Article Per Year (5 Year)
p-Index From 2021 - 2026
1.728
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Jurnal Computer and Technology Jurnal Ilmiah Teknologi Informatika
Zulpan Hadi
Universitas Teknologi Mataram
Computer Science & IT Other

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

Found 9 Documents
Search

 1 
PREDIKSI KEBAKARAN HUTAN MENGGUNAKAN ALGORITMA NAIVE BAYES DAN KNN Ahsan, Muhammad Salimy; Zakaria, Zakaria; Hadi, Zulpan; Kurni, Samuel Everth Andrias; Kusrini
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 4 (2022): Article Research: Volume 6 Number 4, October 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i4.11609

Abstract

Forest fires are one of the disasters that cause problems for the environment. Forest fires can cause damage and threats, not only to forest resources but also to the entire ecosystem, both fauna and plants that can damage biodiversity and the environment of an area and can endanger human life. The source of forest fires was initially thought to come from a dry and hot environment, but in some cases, forest fires are triggered by human activities in clearing land for agriculture or other purposes. One of the factors that influence the spread of forest fires is several variables combined with humidity levels, wind speed, and rainfall. In this study, researchers used machine learning algorithms KNN and Naïve Bayes to predict forest fires and compare the results of the performance levels of each method used. The results obtained indicate that the naive Bayes method has an accuracy value of 53.33% and K-NN has an accuracy value of 62.66%
Detect Fake Reviews Using Random Forest and Support Vector Machine Hadi, Zulpan; Utami, Ema; Ariatmanto, Dhani
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 2 (2023): Research Article, Volume 7 Issue 2 April, 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i2.12090

Abstract

With the rapid development of e-commerce, which makes it possible to buy and sell products and services online, customers are increasingly using these online shop sites to fulfill their needs. After purchase, customers write reviews about their personal experiences, feelings and emotions. Reviews of a product are the main source of information for customers to make decisions to buy or not a product. However, reviews that should be one piece of information that can be trusted by customers can actually be manipulated by the owner of the seller. Where sellers can spam reviews to increase their product ratings or bring down their competitors. Therefore this study discusses detecting fake reviews on productreviews on Tokopedia. Where the method used is the distribution post tagging feature to perform detection. By using the post tagging feature method the distribution got 856 fake reviews and 4478 genuine reviews. In the fake reviews, there were 628 reviews written with the aim of increasing product sales or brand names from store owners, while there were 228 reviews aimed at dropping their competitors or competitors. Furthermore, the classification is carried out using the random forest algorithm model and the support vector machine. By dividing the dataset for training data by 80% while 20% for data testing. Here it is known that the support vector machine gets much higher accuracy than the random forest. The support vector machine gets an accuracy of 98% while the random forest gets an accuracy of 60%
CYBER BULLYING SENTIMENT ANALYSIS BASED ON SOCIAL CATEGORIES USING THE CHI-SQUARE TEST Hadi, Zulpan; Suryadi, Emi; Akbar, Ardiyallah; Zaenudin; Muslim, Rudi
Journal Computer and Technology Vol. 2 No. 1 (2024): Juli 2024
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/comtechno.v2i1.144

Abstract

This research evaluates various machine learning models in classifying sentiment in cyberbullying data across six categories: not_cyberbullying, gender, religion, other_cyberbullying, age, and ethnicity. Using a Bag of Words approach combined with Chi-Square feature selection (1000 features), models tested include SVM, Logistic Regression, Naïve Bayes, KNN, and Random Forest. Results show SVM and Logistic Regression achieving the highest accuracy at 83%, indicating their effectiveness in prediction. Naïve Bayes performed the poorest with 62% accuracy, suggesting a mismatch with the data or need for further tuning. KNN and Random Forest showed good performance with 75% and 81% accuracy respectively, though not as high as SVM and Logistic Regression. This multi-algorithm approach provides insights into each model's effectiveness and behavior on diverse data characteristics, essential for understanding the unique nuances of each cyberbullying category. Model selection should consider accuracy, interpretability, computational cost, and suitability to specific problem characteristics. This research aims to deepen understanding of cyberbullying to support more effective mitigation strategies.
Rancang Bangun Sistem Informasi Jasa Proyek Berbasis Web Wahyudi, Muhammad Syahrul; Arwidiyarti, Dwinita; Hadi, Zulpan
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 13, No 3: Desember 2024
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v13i3.2237

