cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kab. kuantan singingi,
Riau
INDONESIA
JURNAL TEKNOLOGI DAN OPEN SOURCE
Published by Universitas Islam Kuantan Singingi
ISSN : 26557592     EISSN : 26221659     DOI : 10.36378/jtos
Core Subject : Science,
Computer Science & IT
Jurnal Teknologi dan Open Source menerbitkan naskah ilmiah. yang berkaitan dengan sistem informasi, teknologi informasi dan aplikasi open source secara berkala (2 kali setahun). Jurnal ini dikelola dan diterbitkan oleh Program Studi Teknik Informatika Fakultas Teknik, Universitas Islam Kuantan Singingi. Tujuan penerbitan jurnal ini adalah sebagai wadah komunikasi ilmiah antar akademisi, peneliti dan praktisi dalam menyebarluaskan hasil penelitian.
Arjuna Subject : -
Articles 372 Documents
 28   29   30   31   32 
Transfer Learning Implementation with MobileNetV2 for Cassava Leaf Disease Detection Aulia, Muhammad Fathir; Gibran, M. Khalil; Sitorus, Nur Shafwa Aulia; Nugroho, Agung; Faiza, Nayla; Siregar, Hervilla Amanda R.
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4442

Abstract

Cassava (Manihot esculenta) is one of Indonesia’s key agricultural commodities but is vulnerable to various leaf diseases, such as Cassava Bacterial Blight (CBB) and Cassava Mosaic Disease (CMD). These diseases often exhibit similar visual symptoms, making it challenging for farmers to accurately identify them through manual observation. This study aims to develop an automatic cassava leaf disease detection system based on transfer learning, utilizing the MobileNetV2 architecture. The dataset used consists of 1,500 images, evenly distributed across three categories: CBB, CMD, and healthy leaves. The data underwent preprocessing, augmentation, and model training, including fine-tuning of the last 20 layers of the MobileNetV2 model. Evaluation results indicated that the model achieved an accuracy of 67% on the test set, with the highest performance in detecting Cassava Mosaic Disease, reflected by an F1-score of 0.75. These results demonstrate the potential of MobileNetV2 as a lightweight and efficient solution for detecting cassava leaf diseases, particularly when supported by a larger and more diverse dataset. This research serves as a foundation for developing mobile-based diagnostic tools to help farmers make faster and more accurate decisions in the field.
A Deep Learning-Based Sentiment Classification for Identifying Advertorial Content in Online News Darnoto, Brian Rizqi Paradisiaca; Firmawan, Dony Bahtera; Adnan, Fahrobby
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4450

Abstract

The rapid advancement of technology and the widespread use of the internet have brought significant positive and transformative impacts across various aspects of human life, including finance, healthcare, education, and the media industry. One notable consequence of information transparency is the vast availability and large-scale exchange of data. However, this also presents new challenges, particularly in the spread of misleading content such as disguised advertorials that resemble genuine news. This threatens the objectivity of the information received by the public. To address this issue, an automated solution is needed to identify the distinguishing characteristics of advertorials in online news content. This study proposes a deep learning approach using the Convolutional Neural Network (CNN) model to detect sentiment as an indicator of advertorial content. CNN is a widely used deep learning model for processing sequential and spatial data, capable of automatically learning features from text. The dataset comprises news articles categorized by advertorial traits, such as positive or neutral sentiment, persuasive language, and promotional content highlighting specific entities. The data undergo several processing stages, including text preprocessing, tokenization, padding, and CNN model training. Model performance is evaluated using accuracy, precision, recall, and F1-score. The experimental results show a validation accuracy of 84%, although overfitting issues were observed. Despite ongoing limitations, such as restricted data and suboptimal parameter tuning, the findings suggest that the CNN model has potential for automatically detecting advertorial content and can serve as a basis for future research using more advanced models and refined parameter adjustments.
Decision Support System For Submitting and Evaluating Web-Based Scholarships Using The Topsis Method at SMP Kusuma Raya Afdhaluddin, Muhamad; Rahmi, Lailatur; Amalia, Tasya
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4452

Abstract

This research aims to develop a web-based decision support system for the scholarship application and assessment process. The system is designed to improve efficiency, transparency, and objectivity of selection. The TOPSIS method is used to evaluate potential recipients based on a number of relevant criteria. The system was developed using PHP, MySQL, Visual Studio Code, and XAMPP as the development platform. System testing shows that this application is able to provide accurate scholarship recipient recommendations, so that it can help decision makers in determining recipients more fairly and systematically. With this approach, it is expected that the scholarship selection process will become more structured and reduce the potential for subjectivity in assessment. The results of this research contribute to the application of information technology in supporting a better selection system in the academic environment and scholarship granting institutions.
Analysis and Modeling of the Internal Quality Audit Information System Islamic University of Kuantan Singingi Nopriandi, Helpi; Al-Hafiz, Nofri Wandi; Chairani, Sri
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4456

