cover
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
ISSN : 2622271X     EISSN : 26222728     DOI : https://doi.org/10.32877/bt
Core Subject : Science,
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.
Articles 370 Documents
Digitization of Warehouse Stock Management Through Web-Based Information Systems Marpaung, Andreas Adiputra; Wijiyanto; Utomo, Bangun Prijadi Cipto
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2806

Abstract

Digitalization in warehouse stock management has become increasingly important, particularly for small and medium enterprises that still rely on manual recording methods. These traditional systems often lead to delays, data inaccuracies, and operational inefficiencies. This study aims to design and implement a web-based warehouse stock management information system to improve the recording process, increase accuracy, and support decision-making at Digital Connection, a company still using Microsoft Excel for inventory tracking. The system was developed using the waterfall method, which includes five structured stages: needs analysis, system design, implementation, testing, and maintenance. Functional testing was conducted through black box testing to validate the performance of all system features from a user perspective. The results demonstrate that the developed system enables real-time recording of incoming and outgoing goods, provides interactive data visualization through a dashboard, and issues automatic alerts for minimum stock thresholds. Compared to the previous manual system, the digital solution significantly enhances data accuracy, reduces the risk of duplication or loss, and speeds up reporting processes. This transition not only streamlines warehouse operations but also improves user responsiveness in stock management activities. In conclusion, the proposed information system offers an effective and adaptive approach for small businesses to transition from manual to digital warehouse management, contributing to operational efficiency and supporting broader digital transformation initiatives in logistics and supply chain environments.
IoT-Based Alcohol Presence Detection in Soy Sauce Using MQ-3 and ESP32 Almirah, Narita Tria; Taqwa, Ahmad; Salamah, Irma
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2811

Abstract

Ethanol is a compound that naturally forms during the fermentation process of products such as soy sauce, raising concerns about their halal status for Muslim consumers. This research develops an alcohol detection system based on the Internet of Things (IoT) that integrates an MQ-3 sensor, ESP32 microcontroller, and the Blynk mobile application. The MQ-3 sensor detects ethanol vapor, and the ESP32 processes the sensor data and transmits it via Wi-Fi, enabling real-time monitoring through both a 16x2 LCD display and the Blynk app. The system’s calibration process involves standard ethanol solutions with concentrations ranging from 0% to 10%. The sensor output is converted from analog-to-digital (ADC) values to voltage, parts per million (ppm), and percentage estimates. A regression analysis of the sensor data yielded the equation y = 684.59x + 3198.9, with an R2 value of 0.7288, indicating a moderate correlation between ethanol concentration and sensor readings. Using solutions with ethanol concentrations of 1% and 3%, a detection threshold of 5300 ppm was established. Testing on commercial soy sauce samples (0% and 3.08% ethanol) confirmed the system's ability to distinguish between products with and without detectable ethanol, validating its effectiveness. While not designed for precise quantitative analysis, this system offers a practical, economical, and portable solution for initial screening of alcohol in fermented food products, making it a valuable tool for halal product monitoring.
An Analysis of the Effectiveness of KAN and CNN Algorithms for Human Facial Emotion Classification Riswanto, Beny; Cahyo Edy Sahputro, Slamet
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2819

Abstract

Facial expression-based emotion recognition has various applications, including security, healthcare, human-computer interaction, and behavioral analysis. This study analyzes the effectiveness of the Kolmogorov Arnold Networks and Convolutional Neural Networks algorithms in classifying human facial expressions of emotion using the OSEMN. Experimental data were obtained from the FER-2013 dataset, which consists of 35,887 facial expression images categorized into seven primary emotions: happy, sad, angry, fearful, disgusted, surprised, and neutral. The CNN model was designed with four convolutional layers, while the KAN model used three convolutional layers and a B-spline-based approach to handle non-linear transformations. Evaluation was based on accuracy, precision, recall, F1-score, and computational efficiency. The results showed that CNN achieved higher accuracy but tended to overfit, particularly on emotion classes with imbalanced data distribution. On the other hand, KAN demonstrated more stable performance with lower computational resource consumption, making it more efficient for systems with limited power and memory. CNN was selected for its superior pattern recognition capability, while KAN was chosen due to its efficiency in resource-constrained environments. From the comparison, CNN performed better in detecting complex expressions, while KAN was more optimal in processing efficiency and classification stability. The choice of the most suitable algorithm depends on the specific needs of the system—whether prioritizing high accuracy (CNN) or computational efficiency (KAN). This study is expected to provide insights into the development of more adaptive and efficient deep learning-based emotion recognition systems for practical applications such as mobile devices, healthcare monitoring, and smart surveillance.
Naïve Bayes Algorithm Analysis For Student Graduation Timeliness Prediction Anwar, A. Nurul; Dani, Dani; Napila, Ade
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2825

