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 543 Documents
 44   45   46   47   48 
Android Application Prototype for Detecting Mould on Bread using Machine Learning Frissy Siregar; Daniel Haganta Barus; Clara Stephanie Bernadeth Piay; Evta Indra
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/bptwhn82

Abstract

Mould contamination in bread poses a serious health risk if not detected early, especially in the food industry, which still relies heavily on manual visual inspection. This study aims to develop a prototype Android application capable of automatically detecting mould on bread using a machine learning approach based on the MobileNetV2 architecture. The classification model was trained on a dataset of 666 bread images, consisting of 533 training and 133 validation samples. Training was carried out over 37 epochs using data augmentation techniques and a learning rate of 0.0001. The results demonstrated consistent accuracy improvements and loss reductions without signs of overfitting. The model achieved 94% testing accuracy, with a precision, recall, and F1-score of 0.94 for both "Mouldy" and "Non-Mouldy" classes. The confusion matrix showed 125 correct predictions out of 133 test images. This research addresses the gap in lightweight and practical solutions for mobile-based mould detection. Unlike previous studies that used heavier models such as VGG16 or ResNet, this study shows that MobileNetV2 can achieve high performance with lower computational demands, making it suitable for real-world Android applications. The trained model was integrated into a simple Android interface, allowing users to upload images and instantly receive classification results. For future improvement, this prototype can be enhanced by incorporating object detection or image segmentation techniques such as YOLOv5 or U-Net to enable not only classification but also the localisation of mould areas in real-time.
Analysis of Differences Between AI and Human Texts Using the Natural Language Processing Method Dinda Cahyana; VitoReyLukito Sijabat; Mohammad Irfan Fahmi
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/3wqgd409

Abstract

Artificial Intelligence has become increasingly proficient in generating text that mimics human writing, yet existing detection tools remain limited in accuracy and adaptability. Previous studies indicate that systems like Turnitin and GPTZero often perform below 80% accuracy and struggle with paraphrased or advanced AI-generated content. This study addresses that gap by analyzing linguistic differences between AI-generated and human-written texts using Natural Language Processing. A dataset of 487,235 texts (305,797 human-written and 181,438 AI-generated) was processed using TF-IDF vectorization and classified with the Multinomial Naive Bayes algorithm. The model achieved 99.35% accuracy and an F1-score of 0.9948, with balanced performance in detecting both text types. Results show that while AI-generated texts are structurally consistent, they often lack the emotional depth and cultural nuance found in human writing. These findings suggest NLP methods are highly effective in distinguishing between the two, and have practical implications for developing more reliable detection systems to ensure textual authenticity in education, journalism, and digital media monitoring.
Design of Website-Based Waste Management System using Laravel Framework in RT 06 Kramat Jati Budi Eka Saputra; Isa
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/ga9s2g90

Abstract

Waste management fees at the Neighbourhood Association level often experience obstacles such as recording errors, late payments, and a lack of information transparency. This has an impact on low service efficiency and citizen participation. The purpose of this research is to build a web-based information system that can support the waste management process, using the Laravel framework as the main tool to improve efficiency, transparency, and administrative accountability in RT 006 RW 010, Kramat Jati, East Jakarta. The study was conducted on 10 residents and RT administrators as respondents, selected based on their activity in every resident activity from February to May 2025. The system allows RT administrators to manage data digitally, while residents can monitor payment status in real-time. For residents who are not familiar with technology, admins can enter data manually. The test results show that all features in the system run smoothly and support the administration process effectively. This system has been proven to significantly reduce manual recording and recap time, as well as increase citizen involvement in the payment process. In the future, this system has the potential to be further developed with the integration of digital payments such as QRIS and mobile applications, to expand reach and improve service convenience
User Satisfaction Analysis of the Website Using the E-Servqual Method Mazia Zuleffa; Hari Widi Utomo; Arif Riyandi
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/m9a6r812

