Article Per Year (5 Year)
p-Index From 2021 - 2026
11.071
P-Index
This Author published in this journals
All Journal Riau Journal of Computer Science Komunikasi : Jurnal Komunikasi ILKOM Jurnal Ilmiah INTECOMS: Journal of Information Technology and Computer Science JURNAL TEKNOLOGI DAN OPEN SOURCE Jurnal Teknologi Sistem Informasi dan Aplikasi Informatika : Jurnal Informatika, Manajemen dan Komputer JOISIE (Journal Of Information Systems And Informatics Engineering) Journal of Technopreneurship and Information System (JTIS) Infotekmesin Jurnal Teknologi Informasi dan Multimedia Journal of Robotics and Control (JRC) Journal of Applied Engineering and Technological Science (JAETS) JSR : Jaringan Sistem Informasi Robotik Community Engagement and Emergence Journal (CEEJ) JTIULM (Jurnal Teknologi Informasi Universitas Lambung Mangkurat) Jurnal Ilmu Komputer Journal of Applied Data Sciences Jurnal Pengabdian kepada Masyarakat Jurnal J-PEMAS Jurnal Ipteks Terapan : research of applied science and education pendidikan, science, teknologi, dan ekonomi Jurnal Rekam Medis (Medical Record Journal) Jurnal Teknik Informatika Malcom: Indonesian Journal of Machine Learning and Computer Science Journal of Telecommunication Control and Intelligent System Journal of Software Engineering and Information System (SEIS) SATIN - Sains dan Teknologi Informasi RJOCS (Riau Journal of Computer Science) Jurnal Pengabdian dan Pemberdayaan Masyarakat Indonesia Jurnal 7 Samudra Politeknik Pelayaran Surabaya Jurnal Masyarakat Berdikari dan Berkarya (MARDIKA) Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) The Indonesian Journal of Computer Science Jurnal Pengabdian Masyarakat Terapan
Yuda Irawan
Universitas Hang Tuah Pekanbaru
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering 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 Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 137 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 137 Documents
Search

 10   11   12   13   14 
Multimodal Deep Learning and IoT Sensor Fusion for Real-Time Beef Freshness Detection Kurniawan, Bambang; Wahyuni, Refni; Yulanda, Yulanda; Irawan, Yuda; Habib Yuhandri, Muhammad
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.977

Abstract

Beef freshness quality is one of the important indicators in ensuring food safety and suitability. However, conventional methods such as manual visual inspection and laboratory testing cannot be widely applied in real-time and mass scale. To overcome these challenges, this study proposes a meat freshness detection system based on a multimodal approach that combines visual imagery and gas sensor data in a single IoT-based framework. This system is designed by utilizing the YOLOv11 architecture that has been optimized using the Adam optimizer. The dataset consisted of 540 original beef images, expanded into 1,296 images after augmentation. The model is trained on these augmented images and is able to achieve detection performance with a mAP@0.5 value of 99.4% and mAP@0.5:0.95 of 95.7%. As a further improvement, the cropped image features from the YOLOv11 model are processed through a combination of the ViT model and CNN to classify the level of meat freshness into three classes: Fresh, Medium, and Rotten with an accuracy of 99%. On the other hand, chemical data was obtained from the MQ136 and MQ137 gas sensors to detect H₂S and NH₃ levels which are indicators of meat spoilage. Data from visual and chemical data were then combined through a multimodal fusion method and classified using the Random Forest algorithm, producing a final prediction of Fit for Consumption, Need to Check, and Not Fit for Consumption. This multimodal model achieved a classification accuracy of 98% with a ROC-AUC score approaching 1.00 across all classes. While the proposed system achieved very high accuracy, further validation across diverse real-world environments is recommended to establish its generalizability.
Aplikasi Pengarsipan Surat Masuk dan Surat Keluar Berbasis Web pada SMP Negeri 32 Pekanbaru Yulisman, Yulisman; Wahyuni, Refni; Irawan, Yuda
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 3 No. 4 (2020): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

