Article Per Year (5 Year)
p-Index From 2021 - 2026
1.704
P-Index
This Author published in this journals
All Journal Jurnal Media Infotama Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Journal of Practical Computer Science (JPCS) Jurnal Media Computer Science Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Jurnal Manajemen Informatika & Teknologi VIDHEAS: Jurnal Nasional Abdimas Multidisiplin
Hidayat, Jose Julian
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Analisis Penyakit pada Daun Padi Menggunakan VGG-16 Transfer Learning dan Teknik Segmentasi K-Mean Hidayat, Jose Julian; Setyowati, Cindy; Werdana, Aditya Pratama
Jurnal Media Infotama Vol 21 No 1 (2025): April 2025
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v21i1.7313

Abstract

Diagnosis dini penyakit daun sangat penting untuk meningkatkan hasil panen karena penyakit pada tanaman padi dapat secara signifikan mempengaruhi produksi pertanian. Dengan menggunakan teknik Transfer Learning pada model VGG-16 yang telah disempurnakan bersama dengan segmentasi berbasis K-Means, penelitian ini menyarankan pendekatan berbasis pembelajaran mendalam untuk diagnosis penyakit daun padi. Karena kemampuannya yang luar biasa dalam mengekstrak fitur dari foto digital, VGG-16 dipilih untuk menangkap informasi penting tentang permukaan daun yang mungkin mengindikasikan adanya penyakit. Untuk memisahkan daerah yang terkontaminasi dari latar belakang dan memungkinkan identifikasi yang lebih tepat dan efektif, segmentasi K-Means digunakan sebagai langkah prapemrosesan. Kumpulan data yang digunakan dalam percobaan ini berisi berbagai macam foto dari berbagai kategori penyakit pada tanaman padi. Menurut data percobaan, pendekatan ini dapat mengidentifikasi jenis penyakit pada daun dengan sangat akurat-akurasi dapat melampaui 90%. Dengan berkonsentrasi pada daerah-daerah kunci pada gambar, K-Means meningkatkan kinerja deteksi. Jika dibandingkan dengan metode konvensional, hasil ini menunjukkan bagaimana strategi kombinasi ini dapat meningkatkan akurasi diagnosis penyakit daun padi. Penggunaan sistem ini diharapkan dapat membantu para ahli agronomi dan petani untuk memantau kesehatan tanaman secara efisien, sehingga dapat meningkatkan hasil pertanian
Perancangan Sistem Prediksi Penyakit pada Tanaman Padi Berbasis Image Processing Menggunakan Algoritma VGG-16 Transfer Learning dan K-Means Segmentation Hidayat, Jose Julian; Setyowati, Cindy; Werdana, Aditya Pratama
Journal of Practical Computer Science Vol. 5 No. 1 (2025): Mei 2025
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v5i1.5759

Abstract

Early diagnosis of foliar diseases is essential for improving crop yields as diseases in rice plants can significantly affect agricultural production. By using Transfer Learning techniques on an enhanced VGG-16 model along with K-Means segmentation, this study suggests a deep learning-based approach for rice leaf disease diagnosis. Due to its outstanding ability to extract features from digital photos, VGG-16 was chosen to capture important information about the leaf surface that may indicate the presence of disease. To separate contaminated regions from the background and enable more precise and effective identification, K-Means segmentation was used as a preprocessing step. The dataset used in this experiment contains a wide variety of photos of different categories of diseases on rice plants. According to the experimental data, this approach can identify the type of disease on the leaves very accurately the accuracy can exceed 90%. By concentrating on key regions of the image, K-Means improves the detection performance. When compared to conventional methods, these results show how this combination strategy can improve the accuracy of rice leaf disease diagnosis. The use of this system is expected to help agronomists and farmers to monitor plant health efficiently, thereby increasing agricultural yields. In this study, the VGG-16 method and K-Means segmentation were combined to create a rarely used image-based automatic diagnosis system simultaneously on rice plants. This method has been shown to have higher accuracy than previous methods.
Deep Learning-based Sentiment Analysis of Public Comments on Military Education Using RoBERTa Algorithm and Rule-Based Hybird Parameters Hidayat, Jose Julian; Setyowati, Cindy; Amin, Muhammad Dikaisa Ibnu; Bimasakti, Khodir; Werdana, Aditya Pratama
Jurnal Media Computer Science Vol 4 No 2 (2025): Juli
Publisher : LPPJPHKI Universitas Dehasen Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmcs.v4i2.8769

