cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agus Tedyyana
Contact Email
agustedyyana@polbeng.ac.id
Phone
+6285289866666
Journal Mail Official
jurnaoinformatika@polbeng.ac.id
Editorial Address
Jl. Bathin alam, Sungai Alam Bengkalis-Riau 28711
Location
Kab. bengkalis,
Riau
INDONESIA
INOVTEK Polbeng - Seri Informatika
Published by Politeknik Negeri Bengkalis
ISSN : 25279866     EISSN : -     DOI : https://doi.org/10.35314
Core Subject : Science,
Computer Science & IT
The Journal of Innovation and Technology (INOVTEK Polbeng—Seri Informatika) is a distinguished publication hosted by the State Polytechnic of Bengkalis. Dedicated to advancing the field of informatics, this scientific research journal serves as a vital platform for academics, researchers, and practitioners to disseminate their insightful findings and theoretical developments. Scope and Focus: INOVTEK Polbeng - Seri Informatika focuses on a broad spectrum of topics within informatics, including but not limited to Web and Mobile Computing, Image Processing, Machine Learning, Artificial Intelligence (AI), Intelligent Systems, Information Systems, Databases, Decision Support Systems (DSS), IT Project Management, Geographic Information Systems, Information Technology, Computer Networks and Security, and Wireless Sensor Networks. By covering such a wide range of subjects, the journal ensures its relevance to a diverse readership interested in both the practical and theoretical aspects of informatics.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 269 Documents
 23   24   25   26   27 
Banana Leaf Disease Identification Using SqueezeNet Architecture with Convolutional Block Attention Module Wijaya, Daniel; Alamsyah, Derry
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/ktx6vp08

Abstract

Banana leaf diseases significantly reduce crop productivity and quality, while conventional visual inspection methods are often subjective, time-consuming, and inefficient for large-scale plantations. This study proposes an automated banana leaf disease identification approach using a lightweight Convolutional Neural Network (CNN) based on the SqueezeNet architecture integrated with the Convolutional Block Attention Module (CBAM). The dataset consists of four classes Cordana, Healthy, Pestalotiopsis, and Sigatoka with image augmentation applied to increase data variability. Several experimental scenarios were conducted to evaluate the impact of data augmentation and CBAM integration on model performance. The models were evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results show that SqueezeNet combined with CBAM achieved superior performance compared to the baseline SqueezeNet model, particularly in non-augmented conditions, with an accuracy of 93.75% while maintaining a relatively small number of parameters. Although data augmentation alone led to performance degradation, the inclusion of CBAM mitigated this effect by enhancing spatial and channel-wise feature representation. These findings indicate that the proposed SqueezeNet–CBAM model offers an effective and computationally efficient solution for banana leaf disease identification, with strong potential for real-world agricultural applications.
Business Process Reengineering of Child Case Reporting and Approval Integrated With Weighted Triage Harsoyo, Farras Sandy; Suharso, Wildan
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/7hfnjd34

Abstract

This study aims to analyze and redesign the child case reporting and approval process at the Social Service Office of Batu City, which is still dominated by manual procedures. The Business Process Reengineering (BPR) approach is modeled using Business Process Model and Notation (BPMN) to identify process bottlenecks and formulate information technology–based solutions. Data were collected through field observations during an internship program, a review of standard operating procedures, and short interviews with officers, then validated through the development of a web-based prototype consisting of a reporting portal and an internal dashboard. The redesigned process includes the implementation of digital ticketing and queue status, early validation and duplicate checking, requests for data correction, weighted triage (P1–P3), as well as electronic approval and automatic issuance of assignment letters. Evaluation results show an increase in throughput efficiency from 56.41% and 40.74% to 86.96% and 89.29%, along with a reduction in process time from 78 to 23 minutes and from 108 to 28 minutes. This redesign accelerates service delivery, organizes queues, and improves traceability without changing existing SOP provisions.
Enhancing Sleep Disorder Prediction Through Feature Engineering and Stacking Ensemble Learning on Imbalanced Lifestyle Data Julianto, Richy; Prasetiyo, Budi
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/mzd3t096

Abstract

Undiagnosed sleep disorders pose significant cardiovascular risks, necessitating accessible screening tools beyond invasive clinical procedures. This study aims to develop a robust diagnostic framework using the Sleep Health and Lifestyle Dataset. To address class imbalance and enhance predictive sensitivity, a Stacking Ensemble architecture integrating Random Forest, Gradient Boosting, CatBoost, and XGBoost is implemented, augmented by Pulse Pressure feature engineering and the Synthetic Minority Over-sampling Technique (SMOTE). The proposed model achieved a superior accuracy of 98.61% and a recall of 99.24%, significantly outperforming single classifiers. Feature analysis further identified heart rate and sleep duration as critical physiological determinants. These findings conclude that combining feature engineering with optimized ensemble learning offers a highly accurate diagnostic approach with rapid training convergence, providing a scalable pathway for early sleep disorder detection.
Performance Analysis of YOLOv11 Integrated with Lightweight Backbones (MobileNetV2, GhostNet, ShuffleNet V2) for Cigarette Detection Andreas, Kevin; Yohannes; Meiriyama
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/0gjq1j10

