, and maintenance. The application is built using PHP programming language version 8.1, the CodeIgniter 4 framework, and the MySQL database. This system consists of two main roles, namely admin and user. Admins have full access to product and category management features, including adding, modifying, and deleting data, as well as uploading images and order information. Meanwhile, users can view a list of products by category and place orders directly through the WhatsApp button that has been provided with automatic messages. The results of the system test show that all features run according to the design that has been determined. The TaniMarket application is considered to be able to provide convenience for MSME actors in marketing their garden products more widely and efficiently. With a simple and responsive interface, this system also supports users in accessing product information quickly and practically. Overall, this application is an effective digital solution in supporting the increase in the competitiveness of agricultural MSMEs in the era of digital transformation.
Enhanced Rainfall Forecasting Through Deep Learning Optimization Using Long Short-Term Memory Networks Harefa, Ade May Luky; Antoni, Robin; Sitepu, Andri Ismail; Limbong, Yohannes France; Novelan, Muhammad Syahputra
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 4 No. 2 (2025): Mei - Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v4i2.487

Abstract

This study aims to develop a rainfall prediction system using Deep Learning with the Long Short-Term Memory (LSTM) method to improve prediction accuracy and efficiency. The model was built using rainfall data from Gunung Sitoli, covering the period from October 16 to December 14, 2004. The dataset was divided into 90% for training and 10% for testing. The LSTM model was configured with 1 hidden layer and trained for 50 epochs. To evaluate its performance, the Mean Squared Error (MSE) metric was applied. The model achieved an MSE of 0.03 on the test data, indicating a low prediction error and good accuracy. This result shows that LSTM is capable of learning rainfall patterns over time and producing reliable forecasts. Furthermore, the model was integrated into a system to streamline the forecasting and evaluation process. This integration provides an efficient alternative to manual calculations, offering users faster and more accessible predictions. The implementation of this system is especially beneficial for early warning and decision-making processes in regions like Gunung Sitoli, where rainfall patterns can significantly impact on daily activities and disaster preparedness.
Implementation of Grey Wolf Optimizer (GWO) Algorithm for Predicting Multidrug Resistance Patterns in Bacteria Harefa, Ade May Luky
Journal of Computer Science and Research (JoCoSiR) Vol. 2 No. 2 (2024): April: Computer Science
Publisher : Asosiasi Perguruan Tinggi Informatika dan Ilmu Komputer (APTIKOM) Provinsi Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65126/jocosir.v2i2.62

Abstract

The emergence of multidrug-resistant (MDR) bacterial pathogens poses a critical threat to global health, demanding intelligent and adaptive predictive systems. This study proposes the application of the Grey Wolf Optimizer (GWO) algorithm as an innovative computational approach for predicting and analyzing multidrug resistance patterns in clinical bacterial isolates. Unlike conventional statistical methods that often fail to handle complex, nonlinear biomedical data, GWO effectively balances exploration and exploitation through swarm intelligence inspired by wolf hierarchy and hunting behavior. A dataset of 10,700 clinical bacterial samples obtained from Kaggle was analyzed, encompassing antibiotic susceptibility profiles and clinical parameters such as patient comorbidities and hospitalization history. The data were normalized and optimized using GWO to identify the most influential attributes contributing to antibiotic resistance. Experimental results demonstrate that GWO achieves strong stability in convergence, efficiently identifying dominant resistance predictors such as CTX/CRO, FOX, and IPM. Compared to traditional optimization methods, GWO offers improved accuracy and robustness in feature weighting and selection. The study concludes that GWO provides a scalable and interpretable framework for multidrug resistance prediction, enabling early identification of critical resistance trends. The implementation of this approach can assist healthcare institutions in formulating more precise antimicrobial stewardship strategies and controlling the spread of resistant pathogens in clinical environments.
Co-Authors Ade Maulana Adhitya Pratama, Yudhistira Afif Yasri Antoni, Robin Dulianto, Des Fitri Amalini Hasugian , Paska Marto Insandi, Arief Muhazir Jijon Raphita Sagala Limbong, Yohannes France Medhian Ahmadi Putra MIFTAHUL JANNAH Muhammad Syahputra Novelan Nababan, Adli Abdillah Nazara, Melfance Priskila Parimanam Ramlan Marbun Sijabat, Petti Indrayati Sitepu, Andri Ismail Yudhistira Adhitya Pratama