Claim Missing Document
Check
Articles

Found 39 Documents
Search

Analisis Tren Dan Topik Populer Tugas Akhir Mahasiswa Teknik Informatika Menggunakan Bertopic Dan Lda Studi Kasus: Universitas Mercu Buana Suharyadi; Sajarwo Anggai; Abu Khalid Rivai
Jurnal Informatika dan Komputer Vol 16 No 1 (2026): April
Publisher : Sekolah Tinggi Ilmu Komputer PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55794/jikom.v16i1.349

Abstract

In recent years, there has been little systematic mapping of trends and popular topics in student final projects, particularly in the field of Information Technology at Mercu Buana University. This is important because identifying trends can provide insight into the direction of scientific development and student research interests. This study aims to analyze the dominant trends and topics of the past few years in the final projects of Information Technology students at Mercu Buana University. The research object consists of a collection of titles and abstracts of student final projects from 2019 to 2024, totaling 1677 datasets. The data was collected through internal faculty documentation and compiled into a text-based dataset. The analysis process included the stages of preparation, text pre-processing, feature extraction, and the application of two topic modeling methods with BERTopic and LDA. BERTopic uses transformer-based representation and semantic clustering, while LDA utilizes a probabilistic distribution approach. The evaluation was conducted by comparing topic coherence and prediction accuracy to assess the quality and relevance of the results produced by each method. The results showed that there were 15 main topics. Model evaluation was conducted using a coherence score of 0.4 for LDA with an accuracy rate of 100%, while BERTopic had a coherence score of 0.39 with an accuracy rate of 86.01%.
Performance Evaluation of ARIMA, LSTM, and Hybrid ARIMA–LSTM Models for Daily Solar Energy Prediction in Bali Aslimah; Sajarwo Anggai; Tukiyat
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3283

Abstract

Solar energy is one of the most promising renewable energy sources in Indonesia, particularly in Bali, which has relatively high solar irradiance throughout the year. However, daily variability in solar radiation caused by weather conditions and atmospheric factors leads to fluctuations in solar energy production, making accurate forecasting essential for effective energy planning. This study aims to evaluate the performance of the Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and hybrid ARIMA–LSTM models in forecasting daily solar energy at the Jembrana Climatological Station, Bali. The dataset consists of 10-minute solar radiation observations obtained from an Automatic Weather Station (AWS) for the period January 2023 to September 2025, which were aggregated into daily solar energy values expressed in kWh/m². Data preprocessing included missing value handling, outlier correction, normalization, and an 80:20 split between training and testing datasets. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results show that the hybrid ARIMA–LSTM model achieved the best performance, with an RMSE of 0.960 kWh/m², MAE of 0.771 kWh/m², and MAPE of 22.245%, outperforming both the ARIMA and LSTM models. These findings indicate that the hybrid approach is more effective in capturing both linear and nonlinear characteristics of daily solar energy time series.
Comparison of Faster R-CNN and YOLO v12 on Passport Text Extraction Based on Optical Character Recognition Masniari Samosir; Sajarwo Anggai; Taswanda Taryo
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3307

Abstract

Current developments in information technology are driving the need for digitalization of official identity documents, including passports, to improve service efficiency and reduce reliance on manual processes. The digitalization of official identity documents such as passports still faces efficiency and accuracy challenges due to manual data entry processes. This study aims to compare the performance of Faster R-CNN and YOLO v12 in an automatic text extraction system based on Optical Character Recognition (OCR). The research employed an experimental method with a comparative approach using 31 preprocessed passport images. YOLO v12 was integrated with EasyOCR, while Faster R-CNN was combined with a PyTorch-based OCR module. The evaluation metrics included mAP, Character Accuracy Rate (CAR), Word Error Rate (WER), F1-score, and inference time. The results indicate that YOLO v12 outperforms Faster R-CNN in object detection, achieving an mAP@50 of 95.0% and mAP@50–95 of 90.0%, compared to 93.0% and 89.0%, respectively. In terms of text extraction accuracy, Faster R-CNN achieved a CAR of 50.01% and an F1-score of 55.75%, slightly higher than YOLO v12 with a CAR of 47.72% and an F1-score of 53.84%. However, YOLO v12 produced a lower WER and faster inference time of 2.4202 seconds (0.45 FPS). The findings suggest that YOLO v12 excels in efficiency and detection performance, while Faster R-CNN performs better in specific text extraction accuracy.
Application of Latent Dirichlet Allocation (LDA) and BERTopic Algorithms for Headline and Topic Analysis of Palestine–Israel Conflict News in Indonesian Online Media Raden Gumilar Riyansyah; Sajarwo Anggai; Tukiyat Tukiyat
Jurnal Impresi Indonesia Vol. 5 No. 1 (2026): Jurnal Impresi Indonesia
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/jii.v5i1.7395

