Article Per Year (5 Year)
p-Index From 2021 - 2026
1.822
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal Pilar Nusa Mandiri Paradigma Nuansa Informatika Journal of Computing Innovations and Emerging Technologies Bulletin of Intelligent Machines and Algorithms Jurnal Informatika
Nur Alamsyah
Universitas Informatika Dan Bisnis Indonesia
Computer Science & IT

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Emoji-Based Sentiment Classification Using Ensemble Learning with Cross-Validation: A Lightweight Approach for Social Media Analysis: Klasifikasi Sentimen Berbasis Emoji Menggunakan Ensemble Learning dengan Validasi Silang: Pendekatan Ringan untuk Analisis Media Sosial Nur Alamsyah; Gunthur Bayu Wibisono; Titan Parama Yoga; Budiman; Acep Hendra
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.396

Abstract

The increasing use of emojis in online communication reflects emotional expression that is often more immediate and intuitive than text. This study proposes a lightweight sentiment classification approach that utilizes only emoji features extracted from social media posts, without relying on textual content. The importance of this research lies in its relevance to short-form digital content, where textual sentiment cues are minimal or absent. To address the classification problem, we implement and compare multiple machine learning models including Random Forest (RF), Support Vector Machine, and an ensemble Voting Classifier combining both. Emoji tokens were vectorized using character-level count vectorization, and performance was evaluated using 5-fold cross-validation to ensure robustness and generalizability. Results show that the ensemble model achieved the highest average accuracy of 93.6%, outperforming the individual classifiers. These findings confirm that emojis alone can serve as reliable indicators of sentiment and support the deployment of fast, interpretable, and scalable models for social media sentiment analysis.
A Bidirectional GRU Approach with Hyperparameter Optimization for Sentiment Classification in Game Reviews : Pendekatan GRU Dua Arah dengan Optimasi Hiperparameter untuk Klasifikasi Sentimen dalam Ulasan Game Nur Alamsyah; Titan Parama Yoga; Budiman; Imannudin Akbar; Acep Hendra; Alif Januantara Prima
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.399

Abstract

Sentiment analysis plays a vital role in understanding user perspectives, especially in domains such as game reviews where user feedback influences product perception and engagement. This study presents a comparative approach using Gated Recurrent Unit (GRU), hyperparameter-tuned GRU, and Bidirectional GRU models to classify sentiments in a dataset of game reviews. The experiment begins with standard preprocessing and tokenization steps, followed by vectorization and supervised training. Hyperparameter optimization is conducted using Keras Tuner to identify the most effective configuration of embedding dimensions, GRU units, dropout rates, and learning rates. The best model, a Bidirectional GRU with tuned parameters, achieves a validation accuracy of 85.37% and shows superior performance across key metrics such as precision, recall, and F1-score. Despite the relatively small and imbalanced dataset, the Bidirectional GRU model demonstrates robust generalization. This study also highlights future directions, including class balancing techniques and the integration of pretrained word embeddings to further improve model performance.
A Data-Driven Approach to Comparative Evaluation of Regression Models for Accurate House Price Prediction: Pendekatan Berbasis Data untuk Evaluasi Komparatif Model Regresi untuk Prediksi Harga Rumah yang Akurat Tiara Permata Hati; Budiman Budiman; Imannudin Akbar; Nur Alamsyah
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.411

Abstract

This study aims to develop and evaluate a property price prediction model in Bandung by applying machine learning (ML) algorithms. The need for more accurate property price predictions is increasing due to fluctuations in the property market. This study analyzes property characteristics, including the number of bedrooms, bathrooms, land area, building area, and location, as well as their impact on house prices. The study evaluates four regression algorithms, including linear regression, K-Nearest Neighbors (KNN), Random Forest, and XGBoost. Finally, this study proposes price_per_m2 and building_land_ratio as new features recommended for improvement in accuracy. The bottleneck method is derived from the data collection area of the Rumah123.com website, encompassing data preprocessing and data exploration. The following metrics will be used to evaluate each model: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). Based on our study, we conclude that both Random Forest Regression and XGBoost Regression achieve the highest accuracy, with R² values of 0.9941 and 0.9955, respectively, after adjustment. Conversely, Linear Regression and KNN Regression have the lowest accuracy, with KNN Regression being the least accurate. The primary contribution of this study is the development of a more accurate house price prediction model that can be applied in cities with similar market characteristics. These findings provide practical insights for property developers and buyers when making investment decisions.
An Analysis of the Impact of Zoom on Online Learning Using the Technology Acceptance Model Zatin Niqotaini; Budiman Budiman; Fahreja Ramadhan; Artika Arista; Esa Prakasa; Arafat Febriandirza; Nur Alamsyah; Rezza Novian Noor Rochmat; Henki Bayu Seta
Journal of Computing Innovations and Emerging Technologies Vol. 2 No. 1 (2026): Volume 2 No 1
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v2i1.30