Abstract

CV. Bangun Bersama has been operating since 1985, providing construction services for various projects such as office buildings, housing, irrigation and other infrastructure. This company experiences difficulty in providing adequate access to information regarding the services offered, especially for projects from the general public. The research aimed to develop a Project Services Information System (SIJAPRO) using Web-Based to increase information accessibility, and simplify service processes and transaction calculations. This system was designed using the web-based prototype technique with the Laravel framework. The developed system design is carried out using Usecase Diagrams and Activity Diagrams, database design uses Entity Relationship Diagrams. The user evaluation was examined using questionnaires with Likert scales of 1-5 and system functionality was assessed using the Black Box testing method. The results of user evaluation showed a high average score, about 90.8%, which was interpreted as the very good category, so it can be concluded that this application is applicable, practical, and fulfills the user needs. In addition, the results of functional testing using the Black Box Testing Method produced all (100%) menus, actions, and buttons that can be used effectively which showed the functions can run as expected so it was feasible to use by CV. Build Together. Keywords: Information Systems; Project Services; Sijapro; Web Base. AbstrakCV. Bangun Bersama telah beroperasi sejak tahun 1985, menyediakan layanan konstruksi untuk berbagai proyek seperti gedung perkantoran, perumahan, irigasi, dan infrastruktur lainnya. Perusahaan ini mengalami kesulitan dalam memberikan akses informasi yang memadai mengenai layanan yang ditawarkan, terutama untuk proyek dari masyarakat umum. Penelitian ini bertujuan untuk mendesain dan mengembangkan sebuah Sistem Informasi Jasa Proyek (SIJAPRO) Berbasis Web guna meningkatkan aksesibilitas informasi, mempermudah proses pelayanan, dan perhitungan transaksi. Sistem ini dikembangkan dengan Metode Prototipe berbasis web dengan kerangka kerja Laravel. Perancangan sistem dilakukan dengan Diagram Use case dan Diagram Aktivitas, perancangan database menggunakan Entity Relationship Diagram. Evaluasi pengguna menggunakan angket dengan skala Likert 1-5 dan pengujian terhadap fungsionalitas sistem dievaluasi dengan Metode Black Box testing. Hasil evaluasi pengguna menunjukkan persentase rata-rat skor yang sangat tinggi yaitu sebesar 90,8% dengan interpretasi sebagai kategori sangat baik, sehingga disimpulkan bahwa aplikasi ini mudah digunakan, praktis dan memenuhi kebutuhan pengguna. Selain itu, hasil uji fungsional dengan Metode Black Box Testing menghasilkan nilai 100% atau sempurna pada fungsi menu, aksi, dan tombol yang dapat berfungsi sesuai dengan harapan sehingga layak untuk digunakan oleh CV. Bangun Bersama. 
Detecting Fake Reviews Using BERT and Sublinear_TF Methods on Hotel Reviews in the Lombok Tourism Area Hadi, Zulpan; Zulpahmi, M.; ., Zaenudin; Asrory, Akmaludin
Journal of Applied Informatics and Computing Vol. 8 No. 2 (2024): December 2024
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v8i2.8721