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

Abstract

Archiving incoming and outgoing mail is very important in an organization, especially for institutions such as SMP Negeri 32 Pekanbaru. The filing of letters at SMP Negeri 32 Pekanbaru is still done by writing incoming and outgoing letters on the agenda book and storing letters in filing cabinets, making it difficult to find old letter archives and often losing letters. The purpose of this research is to find the right solution so that the archiving of incoming and outgoing mail at SMP Negeri 32 Pekanbaru is more effective and efficient by making an application for archiving incoming and outgoing mail. The method used in this research is the system development model method, namely the Waterfall Model. The application design and analysis model uses the UML (Unified Modeling Language) model which is an object-oriented language or OOP (Object Oriented Programming). Application development and development uses a static programming language, namely PHP (Hypertext Pre-processor) and MySQL as application database. The results of the research on the making of incoming and outgoing mail archiving applications are very helpful and easier for SMP Negeri 32 Pekanbaru in filing incoming and outgoing mail, especially the Administration (School Administration) section because letter archiving is already stored in the database. The conclusion is that the application is very easy and helpful in archiving incoming mail and this letter is evident from the user's assessment of the application with a value of 92% more effective and efficient.
Penyuluhan Cyberbullying dan Etika Digital bagi Siswa Sekolah Dasar di SDIT Ar Royyan Pekanbaru Riau berbasis Teknologi Interaktif Wahyuni, Refni; Irawan, Yuda
Jurnal Pengabdian Masyarakat Terapan Vol 2 No 3 (2025): JUPITER Desember 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jupiter.2.3.92

Abstract

Penggunaan teknologi digital yang semakin meluas di kalangan siswa sekolah dasar memberikan peluang besar dalam proses pembelajaran, namun juga menghadirkan risiko serius berupa cyberbullying dan perilaku bermedia yang tidak etis. Permasalahan yang ditemukan di SDIT Ar Royyan Pekanbaru menunjukkan bahwa banyak siswa terlibat dalam tindakan seperti ejekan di media sosial, komentar kasar, penggunaan bahasa tidak sopan saat bermain game daring, hingga tindakan lain seperti penyebaran pesan bernada merendahkan dan pelecehan verbal digital. Minimnya literasi digital, rendahnya etika berinternet, serta kurangnya edukasi formal mengenai keamanan digital menjadikan siswa rentan menjadi pelaku maupun korban perundungan siber. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan pemahaman siswa mengenai bahaya cyberbullying dan menanamkan etika digital melalui pendekatan edukatif dan interaktif berbasis teknologi. Metode kegiatan meliputi presentasi visual, video edukatif, diskusi kelompok, kuis digital, serta roleplay yang menggambarkan kasus nyata seperti flaming, harassment, trolling, impersonation, dan outing. Kegiatan diikuti oleh 30 siswa kelas IV dan V, diawali dengan pre-test yang menunjukkan hanya 45% siswa mampu mengidentifikasi bentuk-bentuk cyberbullying beserta dampaknya. Setelah penyuluhan, hasil post-test meningkat signifikan menjadi 87%. Selain peningkatan kognitif, observasi lapangan menunjukkan perubahan sikap positif, seperti meningkatnya kehati-hatian siswa dalam berkomentar, menurunnya penggunaan bahasa kasar saat bermain daring, serta tumbuhnya empati terhadap korban cyberbullying. Guru pendamping juga melaporkan bahwa siswa mulai lebih terbuka dalam membicarakan pengalaman digital mereka dan meminta bimbingan dalam menggunakan media sosial dengan bijak. Kegiatan ini membuktikan bahwa pendekatan edukatif berbasis teknologi, dipadukan dengan metode partisipatif seperti roleplay dan gamifikasi, sangat efektif dalam meningkatkan literasi digital, kesadaran etika bermedia, dan kemampuan siswa dalam mengenali serta mencegah berbagai bentuk cyberbullying.
An Integrated Machine Learning and Deep Learning Approach for Multiclass Flood Risk Classification with Feature Selection and Imbalanced Data Handling Irawan, Yuda; Refni Wahyuni; Herianto
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4639