Abstract

Internal Quality Audit (AMI) is an integral part of the Internal Quality Assurance System (SPMI) for Higher Education (Dikti), aimed at evaluating the implementation of Dikti standards. AMI plays a crucial role in examining the compliance with Dikti standards during their implementation phase. The AMI system encompasses numerous processes, including desk evaluation, visitations, requests for corrective actions, and documentation. Moreover, AMI activities ideally should be conducted annually for every Unit at Islamic University of Kuantan Singingi. Due to the limited number of auditors, it is necessary to develop an information system that enables easier monitoring and decision-making processes. This will ensure efficient and sustainable management. The unstructured archiving of audit results increases the risk of data loss and complicates information access. To address this issue, it is necessary to develop an information system using the System Development Life Cycle (SDLC) approach, which involves four major phases: planning, analysis, design, and implementation. The AMI system developed aims to support the AMI process in higher education institutions, especially at Islamic University of Kuantan Singingi (UNIKS). Before the implementation of the information system, several challenges were faced, such as difficulties in quickly obtaining information related to quality improvements for each unit periodically. This research produced a design for an information system that integrates various AMI requirements, including scheduling, self-assessment (desk evaluation) by the institution, visitations, corrective actions, and reporting.
Examining User Privacy and Trust in the Lazada Application Through the Lens of the Theory of Planned Behavior Saragih, Theresia Cilcilia; Suratno, Tri; Lestari, Dewi
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4482

Abstract

The results of decision making play an important role in achieving a goal in solving certain problems. Decision making process requires data or supporting evidence that can be used as a guide for the selection of solutions based on available alternatives, to produce choices that can increase productivity. Multi Criteria Decision Making (MCDM) method for the analysis of research data namely SMART, TOPSIS, and AHP. The three methods are tested, because each MCDM method has a different way of working or algorithm, so it is necessary to experiment with certain cases. This study aims to determine the performance of the SMART, TOPSIS, and AHP methods with a case study of selecting of tobacco land recommendations. The application of three MCDM methods for alternative analysts of prospective tobacco land based on testing to determine the accuracy of comparing the results/output of the system with expert recommendation solutions using a sample of 10 tobacco land that produce priority/ranking for tobacco land recommendations, shows that the performance of the three methods produces priority selection results different, with an accuracy of SMART 80%, TOPSIS 80%, and AHP 70%.
BCA Stock Price Prediction Using Time Series Method With GRU (Gated Recurrent Unit) Nugraha, Rizky; Abdul Rezha Efrat Najaf; Reisa Permatasari
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4500

Abstract

Stock price prediction is a crucial component in investment decision-making, enabling investors to plan strategies more accurately and minimize risks. This study applies the Gated Recurrent Unit (GRU) model to predict the stock prices of blue-chip banking companies in Indonesia using data from the period 2019 to 2024. The model utilizes historical stock data to forecast future trends. The results from the first testing scheme, with a data split ratio of 70% / 30%, using GRU units (128,256) with the Adam optimizer, show that the GRU model is the most optimal in terms of prediction, measured by metrics such as MSE, RMSE, and MAPE. This study also proposes a web-based dashboard that visualizes the predicted stock prices and provides decision-support tools for investors. The findings highlight the effectiveness of deep learning in financial forecasting and underscore its potential to enhance investment strategies.
Design and Development of an E-Commerce Website Using the Waterfall Method with the Laravel Framework Mindara, Gema Parasti; Aisya Tyanafisya; Siti Farah Fakhirah; Azhar Nadhif Annaufal; Ibnu Aqil Mahendar; Aditya Wicaksono
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4570

Abstract

The e-commerce sector has experienced significant growth in Indonesia in recent years. However, many small business owners still rely on manual operations through social media platforms. This study focuses on the design and implementation of an e-commerce website for Comot Langsung, a local thrifting business, using the Waterfall methodology and the Laravel framework. The sequential nature of the Waterfall method is applied through six phases: requirement analysis, system design, development, testing, deployment, and ongoing maintenance. In the analysis phase, several key features were identified, including user registration, product catalog, shopping cart, ordering system, and QRIS payment integration. The design process utilized UML diagrams to clearly and structurally visualize the system architecture and user flow. The results show that all features were successfully implemented, offering high responsiveness and ease of navigation. This website is expected to expand market reach for thrifting entrepreneurs while enhancing the online shopping experience for consumers in selecting and purchasing vintage fashion products efficiently and conveniently.
Comparative Sentiment Analysis of Indonesian Leadership Transitions on Platform X Using LSTM and Naïve Bayes: A Dual-Label Evaluation Using Lexicon-Based and Manual Annotation Alief Rama, Alief Ramadhan Dwi Putra; Afiyati, Afiyati
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4596