Abstract

The number of visitors to Lombok, one of the famous tourist destinations in Indonesia, increased from 400,595 in 2020 to 1,376,295 in 2022. Although the government supports the hotel industry, fake reviews are a significant problem that can damage hotel reputations and mislead tourists. This study uses BERT and Sublinear_TF feature extraction techniques to analyze fake reviews from three main areas: Gili Trawangan, Senggigi, and Kuta. BERT detects fake reviews by understanding the context of words, while Sublinear_TF emphasizes more informative words by reducing the weight of irrelevant common words. The results showed that the more extensive and diverse dataset from Gili Trawangan had the best classification results. The combination of BERT and Random Forest achieved the highest accuracy of 0.84. Overall, BERT excels in Gili Trawangan with an accuracy of 0.79 for SVM and 0.84 for Random Forest. In contrast, smaller and more homogeneous datasets such as Senggigi and Kuta have lower accuracy. In addition, Sublinear_TF performed well on Gili Trawangan with an accuracy of 0.82 using SVM and 0.83 using Random Forest; however, its performance declined in Senggigi and Kuta. BERT and Sublinear_TF techniques are more effective on large and diverse datasets such as Gili Trawangan. Sublinear_TF is better for varied data but less effective on more homogeneous datasets, while BERT with Random Forest showed the highest accuracy due to its ability to capture broader language context. This suggests that the size and variety of the dataset highly influence the success of fake review classification techniques.
FAKE REVIEW DETECTION ON DIGITAL PLATFORMS USING THE ROBERTA MODEL: A DEEP LEARNING AND NLP APPROACH Hadi, Zulpan; Nurkholis, Lalu Moh.; Imran, Bahtiar; Riadi, Selamet; Suryadi, Emi
Journal Computer and Technology Vol. 3 No. 1 (2025): Juli 2025
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/comtechno.v3i1.355

Abstract

Fake reviews have emerged as a serious threat to the integrity of digital platforms, particularly in e-commerce and online review sites. This study explores the application of RoBERTa (Robustly Optimized BERT Approach), a transformer-based architecture optimized for natural language processing (NLP), in automatically detecting fake reviews. The methodology includes data collection from online platforms, contextual feature extraction using RoBERTa embeddings, model training through supervised learning, and evaluation using classification metrics such as accuracy, precision, recall, and F1-score. The training results indicate a significant convergence trend in the training loss, while the validation loss remains relatively unstable, reflecting challenges in model generalization. Nevertheless, experimental results demonstrate that RoBERTa outperforms other approaches such as Logistic Regression PU, K-NN with EM, and LDA-BPTextCNN, achieving an accuracy of 86.25%. These findings highlight RoBERTa's strong potential in detecting manipulative content and underscore its value as an essential tool in building a transparent and trustworthy digital ecosystem.
Pengembangan Aplikasi Berbasis Web untuk Pengelolaan Arsip Surat Masuk dan Surat Keluar di Kantor Dinas Lingkungan Hidup Kota Palopo Zulpan Hadi; Pratiwi
Jurnal Ilmiah Teknologi Informatika Vol 2 No 1 (2024): JITAKU: Jurnal Ilmiah Teknologi Informatika UNCP
Publisher : Universitas Cokroaminoto Palopo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30605/jitaku.v2i1.92

Abstract

Penelitian ini bertujuan untuk merancang dan membangun aplikasi pengarsipan surat masuk dan keluar berbasis web di Kantor Dinas Lingkungan Hidup Kota Palopo. Sistem ini dikembangkan karena metode pengarsipan konvensional menyulitkan pencarian dan meningkatkan risiko kehilangan surat. Aplikasi ini dibuat menggunakan Sublime Text 3, XAMPP, MySQL, Bootstrap, dan PHP, dengan metode pengembangan Research and Development serta model waterfall. Pengujian menggunakan teknik black box menunjukkan bahwa semua fitur berfungsi dengan baik, dan sistem layak digunakan.
KLASIFIKASI PENYAKIT TANAMAN TEMBAKAU MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) BERBASIS WEB Baiq Norma Alyanesti Abella; Muhammad Multazam; Zulpan Hadi; Zumratul Muahidin
Journal Computer and Technology Vol. 3 No. 2 (2025): Desember 2025
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/comtechno.v3i2.383

