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 256 Documents
Digital Record Classification Using SVM on Permissioned Blockchain Hyperledger Fabric for Regional Status Visualization Muhammad Azhar Rasyad; Widdy Chandra Permana; Mohammad Syafrullah
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/dfyc4v87

Abstract

This paper proposes a simulation-based model for classifying public aspiration records using the Support Vector Machine (SVM) Linear algorithm integrated with a permissioned blockchain network, Hyperledger Fabric. A total of 1,000 simulated text entries were manually labeled into two categories, complaints and aspirations, and three urgency levels (high, medium, and low) by the researchers. Text preprocessing included case folding, stopword removal, stemming, and TF–IDF vectorization. The model was evaluated using 5-fold cross-validation with an 80:20 train-test split and random seed 42, producing an accuracy of 77.5%, an F1-score of 0.78, and AUC of 0.86 for category classification, and 35.5% accuracy with AUC 0.58 for urgency classification. Integration testing with Hyperledger Caliper achieved 128 transactions per second throughput, 182 ms latency, and 2.4 s block commit time with an average block size of 412 KB, demonstrating efficient and verifiable data management. Although based on simulated data, the proposed SVM Blockchain architecture provides an initial foundation for secure, transparent, and data-driven decision-making in digital government systems.
Design and Prototype Implementation of a Web-Based Car Rental Information System using Agile Scrum Harissa, Fitto Victorya
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/wfaayr38

Abstract

This study designs and implements a web-based car rental information system prototype to overcome manual process inefficiencies at the case-study company. Development followed Agile Scrum across several sprints that delivered core features: authentication, online booking, real-time vehicle management, transaction handling, and an integrated payment gateway. The technology stack comprises Laravel, MySQL, and XAMPP in a test environment. An early-stage evaluation was conducted in the partner’s operational setting using black-box testing per use-case scenario, along with measurements of process performance, data-recording accuracy, and user satisfaction. Results show transaction time decreased from 20–30 minutes to 5–10 minutes, recording errors dropped from approximately 10% to <1%, 85% of respondents reported satisfaction with booking convenience, and 90% considered the integrated payment helpful. These findings indicate that the prototype effectively improves operational efficiency and service quality, while underscoring the relevance of Agile practices for dynamic rental business needs. Future work includes standardized usability testing, load testing, and a more comprehensive security assessment.
Comparative Analysis of Machine Learning Models for BUMN Bank Stock Sentiment Classification During Danantara Formation Period Hafizha Nurul Qolby; Rangga Gelar Guntara; Syti Sarah Maesaroh
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: 10.35314/91z79392

Abstract

Discussions about state-owned bank stocks (BBRI, BBNI, and BMRI) on platform X intensified during the formation of Danantara. However, the correlation between social media sentiment and stock movements remains weak due to high noise levels and potential buzzer activity. This study combines sentiment and text similarity analyses (cosine similarity) to identify repeated communication patterns in discussions related to state-owned bank stocks. A total of 1,086 tweets were manually labeled and verified by two independent validators Text features were represented using TF–IDF and evaluated through four classical machine learning algorithms: Naïve Bayes, Logistic Regression, Support Vector Machine, and XGBoost. The model was validated using a hold-out scheme (80:20) and assessed with a confusion matrix. The sentiment distribution of the dataset shows 53% negative and 47% positive tweets Logistic Regression achieved the highest accuracy of 66%. The cosine similarity analysis identified 1.8% of tweets with similarity ≥0.90, indicating limited recurring communication patterns. These findings suggest that integrating sentiment and text similarity analyses can serve as an initial approach to detect indications of coordinated activity and to understand public opinion dynamics toward state-owned bank stocks.
Integration of MCDM and GIS in Household Gas Network Development Strategy Planning Through DSS Kurniawan Suprapto, Yossy; Retnowati
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/y1kmay03