Abstract

Floods are hydrometeorological disasters that often occur in tropical regions such as Indonesia and can have significant impacts on infrastructure, economy, and public health. This study aims to build and compare the performance of 21 artificial intelligence models, consisting of 15 Machine Learning algorithms and 6 Deep Learning architectures, in classifying flood risk levels based on multivariate tabular data. The dataset used includes 22 relevant environmental and social variables, with classification targets in four classes: Low, Moderate, High, and Very High. To improve data quality, feature selection was carried out using the LASSO method and class balancing with the SMOTEENN technique. The evaluation results showed that the C4.5, MLP, Random Forest, and Logistic Regression models obtained the highest accuracy (>94%), followed by deep learning models such as BiLSTM, CNN, and BiGRU with competitive accuracy (≥90%). Confusion matrix analysis confirmed the consistency of predictions across classes with a balanced distribution, especially in the decision tree and deep neural network models. This study emphasizes the importance of selecting a model that suits the characteristics of the data to achieve optimal predictions. The pipeline developed in this study is expected to be the basis for a more accurate and adaptive AI-based early warning system in mitigating flood risks in the future.
Integration of Machine Learning Models Random Forest and XGBoost for Credit Card Fraud Detection in a Python Flask-Based Application Heri, Herianto; Zupri Henra Hartomi; Rian Ordila; Yuda Irawan
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4821

Abstract

Credit card fraud is one of the major challenges in modern digital payment systems. The increasing volume of online transactions raises the potential for unauthorized use of cardholder data. This research aims to develop a robust and accurate fraud detection system by integrating two machine learning algorithms, Random Forest and XGBoost, both of which are known for their high performance in data classification. The research process begins with the collection and preprocessing of credit card transaction data, followed by model training using the selected algorithms. The model’s performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. To enable real-time application, the model is implemented in a web-based system using the Python Flask framework, allowing direct integration into financial transaction environments. The need for adaptive systems that can respond to emerging fraud patterns serves as a key motivation for this study. By combining two complementary algorithms within a single web application platform, the system is expected to detect fraudulent activities quickly and accurately. The expected outcomes of this research include: (1) an optimized fraud detection model based on Random Forest and XGBoost, (2) a prototype web application developed with Python Flask for system implementation, and (3) a scientific publication describing the development and results of the proposed system. The targeted outputs are a publication in a nationally accredited journal (Sinta 4) and intellectual property registration. This research is expected to provide a significant contribution to preventing credit card fraud through the effective application of machine learning technologies
Utilization of IndoBERT Representation and Random Forest for Sentiment Analysis on User Reviews of Halodoc Pharmacy Services in Google Play Hendry Fonda; Herianto; Yuda Irawan
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4822

Abstract

With the growing use of digital healthcare platforms such as Halodoc, maintaining consistent service quality that meets user expectations is essential. User reviews on platforms like Google Play provide valuable insights into user perceptions. This study aims to classify user sentiments toward Halodoc’s pharmacy services based on reviews obtained through web scraping from the Google Play Store. The analysis employs the pre-trained IndoBERT model to extract textual features, followed by sentiment classification using the Random Forest algorithm. This combination was selected for its efficiency with limited hardware resources and small dataset size. To enhance data diversity and minimize overfitting, simple augmentation methods such as random word deletion and synonym substitution were implemented. The expected outcomes include an effective sentiment classification model and visualizations of sentiment distributions (positive, negative, neutral). Furthermore, the study contributes to the development of sentiment analysis techniques for Indonesian-language data through an efficient and contextually relevant approach. The research outputs target publication in a nationally accredited (Sinta 4) journal and Intellectual Property Rights (IPR) registration. Ultimately, this study is expected to support the improvement of technology-based pharmacy services through the strategic application of machine learning.
COMPARISON OF DEEP LEARNING MODELS LSTM AND BILSTM IN DIABETES PREDICTION: COMPARISON OF DEEP LEARNING MODELS LSTM AND BILSTM IN DIABETES PREDICTION Wahyuni, Refni; Irawan, Yuda
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4904

