Article Per Year (5 Year)
p-Index From 2021 - 2026
5.847
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi JOIV : International Journal on Informatics Visualization Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Infomedia MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Jurnal Ilmu Komputer dan Bisnis Abdimas Galuh: Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Mitra Masyarakat (JPMM) SmartComp The Indonesian Journal of Computer Science
Majid Rahardi
Universitas Amikom Yogyakarta
Agriculture, Biological Sciences & Forestry Computer Science & IT Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Nursing Social Sciences Other

Published : 45 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 45 Documents
Search

 1   2   3   4   5 
Comparative Analysis of EfficientNet-B0 and ViT-B16 for Multiclass Classification of Green Coffee Beans Syaputra, Muh. Rezky; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11563

Abstract

Green coffee bean classification plays an important role in the coffee supply chain, as bean quality has a direct impact on the taste and final quality of the product. The USK-Coffee dataset, which consists of four bean object classes defect, longberry, peaberry, and premium, is photographed under varied lighting conditions and capture angles, thus challenging the accuracy of conventional visual models. Although lightweight CNN models have been used, not many studies have directly compared transformer-based architectures (ViT-B16) and modern efficient CNNs (EfficientNet-B0) for green coffee bean classification under real conditions. With transfer learning strategy, image augmentation (resize, flip, rotation, color jitter, random crop), and normalization, we evaluate the performance of both models on the dataset. ViT-B16 achieved 85% accuracy on the test data (F1-score 0.85), with a fast batch inference latency of 0.0074 seconds per batch. EfficientNet-B0 achieved 87% accuracy (F1-score 0.87), with a slower batch latency (0.0106 seconds per batch). However, EfficientNet-B0 is significantly faster for single image inference (real-time) (0.035 seconds) compared to ViT-B16 (0.426 seconds). This trade-off higher accuracy/faster single inference on EfficientNet-B0 vs. faster batch processing on ViT-B16 shows that both are feasible for edge computing-based classification systems.
L2IC and MobileViT-XXS for BISINDO Alphabet Recognition Artamma, Chanan; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.11575

Abstract

This study proposes a Landmark-to-Image Conversion (L2IC) approach integrated with the MobileViT-XXS architecture for Indonesian Sign Language (BISINDO) alphabet recognition. The method converts 42 hand keypoints, extracted using MediaPipe Hands into normalized 224×224 grayscale images to capture spatial hand patterns more effectively. These L2IC representations are then used as input to the MobileViT-XXS model, trained for 30 epochs with a learning rate of 0.001. Experimental results show that the model achieves an accuracy and Macro F1-Score of 97.98%, outperforming baseline approaches using raw RGB images and MLP-based classification on numerical keypoints. While the model demonstrates strong performance in controlled offline experiments, further evaluation is required to assess its robustness under real-world dynamic BISINDO usage and deployment on resource-limited devices. These findings indicate that the L2IC representation effectively captures essential spatial information, contributing to high recognition accuracy in static BISINDO hand gesture classification.
Sentiment Analysis of Neobank Digital Banking using Support Vector Machine Algorithm in Indonesia Kusnawi, Kusnawi; Rahardi, Majid; Pandiangan, Van Daarten
JOIV : International Journal on Informatics Visualization Vol 7, No 2 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.2.1652

Abstract

Currently, in the industrial era 4.0, information and communication technology is very developed, whereas, in this era, there is an increase in complex activities, one of which is in the banking sector. With the ease and efficiency of online finance, people want to switch to using digital banks. Neobank is an online savings and deposit application from Bank Neo Commerce (BCN) that the public can use by using the Internet. One of the online services is mobile banking which can be used by both Android and iOS versions of customers. Users can review Neobank's performance and services through the Google Play Store to improve and evaluate Neobank's performance. Neobank application reviews on the Google Play Store are increasing. Therefore, a review analysis is needed by conducting a sentiment analysis on Neobank's review. The data amounted to 3159 user reviews collected from reviews of the Neobank application on the Google Play Store. This study aims to classify Neobank user review data, including positive or negative sentiments. The method used in this study is an experimental method using the Support Vector Machine algorithm. The accuracy results obtained using the Support Vector Machine algorithm are 82.33%, which is owned by the scenario of 90% training data and 10% test data. The precision results are 82%, and recall is 81%. Future studies can add datasets from various sources so that there are even more datasets so as to increase the accuracy of model classification.
Rancang Bangun Aplikasi Smart Touring Berbasis Android Majid Rahardi; Afrig Aminuddin
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 21 No. 1 (2021)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v21i1.1185