Abstract

The news coverage of the Palestine–Israel conflict has become one of the most dominant international issues in Indonesian online media, necessitating a systematic analysis to understand the topic structures formed from the intensity and variation of the narratives presented. The main challenges arise from the high volume of text, differences in writing styles across media outlets, and the diversity of terminology, all of which hinder consistent and manual topic identification. To address these challenges, this study proposes a combined and comparative approach using two topic modeling algorithms, LDA and BERTopic, to obtain a more accurate, structured, and interpretable topic mapping. The modeling process begins with data collection through web scraping, followed by a preprocessing stage consisting of cleansing, case folding, tokenization, normalization, filtering, and stemming. The LDA model is developed by determining the optimal number of topics based on Coherence Score and Perplexity, whereas BERTopic leverages transformer-based embeddings, UMAP dimension reduction, and HDBSCAN clustering. Evaluation is conducted using Coherence Score, Perplexity, Silhouette Score, and visualizations such as Intertopic Distance Maps and Word Clouds to assess topic quality. The results show that BERTopic achieves the highest coherence score of 0.99 and lower perplexity, producing semantically cohesive topics. Meanwhile, LDA remains advantageous in providing a stable and measurable probabilistic structure. The combination of both models yields a mapping of five main topics: attacks in Gaza, Indonesian diplomacy, international support, humanitarian issues, and global political dynamics. These findings demonstrate that integrating LDA and BERTopic enhances the quality of topic analysis on complex issues
Analysis of Multilayer Perceptron, Long Short-Term Memory, and Temporal Convolutional Network Modeling Algorithms for Rainfall Prediction at Soekarno–Hatta Airport Eko Widyantoro; Eko Widyantoro HS; Sajarwo Anggai; Sudarno Wiharjo
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 2 (2026): AUGUST 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i1.7332

Abstract

Tropical atmospheric variability poses challenges for daily precipitation prediction at Soekarno–Hatta International Airport, with implications for aviation safety. This study aimed to compare the performance of three deep learning architectures—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Temporal Convolutional Network (TCN)—for daily precipitation prediction using meteorological observations from the BMKG Soekarno–Hatta Station for the period 2019–2025. A quantitative experimental approach was employed using a time-series split scheme to preserve the temporal structure of the data and reduce the risk of data leakage. Air temperature, relative humidity, atmospheric pressure, and wind speed were used as input variables, while precipitation was used as the target variable. Model performance was evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²). The results showed that TCN achieved the best predictive performance, with an RMSE of 10.32 mm, MAE of 7.15 mm, MAPE of 18.27%, and R² of 0.87, followed by LSTM and MLP. Permutation-based sensitivity analysis identified relative humidity and air temperature as the two most influential variables for model prediction. Overall, TCN demonstrated stronger performance in capturing temporal patterns in daily precipitation than LSTM and MLP and showed potential for future application in operational precipitation forecasting and extreme-weather early warning systems at airport environments.
Face Image Authenticity Detection for ASN Attendance Using CNN MobileNetV2: A Case Study of Tangerang City Government Suryadi Suryadi; Sajarwo Anggai; Sudarno Wiharjo
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 2 (2026): AUGUST 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i2.7459

Abstract

Face recognition-based attendance systems can improve the convenience of attendance processes, but they remain vulnerable to presentation attacks, in which facial images displayed on another device are used to simulate a user's physical presence. At the Tangerang City Government, the Tangerang AYO application is used as the main attendance channel for civil servants (ASN) across government agencies (OPD), with attendance data linked to the calculation of Additional Employee Income (TPP). This study develops a face liveness detection model to distinguish between real and fake facial images using a CNN MobileNetV2 architecture with a transfer learning and two-phase fine-tuning approach. The dataset was constructed from actual ASN attendance data and consisted of real and fake images representing facial displays through a secondary device. The model was evaluated using a confusion matrix, accuracy, precision, recall, specificity, F1-score, ROC curve, and AUC. On the testing data (n=301), the model achieved an accuracy of 97.34%, precision of 96.13%, recall of 98.68%, specificity of 96.00%, F1-score of 97.39%, and AUC of 0.9934 at a threshold of 0.5. Grad-CAM analysis showed that the model produced different activation patterns between real and fake images, including contextual visual information in real images and screen-surface characteristics in fake images. A FastAPI-based REST API prototype achieved an average response time of 306.48 ms under warm conditions without a dedicated GPU, indicating the potential feasibility of the model as an additional verification layer for an ASN attendance system.
Comparative Analysis of MLP, BiLSTM and GRU Models for Maximum Wind Speed Prediction in Bogor Any Widyawati; Sajarwo Anggai; Tukiyat
Bulletin of Network Engineer and Informatics Vol. 4 No. 2 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) October 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/04wtn645

