cover
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
ISSN : 25279866     EISSN : -     DOI : https://doi.org/10.35314
Core Subject : Science,
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.
Articles 42 Documents
Search results for , issue "Vol. 11 No. 1 (2026): February" : 42 Documents clear
Detection of Coffee Bean Defects in Speciality Coffee Association Standards using YOLOv12 Hocwin Hebert; 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: 10.35314/47yqwd13

Abstract

Coffee is a high-value plantation commodity with a significant role in the global economy. Coffee consumption, reaching more than two billion cups per day, continues to increase global demand for coffee beans. To ensure quality and consumer acceptance, green coffee bean quality evaluation must follow consistent international standards. However, inspection is still carried out manually, making it time-consuming and subjective. This study proposes coffee bean defect detection based on the Specialty Coffee Association (SCA) standard using YOLOv12. YOLOv12 addresses limitations of previous YOLO versions by integrating R-ELAN to improve training efficiency and reduce gradient loss, as well as Flash Attention to enhance focus on important regions in complex images. A total of 225 images were obtained through augmentation from 45 original samples captured using a smartphone camera under controlled indoor conditions, with each image representing 300 grams of Mandheling coffee beans. The dataset was divided into training (80%), validation (10%), and testing (10%). Eight experimental configurations were evaluated using variations in initial learning rate (0.001 and 0.0005), batch size (8 and 16), and epochs (100 and 150). The optimal configuration, an initial learning rate of 0.0005, a batch size of 16, and 150 epochs, achieved a precision of 87%, a recall of 85%, and an F1 score of 84%. These results indicate that the effectiveness of YOLOv12 in detecting coffee bean defects depends on proper hyperparameter tuning. The model performs well on visually prominent defects such as cherry pods but shows reduced performance on subtle defects including floaters, fungus damage, and slight insect damage.
Classification of Diabetic Retinopathy Using ShuffleNet V2 and Real-ESRGAN with CLAHE Image Enhancement Edison, Nicholas; Tinaliah
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/g1xj7p28

Abstract

Diabetic retinopathy (DR) is a microvascular complication of diabetes that can lead to blindness if not detected and treated early. Manual DR grading from fundus images is time-consuming and highly dependent on expert availability, motivating the need for automated and efficient decision-support systems. This study proposes a lightweight DR severity classification model using ShuffleNet V2 combined with a preprocessing pipeline consisting of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Real-ESRGAN-based super-resolution. Unlike prior works that mainly employ these enhancement techniques with deeper or computationally expensive networks, this study explicitly investigates their synergistic integration with ShuffleNet V2 to improve lesion visibility while preserving computational efficiency for resource-constrained environments. Experiments conducted on the APTOS 2019 dataset demonstrate that the proposed combination significantly improves classification performance, achieving a best accuracy of 90.70%, with balanced precision, recall, and F1-score when optimized using Adam. Comparative analysis with the SGD optimizer further reveals a trade-off between accuracy and inference speed. The results confirm that combining CLAHE and Real-ESRGAN with ShuffleNet V2 offers an effective and efficient solution for automated diabetic retinopathy grading, highlighting its suitability for large-scale screening and low-resource clinical deployment
Classification Of Ulos Fabric Motifs Using MobileNetV3-Small Architecture Sihombing, Mecha Bella Permata; Devella, Siska
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/d2sfn245

Abstract

Ulos fabric is an important cultural heritage of the Batak people in North Sumatra, characterized by diverse motifs and philosophical meanings that support social and ritual life. Public knowledge of Ulos motifs is declining due to lifestyle changes and limited use of digital technology for cultural education, so accurate image-based motif classification is needed for preservation and wider utilization. This study evaluates the performance of the lightweight MobileNetV3-Small architecture with a transfer learning approach for classifying Ulos motif images, positioning it as one of the earliest uses of MobileNetV3-Small for Ulos motif classification compared to previous Ulos studies that relied on heavier CNN or earlier MobileNet variants. The dataset consists of 906 images split into 80% training, 10% validation, and 10% testing, and the model is trained using the Adam optimizer with a batch size of 32 and learning rates of 0.001 and 0.0001. On the test data, the model achieves accuracies of 98.96% and 97.92%, with consistently high precision, recall, and F1-scores, demonstrating the effectiveness of MobileNetV3-Small for Ulos motif classification as a digital educational medium to support Batak cultural heritage preservation.
Performance Analysis of MobileNetV2 and GhostNetV2 in Classifying Cervical Cancer Images in the SIPaKMeD Dataset Shela; Siska Devella
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: 10.35314/62samp73