Abstract

Social media such as Instagram has become an important digital public space for people to voice opinions on various policy issues, including the military education policy, which has recently become highly debated, especially in West Java and even outside Java. The purpose of this research is to develop a sentiment analysis model for public comments on Instagram regarding military education policy using a deep learning approach. m The RoBERTa model was trained and tested using classification performance metrics such as accuracy, precision, recall, and f1-score. The test results show that the model achieved an accuracy of 97%, with the highest f1-score value in the positive category at 0.98. The results show that RoBERTa can effectively classify sentiment based on public opinion on social media. This method can not only provide an overview of public responses, but can also be used as a tool in the decision-making process or public policy evaluation based on real-time digital opinion analysis.
Pendampingan Pembuatan Website Menggunakan CMS untuk Agen Umroh dan Haji AFA Agency Wiyanto, Wiyanto; Hidayat, Jose Julian; Werdana, Aditya Pratama; Nugroho, Agung; Suwarno, Agus
VIDHEAS: Jurnal Nasional Abdimas Multidisiplin Vol. 3 No. 1 (2025): Juni 2025
Publisher : VINICHO MEDIA PUBLISINDO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61946/vidheas.v3i1.121

Abstract

It is an obligation for lecturers to fulfill the Tridharma of Higher Education, namely education, research, and service. In order to fulfill these obligations, various forms of service to others should be carried out by lecturers and can involve students in the Pelita Bangsa University environment, especially in the Informatics Engineering study program and other study programs so that they can collaborate with each other. The service program carried out is at the Umrah and Hajj service agency Afa Agency which is located at Perum. Bumi Citra Lestari Jl. Cempaka XI, Blok C66 No. 16 Kab. Bekasi. Afa Agency is an Umrah and Hajj agent established in January 2024 which is committed to accompanying your worship to the holy land, which at this time in marketing Umrah and Hajj services using WhatsApp, Facebook, Instagram and other media, and does not yet have a website in marketing its products and services, from this Afa Agency needs a website to make the marketing process easy and widespread. The purpose of this community service is to provide assistance in making a website using CMS to market Umrah and Hajj products and services at Afa Agency. Another benefit of this service is to contribute to the community in the application of science in the computer field. This service is organized using the method of mentoring in making websites assisted by Informatics Engineering study program students
Pelatihan Pengelolaan Website Afa Agency Sebagai Media Pemasaran Umroh dan Haji Wiyanto, Wiyanto; Hidayat, Jose Julian; Werdana, Aditya Pratama; Raharjo, Sugung Budi; Suwarno, Agus
VIDHEAS: Jurnal Nasional Abdimas Multidisiplin Vol. 3 No. 1 (2025): Juni 2025
Publisher : VINICHO MEDIA PUBLISINDO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61946/vidheas.v3i1.127

Abstract

Dalam memenuhi kewajiban bagi Dosen pada Tridharma Perguruan Tinggi, yaitu pendidikan, penelitian, dan pengabdian. Kewajiban tersebut ialah dalam rangka pemenuhan pengabdian kepada masyarakat, yaitu berbagai macam bentuk pengabdian terhadap sesama hendaknya dapat dilakukan oleh dosen dan dapat melibatkan mahasiswa dilingkungan Universitas Pelita Bangsa khususnya pada prodi Teknik Informatika dan Prodi lainnya agar dapat saling berkolaborasi dengan baik. Program pengabdian yang dilakukan ini adalah ialah pada agen pelayanan umroh dan haji Afa Agency yang beralamat di Perum. Bumi Citra Lestari Jl. Cempaka XI, Blok C66 No. 16 Kab. Bekasi. Afa Agency merupakan agen umroh dan haji yang berdiri di bulan Januari 2024 yang mempunyai komitmen mendampingi ibadah anda ke tanah suci, yang mana pada saat ini dalam memasarkan jasa pelayanan umroh dan haji menggunakan media whatsapp, facebook, istagram dan media lainnya, dan belum mempunyai website dalam memasarkan produk dan jasanya, dari hal ini Afa Agency sudah memiliki website sebagai media informsai dan pemasaran produk dan jasanya, yaitu perjalannan ibadah umroh maupun haji. Tujuan dari pengabdian kepada Masyarakat ini ialah melakukan pelatihan pengelolaan website www.afaagencytour.com kepada team Afa Agency agar mandiri dalam pengelolaan website dan up to date dalam hal informasi. Manfaat lain dari dari pengabdian ini ialah memberikan kontribusi kepada masyarakat dalam penerapan keilmuan dibidang komputer. Pengabdian ini diselenggarakan dengan menggunakan metode pelatihan pengelolaan website yang dibantu oleh Mahasiswa prodi Teknik Informatika.
Prediksi Volatilitas IHSG Dengan Hybrid Model GARCH–Random Forest Berbasis Machine Learning Hidayat, Jose Julian; Hasanudin, Surya
Jurnal Manajemen Informatika & Teknologi Vol. 6 No. 1 (2026): Mei : Jurnal Manajemen Informatika & Teknologi
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/mifortekh.v6i1.1134