Abstract

This study aims to analyze the effect of using the ZOOM application at the University of Informatics and Business Indonesia (UNIBI) using the Technology Acceptance Model (TAM) approach, which is often used by some researchers to examine user acceptance of technology. This research is quantitative using descriptive method. The data analysis technique was carried out using SEM (Structural Equation Model) with AMOS (Analysis of Moment Structure) software. The population in this study were UNIBI students. Determination of the sample is carried out by proportional sampling, which is a proportional sampling method based on sub-populations. The results of this study prove that only 4 hypotheses are accepted from a total of 6 hypotheses proposed. The following is the percentage of the influence of each variable: a) Perceived Ease of Use (PEOU) is 28%, b) Perceived Usefulness (PU) is 74%, c) Attitude Toward Using (ATU) is 57%, d) Behavioral Intention to Use (BITU) is 65%, and e) Actual system usage (AU) is 75%. This proves that the use of the ZOOM application as an online learning medium cannot be fully explained by the Technology Acceptance Model.
Enhancing Breast Cancer Diagnosis with Ensemble Learning: Leveraging Convolutional Neural Networks and Pretrained Models through Averaged Predictions Elia Setiana; Reni Nursyanti; Nur Alamsyah; Nayla Nurul Azkiya
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 4 (2026): BIMA May 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i4.26

Abstract

Breast cancer continues to be a serious health issue at the global level, and early detection can significantly improve patient outcomes. This research uses imaging techniques to examine the design of an improved classification model in breast cancer detection. This project uses deep learning approaches through Convolutional Neural Networks (CNN) and ensemble learning models to potentially improve classification accuracy. To further enhance performance while controlling for class imbalance and overfitting, we leverage several models, such as ResNet18 and VGG16, with data augmentation and pre-trained models. Our methods included standard preprocessing of medical images, splitting datasets into training, testing and validation sets, and training each model with the Adam optimizer. Performance measurement included accuracy, precision, recall, and F1 score metrics. Overall, prototypes recently created displayed clear advantages based on finding results achieved through an ensemble method, which demonstrated improved model stability and reduced significant misclassification errors, and model accuracy reached 0.96. This research is crucial while developing strong deep-learning models to aid in breast cancer detection, ultimately allowing us to set a base for developing better diagnostic inference systems in medical-based applications. These systems may help improve early detection and overall patient care.
A stacking ensemble model with SMOTE for improved imbalanced classification on credit data Nur Alamsyah; Budiman Budiman; Titan Parama Yoga; R. Yadi Rakhman Alamsyah
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 3: June 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i3.25921

Abstract

This research is based on a significant problem in credit risk analysis in the banking sector caused by class imbalance. We face the problem of the model’s inability to accurately identify risks in the ‘‘Charged Off’’ class. As a solution, we propose a stacked ensemble approach that utilizes synthetic minority over-sampling technique (SMOTE) to balance the class distribution. Experiments were conducted by applying SMOTE to the training data before training the credit model using gradient boosting (XGBoost) and random forest (RF) algorithms in a single ensemble. The results show significant improvements in precision, recall, and F1-score after applying SMOTE on the unbalanced classes. The updated model achieved a striking accuracy rate of 0,97 on resampled training data. This re-search clearly identifies the problem of class imbalance as a major challenge in credit risk analysis. The application of SMOTE in a stacked ensemble was found to be effective in improving model performance, making a valuable contribution to the development of more reliable credit models for better risk management and revenue generation in financial institutions.
ISOLATION FOREST PARAMETER TUNING FOR MOBILE APP ANOMALY DETECTION BASED ON PERMISSION REQUESTS Valencia Claudia Jennifer Kaunang; Nur Alamsyah; Reni Nursyanti; Budiman Budiman; Venia R Danestiara; Elia Setiana
Jurnal Pilar Nusa Mandiri Vol. 21 No. 2 (2025): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v21i2.6647

Abstract

Ensuring mobile app security needs the capability to detect apps that request excessive or inappropriate permissions. This research proposes an anomaly detection approach using Isolation Forest, enhanced through hyperparameter tuning, to identify suspect apps based on permission request patterns. The dataset is processed into binary features, followed by exploratory data analysis (EDA) to examine the distribution and highlight sensitive permissions. The Isolation Forest model is then optimized by tuning parameters such as contamination level, number of estimators, and sample size. The fine-tuned model achieved a more accurate separation between normal and anomaly applications, detecting 10 anomalies out of 200 applications, with anomaly applications averaging 125.10 permits compared to 42.76 in normal applications. These anomalies often requested permissions related to network, storage, contacts and microphone, indicating potential privacy risks. The results show that parameter tuning improves the detection performance of Isolation Forest, providing a practical solution for mobile security monitoring. After tuning, the number of false positives decreased by 50%, and the model successfully reduced detected anomalies from 20 to 10, increasing the precision of anomaly detection from 70% to 90%. Future work could include improving feature selection and integration into real-time detection systems. 
Fine-Tuned Autoencoder Neural Network for Anomaly Detection in Accounting Transactions Nur Alamsyah; Budiman Budiman; Hani Fitria Rahmani; Wala Erpurini
Paradigma - Jurnal Komputer dan Informatika Vol. 27 No. 2 (2025): September 2025 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v27i2.8697