Abstract

Cervical cancer remains a significant global health burden, largely due to limited screening coverage and the reliance on manual cytological interpretation. The intrinsic complexity of cervical cell morphology and constraints in clinical resources necessitate automated classification systems that are both accurate and computationally efficient. This study aims to evaluate and compare the performance of two lightweight CNN architectures, MobileNetV2 and GhostNetV2, for cervical cell image classification using the SIPaKMeD dataset. The dataset comprises 4,049 cell images, which were preprocessed through normalization, augmentation, and partitioning into training, validation, and testing sets. Both models were implemented using transfer learning and trained under comparable hyperparameter settings with basic data augmentation. Model performance was assessed using confusion matrices and standard evaluation metrics, including accuracy, precision, recall, and F1-score. Experimental results demonstrate that MobileNetV2 achieved superior performance with an accuracy of 98.50%, outperforming GhostNetV2, which attained a maximum accuracy of 97.60%. The consistent performance across metrics indicates robust and balanced classification capability. These findings suggest that MobileNetV2 offers an optimal trade-off between accuracy and computational efficiency, making it a promising candidate for deployment in resource-constrained and edge-based cervical cancer screening systems. Nevertheless, further external validation and clinical evaluation are required prior to real-world implementation.
Classification of Herbal Plant Images Using Transfer Learning EfficientNetV2-B3 Ambarwati, Rizki; Devella, Siska
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/fz4jy549

Abstract

Herbal plants are natural resources that have high economic and health value, but the identification process is still done manually, making it prone to errors due to morphological similarities between species. This study aims to develop a leaf image classification model for herbal plants using a Convolutional Neural Network (CNN) with the EfficientNetV2-B3 transfer learning approach and AdamW optimizer. The dataset used is the Indonesian Herb Leaf Dataset 3500, which consists of 3,500 leaf images from 10 types of Indonesian herbal plants, namely Belimbing Wuluh, Jambu Biji, Jeruk Nipis, Kemangi, Lidah Buaya, Nangka, Pandan, Pepaya, Seledri, and Sirih. The research stages included preprocessing, dataset division, and augmentation such as flipping, rotation, zooming, contrast and brightness changes, translation, and the addition of Gaussian noise and salt-and-pepper noise to increase data variation and test model robustness. Evaluation based on accuracy, precision, recall, and F1-score shows that the model without augmentation achieved 98.57% accuracy, 98.63% precision, 98.57% recall, and 98.58% F1-score, while the model with augmentation and noise addition achieved an accuracy of 97.71%, precision of 97.83%, recall of 97.71%, and an F1-score of 97.72%. These results prove that EfficientNetV2-B3 is capable of effectively classifying herbal plant leaves with good performance.  
Comparative Analysis of Random Forest and Xgboost Performance for Network Flow-Based Malware Classification Wicaksana, Fajar Adji; Umam, Chaerul
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: 10.35314/8f891c76

Abstract

The evolving complexity of cyber threats, particularly malware propagation through network infrastructure, necessitates intrusion detection mechanisms that are both precise and computationally efficient. This study presents an in-depth comparative analysis of two ensemble learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), in classifying network traffic anomalies based on network flow features. Empirical validation was conducted using the CSE-CIC-IDS2018 dataset, which comprehensively represents a spectrum of modern attacks. The research methodology systematically includes data preprocessing, handling class imbalance via weighting techniques, and performance evaluation based on accuracy, F1-score, and inference time metrics. Experimental results indicate that both models achieved high performance convergence with perfect Area Under Curve (AUC) scores. However, XGBoost demonstrated technical superiority with an accuracy of 99.8%, slightly surpassing Random Forest at 99.4%. The most significant finding of this study lies in computational efficiency, where XGBoost proved to be 14% faster (6.36 seconds) in prediction compared to Random Forest (7.42 seconds) on a large-scale test set. This fact confirms that the boosting architecture in XGBoost offers an optimal balance between detection sensitivity and system latency. Based on this evidence, XGBoost is recommended as the best classification model for real-time intrusion detection system implementations that prioritize rapid threat response.  
Assessing the Impact of Image Preprocessing on Convnext Performance for Waste Classification Destian Luis, Ivander; Tinaliah
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/fsa3at15

Abstract

Waste has become an increasingly urgent environmental issue in everyday life. The waste is constantly increasing due to population growth, urbanization, and consumption. The increasing amount of waste needs more intelligent systems to help with the management of waste, especially with the sorting of waste. Unfortunately, the absence of the public's awareness of the importance of waste management has led to the ineffective collection of waste. Thus, there is a need for classifying the waste into technological systems based on various waste types. This research has computing waste types using ConvNetX. The research methodology is based on the collection and preprocessing of data that includes different image enhancement techniques such as CLAHE and bilateral filtering. This study employed the ‘Garbage Classification Dataset’ found on Kaggle. The dataset is split into 80% of it as training data, 10% of it as testing data, and the last 10% of it as validation data. The ConvNeXt model was trained using one of the training sets after the data was split and was subsequently measured using the validation and test sets for the training of the model. This research analyzed the effects of image preprocessing by using a baseline, which was no preprocessing (Scenario 1), and then using preprocessing (Scenario 2). The results from the experiments showed Scenario 2 had a higher accuracy of 94% compared to the baseline of 90%. The use of CLAHE and bilateral filtering positively impacted the F1 score by increasing it to Glass (96%) and Plastic (92%) and having a full recall (100%) for Metal. Scenario 2 resulted in a total training time of 20.86 minutes, and Scenario 1 was 11.83 minutes, which means that Scenario 2 had a lower computational efficiency. Nevertheless, the additional time was well spent for the considerable consistency improvement in the classification of all categories. This makes it evident that substantial image preprocessing is necessary for the model to be able to generalize and classify images with complex visual details.
Ensemble-Based Machine Learning for Improving Local Weather Prediction Accuracy in Batam, Indonesia Sama, Hendi; Gumolung, Randy; Christian, Yefta
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: 10.35314/9p53qe06