Abstract

Cigarette object detection in indoor environments plays a vital role for enforcing smoke-free zone regulations and protecting public health from secondhand smoke exposure. This study investigates the performance of YOLOv11n architecture integrated with three lightweight backbone modifications (MobileNetV2, GhostNet, and ShuffleNet V2) for real-time cigarette detection with the aim of achieving efficiency suitable for potential deployment on resource-constrained edge devices. Comprehensive experiments were conducted using the Cigar Detection Dataset comprising 5,333 images, augmented to 8,890 samples through horizontal flipping and brightness adjustment techniques. All models were trained for 100 epochs using the SGD optimizer on an NVIDIA Tesla T4 GPU. The evaluation metrics included detection accuracy (mAP@0.5, mAP@0.5:0.95, precision, recall, and F1-score) and computational efficiency (parameters, model size, GFLOPs, and FPS). Experimental results demonstrate that the pretrained YOLOv11n baseline achieves the highest detection accuracy with mAP@0.5 of 0.8072 and precision of 0.8688. Among lightweight backbone variants, ShuffleNet V2 (0.5x) provides the most compact solution with only 2.28M parameters and a 4.73 MB model size, while ShuffleNet V2 (0.75x) offers an optimal balance between accuracy (mAP@0.5: 0.7430) and efficiency with only 0.95% accuracy degradation compared to the 1.0x variant. These findings provide practical guidance for selecting appropriate model configurations based on deployment constraints in smoke-free area monitoring systems.
Implementation of MobileNetV4 and Efficient Channel Attention in Anti-Spoofing Face Attack Detection Rayvin Suhartoyo; Yoannita
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/kth2nc32

Abstract

Face Anti-Spoofing (FAS) is essential for preventing presentation attacks in biometric systems, yet deploying robust models on mobile devices remains a challenge due to computational constraints. This study proposes a lightweight FAS model integrating the MobileNetV4 architecture with an Efficient Channel Attention (ECA) module. The ECA mechanism is designed to enhance the network’s ability to detect subtle spoofing artifacts, such as texture anomalies, with negligible computational overhead. The model was evaluated using a dataset of 6,400 images, comprising both bona fide and attack presentations. Experimental results demonstrate robust performance, achieving an overall accuracy of 99.69%, 100% precision, and an Average Classification Error Rate (ACER) of 0.25%. Crucially, the model yielded a Bona Fide Presentation Classification Error Rate (BPCER) of 0.00%, ensuring that no genuine users are falsely rejected. While the baseline architecture provided a strong benchmark, the proposed attention-enhanced framework offers a viable trade-off between security and usability, providing a computationally efficient solution suitable for real-time mobile authentication.
Implementation of Retrieval-Augmented Generation  Method on Large Language Model for Development of Campus Service and Information Chatbot Muhammad Dzaki Salman; Rahmaddeni; Torkis Nasution; Susanti
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/3y9hy151

Abstract

Large language models have the potential to improve the quality of information services in higher education environments through responsive and natural interactions. However, LLMs are prone to generating answers that are not supported by valid knowledge sources due to knowledge cut-off limitations. This study implements Retrieval-Augmented Generation on LLMs to build an information service chatbot for the Indonesian University of Science and Technology (USTI). RAG is built using a hybrid retrieval mechanism that combines dense retrieval and sparse retrieval (BM25) through reciprocal rank fusion and is equipped with cross-encoder reranking. The knowledge base is compiled from official and public documents obtained through the USTI website. The evaluation was conducted using 13 test queries by comparing several configurations to analyze the contribution of each component. The evaluation results show that the hybrid retrieval configuration produces the best retrieval performance with Precision@3 of 71.7%, Recall@3 of 87.5%, and NDCG@3 of 96.3%. In addition, the application of RAG improved the quality of answers compared to LLM without retrieval, as shown by an increase in BERTScore-F1 from 84.8% to 89.4% and a faithfulness score of 88.8%. These findings indicate that RAG integration improves the relevance of LLM answers to source documents, with the hybrid configuration providing an optimal balance between retrieval quality and faithfulness.
A Comparative Analysis of Deep Learning Models for Stock Price Prediction Ayu Nandia Lestari, I Gusti; Deviana; Tubagus Mahendra Kusuma
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/aweyzn77