Abstract

Perkembangan teknologi saat ini begitu cepat. Teknologi membuat perubahan pada peradaban manusia. Telah banyak kegiatan manusia yang didukung oleh kemajuan teknologi. Tak terkecuali kegiatan touring yang dilakukan bersama-sama. Touring adalah kegiatan berkendara dari suatu tempat ke tempat lain secara bersama-sama. Saat ini komunitas touring terus meningkat, namun masih memiliki beberapa permasalahan saat melakukan aktifitasnya. Saat ini salah satu permasalahan yang ada pada aktifitas touring adalah pengendara satu dengan yang lainnya tidak bisa mengetahui lokasi semua teman touring mereka. Oleh karena itu sangat dimungkinkan ada anggota touring mereka yang tertinggal jauh atau salah jalur. Dengan teknologi smartphone yang sangat pesat, dimungkinkan dibangun sebuah sistem yang dapat mendukung kegiatan touring tersebut. Pada penelitian ini telah berhasil dibangun sistem yang dapat mendukung kelancaran aktifitas touring. Fokus penelitian ini adalah membangun sistem touring yang dapat mendeteksi keberadaan semua member touring ketika sedang melakukan kegiatan touring. Sistem yang dibangun adalah berbasis contextual awareness, yaitu sistem yang mampu memberikan informasi kepada pengguna dengan data yang didapat dari lingkungannya. Dalam hal ini adalah memberikan informasi ketika ada member touring yang berjauhan dengan member touring lainnya.
AirDisinfeX: Pengembangan IoT pada Sistem Pencegahan Penyebaran COVID-19 melalui Udara Kharisma, Rizqi Sukma; Kusrini, Kusrini; Saputro, Uyock Anggoro; Sulistiyono, Mulia; Rahardi, Majid; Bernadhed, Bernadhed; Muktafin, Elik Hari
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 12, No 1 (2023): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v12i1.4483

Abstract

Ruang tertutup merupakan tempat yang memiliki potensi lebih tinggi dalam penyebaran virus COVID-19. Hal ini dikarenakan virus COVID-19 dapat terbawa udara. Ruang tertutup membuat udara semakin lama di ruang tersebut. Terlebih ruang tertutup sangat banyak digunakan untuk beraktivitas seperti rumah, sekolah, mall, kantor, tempat ibadah, dll. Sehingga untuk ruang tertutup harus mendapat perhatian serius untuk dapat menghindari penyebaran virus. AirDisinfeX adalah alat berbasis IoT dengan dilengkapi sinar UVC yang dapat membunuh virus termasuk virus COVID-19. Alat ini dapat dikendalikan dari jarak jauh secara manual atau timer. Sehingga alat bisa diaktifkan terlebih dahulu sebelum ruang tertutup digunakan. Penelitian ini juga menggunakan mikrokontroler ESP32 dalam mendukung pengembangan alat AirDisinfeX berbasis IoT. Hasil penelitian ini dengan akurasi sistem IoT AirDisinfeX sebesar 96,10% dan waktu respon rata-rata 5,32 detik
Optimasi Analisis Sentimen terhadap Kinerja Direktorat Jenderal Pajak Indonesia Melalui Teknik Oversampling dan Seleksi Fitur Particle Swarm Optimization Sholihah, Nafiatun; Abdulloh, Ferian Fauzi; Rahardi, Majid
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 12, No 4 (2023): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v12i4.5814

