cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Budi Hermawan
Contact Email
-
Phone
+62081703408296
Journal Mail Official
info@kdi.or.id
Editorial Address
Jl. Flamboyan 2 Blok B3 No. 26 Griya Sangiang Mas - Tangerang 15132
Location
Kab. tangerang,
Banten
INDONESIA
bit-Tech
Published by Komunitas Dosen Indonesia
ISSN : 2622271X     EISSN : 26222728     DOI : https://doi.org/10.32877/bt
Core Subject : Science,
Computer Science & IT
The bit-Tech journal was developed with the aim of accommodating the scientific work of Lecturers and Students, both the results of scientific papers and research in the form of literature study results. It is hoped that this journal will increase the knowledge and exchange of scientific information, especially scientific papers and research that will be useful as a reference for the progress of the State together.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 642 Documents
 36   37   38   39   40 
Adoption of the CSD Matrix to Improve the Business Process Quality of Software Development Teams Nabila Putri Ocktavia; Beni Suranto; Chanifah Indah Ratnasari
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2739

Abstract

This research aims to improve the quality of business processes in software development teams through the application of the CSD Matrix method. The CSD Matrix was reformulated in this research as a visual decision support tool to improve early sprint planning, by mapping project elements into three categories: certainties, suppositions, and doubts. The method was applied to the software engineering team at Mamikos through the completion of Capability Maturity Model Integration (CMMI) indicator-based questionnaires, both before (pre-test) and after (post-test) implementation. The results showed a significant improvement in the process maturity level, from an average score of 2.70 (Level 2: Developing) to 4.20 (Level 4: Managed), especially in the areas of retrospective, requirements management, and onboarding. This finding confirms that the CSD Matrix is able to encourage the structuring of the planning process, strengthen the team's collective awareness of risks and assumptions, and improve the effectiveness of cross-functional communication. With its lightweight, visual, and adaptive characteristics to Agile work environments, CSD Matrix proves to be a practical approach that can fill the gap between formal documentation and the daily coordination needs of software development teams.
Implementation of a Decision Support System for Selecting the Best Employees Using the AHP-SAW Method Tantrik Ulil Lusianti; Abdul Rezha Effrat Najaf; Seftin Fitri Ana Wati
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2770

Abstract

This study develops a Decision Support System (DSS) to assist in selecting the best employees by combining the Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods. Manual employee evaluations often result in subjectivity and bias, potentially impacting fairness and strategic HR planning. Therefore, a structured and objective evaluation system is crucial to enhance decision-making accuracy. AHP is applied to determine the weight of each evaluation criterion through pairwise comparisons and consistency analysis, ensuring reliable and valid weight values. These weights are then used in the SAW method to normalize employee performance scores and compute the final rankings. The DSS is built using the Extreme Programming (XP) methodology, emphasizing iterative development and active user feedback to ensure usability and functionality. The evaluation process is based on five benefit-type criteria: Innovative, Creative, Experimental, Agile, and Visionary. Results indicate that Employee 2 achieved the highest final score of 95.58, and was selected as the best employee. Black-box testing was conducted to validate the system’s functionality, and all modules such as employee data input, criteria management, score computation, and ranking display performed correctly. This DSS promotes fairness, transparency, and accountability in performance evaluation and provides a scalable framework that can adapt to organizational needs. Future enhancements may include integrating data visualization and expanding criteria dynamically. Overall, the system supports strategic human resource decisions and ensures objective evaluations through a reliable and systematic approach.
Application Of Random Forest Algorithm in Music Recommendation System Using Content-Based Filtering Rubby Malik Fajar; Indra Yustiana; Alun Sujjada
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2803

