Bachelor of Informatics Engineering
Magister of Information Technology
Doctoral Student of Computer Science
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Artificial Intelligence, Software, Information Systems
9
Scopus Publications
158
Scholar Citations
6
Scholar h-index
2
Scholar i10-index
Scopus Publications
Evaluating Hyperparameter Tuning of Random Forest and CatBoost on Complex and Imbalanced Real-world Datasets Andri, Darwin, Poi Wong Ng, Sutarman, Erna Budhiarti Nababan Pertanika Journal of Science and Technology, 2026 Research on hyperparameter tuning of Random Forest (RF) and CatBoost on imbalanced datasets often focusses on these algorithms separately, with limited evaluation of both comprehensively across a wide range of dataset complexities. The effects of hyperparameter tuning in handling pattern complexity and class distribution in real-world imbalanced datasets remain unexplored. This gap hinders the understanding of how hyperparameter optimisation can improve performance for such data, leading to potential model unoptimality and challenges in selecting the most effective algorithm. This research evaluates the impact of RF and CatBoost hyperparameter tuning on complex and imbalanced real-world datasets, with XGBoost added as a comparative baseline. The datasets used include binary and multi-class categories with varying degrees of class imbalance and feature complexity, as measured using Shannon Entropy and Coefficient of Variation (CV). Hyperparameter tuning uses Bayesian Optimisation (BO-TPE), Hyperband (HB), and Random Search (RS). Results show that datasets with high CV result in significant differences between accuracy and F1-score values. Hyperparameter tuning on RF improved the average accuracy and F1 score on binary-class datasets, but did not have a significant impact on AUC. In contrast, tuning on RF for multi-class datasets provided more consistent improvements across all three evaluation metrics. On the other hand, CatBoost and XGBoost tuning provided consistent average improvements on all three metrics for both binary and multi-class datasets. CatBoost generally shows the best efficiency on large datasets, followed by XGBoost and RF. In contrast, on small datasets, XGBoost is the most efficient, followed by RF and CatBoost.
DEVELOPMENT OF A HYBRID SIAMESE AND FEEDFORWARD NEURAL NETWORKS ARCHITECTURE FOR SEMANTIC TEXT SIMILARITY MEASUREMENT Ng Poi Wong, Tengku Henny Febriana Harumy, Syahril Efendi Eastern European Journal of Enterprise Technologies, 2025 The object of this study is the semantic similarity between two texts. This research focuses on developing a hybrid architecture that combines Siamese Neural Network (SNN) with Feedforward Neural Network (FNN) to measure the semantic text similarity, with text representation using Sentence-BERT (SBERT). The problem addressed is the challenge of capturing deep semantic relationships between two texts, which traditional methods, such as Term Frequency-Inverse Document Frequency (TF-IDF) or Word2Vec, find difficult to achieve. This research aims to overcome these weaknesses by combining the two architectures into a more powerful hybrid system. The test results show the highest accuracy of 87.82 % on the Semantic Textual Similarity (STS) dataset using the SBERT “all-MiniLM-L6-v2” model, 76.72 % on the Quora Question Pairs (QQP) dataset using the “multi-qa-MiniLM-L6-cos-v1” model, and 73.79 % on the Microsoft Research Paraphrase Corpus (MSRP) dataset using the “paraphrase-MiniLM-L12-v2” model. The optimal parameters for the number of epochs ranged from 300 to 700, and the optimal learning rate ranged from 0.01 to 0.5. SBERT models, such as “paraphrase-MiniLM-L6-v2” and “paraphrase-MiniLM-L12-v2”, gave the best results on the relevant datasets. The flexibility of the “multi-qa-MiniLM-L6-cos-v1” model also shows that the model designed for question and answer tasks can be used in the paraphrase detection domain. A unique feature of the model is the integration of SBERT as a text representation, which results in a richer semantic vector than traditional methods. The model has potential for wide application in various domains, such as plagiarism detection, legal documents, and question-and-answer systems. However, implementation requires attention to parameter selection, such as learning rate and number of epochs, to avoid overfitting or underfitting