Abstract

Accurate short-term rainfall prediction in tropical microclimates such as Batam remains challenging due to strong local atmospheric variability and the limited generalization capability of single-model classifiers. This study proposes an ensemble-based framework that integrates Naive Bayes, C4.5, and Random Forest through a majority-voting mechanism for multi-class hourly rainfall prediction. The experiments were conducted using multi-year hourly meteorological data collected for Batam City from an open-source weather archive, covering key atmospheric variables and exhibiting an imbalanced rainfall-class distribution. Model performance was evaluated using ten-fold cross-validation with accuracy, precision, recall, and F1-score metrics. The proposed ensemble achieved an accuracy of 84.74%, consistently outperforming the corresponding base classifiers. The model demonstrated strong predictive capability for dominant rainfall classes (TidakHujan and HujanRingan), while reduced performance was observed for HujanSedang and HujanBerat due to class imbalance, a well-documented challenge in tropical rainfall modeling. Overall, the results indicate that combining probabilistic and tree-based learners yields a more stable and reliable prediction framework for localized tropical weather. This work contributes a practical and reproducible ensemble approach tailored to microclimate conditions, offering a foundation for improved data-driven rainfall forecasting in similar high-variability regions
Application of EfficientNet Deep Learning with Wiener Filter for Freshwater Fish Disease Image Classification Setiawan, Christofer Evan; Tinaliah
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/k1xeb958

Abstract

Challenges pertaining to the timely and accurate diagnosis of diseases in freshwater fish have adversely impacted the productivity of the aquaculture industry. Image classification using deep learning techniques has the potential to overcome such challenges. However, this potential has not been realized due to such problems as image noise, motion blur, and small dataset sizes. Most prior studies in this area employ the same Convolutional Neural Network (CNN) architectures and, while using the same or similar techniques generic to the studies, preprocess the images. The focus of this study is to compare and benchmark the image classification performance of the EfficientNet architectures (B0 to B7) using the Wiener filter as a preprocessing technique for the classification of diseases in freshwater fish. The experiments used a publicly available dataset of 1,750 images of seven diseases in fish, while maintaining identical training parameters to yield sixteen different experimental configurations. Metrics such as accuracy, precision, recall, and F1 score were exercised while evaluating model performance. The data show that medium-scale architectures surpass both smaller- and larger-sized variants. The optimal performance was achieved by EfficientNet-B4 and Wiener Filter with an accuracy of 94.89%, a precision of 95.15%, a recall of 94.92%, and an F1-score of 94.89%. The results confirm that preprocessing with a Wiener filter improves performance on classification tasks using medium-sized models and further elucidate the applicable value of the model developed in this study in aquaculture and its related interventions.
Comparison of MobileNetV3-Small and EfficientNetV2-Small for Low-Resolution X-ray Image Classification Andhika Rizky Cahya Putra; Siska Devella
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: 10.35314/7j5twc37

Abstract

Lung diseases are a global health concern that require accurate and efficient automated diagnostic systems, particularly in healthcare facilities with limited resources. This study evaluates the performance and computational efficiency of two lightweight convolutional neural network architectures, namely MobileNetV3-Small and EfficientNetV2-Small, on the multi-label classification task of low-resolution ChestMNIST chest X-ray images. Experiments were conducted across eight testing scenarios with and without light spatial data augmentation. The evaluation encompassed predictive performance using accuracy and Area Under the Curve (AUC-ROC) metrics, as well as computational efficiency based on the number of parameters, FLOPs, model size, training time, and inference time. Results indicated that although both models achieved high accuracy (0.93–0.95), MobileNetV3-Small consistently produced higher and more stable AUC-ROC values compared to EfficientNetV2-Small, while being significantly more computationally efficient. Moreover, the application of light spatial data augmentation on low-resolution datasets such as ChestMNIST did not provide consistent performance improvements and instead increased training costs, indicating the limited effectiveness of simple geometric variations when spatial information in the images is highly constrained. These findings provide insight that, in low-resolution medical image multi-label classification, the suitability of an efficient CNN architecture design has a greater impact on overall performance than increasing model complexity or applying light spatial augmentation.