Abstract

Tanaman tembakau merupakan salah satu komoditas pertanian yang signifikan dan memiliki nilai ekonomi yang tinggi. Namun, produktivitas tanaman ini seringkali mengalami penurunan akibat serangan berbagai jenis penyakit pada daun yang sulit dikenali secara langsung oleh para petani. Untuk mengatasi permasalahan tersebut, penelitian ini mengembangkan sebuah sistem klasifikasi penyakit pada tanaman tembakau yang berbasis website, dengan memanfaatkan algoritma Convolutional Neural Network (CNN). Sistem ini dirancang untuk mengklasifikasikan penyakit tersebut. citra daun tembakau ke dalam tiga kategori, yaitu Alternia Alternata, Cescospora Necotianae, dan daun sehat (tidak terinfeksi). Model CNN dilatih menggunakan dataset citra daun tembakau yang telah diberi labeb sesuai jenis penyakitnya. Selain memberikan hasil klasifikasi, sistem ini juga menyajikan deskripsi penyakit, tingkat akurasi prediksi, saran penanganan, serta menyimpan riwayat diagnosa ke dalam database. Dengan adanya sistem ini, diharapkan petani dapat memperoleh informasi diagnosis penyakit secara cepat, akurat, dan mudah diakses melalui perangkat digital.
A Dual-Pipeline Imbalance-Robust Framework for SMS Spam Detection: Achieving Flawless Precision via SMOTE-Augmented Ensembles with Rigorous Statistical Validation Zulpan Hadi; Selamet Riadi; Supardianto; Aulia Riswanti Naya; Liana Trihardianingsih
Journal Computer and Technology Vol. 4 No. 1 (2026): July 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/comtechno.v4i1.510

Abstract

The rapid proliferation of digital communication has exponentially increased the volume of Short Message Service (SMS) spam, exposing mobile users to systemic convenience disruptions, productivity drops, and severe financial losses through sophisticated fraudulent schemes. To construct a highly dependable filtering mechanism, this study presents a rigorous dual-pipeline machine learning framework that systematically addresses the challenges of class imbalance in statistical text mining. Utilizing a verified dataset of 5,572 Indonesian-context short messages, the raw textual corpus is subjected to uniform case normalization, structural URL extraction, and character filtering before feature projection via Term Frequency–Inverse Document Frequency (TF-IDF) vectorization. To overcome the inherent accuracy paradox of skewed class distributions, the experimental design evaluates a baseline pipeline (imbalanced data) against a synthetic data augmentation pipeline leveraging the Synthetic Minority Oversampling Technique (SMOTE) across four distinct classifiers: Logistic Regression, Naive Bayes, Linear Support Vector Machine (Linear SVM), and Random Forest. Empirical results demonstrate that while the baseline Linear SVM serves as the optimal standalone model for overall balance, achieving a peak accuracy of 98.11% and a dominant F1-Score of 92.83%, the SMOTE-augmented Random Forest configuration yields an exceptional high-security alternative by securing a flawless 100.00% precision envelope alongside an 83.89% recall rate. Advanced post-hoc evaluations including McNemar's statistical significance tests (,  for Random Forest), qualitative error analyses of semantic edge cases, and runtime profiling confirm that the developed architecture establishes a highly scalable, mathematically verified, and low-latency solution suitable for integration into real-time telecom filtering gateways.
Co-Authors Abda Abda Ahsan, Muhammad Salimy Akbar, Ardiyallah Arwidiyarti, Dwinita Asrory, Akmaludin Aulia Riswanti Naya Baiq Norma Alyanesti Abella DHANI ARIATMANTO Ema Utami Imran, Bahtiar Kurni, Samuel Everth Andrias Kusrini Liana Trihardianingsih Nurkholis, Lalu Moh. Nurwijayanti Pratiwi Rudi Muslim Selamet Riadi Selamet Riadi Supardianto Suryadi, Emi Wahyudi, Muhammad Syahrul Zaenudin Zaenudin ., Zaenudin Zulpahmi, M. Zumratul Muahidin