Abstract

This study aims to specifically analyze the key service quality dimensions—Efficiency, Privacy, and Contact—that influence user satisfaction with the PMB website of Madyathika Polytechnic. A structured questionnaire based on the E-SERVQUAL model was distributed to respondents, and the collected data were analyzed using descriptive statistics, SPSS-based validity and reliability testing, and Importance Performance Analysis (IPA). The findings reveal that although several service dimensions meet user expectations, attributes such as cross-device accessibility, user data privacy, and clarity of contact information still show negative service quality gaps. These results provide a foundation for targeted recommendations to improve the overall digital service experience. This research contributes to the strategic enhancement of digital service quality in higher education admissions systems.
Implementation of Ibis Pain X Application in Fashion Design Learning Based on Students' Learning Interests Raudatul Jannah; Ita Fitriati; Ika Irawati; Nur Fitrianingsih; Nurhairunnisah
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/661f3e36

Abstract

This study aims to examine the use of the Ibis Paint X application in fashion design learning to enhance the interest and learning outcomes of Grade X Fashion Design students at Vocational High School 1 Monta. This research is the first study to directly implement Ibis Paint X in the context of fashion design education at a vocational school. The study is motivated by the low student interest in manually drawing designs and the limited availability of digital learning media. The research employed an experimental method with a One-Group Pretest -Posttest design, involving 9 purposively selected students. Data were collected through observation, pretest, posttest, and a Likert scale questionnaire. The paired sample t-test results showed a significant improvement (p = 0.000 < 0.05), with the average pretest score of 51.1 and posttest score of 91.1. A Cohen’s d value of 4.00 indicates a very large effect. The average score of the learning interest questionnaire was 4.45, indicating a high category. These findings demonstrate that Ibis Paint X is effective in increasing student engagement, motivation, and learning outcomes. The results encourage vocational school teachers to integrate Ibis Paint X into the fashion design software syllabus as an innovative and contextual digital learning medium.
Enhancing Fraud Detection Performance in E-Commerce Platforms Using Gradient Boosting Algorithms Ardi Saputra; Fauzi Adi Rafrastara; Wildanil Ghozi
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/s8q6t594

Abstract

The rapid growth of e-commerce has attracted many users. However, as transaction volumes increase, so do cases of fraud. This not only causes financial losses for sellers but also threatens the trust that is so important in the e-commerce industry. Previous studies have used the Naïve Bayes and Multilayer Perceptron algorithms to detect fraud in e-commerce with accuracy percentages of 95.00% and 94.00%, respectively, without other assessment measures, including precision, recall, and F1-score. This research seeks to create a predictive model for the likelihood of online sales fraud by comparing Gradient Boosting, Neural Network, Random Forest, and Naïve Bayes models through feature extraction and feature scaling pre-processing, with 10-fold cross-validation. The dataset used was taken from the Kaggle platform. The features included in the dataset include buyer characteristics, products sold, transaction volume, devices used, and other fraud indicators. The study's findings demonstrate that the Gradient Boosting algorithm excels in detecting fraud risk with an accuracy rate of 95.30%, precision of 94.10%, recall of 95.30%, and an F1-score of 93.80%.  These findings are anticipated to enhance the development of more efficient e-commerce security solutions.
Implementation of a Hybrid Fuzzy SAW and Particle Swarm Optimization Algorithm for a Dynamic Laptop Recommendation System Based on User Preferences Wildi Amalia; Asrianda; Fajriana
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/nqkpbg48

Abstract

Recommendation systems often struggle to balance personalization with fairness, particularly in addressing the marginalization of minority brands caused by data and algorithmic biases. This study tackles that challenge by developing a dynamic laptop recommendation system tailored to user preferences, leveraging a hybrid algorithm that combines Fuzzy Simple Additive Weighting (Fuzzy SAW) and Particle Swarm Optimization (PSO). Fuzzy SAW is employed to manage uncertainties in subjective preferences such as budget and intended use, while PSO dynamically optimizes the weight of each criterion to enhance personalization. Evaluation was conducted using primary data from 27 respondents in Lhokseumawe, Aceh, collected via surveys and interviews, alongside secondary data on laptop specifications retrieved from the Tokopedia API. The resulting match accuracy reached 74.1%, with Asus accounting for 85.0% of the successful recommendations. In contrast, brands like Lenovo and Advan were significantly underrepresented, underscoring the system’s limited sensitivity to minority brands. This research contributes to the field of recommendation systems by empirically demonstrating the trade-off between optimization and fairness, as well as proposing strategies to mitigate algorithmic bias. Practical implications include better-informed user decisions and fairer brand exposure for e-commerce platforms. Future improvements will focus on expanding data sources and refining PSO parameter tuning to better accommodate underrepresented brands.  
Classification of Coronary Heart Disease Based on Community Health Centre Medical Record Data Using SVM Algorithm M Reza Kausar; Wahyu Fuadi; Zahratul Fitri
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/ng11kk81