Abstract

Anomaly detection in accounting transactions plays a crucial role in identifying irregularities that may signal fraud, errors, or unusual financial behavior. Traditional rule-based and statistical methods often struggle to detect complex and hidden patterns in large-scale financial datasets. This paper presents a fine-tuned Autoencoder Neural Network for detecting anomalies in structured accounting records. The model processes feature such as date, account type, debit, credit, transaction category, and payment method. Preprocessing includes handling missing values, encoding categorical data, and extracting temporal features. The Autoencoder architecture was optimized using multiple hidden layers and dropout regularization to prevent overfitting. Reconstruction errors were used to determine anomaly scores, with a dynamic threshold set at the 98th percentile. Experimental results show that the model accurately distinguishes normal and anomalous transactions, identifying 2,000 outliers from a total of 100,000 records. Additional analysis indicates that anomalies often occur during weekends or holidays and involve unusual payment methods. These findings demonstrate the potential of the fine-tuned Autoencoder as a scalable and intelligent anomaly detection framework to support auditors and financial analysts in proactive fraud prevention.
A Progressive Training Framework for Robust YOLOv11-Based Vehicle Detection Across Domain Shifts in Real-World CCTV Environments Aditya Gunaldhi; Budiman; Chairul Habibi; Nur Alamsyah
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 5 (2026): BIMA July 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i5.27

Abstract

The performance of deep learning-based vehicle detection models often deteriorates when applied to real-world CCTV environments due to domain shift caused by variations in lighting, occlusion, glare, and changes in camera viewpoint. This study aims to develop a YOLOv11-based progressive training framework to improve the model’s generalization ability under heterogeneous operational conditions. The proposed method consists of four stages: base training, fine-tuning, and a supervised progressive domain adaptation strategy implemented through sequential fine-tuning on labeled target-domain CCTV images before OpenVINO-based inference optimization. The model is trained using a source dataset and adapted to a target dataset representing real-world CCTV conditions. Evaluation was conducted using Precision, Recall, mAP@50, mAP@50–95, loss curve analysis, per-vehicle-class evaluation, visual testing on CCTV video, as well as latency and throughput measurements. The results show that base training achieved an mAP@50 of 0.919 and built a robust feature representation, while fine-tuning maintained performance stability with an mAP@50 of 0.915. Although domain adaptation reduced mAP@50 to 0.811 due to domain shift, the model demonstrated improved generalization capabilities and maintained more consistent detection under low-light conditions, glare, occlusion, and heavy traffic. OpenVINO INT8 optimization increased inference speed from 4.86 FPS to 9.08 FPS with minimal accuracy loss. These findings demonstrate that the progressive training framework effectively bridges differences in data distribution while producing a vehicle detection model that is more robust, efficient, and suitable for deployment in real-time CCTV-based traffic monitoring systems.
Optimization of Human Development Index in Indonesia Using Decision Tree C4.5, Support Vector Machine Algorithm, K-Nearest Neighbors, Naïve Bayes, and Extreme Gradient Boosting Ilham Ramadhan; Budiman Budiman; Nur Alamsyah
Jurnal Informatika Vol. 12 No. 1 (2025): April
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/informatika.v12i1.12253

Abstract

The Human Development Index (HDI) is a measure of human development achievement based on quality of life indicators such as Life Expectancy (LE), Mean Years of Schooling (MYS), Expected Years of Schooling (EYS), and Adjusted Per Capita Expenditure (AECE). HDI describes how people access development outcomes through income, health, and education. The determination of development programs implemented by local governments must be based on district/city priorities based on their HDI categories and must be right on target. Therefore, a decision system is needed that can accurately determine the HDI category in each district/city in Indonesia, using machine learning models such as Decision Tree C4.5, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes, and Extreme Gradient Boosting (XGBoost). Machine learning models will be used to classify the HDI in Indonesia in 2022 and determine the performance of the most optimal model in classification. This research uses the CRISP-DM method with secondary data from the Central Statistics Agency (BPS) as much as 548 data. The analysis results show that the Decision Tree C4.5 models have an accuracy of 0.86, KNN of 0.95, Naïve Bayes of 0.90, XGBoost of 0.93, and SVM provides the most optimal results with an accuracy of 0.97. UHH, RLS, and HLS variables significantly influence changes in HDI values in Indonesian regions based on the Chi-square, Pearson Correlation, Spearman, and Kendal test results. 
Co-Authors Acep Hendra Aditya Gunaldhi Akbar, Imannudin Alif Januantara Prima Arafat Febriandirza Artika Arista Budiman Chairul Habibi Esa Prakasa Fahreja Ramadhan Gunthur Bayu Wibisono Hani Fitria Rahmani Henki Bayu Seta Ihsan AlFauzi Ilham Ramadhan Nayla Nurul Azkiya Niqotaini, Zatin Nursyanti, Reni R. Yadi Rakhman Alamsyah Rezza Novian Noor Rochmat Setiana, Elia Tiara Permata Hati Titan Parama Yoga Titan Parama Yoga Valencia Claudia Jennifer Kaunang Venia R Danestiara Wala Erpurini