Modeling Face Detection Application Using Convolutional Neural Network and Face-API for Effective and Efficient Online Attendance Tracking Carles Juliandy, Ng Poi Wong, Darwin Jurnal Online Informatika, 2024 The pandemic of Covid-19 emergency has ended, but it gives us a new lifestyle every aspect of life and also in the education aspect has changed. At that moment as one of the ways to prevent pandemic infection, many governments give the policy to close the offline class and continue with online classes. The online class system encountered several problems and one of those problems was to track the students’ attendance to ensure all the students were attending the class. The teacher needed extra effort to track it because they needed to call the students one by one which is wasting time and sometimes would miss the presence of the students who attend the class. To make it effective efficient accurate and time-consuming when tracking attendance in online classes for teachers, we proposed the face detection model which combines face-api.js and CNN to detect and recognize the students’ faces to help teachers track attendance by just uploading the screenshot image of the online meeting application. We tested our model with accuracy and speed testing. With 3 images of every student’s face as training data, our model was able to recognize the face with 100% accuracy in just 41,65 seconds which is faster than calling students one by one that need almost 3 to 5 minutes if there are many students. Future research can be done by focusing research on improving the model to detect the students’ faces with different brightness, contrast, and saturation because students may not have the same place and condition when joining an online meeting class.
Modeling Plagiarism Prevention in Scientific Publication Using Enhanced Blockchain Ng Poi Wong, Carles Juliandy, Darwin Proceedings 2024 2nd International Conference on Technology Innovation and Its Applications Ictiia 2024, 2024 The improvement in technology causes plagiarism to occur and causes losses for the original creator. Plagiarism easily occurs in many areas including research papers. From this problem., we proposed a model to not only detect but also prevent plagiarism by merging Blockchain technology., the Elliptic Curve Digital Signature Algorithm (ECDSA)., and the Rabin-Karp algorithm. The proposed model was improved model by another researcher. Our model is separated into two parts., the front end will be used to detect similarity percentage and prevent plagiarism also the back end will be used to prevent plagiarism. The simulation result shows that the Rabin-Karp algorithm is robust enough to detect similarity percentages. The ECDSA algorithm ensures that the authorized can open the submission paper. Lastly., Blockchain technology prevents any change in the data that is stored inside the network. This research successfully introduced a more secure model in the research paper submissions.
Enhancing Warehouse Inventory Management through IoT Tools for Monitoring Stock Items Sunaryo Winardi, Ng Poi Wong, Arifin, Apriyanto Halim, Sunario Megawan Proceedings 2024 2nd International Conference on Technology Innovation and Its Applications Ictiia 2024, 2024 The increasing demand for personalized products and a global presence complicates inventory management, requiring accurate and timely stock information. To address this, businesses must leverage Internet of Things (IoT) solutions, which connect various electronic devices to the internet via advancements in cloud technology, sensor networks, and wireless communication. This research proposes a tailored IoT architecture for warehouse inventory checking processes, focusing on real-time tracking and visibility, cost reduction, enhanced security, improved inventory management, and increased supply chain speed. Implementing an IoT-based Warehouse Inventory Management system, designed with four layers (Physical, Gateway, Middleware, and Application), significantly improves operational efficiency and inventory tracking. While human involvement remains necessary, IoT solutions optimize inventory management and enhance overall efficiency.