Abstract

This research develops a Decision Support System (DSS) that integrates the Fuzzy AHP (FAHP), VIKOR, TOPSIS, and GIS methods to optimize the prioritization of the realization of Work Request (SPK) documents for the house holds gas network project in Tangerang City. FAHP is used to determine the weights of five main criteria, namely: workforce readiness (28%), material availability (22%), location accecibility (20%), customer urgency (18%), and permit status (12%). VIKOR and TOPSIS are used for ranking the alternative SPK, while GIS is used for spatial analysis and visualization. Testing (UAT) involving 10 end-users using a Likert Scale questionnaire and the System Usability Scale (SUS). The evaluation result show an SUS score of 82 (categorized as “excellent”) and a reduction in decision-making time from an average of 2 weeks to 2 days. The FAHP weighting results also demonstrated valid consistency (CR = 0.09). This system is proven to provide a comprehensive solution in supporting energy infrastructure project priority decisions by simultaneously considering technical, administrative, and geographical aspects.
Predicting Technical Intern Training Program Trainee Success: A Comparative Machine Learning Analysis For Risk Mitigation Maulana, Syaban; Fatonah, Nenden Siti; Firmansyah, Gerry; Widodo, Agung Mulyo
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: 10.35314/1r93bf26

Abstract

Japan's demographic crisis has increased demand for the Technical Intern Training Program (TITP). However, for Sending Organizations (SOs) in Indonesia, this process carries high financial risk due to an upfront talent funding scheme, where significant costs (up to IDR 35,000,000) are paid in advance. Trainee failure (dropouts or runaways) leads to substantial bad debt. This research aims to develop and validate a robust machine learning model for risk mitigation. We compare XGBoost and Random Forest on a dataset of 784 historical trainee records, characterized by extreme class imbalance (75.5% majority class). To address prior methodological weaknesses and prevent data leakage, we implement a 10-fold stratified cross-validation pipeline incorporating StandardScaler and SMOTE. The results show XGBoost (mean macro F1-Score: 0.5470 ± 0.15) significantly outperforms Random Forest (mean macro F1: 0.5098 ± 0.15), which is confirmed as statistically significant (p=0.0384) by a paired t-test. Furthermore, SMOTE is validated as a superior imbalance strategy compared to class_weight (p=0.0076). SHAP analysis identified 'contract duration' and lifestyle factors (e.g., 'alcohol consumption') as key predictors. The final model effectively predicts 'Runaway' cases (F1=0.533) but struggles with 'Training Dropouts' (F1=0.170), indicating a key limitation and a need for temporal features in future work.
Implementation of Convolutional Neural Network and Support Vector Machine Classification for Disease Detection in Rice Plants Gema Umara Muhammad; Zuni Astuti, Erna
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/r2wzfn43

Abstract

Rice is a major staple crop that is highly susceptible to various leaf diseases, necessitating an accurate early detection method to prevent yield losses. This study proposes a hybrid approach combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for rice leaf disease classification based on digital images. The CNN is employed as a deep feature extractor, while the SVM serves as the main classifier. The dataset consists of rice leaf images categorized into four disease types: bacterial blight, blast, brown spot, and tungro. The data were divided into training and validation sets, and the CNN model was trained for 10 epochs, achieving a validation accuracy of 98.14% at the 10th epoch. The extracted CNN features were then evaluated using different SVM kernels, namely Linear, Polynomial, RBF, and Sigmoid. The experimental results show that the Sigmoid kernel achieved the best performance with an accuracy of 49%, followed by Polynomial, RBF, and Linear kernels.
Implementation of Fuzzy Logic on Motorcycle Emission Testing Device Using Multi-Gas Sensors Afridon, M.; Syah, Khairudin; Susanto, Heri; Arifin, Muhammad; Syindau Abdillah, M. Andrian; Ramadhan, M. Zaki Nawaf; Marzuarman
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/w1802r28