Abstract

In risk analysis and investment decision-making, stock market volatility is very important, especially in the Composite Stock Price Index (IHSG), which is constantly changing and influenced by many economic factors.  To predict IHSG volatility, this study uses a Hybrid GARCH–Random Forest approach. This approach combines the strength of Random Forest in modelling non-linear relationships with the ability of the GARCH model to identify financial data heteroscedasticity.  To predict volatility on the following day, data from the IHSG closing price is processed into logarithmic returns and then used to estimate volatility using the GARCH(1,1) model. According to performance evaluations, this hybrid model is capable of providing highly accurate predictions.  In addition, the model was tested in a volatility classification scheme into three categories: low, medium, and high. In regression testing, an MSE value of 0.000386 and an RMSE value of 0.01965 were obtained, indicating that the volatility prediction error was very low. The accuracy, recall, and f1-values were between 0.99 and 1.00. The results show that the Hybrid GARCH–Random Forest approach is very effective in modelling IHSG volatility. This approach can also be a reliable tool to support risk analysis and decision-making strategies in financial markets.
Pemodelan Deteksi dan Klasifikasi Fraktur Tulang pada Radiografi X-Ray Menggunakan YOLOv8 dan Preprocessing CLAHE Hidayat, Jose Julian; Anshor, Abdul Halim; Anwar, M. Syaibani
JURNAL FASILKOM Vol. 16 No. 1 (2026): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v16i1.11241

Abstract

This study aims to develop a model for detecting and classifying bone fractures in digital X-ray radiography images using the You Only Look Once version 8 (YOLOv8) architecture with the application of Contrast Limited Adaptive Histogram Equalization (CLAHE) as a preprocessing method. The CLAHE method is used to improve contrast quality and clarify bone structure details, thereby facilitating the feature extraction process by the detection model. The research dataset comprises 641 X-ray and MRI images divided into ten classes consisting of various types of bone fractures, namely Comminuted, Greenstick, Linear, Oblique, Oblique Displaced, Segmental, Spiral, Transverse, and Transverse Displaced, as well as the Healthy class as a comparison. Model training was conducted for 100 epochs using YOLOv8n with CLAHE-based augmentation to improve the visibility of the fracture area. The best results were obtained from the YOLOv8-CLAHE (balanced) model with a mAP@0.5 of 0.933 to 0.941, precision of 0.939 to 0.965, and recall of 0.877 to 0.901. The Segmental and Comminuted classes showed the highest performance, while classes with limited data such as Greenstick and Linear still had relatively low accuracy.  The model's inference speed reached 8.3 milliseconds per image, demonstrating the potential application of this system for real-time fracture detection in clinical settings. The results of this study show that the application of the CLAHE method in the image pre-processing stage can improve the detection and classification performance of YOLOv8, and has the potential to support the development of automated diagnosis systems in the field of orthopedic radiology.
Perbandingan Metode Oversampling SMOTE dan ADASYN pada Klasifikasi Diabetes Menggunakan Algoritma CatBoost Hidayat, Jose Julian; Rozikin, Zaenur
Jurnal Manajemen Informatika & Teknologi Vol. 6 No. 1 (2026): Mei : Jurnal Manajemen Informatika & Teknologi
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi - Studi Ekonomi Modern