Enhancing Student Dropout Prediction Using Chi-Square, SMOTE-ENN, and Hyperparameter Tuning of Random Forest Andri, Roni Yunis, Djoni, Ng Poi Wong, Robin, Darwin 2024 9th International Conference on Informatics and Computing Icic 2024, 2024 Reducing dropout rates is crucial for enhancing human capital and education standards. Existing methods, such as Random Forest with Chi-Square and SMOTE-ENN, effectively addressed class imbalance and improved prediction accuracy for dropout data. However, there is still a research gap in achieving optimal model performance. This study addresses the gap by incorporating hyperparameter tuning alongside ChiSquare for feature selection and SMOTE-ENN for handling class imbalance. The dataset was segmented into training and evaluation subsets through the implementation of 10 -fold cross-validation. The testing was conducted with seven variations, namely building and implementing a Random Forest model using the default parameters from the Weka tool and applying six different hyperparameter tuning techniques. The results showed that Hyperband, along with other techniques like TPE, RandomSearch, and BO-TPE, led to substantial improvements in model accuracy, precision, and F-measure, and achieved perfect AUC scores. However, BO-GP and Nevergrad did not improve model performance. These findings suggest that the combination of SMOTE-ENN, Chi-Square, and hyperparameter tuning can enhance the effectiveness of dropout prediction models, with potentially positive implications for early intervention strategies in educational institutions.
Implementation of Sentiment Analysis of Shopee E-Commerce Reviews using Naïve Bayes, N-Gram, and Information Gain Andriana Sunjaya, Novresia Wijaya, Ng Poi Wong, Sunaryo Winardi 2023 8th International Conference on Informatics and Computing Icic 2023, 2023 One of the important parts of e-commerce like Shopee reviews. The reviews are part of user trust in conducting business transactions, so it becomes a challenge for sellers to evaluate their products and services. Evaluation can be done by looking at star ratings, but the discrepancy between the content of the review text and the star rating causes the information received to be biased and evaluations carried out by classifying reviews manually require a longer time so sentiment analysis is needed to speed up the process of classifying by objectively dividing product quality into several categories such as positive, neutral, and negative. This study uses the Naïve Bayes method combined with N-Gram feature extraction and Information Gain feature selection to determine positive, neutral, and negative sentiments toward buyer reviews. In its testing, this study used confusion matric to obtain accuracy, precision, recall, and f1-Score results. The best results show an accuracy value of 92%, precision of 56%, recall of 65%, and f1-score of 60%.
Measuring the Maturity Level of ITSM Using ITIL Framework Andri, Paulus, Hanes, Ng Poi Wong Proceedings of 2019 4th International Conference on Informatics and Computing Icic 2019, 2019 At present Indonesia is facing a 4.0 industrial revolution in various industrial sectors including education called Education 4.0. This can be seen in the use of digital technology in the learning process. To support the digital transformation, educational institutions must maximize Information Technology Service Management (ITSM). IT service from STMIK Mikroskil is managed by an IT department. To improve this ITSM, the IT department first needs to know the current level of maturity. So far there has only been a measurement of IT service satisfaction based on a questionnaire filled out by students but has not included detailed processes and functions in delivering service. The purpose of this study is to measure the maturity of ITSM using ITIL framework. The ITIL Framework was chosen because it is the most popular framework. Measurements are made at the Service Operation stage which consists of 5 processes and 4 functions. Maturity measurement tool uses a questionnaire template defined by UCISA. The benefits obtained from this study are STMIK Mikroskil can find out the maturity level of the current ITSM (baseline). By knowing the level of maturity, STMIK Mikroskil is easier to improve weak service management.
Steganography using Mode-Based Least Significant Bit (MBLSB) Method Ng Poi Wong, Hardy, Sunario Megawan, Andri Proceedings of 2019 4th International Conference on Informatics and Computing Icic 2019, 2019 In the Least Significant Bit (LSB) method of steganography, inserting bits into the cover image is generally done using the blue channel while ignoring the red and green channels as the human eye is relatively insensitive to blue color as such making it easier to hide the secret bits. However this approach is also easier to be detected and therefore attacked as one can discover the secret bits by observing the size distribution in each channel of the cover image. Our work introduces a simple method that insert the secret bits into cover image based on mode value of the bits of all channels, as such the insertion is evenly distributed based on the cover image size and is harder to be detected or attacked. Our proposed MBLSB approach divides the cover image into several insertion blocks, of which each pixel value will be taken from all pixels in each channel. Finally a XOR gate is applied to the secret bit and the retrieved pixel value to get the mode value for the purpose of determining the insertion bit value. The resulting stego-image quality are evaluated using PSNR with value above 60 dB (no apparent noise) and MSE with value below 1.0 while the average success rate of secret data extraction in the event of a color noise attack is 66.45%.