Abstract

The rapid growth of digital technology has revolutionized how people access and listen to music, especially through online streaming platforms. However, the overwhelming number of available songs often confuses users, particularly new users who have no listening history. To address this, the study proposes a music recommendation system using a content-based filtering approach that recommends songs based on similarities in both textual and numerical features, such as genre, artist, lyrics, tempo, energy, and danceability. The system operates in two main stages. First, it classifies the popularity of songs into two categories, “High” and “Low,” using three classification algorithms: Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Second, it generates music recommendations based on content similarity using TF-IDF and cosine similarity. Random Forest is chosen as the main algorithm due to its superior performance in high-dimensional data and its ensemble learning mechanism. The evaluation uses confusion matrix metrics including accuracy, precision, recall, and F1 score, tested across multiple data split ratios (90:10, 80:20, 70:30, 60:40). The results show that Random Forest consistently delivers better classification and recommendation performance compared to KNN and SVM. It demonstrates higher accuracy and F1 score, making it suitable for real-world applications. The system is developed using Streamlit, allowing users to interactively receive music recommendations through a user-friendly web interface. The findings support the integration of Random Forest in content-based recommendation systems to improve accuracy and solve cold-start problems effectively in digital music platforms.
Comparison of K-means and DBSCAN Web- Based Food in Clustering Based on Nutritional Content Gina Purnama Insany; Anggun Fergina; Muhammad Ilham Juardi
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2813

Abstract

Food is the main energy source for the human body; however, poor dietary habits can lead to health risks such as obesity and cardiovascular diseases. Understanding the nutritional composition of food is essential to support healthier dietary decisions. Clustering food based on nutritional content can support personalized diet planning and assist healthcare professionals in recommending healthier food choices. This study applies clustering techniques to group foods based on their nutritional content specifically carbohydrate, calorie, protein, and fat levels using K-Means and DBSCAN algorithms. These unsupervised learning methods are suitable for analyzing numerical data without predefined categories. A key challenge in clustering is determining the optimal number of clusters; thus, evaluation methods such as the Elbow Method, Davies-Bouldin Index (DBI), and Silhouette Score were utilized. The K-Means algorithm achieved a Silhouette Score of 0.578 and a DBI of 0.661, indicating reasonably good clustering, though cluster separation was not optimal. In contrast, DBSCAN outperformed K-Means with a Silhouette Score of 0.626 and a DBI of 0.328, suggesting more compact and well-defined clusters. This indicates that DBSCAN formed more distinct and separated clusters, which is essential for effective grouping of foods based on nutritional similarity. The clustering results were deployed via an interactive web application using Streamlit an open-source Python framework enabling rapid development of lightweight web interfaces. This platform allows users to interactively explore clustering patterns through visualizations and tables, providing an intuitive tool to understand food groupings based on nutritional profiles
Sentiment Analysis of The Digital Population Identity (IKD) Using SVM and Decision Tree Methods M Sahrul Alfa Salam Shafrani; Eddy Nurraharjo
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2827

Abstract

The increasing integration of digital services in Indonesia has driven the development of the Digital Population Identity (IKD) application, aimed at enhancing citizen access to demographic data and optimizing administrative processes. This study explores public sentiment toward the IKD by analyzing 20,703 user reviews from the Google Play Store. Reviews were preprocessed using case folding, normalization, stopword removal, tokenization, and stemming, then transformed into numerical features using the Term Frequency-Inverse Document Frequency (TF-IDF) technique. Sentiment categories positive, neutral, and negative were determined based on user rating scores. Two machine learning algorithms, Support Vector Machine (SVM) and Decision Tree, were utilized due to their respective strengths: SVM for its effectiveness in handling high-dimensional text data and Decision Tree for its interpretability, which is relevant for public sector applications. Evaluation results indicate that the SVM model achieved an accuracy of 85.46%, while the Decision Tree attained 80.68%. Both models showed strong performance in detecting positive and negative sentiments, yet encountered challenges in classifying neutral sentiments due to data imbalance. These results demonstrate the potential of sentiment analysis as a practical approach for assessing public perception of digital government applications. The insights gained may support policymakers and developers in identifying service gaps, enhancing user experience, and formulating data-driven strategies to improve the delivery of digital public services in Indonesia.
Web-Based Employee Attendance System Utilizing Face Recognition And CNN Via Face-API.Js Muhammad Ikhsan Thohir; Ivana Lucia Kharisma; Ika
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2828

