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 558 Documents
 52   53   54   55   56 
Development of a Layered Architecture for a Single-Farm Fish Farming Management System Using Prototype Method Danuri Danuri; Jaroji Jaroji
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/6s7f0c21

Abstract

Small-scale fish-farming businesses often experience challenges in managing the fragmented operational data, which includes cultivation activities, inventory, transactions and reporting processes. Lack of an integrated information management structure restricts the traceability of data and reduces the efficiency of operations. Unlike prior digital aquaculture systems, which mainly target environmental monitoring, this study designs a layered architecture for the web-based single-farm fish farming management system using the prototype method, with novelty in the architecture-level integration of five system layers with four business domains rather than in either method individually. The research methodology consists of requirement analysis, software requirements specification development, layered architecture design, prototype development, system implementation, and functionality verification. The proposed architecture separates system components into five logical layers: presentation, application, data access, data and cache layers and decomposes business functions into production, inventory, financial and reporting domains. The developed system comprises eight functional modules that enable the fish farming management processes from end to end. The functional verification was done by black-box testing with nine test scenarios, which had a 100% success rate. The results indicate that the proposed layered architecture provides a structured basis for integrating cultivation and business processes in a single-farm fish farming environment; maintainability and scalability follow from the design but were not empirically measured. Future development may extend the architecture with multi-farm management, Internet of Things integration and quantitative evaluation of software quality attributes.
Navigating Deceptive Realities: Public Perceptions and Cybersecurity Threats of Deepfake Technology Nur Anis Shafiqah Mazlan; Hapini Awang; Nur Suhaili Mansor; Mohamad Fadli Zolkipli; Bingxin Jin
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/fqwbw793

Abstract

The rapid advancement of deepfake technology presents a profound cybersecurity threat by seamlessly fabricating synthetic media, which severely erodes digital trust. This study aims to evaluate the community's awareness of deepfake threats and assess the necessity of multifaceted mitigation strategies. Employing a quantitative methodology, an online survey was conducted with 67 respondents, predominantly young adults, to measure their exposure, psychological vulnerability, and perspectives on cybersecurity countermeasures. The findings reveal that while the public is generally aware of deepfakes, 75 per cent struggle to visually differentiate manipulated content from authentic media. Consequently, the proliferation of deepfakes has diminished perceived societal trust in online information. Notably, there is a unanimous consensus among respondents demanding strict legal frameworks and comprehensive public education to combat this menace. The study concludes that relying exclusively on technical detection algorithms is insufficient. Instead, preserving information integrity requires a multidisciplinary approach combining robust technological defences, proactive policymaking, and widespread digital literacy trainings.
DRASTIC: Big Data Quality in Big Data Integration Muhammad Noor; Fauziah Baharom; Haslina Mohd
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/ajd50z21

Abstract

In today’s digital era, organisations are increasingly relying on data-driven decision-making to enhance operational efficiency and strategic planning. Data from multiple sources should be integrated to support this movement. However, this process is complex due to the emergence of big data. Consequently, it significantly increases the challenges of managing and integrating data, which can degrade data quality and lead to poor decision outcomes. In fact, existing data quality characteristics are no longer adequate in the big data era. Therefore, this paper conducted a comprehensive literature review of peer-reviewed articles retrieved from electronic databases published between 2010 and 2025 to examine existing data quality characteristics and identify gaps related to the 5V's big data characteristics. Moreover, this paper compares and evaluates existing data quality characteristics and their sufficiency for assessing the quality of data in big data integration. Based on these evaluations, this paper proposes DRASTIC, a set of 14 data quality characteristics, with dependency and scalability introduced as new characteristics in the context of big data integration because these characteristics are underexplored in existing literature. The findings contribute to the literature by extending current data quality characteristics and addressing the challenges posed by big data's unique characteristics in data integration.
Evaluation Of CNN-LSTM with Attention for Forest Fire Prediction in Indonesia: Challenges of  Imbalanced Data Susandri; Ahmad Zamsuri; Nurliana Nasution; Feldiansyah; Ilzi Adrolis SNR; Firman Hidayat
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/6dzf1988

Abstract

Forest and land fires are annual disasters in Indonesia that are influenced by the temporal and nonlinear dynamics of surface weather conditions. This study evaluated a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture with an attention mechanism for predicting forest fire risk based on multivariate surface weather data from BMKG stations for the 2015–2024 period. The dataset comprised 4,931 daily observations with eight weather features and four fire risk levels. The models were evaluated using temporal cross-validation and compared with the baselines (Random Forest, XGBoost, LightGBM, SVM, and standalone LSTM). The results indicate that the CNN-LSTM-attention model achieved 71.47% accuracy and 62.36% F1-score in the initial configuration. However, optimization attempts using SMOTE substantially degraded the performance to 50.95% accuracy (F1=0.55). The critical findings are as follows: (1) SMOTE is unsuitable for time-series data as it disrupts temporal patterns; (2) simpler architectures outperform excessive complexity; (3) class weighting is preferable to oversampling for handling class imbalance; and (4) basic weather features (without extensive engineering) yield optimal results. This study concludes that deep learning approaches for forest fire prediction in tropical regions face significant challenges related to class imbalance and temporal stability, necessitating the development of more adaptive modeling strategies
Comparing LSTM, Bi-LSTM, and Transformer Across Feature Scenarios for Rupiah Exchange Rate Forecasting Titis Chusnul Mahrom; Andy Prasetyo Utomo; Soni Adiyono
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/395zyb49