Abstract

Dalam domain kebijakan publik dan tata kelola pemerintahan, isu perpajakan senantiasa menjadi perhatian khusus di kalangan masyarakat. Dengan tujuan mendapatkan pemahaman yang lebih mendalam tentang pandangan publik terhadap performa Direktorat Jenderal Pajak Indonesia, penelitian ini mengadopsi pendekatan analisis sentimen, menggunakan dataset komentar yang terkumpul dari platform media sosial YouTube. Salah satu kendala signifikan yang dihadapi dalam analisis ini adalah ketidakseimbangan data sentimen komentar, dengan dominasi sentimen positif atau negatif. Dengan demikian, kami menerapkan teknik SMOTE oversampling dan Particle Swarm Optimization (PSO) sebagai strategi seleksi fitur, sebagai bagian dari upaya meningkatkan kualitas model analisis sentimen. SMOTE akan membuat data sintetis dari kelas minoritas sehingga data train akan berimbang dan tidak menghasilkan model yang mengandung bias yang disebabkan ketidak seimbangan data. Selanjutnya dilakukan pemilihan fitur yang dianggap memuat informasi penting untuk meningkatkan performa dari suatu model.Metode ini terbukti efektif, khususnya pada skenario dengan pembagian data latih sebanyak 70%. Di sini, nilai recall meningkat dari 0.47 menjadi 0.52, sebuah peningkatan yang signifikan dalam mendeteksi sentimen minoritas yang seringkali terabaikan dalam studi sejenis. Selain itu, teknik seleksi fitur menggunakan PSO, dengan menggunakan nilai F1 sebagai kriteria pbest, menghasilkan peningkatan substansial pada semua metrik evaluasi: akurasi mencapai 0.93, recall 0.63, presisi 0.70, dan F1 score 0.66. Ini menunjukkan keefektifan metode tersebut dalam memodelkan berbagai aspek sentimen terhadap perpajakan di Indonesia.
Analysis of Deep Learning Implementation Using Xception for Rice Leaf Disease Classification Puspitaningrum, Niken; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11800

Abstract

Identifying rice leaf diseases plays a crucial role in maintaining agricultural productivity and preventing massive losses. In recent years, deep learning models have shown very promising performance in plant disease classification tasks. This study proposes a Rice Leaf Disease Detection System based on the Xception model from Keras Applications, an architecture that is still relatively unexplored for rice plant disease cases. Through preprocessing, data augmentation, and model refinement, the developed system achieved a training accuracy of 93% and a testing accuracy of 89% in classifying rice leaf conditions. In addition, metric evaluation showed precision, recall, and F1-score values of 89%, reflecting the model's ability to make consistent and balanced predictions. The trained model was then integrated into a web-based application to facilitate real-time disease diagnosis through image uploads. The results of this study prove the effectiveness of the Xception architecture in extracting agricultural image features and its potential for application in artificial intelligence-based smart farming systems.
Analysis of Gradient Boosting Algorithms with Optuna Optimization and SHAP Interpretation for Phishing Website Detection Abu Bakar, Rahmat Fauzi; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11857

Abstract

Phishing remains a persistent cybersecurity threat, evolving rapidly to bypass traditional blacklist-based detection systems. Machine Learning (ML) approaches offer a promising solution, yet finding the optimal balance between detection accuracy and model interpretability remains a challenge. This study aims to evaluate and optimize the performance of three state-of-the-art Gradient Boosting algorithms—XGBoost, LightGBM, and CatBoost—for phishing website detection. The research utilizes the UCI Phishing Websites dataset consisting of 11,055 instances. The novelty of this study lies in the implementation of the Optuna framework with the Tree-structured Parzen Estimator (TPE) for automated hyperparameter optimization and the application of SHAP (Shapley Additive Explanations) interaction values to interpret the "black-box" models. The experimental results demonstrate that the LightGBM model, optimized via Optuna, achieved the highest performance with an F1-Score of 0.9798, outperforming the baseline model (0.9713) by 0.87%. Furthermore, SHAP analysis identified 'SSLfinal_State' as the most critical determinant for distinguishing phishing sites. This study confirms that optimizing modern boosting algorithms significantly enhances phishing detection capabilities while providing necessary explainability for cybersecurity analysts.
Comparison of Naïve Bayes and Support Vector Machine for Sentiment Classification of Acne Skincare Reviews Arindika, Alti; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11869