Abstract

Indonesian equities exhibit high volatility and non-stationary dynamics, making consistent price forecasting difficult under realistic deployment settings. This study presents a comparative benchmark of Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) for one-step-ahead (t+1) stock price prediction using Walk-Forward Validation (WFV) to preserve temporal causality and avoid optimistic single-split estimates. Historical data are retrieved from Yahoo Finance and modeled in a multivariate OHLCV setting (Open, High, Low, Close, Volume). After missing-value removal, feature standardization, and Min–Max scaling, the series is converted to supervised samples via a sliding window with lookback = 30 trading days; evaluation is focused on the Close variable. Model performance is assessed using MAE, RMSE, and R², including inter-fold variability to quantify stability across market regimes. Across five Indonesian tickers (AGRO, ADES, ADMF, AALI, ADHI), LSTM consistently outperforms Bi-LSTM (5/5 tickers) in both MAE and RMSE, indicating that the added bidirectional complexity does not translate into improved out-of-sample forecasting under WFV. The best error performance is achieved by LSTM on AGRO (MAE = 26.99, RMSE = 32.72), while the least-negative goodness-of-fit is observed on LSTM AALI (R² = -0.63), suggesting that both deep models may still underperform naïve baselines in several folds. Overall, the results support LSTM as a more stable and implementation-ready benchmark for Indonesian stock forecasting under time-aware evaluation, while highlighting the need for explicit baseline comparisons and stronger feature/target designs to improve out-of-sample generalization.
Alzheimer's Disease Classification Using the Tabnet Model Enhanced by Hyperparameter Optimization Triyadi, M Bagus; Sri Kusuma Aditya, Christian
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/yb05hg15

Abstract

Alzheimer's disease is a progressive neurodegenerative disorder that leads to a gradual decline in cognitive function and remains challenging to diagnose at an early stage, as clinical symptoms often emerge after substantial brain damage has occurred. Therefore, accurate and efficient predictive models based on clinical data are essential to support early detection. Recent advances in deep learning for tabular data, particularly the TabNet model, enable adaptive feature selection through attention mechanisms while preserving interpretability. This study applies TabNet for Alzheimer’s disease classification using clinical tabular data and enhances its performance through hyperparameter optimization employing grid search, random search, and Bayesian optimization. Model evaluation was conducted using accuracy, area under the curve (AUC), confusion matrix analysis, and execution time. Experimental results show that random search achieved the highest classification accuracy of 90.53%, whereas Bayesian optimization obtained the highest AUC of 94.82%, indicating superior discriminative capability. These results demonstrate that integrating TabNet with appropriate hyperparameter optimization strategies provides a competitive, efficient, and interpretable approach for Alzheimer’s disease classification, supporting its potential application in data-driven clinical decision support systems.
A PSO-Optimized Stacking Ensemble with Hybrid SMOTE-NC and Tomek Links for Bid-Based Winning Prediction in Procurement Projects Handoko, Kokoh; Purnomo, Agus; Mulyati, Erna
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/dft7w786

Abstract

This research aims to establish a classification model for the prediction of procurement winning outcomes based on bid value and owner cost estimation data. The main challenge in procurement analysis lies in severe class imbalance and complex non-linear relationships among pricing and procurement attributes. The research object utilizes procurement tender data from PT Pos Indonesia, including project owner, owner cost estimation, bid value, and procurement method. The proposed approach integrates hybrid SMOTE and Tomek links for class balancing, regulation-driven feature engineering, and a stacking ensemble model optimized using particle swarm optimization. The stacking framework combines Random Forest, Extra Trees, and Gradient Boosting as base learners. The experimental evaluation demonstrates that the proposed approach delivers the strongest performance, achieving an AUC of 0.92, an accuracy of 0.89, and an F1-Macro of 0.81, thereby surpassing all individual classifiers and homogeneous ensemble methods considered in this study. This study concludes that the hybrid optimization-based ensemble approach is effective for improving procurement winning prediction accuracy and provides a reliable decision-support tool for data-driven and regulation-compliant procurement processes.
Applying Clustering Techniques for Customer Segmentation Based on Shipping Behavior, Cost, and Satisfaction in Logistics Services Sunara, Jaka; Purnomo, Agus; Maniah
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/h62gy548

Abstract

In modern logistics operations, behavioral data-based customer segmentation plays a crucial role in optimizing service delivery and achieving competitive differentiation. This study proposes a clustering-based approach using K-Means, Agglomerative, and Gaussian Mixture to segment sender-level customer profiles in a logistics network based on shipping cost and delivery duration, while customer satisfaction is used for post-cluster profiling and interpretive analysis. A comprehensive preprocessing pipeline is implemented, including temporal feature engineering and sender-based statistical aggregation. Grid search is used for hyperparameter tuning, and clustering performance is evaluated using the Silhouette Score, Calinski-Harabasz Index, and Davies-Bouldin Index. The results indicate that K-Means with two clusters achieves the highest silhouette score (0.843), outperforming the aggregative and Gaussian mixture models. Principal Component Analysis (PCA) reveals clear separability between clusters labeled as Efficient Senders and Costly & Slow Senders. These findings provide actionable information for logistics service providers to improve pricing strategies, delivery efficiency, and customer satisfaction through intelligent segmentation.

Page 26 of 27 | Total Record : 269

 23   24   25   26   27 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 1 (2026): February Vol. 10 No. 3 (2025): November Vol. 10 No. 2 (2025): July Vol. 10 No. 1 (2025): March Vol. 9 No. 2 (2024): November