Abstract

This study compares LSTM, Bi-LSTM, and Transformer models for one-step-ahead JISDOR forecasting across eight feature scenarios using historical JISDOR, IHSG, Brent oil prices, and inflation. The dataset comprised 1,300 chronological observations from January 2021 to May 2026. Evaluation used chronology-safe preprocessing, four expanding-window walk-forward folds, validation-based model selection, five stochastic seeds, a naive persistence benchmark, statistical testing, and Integrated Gradients. Among the deep-learning models, LSTM under S1 achieved the lowest mean MAPE of 0.6662%, followed by Bi-LSTM at 0.6899% and Transformer at 1.8135%. However, naïve persistence achieved a lower mean MAPE of 0.2618%, and all model–scenario combinations were significantly worse after Holm-adjusted Diebold–Mariano testing. External variables did not improve forecasting accuracy over historical JISDOR alone. Integrated Gradients showed that historical JISDOR received the largest attribution in all three architectures. These results highlight the importance of temporal validation and simple benchmarks in exchange-rate forecasting.
Implementation of Handwritten Digit Recognition Using CNN in an Augmented Reality-Based Geometry Learning Application Azizah Fauni Saputri; Feri Candra
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/wfjqak08

Abstract

Instruction on 3D shapes in elementary schools is still dominated by the use of two-dimensional media, making it difficult for students to visualise three-dimensional objects. Furthermore, most Augmented Reality (AR)-based learning applications focus primarily on presenting learning materials without providing an assessment mechanism that supports handwritten student answers. This study aims to implement Handwritten Digit Recognition (HDR) based on a Convolutional Neural Network (CNN) in an AR-based 3D-shape learning application. The proposed approach integrates CNN-based handwritten digit recognition as an evaluation mechanism within the AR-based learning application, allowing students' handwritten answers to be automatically recognised and evaluated. The CNN model utilises the LeNet-5 architecture and was trained using a combined dataset consisting of 70,000 MNIST images and 10,000 handwritten images independently collected by the researcher. The testing results show that the model achieved an accuracy of 98.32%, while HDR testing within the application using 250 samples of student handwriting achieved an accuracy of 96.80%. The results indicate that the implementation of CNN-based HDR in an AR-based 3D shape learning application can recognise handwritten digits with high accuracy and provide an automated learning evaluation mechanism based on handwritten answers.
Production and Evaluation of 360° 3D Assets Using a Mini Booth and CR-Scan Ferret Ibrohim Yofid Fananda; Aji Sapta Pramulen; Jauari Akhmad Nur Hasim; Phafad Unggul Handayu; Irma Wulandari
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 3 (2026): August
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/7djb7k16

Abstract

This study documents and evaluates an end-to-end workflow for producing 30 textured three-dimensional (3D) assets from small-scale objects (maximum dimension 50 cm) using the active near-infrared scanner Creality CR-Scan Ferret inside a mini booth with diffuse lighting. Raw data were processed in Creality Scan and Blender through artefact elimination, remesh/retopology, mesh repairing, texture baking, and export. Digital dimensions were extracted from the model bounding box using Python and Open3D, then compared with reference physical measurements. The mean per-asset RMSE was 2.00 cm (SD = 1.61; median = 1.80; 95% CI = 1.40–2.60; range = 0.02–6.18 cm). Under the internal thresholds of the study, 12 assets were rated Very Good, 11 Good, 5 Fair, and 2 Poor. The mean RMSE for easy, medium, and hard objects was 1.32, 1.31, and 3.36 cm, respectively; an exploratory Kruskal-Wallis test indicated a difference between categories (H = 9.76; p = 0.0076). Mesh analysis was applied to six representative samples only. Two regular bottle models had Non-manifold Edges = 0 and Shells = 1, whereas the Hashmal model had 14,945 non-manifold edges and 7 shells. The workflow is usable as an initial pipeline for digital visualisation, but the results do not prove universal metric accuracy or watertightness because repeated scans, measurement uncertainty, independent scale calibration, and mesh-metric normalisation are not yet available.
Performance Evaluation of a 344-Egg Automatic Incubator with Temperature-Humidity Regulation and Periodic Rack Turning Soni Hestukoro; Marlon Tua Pangihutan Sibarani
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 3 (2025): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/yfzmq211

Abstract

This study evaluates an automatic poultry egg incubator designed for 344 chicken eggs. The prototype combines temperature regulation, humidity monitoring, and periodic rack turning to reduce manual handling during a 21-day incubation cycle. The operating temperature is maintained within 38-39°C, while the humidity setting is 55-70%. A digital temperature sensor, hygrometer, Arduino Uno controller, relay module, heating lamp, ventilation fan, and DC rack-turning motor form the sensing-control-actuation chain. Hatching performance was assessed by classifying the 344 incubated eggs into normal hatch, defective hatch, dead embryo, and no-embryo outcomes. The test produced 327 normal chicks, 10 defective chicks, 5 dead embryos, and 2 eggs without embryos. The proportion of normal hatches was 95.06%, indicating that the incubator can sustain the environmental and mechanical conditions required for high-capacity chicken egg incubation. The study emphasises integrated operation and outcome-based performance rather than only controller implementation.

Page 56 of 56 | Total Record : 558

 52   53   54   55   56 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 3 (2026): August Vol. 11 No. 2 (2026): May 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