Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal International Journal of Engineering, Science and Information Technology Journal of Artificial Intelligence and Digital Business
Jamaludin Hakim
Universitas Yapis Papua
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation

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

Found 3 Documents
Search

 1 
Perbandingan EfficientNet B0 dan DenseNet121 untuk Klasifikasi Jenis Mangga Berdasarkan Citra Daun Siti Khairunnisa Ratu Rahmah; Muhammad Ali Nur Hidayat; Jamaludin Hakim; Mursalim Tonggiroh; Damar Surya Sasono; Stefanus Ndala
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.13366

Abstract

Identifikasi jenis mangga secara konvensional umumnya dilakukan melalui pengamatan visual terhadap karakteristik fisik daun, seperti bentuk, ukuran, dan tekstur. Namun, metode tersebut cenderung bersifat subjektif, membutuhkan waktu yang relatif lama, serta memerlukan keahlian khusus. Perkembangan teknologi di bidang computer vision dan deep learning memungkinkan proses identifikasi tanaman dilakukan secara otomatis melalui klasifikasi citra. Penelitian ini bertujuan untuk membandingkan performa dua arsitektur Convolutional Neural Network (CNN), yaitu DenseNet121 dan EfficientNet B0, dalam mengklasifikasikan jenis mangga berdasarkan citra daun. Dataset yang digunakan terdiri dari empat jenis mangga, yaitu Arumanis, Golek, Indramayu, dan Kweni, yang diperoleh melalui pengambilan gambar secara langsung. Untuk meningkatkan variasi data, dilakukan proses augmentasi berupa rotasi, flipping, zooming, dan pengaturan pencahayaan. Tahapan penelitian meliputi preprocessing citra, augmentasi data, pelatihan model, serta evaluasi menggunakan metrik akurasi, precision, recall, F1-score, dan confusion matrix. Hasil penelitian menunjukkan bahwa model DenseNet121 memperoleh performa terbaik dengan tingkat akurasi sebesar 93%, sedangkan EfficientNet B0 memperoleh akurasi sebesar 31%. Dengan demikian, dapat disimpulkan bahwa DenseNet121 lebih efektif digunakan dalam klasifikasi jenis mangga berdasarkan citra daun dibandingkan EfficientNet B0.
Building a Web Crawler for Text Data Indexing on Online Newspaper Web Jamaludin Hakim; Andrian Sah; Siti Nurhayati; Wahyu Ciptaningrum; Damar Suryo Sasono
International Journal of Engineering, Science and Information Technology Vol 4, No 4 (2024)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v4i4.677

Abstract

The Internet has become a vast repository of information, often filled with distractions that can hinder the user experience. News content, for example, is usually interspersed with advertisements that interrupt the flow of reading. In addition, the fast pace of news publication is also a challenge, with potentially more than 50 new articles appearing in 20 minutes. This high-speed data flow is valuable for various applications, including Social Media Analytics Services. In this context, the speed and efficiency of data acquisition (crawling) and processing (scraping) are critical. These processes must be optimized to ensure comprehensive data collection without gaps, focusing on the latest information. To meet this need, we propose developing an application capable of capturing news data in its entirety, minimizing the risk of missing important information. At the core of this solution is a web crawler- a sophisticated program designed to automatically browse the hyperlink structure of the web, systematically downloading linked pages to local storage. This crawling methodology is often the basis for web mining initiatives and search engine development. Since web information is distributed across billions of pages hosted on millions of servers worldwide, our application utilizes the PHP programming language to capture and process this data effectively. The main goal is to present pure news content to users without any irrelevant elements. We use a Data Flow Diagram (DFD) to model the system architecture and data flow. This approach provides a clear visualization of how web users can navigate through hyperlinks to efficiently access the desired news information. By implementing this system, we aim to improve the user experience of consuming news content, facilitate more effective data analysis, and contribute to the broader web information search and processing field.
Heigh Detection System Using Russel and Rao Method Jamaludin Hakim; Mursalim Tonggiroh; Siti Nurhayati; M. Ali Nur Hidayat; Andrian Sah
International Journal of Engineering, Science and Information Technology Vol 4, No 4 (2024)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v4i4.671

Abstract

Height detection is an exciting area of research with broad applications in fields such as construction, healthcare, and robotics, where measurements are still often done manually. This research aims to automate the height calculation process by developing a height detection system using image processing techniques, which offers improved accuracy and efficiency. The system that will be built works by capturing images of objects through a webcam and using the Russel Rao cluster analysis method to calculate height later. Borland Delphi 07 was chosen as the programming language because of its ability to handle image-processing tasks. This research draws on a thorough literature review of various books and articles, with the system operating in stages, starting with converting images to grayscale to simplify the data for more accessible analysis and then followed by applying Russel Rao's method for height measurement. However, the system is sensitive to environmental factors around the object. The system will perform best when there are no other objects near the target because when there are other objects nearby, it can cause the measurement line to shift and interfere with the results. The detection system requires a controlled environment with no foreign objects nearby for optimal performance. Despite these limitations, Russel Rao's analysis method achieved an accurate detection accuracy of approximately 65%, with three out of eight sample tests yielding correct measurements. While this shows room for improvement if more relevant research is to be done in the future, this system will build a strong foundation for further development in this field. Future enhancements could focus on refining the algorithm to increase detection accuracy, make the system more resilient in dynamic or cluttered environments, and expand its potential applications in various fields.
Co-Authors Andrian Sah Damar Surya Sasono Damar Suryo Sasono M. Ali Nur Hidayat Muhammad Ali Nur Hidayat Mursalim Tonggiroh Siti Khairunnisa Ratu Rahmah Siti Nurhayati Stefanus Ndala Wahyu Ciptaningrum