Abstract

Coronary heart disease (CHD) is one of the leading causes of death worldwide and demands a fast and accurate diagnostic system, especially in community health centres (Puskesmas) where medical resources are limited. This study aims to develop a classification system for CHD using the Support Vector Machine (SVM) algorithm based on numerical medical record data. It also addresses the gap in previous studies that rarely applied SVM to tabular data from primary healthcare facilities. The methodology includes variable weighting, min-max normalization, model training with a linear kernel, and performance evaluation using a confusion matrix. The dataset consists of 100 patient records with variables such as age, blood pressure, heart rate, respiratory rate, and chest pain. The results show that the SVM model achieved an accuracy of 95%, a precision of 100%, recall of 88.9%, and an F1-score of 94.1%. The model was further integrated into a web-based application using Flask to support automated early diagnosis. This study demonstrates that SVM is effective in classifying heart disease based on medical records and offers a practical solution to improve healthcare service quality in Puskesmas.
Classification Of Hypertension Using K-Nearest Neighbor Based On Photoplethysmograph Data And Blood Pressure Estimator Jasmin William Natanael Sinaga; Tasya Rouli Christy Tampubolon; Ester Farida Simanjuntak; Delima Sitanggang; Reyhan Achmad Rizal
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/zswzf122

Abstract

Hypertension is a persistent cardiovascular condition, often termed the “silent killer” because it typically presents no symptoms in its early stages. To address the shortcomings of traditional blood pressure monitoring methods, this study develops a classification system that leverages photoplethysmography (PPG) signals in combination with the K-Nearest Neighbor (KNN) algorithm. PPG provides a promising non-invasive solution that is readily adaptable to portable devices. The classification process employs the Euclidean Distance method to determine the similarity between new data samples and previously labeled instances. Data were collected from 276 individuals spanning various age groups using PPG sensors connected to the MR-IAT Robot Covid platform. The system categorizes individuals into normotensive, prehypertensive, stage 1, and stage 2 hypertension groups. The study evaluates the performance of the KNN algorithm based on its ability to predict blood pressure categories from morphological features extracted from the PPG signals. Ultimately, the outcomes of this research are expected to advance the development of efficient, real-time, continuous blood pressure monitoring systems through user-friendly machine learning approaches.
Link Budget Prediction at 28 GHz Frequency Based on Rain Attenuation Model in Palembang City Tarnita Rizky Prihandhita; Sopian Soim; Mohammad Fadhli
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/apvf0b18

Abstract

5G communication technology brings a major leap in the development of wireless networks, especially through the utilization of millimeter wave frequencies. However, mmWave signals are very susceptible to rain attenuation, which can significantly reduce the quality of 5G services. This study aims to estimate how much signal loss and reception power there will be for 5G at a frequency of 28 GHz in Palembang City and to examine how rain affects the mmWave signals. MATLAB simulations use Palembang rainfall data for the March 2025 period and use the ITU-R P.618-5 rain attenuation model, Simple Attenuation Model, and ITU-R Tropical. Using the Urban Macro propagation scenario in line-of-sight and non-line-of-sight conditions. The results show that distance and rainfall affect signal attenuation, with NLOS conditions producing worse attenuation than LOS. At high rainfall of 84.5 mm/hour in NLOS conditions, ITU-R P.618-5 predicts the highest total path loss of about 317 dB, ITU-R Tropical about 247 dB, and SAM about 227 dB. With the received power of ITU-R P.618-5 model of -260 dBm, ITU-R Tropical of -190 dBm, and SAM of -170 dBm.

Page 46 of 55 | Total Record : 543

 44   45   46   47   48 

Filter by Year

2024 2026


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