Abstract

The increasing popularity of skincare products for acne-prone skin had led to a surge in online consumer reviews, which are characterized by informal language, domain-specific terminology, and imbalanced sentiment distribution, posing challenges for sentiment classification tasks. This study aims not only to compare the performance but also to analyze the generalization behavior of two popular machine learning algorithms, Naïve Bayes and Support Vector Machine (SVM), for sentiment classification of skincare product reviews specifically targeting acne-prone skin. A comprehensive methodology was employed, including thorough text preprocessing, feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) with n-gram representation, and data balancing through Synthetic Minority Over-sampling Technique (SMOTE). The study utilized a dataset of 4,004 labeled reviews categorized into positive and negative sentiments. The models were evaluated using stratified 5-Fold cross-validation to ensure robust and fair assessment. Results indicate that Naïve Bayes slightly outperforms SVM on the testing set, achieving the highest accuracy of 91.14% compared to 90.64% for SVM. While SVM demonstrated higher performance during training, its testing performance suggested a tendency toward overfitting, whereas Naïve Bayes exhibited more stable generalization on unseen data. Further qualitative insight analysis revealed that product effectiveness and user experience are the primary drivers of consumer sentiment, while competitive analysis highlighted distinct brand perception patterns across skincare categories. These findings indicate that simpler probabilistic models such as Naïve Bayes can provide robust and reliable performance for sentiment analysis in specialized and imbalanced skincare review datasets.
Analysis of Gradient Boosted Trees Algorithm in Breast Cancer Classification Suryaputri, Cantika Okzen; Rahardi, Majid
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11875

Abstract

Early and accurate classification of breast cancer is essential to support clinical diagnostic processes and improve patient outcomes. This study proposes a comprehensive machine learning pipeline based on Gradient Boosted Tree algorithms to classify breast tumors into benign and malignant categories. The proposed framework integrates several preprocessing stages, including outlier handling using the Local Outlier Factor (LOF), feature normalization with StandardScaler, class imbalance handling using SMOTE, and feature selection through ANOVA-based SelectKBest. Five ensemble learning models—XGBoost, LightGBM, CatBoost, HistGradientBoosting, and GradientBoosting—were trained and evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The experimental results show that all models achieved strong and comparable classification performance. Among them, CatBoost obtained the highest ROC-AUC value of 0.9960, along with an accuracy of 0.9649, precision of 0.9750, recall of 0.9286, and F1-score of 0.9512. Statistical evaluation using the DeLong test indicated that the differences in ROC-AUC among the evaluated models were not statistically significant (p > 0.05), suggesting similar discriminative capabilities across models. To enhance model interpretability, SHAP (SHapley Additive exPlanations) was applied to the CatBoost model as a representative classifier. The results show that features related to nuclear size and shape, such as radius, area, perimeter, and concavity, contributed most significantly to malignant predictions. This study demonstrates that the integration of robust preprocessing techniques, Gradient Boosted Tree models, and explainable machine learning provides an accurate and interpretable approach for breast cancer classification. However, the evaluation was conducted on a single public dataset without external validation, and further studies using independent and real-world datasets are required before clinical deployment.
Co-Authors Abdulloh, Ferian Fauzi Abiyyu, Ahmad Naufal Abu Bakar, Rahmat Fauzi Afrig Aminuddin Alfian Difa’ul Amien Amelia, Hemas Anggita Andrika, Muhammad Yusuf Arindika, Alti Aristawidya, Winda Ardelia Artamma, Chanan Asadulloh, Bima Pramudya Bernadhed, Bernadhed Dn, Ubaid Khoir Julio Ekayanda, Gilang Elik Hari Muktafin Fadzli, Alief Khairul Febianty, Dennita Noor Frobenius, Arvin Claudy Harianto, Fetrus Jari Indriyatmoko, Toto Joang Ipmawati Kharisma, Rizqi Sukma Kusnawi Kusnawi Kusrini Kusrini Kusrini, Kusrini Laiskodat, Fransisko Andrade Latuconsina, Muhammad Sidik Latupono, Ali Samsul Lefi, Nadia Martha M. Ikhsan Malik Bagaskara Mawar, Heni Sapta Muktafin, Elik Hari Mulia Sulistiyono Musthofa, Alif Nafiatun Sholihah Nandini, Kety Nolejanduma, Dionisius Nusaca Redegnosis Nur'aini, Linnda Prawidya Nurhayati, Lutfiana Deka Pandiangan, Van Daarten Puspitaningrum, Niken Rayadhani, Windy Aldora Rida, Rachmasari Annisa Rizqi Sukma Kharisma Rohmad Fajarudin Salim, Edwin Ibrahim Saputro, Uyock Anggoro Suryaputri, Cantika Okzen Syaputra, Muh. Rezky Sylvester, Gunawan Toto Indriyatmoko Utama, Hastari Uyock Anggoro Saputro Vabilla, Sheila Anggun Yudha, Muhammad Agung Reza