Abstract

This study compares Long Short-Term Memory (LSTM) and Naïve Bayes algorithms for sentiment analysis focused on leadership transitions within Indonesian social media. A dataset of 5,942 Indonesian-language tweets from platform X (formerly Twitter) was collected and labeled using both lexicon-based and manual annotation methods. Manual labeling was crucial to capture the nuanced and context-dependent sentiment often missed by lexicon-based techniques, especially during periods of heightened political discourse. The LSTM model was implemented for its ability to capture sequential dependencies in text, while Naïve Bayes was used as a computationally efficient baseline. Both models were rigorously evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score. Experimental results show that LSTM achieved 71.6% accuracy with lexicon-based labels and 77.9% with manual labels. In comparison, Naïve Bayes achieved 61.5% and 78.2%, respectively. LSTM demonstrated better generalization across sentiment categories, particularly for neutral sentiments, while Naïve Bayes proved more effective on highly polarized datasets. These findings underscore the importance of strategic model selection based on data quality and labeling methods. The results offer valuable insights for political sentiment analysis and the development of data-driven decision-making tools in the digital political landscape.
Implementation of an Information System for Classroom Reservation at Esa Unggul University Siti Rodiyah; Sinulingga, Samuel Mahesa; Putra, Farrel Reyhan; Aryasatya, Muhammad Fathi; Kusdaryanto, Ardo; Sulistiyono, Rovy; Irawan, Bambang
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4633

Abstract

The manual management of room reservations at Esa Unggul University has long faced various administrative challenges, including irregular scheduling, delays in the approval process, and limited access to real-time room availability information. These issues reduce the overall efficiency of academic and administrative services. To address these problems, this study aims to design and implement a web-based information system that facilitates a more structured, transparent, and efficient room reservation process.The system was developed using the CodeIgniter 4 framework for the backend, while Bootstrap 5 and custom CSS were utilized for the frontend interface. MySQL served as the database management system, and application security features were enhanced with session-based authentication, input validation, data encryption, CSRF protection, Honeypot, and CloudFlare integration. Testing was conducted using the gray box method to evaluate both code reliability and system functionality from the user’s perspective.The results indicate that the application effectively handles room reservation requests, minimizes scheduling conflicts, and supports administrative staff in centrally monitoring room usage. This research contributes significantly to the digital transformation of campus administration and may serve as a reference for developing similar systems in other higher education institutions.
An Integrated Machine Learning and Deep Learning Approach for Multiclass Flood Risk Classification with Feature Selection and Imbalanced Data Handling Irawan, Yuda; Refni Wahyuni; Herianto
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i2.4639

Abstract

Floods are hydrometeorological disasters that often occur in tropical regions such as Indonesia and can have significant impacts on infrastructure, economy, and public health. This study aims to build and compare the performance of 21 artificial intelligence models, consisting of 15 Machine Learning algorithms and 6 Deep Learning architectures, in classifying flood risk levels based on multivariate tabular data. The dataset used includes 22 relevant environmental and social variables, with classification targets in four classes: Low, Moderate, High, and Very High. To improve data quality, feature selection was carried out using the LASSO method and class balancing with the SMOTEENN technique. The evaluation results showed that the C4.5, MLP, Random Forest, and Logistic Regression models obtained the highest accuracy (>94%), followed by deep learning models such as BiLSTM, CNN, and BiGRU with competitive accuracy (≥90%). Confusion matrix analysis confirmed the consistency of predictions across classes with a balanced distribution, especially in the decision tree and deep neural network models. This study emphasizes the importance of selecting a model that suits the characteristics of the data to achieve optimal predictions. The pipeline developed in this study is expected to be the basis for a more accurate and adaptive AI-based early warning system in mitigating flood risks in the future.

Page 30 of 38 | Total Record : 372

 28   29   30   31   32 

Filter by Year

2018 2025


Reset
Filter By Issues
All Issue Vol. 8 No. 2 (2025): Jurnal Teknologi dan Open Source, December 2025 Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025 Vol. 7 No. 2 (2024): Jurnal Teknologi dan Open Source, December 2024 Vol. 7 No. 1 (2024): Jurnal Teknologi dan Open Source, June 2024 Vol. 6 No. 2 (2023): Jurnal Teknologi dan Open Source, December 2023 Vol. 6 No. 1 (2023): Jurnal Teknologi dan Open Source, June 2023 Vol. 5 No. 2 (2022): Jurnal Teknologi dan Open Source, December 2022 Vol 5 No 2 (2022): Jurnal Teknologi dan Open Source, December 2022 Vol 5 No 1 (2022): Jurnal Teknologi dan Open Source, June 2022 Vol. 5 No. 1 (2022): Jurnal Teknologi dan Open Source, June 2022 Vol 4 No 2 (2021): Jurnal Teknologi dan Open Source, December 2021 Vol. 4 No. 2 (2021): Jurnal Teknologi dan Open Source, December 2021 Vol. 4 No. 1 (2021): Jurnal Teknologi dan Open Source, June 2021 Vol 4 No 1 (2021): Jurnal Teknologi dan Open Source, June 2021 Vol 3 No 2 (2020): Jurnal Teknologi dan Open Source, December 2020 Vol 3 No 1 (2020): Jurnal Teknologi dan Open Source, June 2020 Vol 2 No 2 (2019): Jurnal Teknologi dan Open Source, December 2019 Vol 2 No 1 (2019): Jurnal Teknologi dan Open Source, June 2019 Vol 1 No 2 (2018): Jurnal Teknologi dan Open Source, December 2018 Vol 1 No 1 (2018): Jurnal Teknologi dan Open Source, June 2018 More Issue