Article Per Year (5 Year)
p-Index From 2020 - 2025
0.562
P-Index
This Author published in this journals
All Journal MIND (Multimedia Artificial Intelligent Networking Database) Journal Dinamika Bahari: Journal of Maritime Dynamic Journal of Applied Data Sciences
Onn, Choo Wou
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering Environmental Science Mechanical Engineering Transportation

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

Found 3 Documents
Search

 1 
Navigating Heart Stroke Terrain: A Cutting-Edge Feed-Forward Neural Network Expedition Praveen, S Phani; Mantena, Jeevana Sujitha; Sirisha, Uddagiri; Dewi, Deshinta Arrova; Kurniawan, Tri Basuki; Onn, Choo Wou; Yorman, Yorman
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.763

Abstract

Heart stroke remains one of the leading causes of death worldwide, necessitating early and accurate prediction systems to enable timely medical intervention. While a variety of machine learning approaches have been employed to address this issue, including Logistic Regression, Decision Trees, Random Forests, Support Vector Machines, and K-Nearest Neighbors, these models often suffer from limitations such as overfitting, insufficient generalization, poor performance on imbalanced datasets, and inability to capture complex nonlinear patterns in clinical data. Additionally, many existing works do not comprehensively integrate both clinical and demographic features or lack rigorous evaluation metrics beyond accuracy alone. This study proposes a novel Feed-Forward Neural Network (FFNN) model for heart stroke prediction, designed to overcome the shortcomings of conventional models. Unlike shallow classifiers, the FFNN architecture employed here leverages multiple hidden layers and nonlinear activation functions to learn intricate relationships within the dataset. The dataset used comprises various attributes such as age, hypertension, heart disease, BMI, and smoking status, which were preprocessed through normalization, one-hot encoding, and imputation techniques to ensure data quality and model performance. Experiments were conducted using a stratified train-test split, and the model was trained using the Adam optimizer with carefully tuned hyperparameters. Comparative evaluations against baseline models (Logistic Regression, Random Forest, and SVM) were carried out using precision, recall, F1-score, and ROC-AUC as performance metrics. The proposed FFNN achieved the highest accuracy of 96.47%, along with substantial improvements in recall and F1-score, highlighting its superior capability in identifying potential stroke cases even in imbalanced datasets. This work bridges a significant gap in heart stroke prediction by demonstrating the effectiveness of deep learning models—specifically FFNNs—in extracting complex patterns from diverse patient data. It also sets the stage for further exploration of deep learning-based clinical decision support systems.
Integrating Machine Learning and Internet of Things for Predictive Maintenance Enhancing Operational Efficiency and Maritime Digitalization Setiawan, Ariyono; Handoko, Wisnu; Onn, Choo Wou; Widyaningsih, Upik
Dinamika Bahari Vol 6 No 2 (2025): October 2025 Edition
Publisher : Politeknik Ilmu Pelayaran Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46484/db.v6i2.1031

Abstract

This study explores the implementation of Machine Learning (ML) and the Internet of Things (IoT) in predictive maintenance to enhance the operational efficiency of ships. The primary goal is to evaluate the effectiveness of these technologies in reducing maintenance costs, minimizing unexpected machinery failures, and improving fuel efficiency. The research is based on previous studies on AI-driven predictive maintenance and IoT-based real-time monitoring. It builds upon the work of Kim & Park (2021) and Li et al. (2019), who demonstrated the advantages of deep learning and IoT in improving maritime asset management. A comparative analysis was conducted using multiple ML algorithms, including Random Forest, Support Vector Machine (SVM), K-Means Clustering, and Long Short-Term Memory (LSTM). Data from IoT-enabled sensors on ship machinery were used to evaluate model accuracy, downtime reduction, and cost efficiency improvements. LSTM outperformed other models with an accuracy of 89.1%. Predictive maintenance reduced downtime by 30%, extended machinery lifespan by 20%, and decreased operational costs by 15%. Challenges include IoT infrastructure limitations, data security concerns, and the need for extensive historical data. This study highlights the necessity for shipping companies to invest in IoT infrastructure, cybersecurity measures, and workforce training to optimize predictive maintenance. The research contributes to maritime digitalization by demonstrating how ML and IoT integration can transform maintenance strategies, leading to a more efficient and cost-effective shipping industry.
Prediksi Ekspor Jasa Transportasi Indonesia Menggunakan LSTM Berbasis Data Perdagangan Global Terbuka SETIAWAN, ARIYONO; HANDOKO, WISNU; ABDUL HADI, ABDUL RAZAK BIN; ONN, CHOO WOU
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 10, No 2 (2025): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v10i2.130-144

Abstract

ABSTRAKPenelitian ini memprediksi nilai ekspor jasa transportasi Indonesia menggunakan model Long Short-Term Memory (LSTM) berbasis data terbuka perdagangan global dalam mengatasi pola nonlinier dan ketergantungan temporal. Peneliti melatih model LSTM tiga lapis dengan aktivasi ReLU dan optimasi Adam menggunakan data ekspor tahunan (2005–2023) dari World Bank dan UNCTAD, dengan pembagian data latih-uji 80:20. Model mencapai MAPE 0,89% dan koefisien korelasi r = 0,999 (p < 0,0001), menunjukkan presisi tinggi. Model secara akurat menangkap gangguan akibat pandemi dan tren pemulihan, menawarkan alat prediksi berbasis AI untuk perencanaan ekspor dan kebijakan perdagangan. Ini merupakan studi pertama yang menerapkan LSTM pada ekspor jasa transportasi Indonesia dengan data terbuka, memberikan kontribusi metodologis dan praktis untuk negara berkembang.Kata kunci: kecerdasan buatan, peramalan ekspor, Indonesia, LSTM, layanan transportasiABSTRACTThis study forecasts Indonesia’s transport service export values using a Long Short-Term Memory (LSTM) model based on open global trade data in capturing nonlinear patterns and temporal dependencies. A three-layer LSTM model is trained using ReLU activation and Adam optimization on annual export data from 2005 to 2023 sourced from the World Bank and UNCTAD. The dataset is split into 80% training and 20% testing portions. The model achieves a MAPE of 0.89% and a correlation coefficient of r = 0.999 (p < 0.0001), indicating high precision.The model accurately reflects pandemic-induced shocks and subsequent recovery trends, provides an AI-driven forecasting tool for export planning and trade policy. This is the first study to apply LSTM to Indonesia’s transport service exports using open data, contributing methodological advancement and practical value for developing economies.Keywords: artificial intelligence, export forecasting, Indonesia, LSTM, transport services
Co-Authors ABDUL HADI, ABDUL RAZAK BIN Dewi, Deshinta Arrova Handoko, Wisnu Kurniawan, Tri Basuki Mantena, Jeevana Sujitha Praveen, S Phani Setiawan, Ariyono Sirisha, Uddagiri Widyaningsih, Upik Yorman