Abstract

There are still significant drawbacks to traditional attendance techniques, like those employed at PT Cloud Hosting Indonesia, including the possibility of fraud, imprecise data capture, and reliance on manual input. The goal of this project is to use Convolutional Neural Network (CNN)-based facial recognition technology, which is implemented using the Face-API.js package, to design and construct an online employee attendance system. To guarantee that attendance can only be completed within a specified office radius, the system is outfitted with geolocation validation. This system's practical advantages include lowering the workload of human resources personnel, increasing the precision of attendance records, and stopping the practice of entrusted attendance. In order to protect user privacy and minimize server load, the facial recognition procedure is carried out directly on the client side (browser). The Agile Scrum system development methodology, which is used iteratively to adapt to user needs, is combined with a quantitative approach in this study. The black-box method is used for testing, and a confusion matrix is used to evaluate performance. According to the test findings, all characteristics function as intended, and the system can identify user faces from 15 registered face samples with an accuracy rate of 86.67%. The efficiency, transparency, and security of this system are better than those of traditional attendance techniques and GPS-based biometrics alone. Face recognition technology and location validation combine to create a digital solution that is suitable, secure, and suitable for use in organizations with flexible or shift-based work schedules.
Prediction of Nile Tilapia Fingerling Production Using Multiple Linear Regression Alfiansyah Hidayat; Gina Purnama Insany; Zaenal Alamsyah; Evi Amriawati; Muhammad Nurdin
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2829

Abstract

The production of Nile tilapia fingerlings plays a crucial role in ensuring the sustainability of freshwater aquaculture systems, particularly in Indonesia, where tilapia is a major source of protein and livelihood. Accurate prediction of fingerling output can significantly enhance resource efficiency, reduce operational costs, and support economic sustainability in hatchery operations. This study aims to predict fingerling production based on environmental factors and feed quantity, using data from the Center for Freshwater Aquaculture Development (BBPBAT) in Sukabumi, Indonesia. Multiple Linear Regression (MLR) was chosen for its interpretability and suitability for modeling linear relationships in moderate-sized datasets. MLR was applied to model the relationship between water temperature, pH, dissolved oxygen (DO), ammonia concentration, and feed quantity with fingerling production. The dataset consisted of 147 historical records, and model performance was evaluated using R² = 0.836, Mean Absolute Error (MAE) = 35,664, Mean Squared Error (MSE) = 2,014,982,858, and Root Mean Squared Error (RMSE) = 44,852. These results indicate a strong predictive capability. Compared to baseline mean-based predictions, the model significantly reduces forecast error and captures the production variability more effectively. Furthermore, the model was deployed via an interactive web-based tool using the Streamlit framework. This application allows hatchery staff to input current environmental conditions and feed data to generate real-time production forecasts, facilitating proactive management and better resource planning. Overall, this study demonstrates that MLR is a practical and effective tool for supporting decision-making in aquaculture production systems.
Vulnerability Assessment of Information Disclosure in Bimasoft CBT Muhammad Hudzaifah Nasrullah; Tilly Raycitra Widya; Lilik Tiara Giantri; Duta Arief Christanto; Dede Cahyadi
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2838

Abstract

This research examines the security parameters of Bimasoft CBT, a prominent computer-based testing platform utilized extensively in Indonesia, particularly during the execution of UNBK and amid the Covid-19 pandemic. Although CBT systems present distinct advantages in terms of efficiency relative to traditional paper-based assessments, they concurrently introduce significant security concerns. This issue is particularly pertinent considering research indicating that students exhibiting high self-efficacy tend to be more inclined towards dishonest practices, potentially capitalizing on system vulnerabilities. The investigation concentrates on the “offline self-simulation” iteration of Bimasoft CBT, which permits autonomous hosting capabilities. The assessment methodology incorporated strategic planning, a technical examination of the system, identification of vulnerabilities utilizing tools such as Chrome DevTools and Burp Suite, and risk evaluation employing the CVSS 4.0 framework. The inquiry revealed two medium-risk vulnerabilities (CVSS score: 6.9) that jeopardize confidentiality, permitting students to access examination questions prior to login and secure tokens without the oversight of a supervisor. To address these concerns, three principal solutions are recommended: the implementation of back-end token validation, the restriction of access to examination questions via the WordPress REST API prior to login, and the avoidance of CSS for concealing critical content. These findings underscore the necessity of fortifying security within CBT systems to ensure equitable assessment, uphold academic integrity, and assist developers and policymakers in the advancement of digital examination platforms.
Multi-Step GRU Model for River Water Level Prediction with IoT Sensors Ahmad Satrio Perdana; Ade Silvia Handayani; Ciksadan Ciksadan; Carlos RS; Asriyadi Asriyadi
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2846