RECENT SCHOLAR PUBLICATIONS
Evaluating Hyperparameter Tuning of Random Forest and CatBoost on Complex and Imbalanced Real-world Datasets. NP Wong, EB Nababan Pertanika Journal of Science & Technology 34 (1) , 2026 2026
IMPLEMENTASI CNN UNTUK IDENTIFIKASI SPESIES REPTIL DAN AMFIBI BERBASIS CITRA DIGITAL AR Napitupulu, HSL Tobing, NP Wong, K Kelvin JURNAL MAHAJANA INFORMASI 10 (2), 135-144 , 2025 2025
A Smart Architecture for Stunting Prediction: Implementing the SOM–Voting Classifier on Healthcare Big Data Kelvin, S Winardi, FM Sinaga, Hardy, ES Panjaitan, NP Wong, Ferawaty, ... Indonesian Journal of Artificial Intelligence and Data Mining 8 (3), 526-535 , 2025 2025
Utilizing TF-IDF Content-based Filtering for Job Recommendation Systems S Winardi, S Megawan, NP Wong, R Kurniawan, FA Putra, Cynthia Jurnal Nasional Komputasi dan Teknologi Informasi 8 (5) , 2025 2025
SISTEM PEMANTAUAN LINGKUNGAN KANDANG KAMBING BERBASIS IOT DALAM MENDUKUNG SMART FARMING PADA ARJUNA FARM NP Wong, Andri, Darwin, IA Pardosi, R Yunis, P Sihombing, YA Pratama Jurnal Masyarakat Mandiri 9 (5), 4650-4661 , 2025 2025
Development of a hybrid siamese and feedforward neural networks architecture for semantic text similarity measurement NP Wong, THF Harumy, S Efendi Eastern European Journal of Enterprise Technologies 3 (2), 30-41 , 2025 2025
Pelatihan Pengenalan Pemrograman Komputer pada SMA Dharma Bakti Lubuk Pakam A Halim, H Gohzali, IA Pardosi, NP Wong, S Megawan ABDIKAN: Jurnal Pengabdian Masyarakat Bidang Sains dan Teknologi 4 (2), 55-66 , 2025 2025 Citations: 1
Enhancing Student Dropout Prediction Using Chi-Square, SMOTE-ENN, and Hyperparameter Tuning of Random Forest Andri, R Yunis, Djoni, NP Wong, Robin, Darwin 2024 Ninth International Conference on Informatics and Computing (ICIC) , 2025 2025
Pengembangan Aplikasi Web untuk Meningkatkan Efisiensi Operasional Organisasi Nirlaba Bidang Kesehatan S Winardi, NP Wong, S Megawan, TW Ginting, FR Fa, C Sintiya, J Jikky Abdi: Jurnal Pengabdian dan Pemberdayaan Masyarakat 7 (1), 57-67 , 2025 2025
Rancang Bangun Sistem Informasi Les Privat Berbasis Web pada Les Privat Medan NP Wong, V Leonora, J Johnson, FM Sinaga METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi 11 (1), 15-19 , 2025 2025
Enhancing Warehouse Inventory Management through IoT Tools for Monitoring Stock Items S Winardi, NP Wong, Arifin, A Halim, S Megawan 2024 2nd International Conference on Technology Innovation and Its … , 2024 2024 Citations: 3
Modeling Plagiarism Prevention in Scientific Publication Using Enhanced Blockchain NP Wong, C Juliandy, Darwin 2024 2nd International Conference on Technology Innovation and Its … , 2024 2024 Citations: 1
Modeling Face Detection Application Using Convolutional Neural Network and Face-API for Effective and Efficient Online Attendance Tracking C Juliandy, NP Wong, Darwin Jurnal Online Informatika 9 (1), 10-17 , 2024 2024 Citations: 9