Abstract

Manual motorcycle emission inspection often leads to inconsistent interpretation due to operator dependency. This study developed a motorcycle emission testing system using multi-gas sensors, consisting of ZE07-CO for CO, an infrared CO₂ sensor for CO₂, TGS2602 for VOC, and O₂ I2C DFRobot for oxygen concentration, integrated with an ESP32 microcontroller. Sensor data are transmitted in real-time via Bluetooth to a computer for processing and visualization on a graphical user interface. The measurement ranges were adjusted to match actual exhaust gas characteristics: CO 0–5000 ppm, CO₂ 0–50000 ppm, VOC 0–500 ppm, and O₂ 0–5%. Emission level classification was performed using the Mamdani fuzzy logic method with three triangular membership functions for each parameter and three output categories: low, medium, and dangerous. Tests on nine motorcycles showed four units classified as low emission (CO <1000 ppm; O₂ >2.4%), three as medium (CO 1100–2500 ppm; O₂ 1.5–2.0%), and two older vehicles classified as dangerous (CO >3500 ppm; VOC >350 ppm; O₂ <1%). The system successfully provides automatic and real-time emission assessment, although verification against standard emission testers and environmental compensation is required for broader practical implementation.
Optimization of Stock Trading Strategies Using a Hybrid Reinforcement Learning and Forecasting Model Hidayat, Rezha Ikhwan; Dwi Hartanto , Anggit
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: 10.35314/9vzmbf06

Abstract

Stock price prediction is an interesting challenge in machine learning due to the non-linear nature of the market. Although forecasting models can predict prices, they often do not provide optimal trading strategies. Reinforcement learning (RL) has the potential to optimize strategies, but it is highly dependent on the input states. This study integrates two methods—a CNN-LSTM forecasting model and RL (A3C)—to develop an algorithmic trading strategy. The model is evaluated using historical INDF stock data (2016–2024) with a data-split validation protocol of 80% training and 20% testing. Backtesting simulations on the period (Feb 2023–Dec 2024) show that the hybrid model achieves a cumulative total return of 121.44%. This result was obtained using an all-in trading strategy (one full position at a time) and includes transaction costs: a trading fee of 0.01% per transaction and a borrow interest rate of 0.0003% per day for short positions. This performance significantly outperforms traditional strategies: Buy and Hold (23.45%), MA Crossover (51.13%), RSI (9.09%), and MACD (−29.08%). The hybrid model also achieves a Sharpe Ratio of 2.381 (annualized, assuming a 0% risk-free rate).
Comparison of the Effectiveness of NocoDB and Nocobase Performance in the Development of Electronic-Based Government System Applications Kurnia Ulisyah, Shelly; Wiyono, Briansyah Setio
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: 10.35314/6yxtrs98

Abstract

The implementation of government digitalization through the Electronic-Based Government System (SPBE) requires a fast and reliable application development platform. The low-code platform is an efficient solution, as it allows for application development with minimal coding. This research compares two open-source low-code platforms, NocoDB and NocoBase, focusing on performance effectiveness in supporting SPBE application development. Testing was conducted using K6 load testing with a configuration of 100 virtual users over the same duration. The results show that NocoDB has a higher throughput of 92.1 requests per second with a total of 2,763 requests, though accompanied by 86 failed checks, indicating response fluctuations under high load. In contrast, NocoBase recorded 33.3 requests per second with 100 successful requests and no failures, demonstrating more consistent response stability despite lower throughput. Thus, NocoDB is more effective for high-load scenarios, while NocoBase excels in service stability. These results are expected to serve as a technical reference in selecting the optimal low-code platform for the implementation of digital government systems based on SPBE.
Comparative Analysis of No-Code and Conventional Development Efficiency in Beauty Product Application Redesign Permatasari, Hanum Zaqiah; Wiyono, Briansyah Setio
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/g56mcv29

Abstract

Advances in information technology are driving the business sector to seek faster and more resource-efficient software development methods. Conventional methods such as PHP–MySQL often require longer development times and high technical expertise, while no-code approaches offer a simpler alternative for small- to medium-scale applications. This study aims to analyze the efficiency of the no-code approach (MIT App Inventor) compared to conventional methods through a case study of the Innerlight application, applying the requirements engineering method that includes requirements formulation, analysis, specification, and validation of development results. Evaluation was conducted by measuring the processing time and effort estimation (person-days), as well as functional testing using black-box testing. The results show that no-code development requires an average of 6.5 working days (13 person-days), while the conventional method requires 8.5 working days (17 person-days), or approximately 24% more in terms of time and effort. Efficiency was measured based on project observation data without financial estimation or analysis of variation between teams. This study is a single case study, so the results cannot be generalized to other projects of different scales and complexities. The no-code approach is considered suitable for simple applications, while conventional methods are superior for systems that require flexibility and advanced logic control.