Abstract

The Simpang Lima PUPR Pump Station on Jalan Radial, Palembang, serves as a critical drainage point for the largest water discharge in the downstream area, making the surrounding region highly vulnerable to surface runoff and flooding, especially during short-duration high-intensity rainfall events. This study aims to develop a 24-hour ahead multi-step river water level prediction model using the Gated Recurrent Unit (GRU) algorithm, powered by real-time data from Internet of Things (IoT) sensors installed at the pump station. The collected dataset spans from June to July and includes water level, rainfall, temperature, humidity, and barometric pressure. The data was preprocessed through normalization before being used as input to the GRU model. The GRU-based prediction model demonstrated strong performance with a Mean Squared Error (MSE) of 0.394, Root Mean Squared Error (RMSE) of 0.628, coefficient of determination (R²) of 0.99, and Nash-Sutcliffe Efficiency (NSE) of 0.9853. These results indicate high predictive accuracy and model reliability. The proposed model has strong potential for integration into early warning dashboards to support flood mitigation strategies and improve the operational efficiency of pump stations in high-risk urban zones. Additionally, this research offers a data-driven framework for the Ministry of Public Works and Housing (PUPR) to design real-time, predictive flood control systems. The approach can optimize pump operations, enhance emergency response planning, and guide drainage infrastructure improvements. Furthermore, it promotes climate-resilient flood adaptation policies and serves as a model for smart technology deployment in other Indonesian cities.
Comparative Analysis Of Random Forest and Naive Bayes for Flood Classification Using Sentinel-1 SAR Clara Silvia Rotua Aritonang; Ade Silvia Handayani; Suroso Suroso; Wahyu Caesarendra; Asriyadi Asriyadi
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2852

Abstract

This research introduces a framework for classifying flood inundation utilising Sentinel-1 Ground Range Detected (GRD) radar imagery alongside machine learning algorithms.  Radar backscatter values from pre- and post-event Sentinel-1 images were processed with SNAP and QGIS to extract spatial features and change indicators in decibel (dB) format.  The tabular dataset, comprising 500,000 samples that equally represent flooded and non-flooded areas, was utilised for model training. Two models, Random Forest and Naive Bayes, were assessed for their classification efficacy.  The Random Forest model demonstrated exceptional performance, attaining an accuracy of 99.81%, precision of 99.75%, recall of 99.67%, and an F1-score of 99.71%.  Naive Bayes achieved an accuracy of 52.63%, with precision and F1-score notably impacted by elevated false positive rates, although recall was 86.36%.  Analysis of confidence distribution indicated that Random Forest exhibited low-confidence errors at the decision boundary, whereas Naive Bayes demonstrated confident misclassifications. Analysis of computation time indicated that Naive Bayes required less than 0.1 seconds per run, whereas Random Forest completed training in under 3 minutes.  The trade-off between speed and reliability underscores the appropriateness of Random Forest for operational flood mapping applications.  This research provides a practical comparison of classification models utilising open-access radar data and establishes a dependable pipeline for pixel-level flood identification.

Page 38 of 65 | Total Record : 642

 36   37   38   39   40 

Filter by Year

2018 2026


Reset
Filter By Issues
All Issue Vol. 8 No. 3 (2026): bit-Tech Vol. 8 No. 2 (2025): bit-Tech Vol. 8 No. 1 (2025): bit-Tech Vol. 7 No. 3 (2025): bit-Tech Vol. 7 No. 2 (2024): bit-Tech Vol. 7 No. 1 (2024): bit-Tech Vol. 6 No. 3 (2024): bit-Tech Vol. 6 No. 2 (2023): bit-Tech Vol. 6 No. 1 (2023): bit-Tech Vol. 5 No. 3 (2023): bit-Tech Vol. 5 No. 2 (2022): bit-Tech Vol. 5 No. 1 (2022): bit-Tech Vol. 4 No. 3 (2022): bit-Tech Vol. 4 No. 2 (2021): bit-Tech Vol. 4 No. 1 (2021): bit-Tech Vol. 3 No. 3 (2021): Remote Delivery Vol. 3 No. 2 (2020): Datamining Vol. 3 No. 1 (2020): Distance Learning Vol. 2 No. 3 (2020): Pandemik ICT Vol. 1 No. 3 (2019): Learning Synchronous and Asynchronous in the Industry 4.0 Vol. 2 No. 2 (2019): Support System Vol. 2 No. 1 (2019): Data Mining and Green Technology Vol. 1 No. 2 (2018): Data and Information Quality Vol. 1 No. 1 (2018): First Impression on Computing More Issue