Pengenalan dan Penerapan Enterprise Resource Planning (ERP) dan Software As A Service (SAAS) melalui Dewatalks Darwin, C Juliandy, NP Wong, B Febrian Jurnal Gembira: Pengabdian Kepada Masyarakat 2 (01), 92-98 , 2024 2024
Implementation of Sentiment Analysis of Shopee E-Commerce Reviews using Naïve Bayes, N-Gram, and Information Gain A Sunjaya, N Wijaya, NP Wong, S Winardi 2023 Eighth International Conference on Informatics and Computing (ICIC), 1-6 , 2023 2023 Citations: 3
Pengembangan Aplikasi Layanan Pemesanan Futsal Gembira Berbasis Web Dan Mobile FGM Sianipar, NH Nainggolan, J Gunawan, NP Wong, S Winardi Jurnal SIFO Mikroskil 24 (2), 187-196 , 2023 2023
Pelatihan Python Sebagai Landasan Awal Belajar Pemrograman bagi Siswa/Siswi SMK Methodist Tanjung Morawa S Winardi, A Andri, NP Wong BERNAS: Jurnal Pengabdian Kepada Masyarakat 4 (4), 3498-3504 , 2023 2023 Citations: 6
RANCANG BANGUN APLIKASI LOKAPASAR JASA PERCETAKAN DENGAN DETEKSI WARNA HALAMAN Ardiansah, IM Habibie, N Poi Wong, Andri JTIK (Jurnal Teknik Informatika Kaputama) 7 (1), 111-117 , 2023 2023 Citations: 1
Operational Improvements In It-Based E-Commerce Companies Using Monday. Com N Poi Wong, D Darwin, R Suwandy Jurnal Teknologi Dan Sistem Informasi Bisnis-JTEKSIS 4 (1), 102-106 , 2022 2022
Hospital Health Services Application Development using Evaluation Based on Distance from Average Solution (EDAS) NS Santoso, N Ongko, G Wijaya, N Poi Wong, FM Sinaga Seminar Nasional Informatika (SEMNASIF) 1 (1), 1-9 , 2021 2021 Citations: 86
MOST CITED SCHOLAR PUBLICATIONS
Hospital Health Services Application Development using Evaluation Based on Distance from Average Solution (EDAS) NS Santoso, N Ongko, G Wijaya, N Poi Wong, FM Sinaga Seminar Nasional Informatika (SEMNASIF) 1 (1), 1-9 , 2021 2021 Citations: 86
Segmentasi buah menggunakan metode k-means clustering dan identifikasi kematangannya menggunakan metode perbandingan kadar warna Andri, Paulus, N Poi Wong, T Gunawan Jurnal SIFO Mikroskil 15 (2), 91-100 , 2014 2014 Citations: 20
Modeling Face Detection Application Using Convolutional Neural Network and Face-API for Effective and Efficient Online Attendance Tracking C Juliandy, NP Wong, Darwin Jurnal Online Informatika 9 (1), 10-17 , 2024 2024 Citations: 9
Steganografi pada Citra dengan Metode MLSB dan Enkripsi Triple Transposition Vigenere Cipher AA Lubis, N Poi Wong, I Arfiandi, VI Damanik, A Maulana Jurnal SIFO Mikroskil 16 (2), 125-134 , 2015 2015 Citations: 8
Pelatihan Python Sebagai Landasan Awal Belajar Pemrograman bagi Siswa/Siswi SMK Methodist Tanjung Morawa S Winardi, A Andri, NP Wong BERNAS: Jurnal Pengabdian Kepada Masyarakat 4 (4), 3498-3504 , 2023 2023 Citations: 6