Abstract

Diabetes mellitus remains a major global health concern, requiring early detection to prevent severe complications and reduce mortality. This study developed and evaluated two deep learning architectures, Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM), for diabetes prediction using the Pima Indians Diabetes Dataset. The research methodology involved systematic preprocessing, including outlier handling with median imputation, data normalization, and training–testing data splitting (80:20). Both models were trained using 614 samples for training and 154 samples for testing, with 50 epochs and a batch size of 32. The evaluation was performed using accuracy, precision, recall, F1-score, and AUC metrics. Results indicated that LSTM achieved an accuracy of 74.03%, while BiLSTM slightly outperformed it with 74.68%. Confusion matrix analysis further revealed that BiLSTM reduced false negatives and provided more consistent learning stability compared to LSTM. Accuracy and loss curves confirmed BiLSTM’s superior convergence and generalization capability. These findings demonstrate that BiLSTM is more effective and reliable for diabetes prediction tasks. The study concludes that BiLSTM offers better potential for integration into decision-support systems, and future research could enhance performance through larger datasets, advanced optimization, and real-world clinical validation.
Co-Authors -, Herianto A.A. Ketut Agung Cahyawan W Abdurrahman Hamid Achmad Deddy Kurniawan Achmad Nizar Hidayanto Adhitya, Ryan Yudha Aditya Rickyta Adyanata Lubis Afresi Yunita Agnita Utami Agus Alamsyah Ahmad Fauzan Azim Akbar, Amri Akhmad Zulkifli Aldiga Rienarti Abidin Anam, M Khairul Andre Wahyu Novrianto Anisa, Lia Anita Febriani Aprilia, Ulfa Areta Sonya Rahajeng Arfianto, Afif Zuhri Arnawilis Arnawilis Arnawilis Bakhrizal Bambang Kurniawan Bayu Saputra Budy Mustika Debi Setiawan, Debi Desi Rahmawati Devis, Yesica Dhea Arina Ramadhini Dhini Septhya Diandra, Roni Edriyansyah Eka Sabna Elisawati, Elisawati Fachry Abda El Rahman Fatmawati, Kiki Fitri, Imelda Fonda, Hendry Gilang Citra Lenardo Habib Yuhandri, Muhammad Hadi Asnal, Hadi Hafizh Sallam Hamdani Hamdani Hartomi, Zupri Henra Hasnor Khotimah Hayami, Regiolina Hendro Agus Widodo, Hendro Agus heri, Herianto Herianto Herianto Herianto Herianto - Herianto Herianto Herianto Herianto Hidayati Kurnia Fitri Hohashi, Naohiro Irwanda Syahputra Jamaris, Muhamad Jenli Susilo Jenni Oinike Br Sitorus Jepisah, Doni Jeri Trio Sentana Junadhi Junadhi Junadhi Junadhi Junadhi, Junadhi Khairunisa Khairunisa Khairunisa, Khairunisa Kharisma Rahayu Kurniawan, Bambang Lucky Lhaura Van FC, Lucky Lhaura Mardainis Mardeni Mardeni Mardeni, Mardeni Matthijs B Punt Maulita Yulia Sari Mbunwe Muncho Josephine Mbunwe Muncho Josephine Melyanti, Rika Mitrin, Abdullah Mohd Rinaldi Amartha Muhaimin, Abdi Muhamadiah, Muhamadiah Muhammad Bambang Firdaus Muhardi Muhardi - Muhardi Muhardi Muhardi Muhardi Mulya Rispani Mutiara Sari, Ria Naima Belarbi Naima Belarbi Nella Sari Nico Chandra Noratama Putri, Ramalia Nurhadi Nurhazimah Rafiah Octaria, Haryani Ordila, Rian Perkasa, Reza Prihandoko, P Purnomo, Nopi Purwanti, Siti Putra Rahmaddeni Rahmaddeni Rahmaddeni Rahmaddeni Rahmalisa, Uci Rahman, Rudi Refni Wahyuni Renaldi, Reno renaldi, reno Reza Perkasa Rian Ordila Rian Ordila Riananda, Dimas Pristovani Richi Andrianto Rickyta, Aditya Rofiqoh, Ummi Rometdo Muzawi, Rometdo Roni Diandra Ruwahida, Dewi Rizani Ruwahida Sabna, Eka Sakroni Indra Gunawan Salsabila Rabbani Saputra, Haris Tri Sarjon Defit Sentana, Jeri Trio Siti Aisyah Siti Aisyah Siti Purwanti Sugiati Suherman Sohor Suherman Suherman Suriandi Suriandi Susanti, Susanti Susi Oustria Simamora Susilo, Jenli Syamsul Arifin Uci Rahmalisa Ulfa Aprilia Vindi Fitria Winda Herrianti Manullang Winda Sari Wulan Sari Yesica Devis Yuhandri, Y Yulanda Yulanda Yulanda Yulanda, Yulanda YULISMAN Yulisman, Yulisman Yunior Fernando Zufari, Faisal Zufi Pratama Noviardi Zupri Henra Hartomi