Abstract

Maximum wind speed is an important indicator for assessing wind energy potential; however, it is dynamic, nonlinear, and affected by interactions among meteorological parameters. This study compares Multi-Layer Perceptron (MLP), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU) models for maximum wind speed prediction in Bogor. The dataset comprises 3,653 daily observations from the BMKG Citeko Meteorological Station during 2011–2020, including minimum, maximum, and average temperature, relative humidity, rainfall, sunshine duration, prevailing wind direction, and average wind speed. Preprocessing involved data cleaning, missing-value imputation, Min-Max Scaling, and chronological splitting into training, validation, and testing subsets. The three models were trained using equivalent configurations and evaluated using MAE, RMSE, MAPE, and R². MLP achieved the lowest MAE of 0.0796 and MAPE of 33.11%, whereas BiLSTM and GRU achieved the lowest RMSE of 0.1025 and the highest R² of 0.2215. GRU was selected as the preferred model because it matched BiLSTM performance with a simpler architecture and lower computational complexity. Nevertheless, the limited R² indicates that additional atmospheric predictors, higher temporal resolution, and further model optimization are required to improve prediction of extreme wind events
Autoformer-Based Significant Wave Height Forecasting with Mutual Information Feature Selection in the Northern Waters of Central Java M.Soleh Ismail; Sajarwo Anggai; Tukiyat
Bulletin of Network Engineer and Informatics Vol. 4 No. 2 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) October 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/q83qhr62

Abstract

Accurate Significant Wave Height (SWH) forecasting is essential for maritime safety in the northern waters of Central Java, where shallow Java Sea conditions and monsoonal winds generate nonlinear and seasonal wave variability. This study evaluates Autoformer for SWH forecasting and examines the effect of Mutual Information (MI)-based multivariate feature selection on predictive performance. The 2025 BMKG Ocean Forecast System dataset contains 2,913 tri-hourly time-series samples comprising wind speed, wind direction, wave period, sea surface temperature, and SWH. Data were partitioned chronologically into 80% training and 20% testing sets, using a sequence length of 96 steps and a prediction horizon of 24 steps. MI ranked wind speed as the most informative exogenous variable (0.7304), followed by sea surface temperature (0.6101), wind direction (0.3946), and wave period (0.1585). The full multivariate configuration achieved the strongest performance, with MAE of 0.0931 m, RMSE of 0.1193 m, MAPE of 20.30%, and R² of 0.6929. Excluding wave period increased RMSE to 0.1464 m and reduced R² to 0.5376, demonstrating that a modest individual MI score can coexist with valuable temporal complementarity. For maritime operations and coastal engineering, the full-feature configuration offers a promising basis for short-range sea-state guidance supporting route planning, port scheduling, and wave-sensitive coastal decisions.
Hybrid CNN-BiLSTM-Attention Modeling for Air Temperature Prediction Using LOF-iForest-RFE Multi-Stage Preprocessing on Soekarno-Hatta Meteorological Station AWS Data (2021–2025) Nur Fuat, Muhamad; Anggai, Sajarwo; Handayani, Murni
Journal of Applied Informatics and Computing Vol. 10 No. 5 (2026): October 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i5.13785

Abstract

Air temperature is a critical meteorological parameter that dynamically affects density altitude and Maximum Take-Off Weight (MTOW) calculations in aviation operations. Although the 10-minute resolution Automatic Weather Station (AWS) data at Soekarno-Hatta International Airport effectively captures micrometeorological fluctuations, it is chaotic and prone to anomalies, often causing prediction failures in conventional models. This study aims to propose an artificial intelligence-based short-term framework to predict air temperature for the next 10-minute horizon by integrating multi-level preprocessing with a hybrid CNN-BiLSTM-AM (Convolutional Neural Network, Bidirectional Long Short-Term Memory, Attention Mechanism) architecture. Utilizing a Data-Centric AI approach on observational data from 2021–2025, the methodology begins with local and global anomaly purification via Local Outlier Factor (LOF) and Isolation Forest (iForest) algorithms. Multicollinearity is then mitigated through hybrid feature selection using Pearson Correlation and Recursive Feature Elimination (RFE). In the modeling phase, the 1D-CNN layer extracts spatial correlations among variables, the BiLSTM evaluates bidirectional temporal dependencies, and the attention mechanism adaptively distributes probability weights to prevent lag response during extreme weather oscillations. The findings demonstrate that data purification is strictly necessary to avoid model generalization failures, and RFE successfully isolated the four most optimal physical predictors: maximum temperature, relative humidity, air pressure, and solar radiation. Comparatively, the proposed CNN-BiLSTM-AM model proved to be the most superior, achieving the highest accuracy with an RMSE of 0.8151 °C, MAE of 0.6329 °C, and R² of 0.9106. The addition of attention and convolution mechanisms was shown to reduce the root mean square error (RMSE) by 16.44% and the mean absolute error (MAE) by 13.64% compared to the pure BiLSTM baseline model. In conclusion, achieving an extreme error deviation (RMSE) consistently below the 1.0 °C operational tolerance confirms that this architecture is highly feasible, robust, and has strong potential as a highly reliable meteorological reference to support Density Altitude and MTOW estimations in equatorial climates.