Aplikasi Pengenalan Karakter pada Plat Nomor Kendaraan Bermotor dengan Learning Vector Quantization N Poi Wong, Hardy, A Maulana SESINDO 2013 2013 , 2013 2013 Citations: 6
Enhancing Warehouse Inventory Management through IoT Tools for Monitoring Stock Items S Winardi, NP Wong, Arifin, A Halim, S Megawan 2024 2nd International Conference on Technology Innovation and Its … , 2024 2024 Citations: 3
Implementation of Sentiment Analysis of Shopee E-Commerce Reviews using Naïve Bayes, N-Gram, and Information Gain A Sunjaya, N Wijaya, NP Wong, S Winardi 2023 Eighth International Conference on Informatics and Computing (ICIC), 1-6 , 2023 2023 Citations: 3
Measuring the Maturity Level of ITSM Using ITIL Framework Andri, Paulus, Hanes, NP Wong 2019 Fourth International Conference on Informatics and Computing (ICIC) , 2019 2019 Citations: 3
Perbandingan Algoritma C4. 5 dan Classification and Regression Tree (CART) Dalam Menyeleksi Calon Karyawan N Poi Wong, FNS Damanik, ES Jaya, R Rajaya Jurnal SIFO Mikroskil 20 (1), 11-18 , 2019 2019 Citations: 3
Aplikasi Algoritma Semi–Fragile Image Watermarking Berdasarkan pada Region Segmentation Andri, N Poi Wong, J Fransiscus Jurnal SIFO Mikroskil 15 (1), 21-30 , 2014 2014 Citations: 3
Prediksi Akurasi Perusahaan Saham Menggunakan SVM dan K-Fold Cross Validation AA Lubis, N Poi Wong, FM Sinaga Jurnal SIFO Mikroskil 21 (1), 11-18 , 2020 2020 Citations: 2
Pelatihan Pengenalan Pemrograman Komputer pada SMA Dharma Bakti Lubuk Pakam A Halim, H Gohzali, IA Pardosi, NP Wong, S Megawan ABDIKAN: Jurnal Pengabdian Masyarakat Bidang Sains dan Teknologi 4 (2), 55-66 , 2025 2025 Citations: 1
Modeling Plagiarism Prevention in Scientific Publication Using Enhanced Blockchain NP Wong, C Juliandy, Darwin 2024 2nd International Conference on Technology Innovation and Its … , 2024 2024 Citations: 1
RANCANG BANGUN APLIKASI LOKAPASAR JASA PERCETAKAN DENGAN DETEKSI WARNA HALAMAN Ardiansah, IM Habibie, N Poi Wong, Andri JTIK (Jurnal Teknik Informatika Kaputama) 7 (1), 111-117 , 2023 2023 Citations: 1
Steganography using Mode-Based Least Significant Bit (MBLSB) Method NP Wong, Hardy, S Megawan, Andri 2019 Fourth International Conference on Informatics and Computing (ICIC) , 2020 2020 Citations: 1
Penerapan Algoritma Cuckoo Search pada Travelling Salesman Problem Hardy, N Poi Wong, D Suwandi SESINDO 2013 2013 , 2013 2013 Citations: 1
Rancang Bangun Pembelajaran Online Sistem Operasi Windows 7 dengan HTML 5 N Poi Wong, H Hardy, R Riche Jurnal SIFO Mikroskil 12 (1), 21-28 , 2011 2011 Citations: 1
Evaluating Hyperparameter Tuning of Random Forest and CatBoost on Complex and Imbalanced Real-world Datasets. NP Wong, EB Nababan Pertanika Journal of Science & Technology 34 (1) , 2026 2026
IMPLEMENTASI CNN UNTUK IDENTIFIKASI SPESIES REPTIL DAN AMFIBI BERBASIS CITRA DIGITAL AR Napitupulu, HSL Tobing, NP Wong, K Kelvin JURNAL MAHAJANA INFORMASI 10 (2), 135-144 , 2025 2025