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/mifortekh.v6i1.1157

Abstract

Class imbalance is a major challenge in diabetes classification, as it can lead models to become biased toward the majority class. Oversampling approaches such as the Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) are applied to address this issue by improving the representation of the minority class. This study compares the performance of both methods using the CatBoost algorithm on a diabetes classification dataset. The evaluation is carried out using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The experimental results indicate that the baseline CatBoost model already achieves strong performance, with an accuracy of 0.9720 and a ROC-AUC of 0.9796; however, the recall for the minority class remains relatively low at 0.6935. The implementation of SMOTE yields the most optimal improvement, achieving an accuracy of 0.9727, precision of 0.9737, recall of 0.6971, and an F1-score of 0.8125, while maintaining a ROC-AUC of 0.9796. Meanwhile, ADASYN also improves performance compared to the baseline, but its results are slightly lower than SMOTE, with an accuracy of 0.9719 and recall of 0.6924. Overall, SMOTE proves to be more effective in enhancing the CatBoost model’s ability to detect the minority class without compromising overall performance. Therefore, SMOTE is recommended as a more stable and optimal oversampling method for handling imbalanced data in diabetes classification tasks.
Klasifikasi Penyakit Diabetes Melitus Berbasis Jaringan Syaraf Tiruan Menggunakan Algoritma Multi-Layer Perceptron Hidayat, Jose Julian; Sujianto, Daffa Eka; Saputra, Muhammad Randika; Ramdhani, Erik Ahmad; Jihansyah, Muhamad; Nandya, Yogi
Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Vol. 5 No. 1 (2026): Juni 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v5i1.1042

Abstract

Diabetes Melitus merupakan salah satu penyakit kronis yang membutuhkan proses deteksi dini secara cepat dan akurat agar risiko komplikasi dapat diminimalkan. Penelitian ini bertujuan untuk mengklasifikasikan penyakit Diabetes Melitus menggunakan Jaringan Syaraf Tiruan dengan algoritma Multi-Layer Perceptron. Dataset yang digunakan terdiri dari 100.000 data dengan 9 atribut, yaitu gender, age, hypertension, heart disease, smoking history, body mass index, HbA1c level, blood glucose level, dan diabetes sebagai target klasifikasi. Setelah dilakukan pengecekan data, tidak ditemukan missing value, namun terdapat 3.854 data duplikat sehingga jumlah data setelah pembersihan menjadi 96.146 data. Proses penelitian meliputi preprocessing data, encoding fitur kategorikal, standardisasi fitur numerik, pembagian data training dan testing, pemodelan Multi-Layer Perceptron, serta evaluasi performa model. Model yang digunakan memiliki beberapa hidden layer dengan aktivasi ReLU, batch normalization, dropout, dan output sigmoid untuk klasifikasi biner. Hasil pengujian menunjukkan bahwa model memperoleh accuracy sebesar 0,9715548622, precision sebesar 0,9939810834, recall sebesar 0,6816037736, F1-score sebesar 0,8086743617, dan ROC-AUC sebesar 0,9749626265. Berdasarkan hasil tersebut, algoritma Multi-Layer Perceptron mampu memberikan performa klasifikasi yang baik, khususnya dalam membedakan pasien non-diabetes dan diabetes berdasarkan atribut kesehatan yang tersedia.
Co-Authors Abdul Halim Anshor Agus Suwarno, Agus Amin, Muhammad Dikaisa Ibnu Anwar, M. Syaibani Azhari, Fajri Fauzan Bimasakti, Khodir Fadilah, Ai Linda Nurahmah Fahmayani , Aulia Nufaila Hasanudin, Surya Husna, Tsania Manzilatul Jihansyah, Muhamad Nandya, Yogi Nugroho, Agung Pradana, Novant Nanda Raharjo, Sugung Budi Ramadhan, Azhyka Rizki Ramdhani, Erik Ahmad Rozikin, Zaenur Saputra, Muhammad Randika Setyowati, Cindy Sigand, Arifubila Ramdhani Sujianto, Daffa Eka Werdana, Aditya Pratama Wiyanto -