Abstract

This study developed a student graduation prediction system using the Naïve Bayes algorithm, using PS1-PS4 scores, PK, and SKS as indicators of academic progress. This model achieved 88.33% accuracy and an ROC value of 0.900, indicating superior predictive ability. These results outperform other common models such as logistic regression and the C4.5 decision tree, which have approximately 85% accuracy in predicting student graduation. These results also outperform previous research in the same field, which had ROC values of approximately 0.85.Graduation predictions were categorized as "ON TIME" and "LATE" with high precision. The Naïve Bayes algorithm has proven effective in predicting student graduation, particularly in identifying factors that influence graduation timeliness, such as poor academic performance, difficulty completing final assignments, poor personal conditions, and lack of motivation and interest.By designing a graduation prediction system using the Naïve Bayes algorithm, this research aims to help educational institutions predict student graduation timeliness and provide appropriate interventions. This system can improve educational quality and reduce dropout rates, making it an important tool for educational institutions to improve graduate quality and achieve their academic goals.This research demonstrates that the Naïve Bayes algorithm can be an effective and accurate graduation prediction method, thus helping educational institutions develop strategies to improve educational quality and reduce dropout rates. Therefore, this research has the potential to significantly impact higher education institutions and assist them in achieving their academic goals.
Prototype of Monitoring and Controlling Rice Field Irrigation Based on Internet of Things Sudibyo, Heri; Asril; Rahman Sidiq, Andrey Eka
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2826

Abstract

The advancement of Internet of Things (IoT) technology has significantly impacted various sectors, including agriculture, by enabling automation and real-time monitoring. In rice farming, one persistent challenge is the reliance on manual irrigation, which often results in water waste, increased labor demands, and reduced crop yields due to delayed or inconsistent water management. This research aims to design and implement a prototype IoT-based irrigation system to address these inefficiencies. The proposed system allows farmers to remotely monitor and control water flow using a smartphone via the Telegram messaging application. Telegram is chosen for its ubiquity, cross-platform compatibility, and ease of use, making it accessible to farmers without specialized technical skills. The system uses an ESP32 microcontroller as the core processor, an HC-SR04 ultrasonic sensor to detect water levels, and an SG90 servo motor to automate the sluice gate mechanism. A 16x2 LCD is integrated for real-time field display. Telegram enables interactive control through command inputs (e.g., opening and closing gates) and automated notifications, providing continuous status updates. The system operates autonomously based on preset water level thresholds but also supports manual override. Testing results show that the system is responsive and accurate (within ±1 cm), and it significantly reduces the need for frequent field visits. This solution enhances irrigation precision, reduces labor, and contributes to better water resource management. By integrating commonly available digital tools with low-cost hardware, the prototype offers a practical and scalable solution for improving agricultural productivity, especially in remote rural areas.
Implementation of Content-Based Filtering in a Novel Recommendation System to Enhance User Experience Sanjaya, Imam; Sujjada, Alun; Pratama, Yudistira
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2833

Abstract

This study addresses a critical challenge in digital novel platforms: the difficulty of delivering personalized and accurate recommendations due to limited user interaction data. This limitation often leads to irrelevant or generic suggestions, which can diminish user engagement and hinder content discovery. The significance of solving this issue lies in enhancing user experience by ensuring that readers are presented with novels that truly align with their interests, even in the absence of extensive behavioral data. To overcome this problem, the study proposes an innovative hybrid recommendation system that integrates Content-Based Filtering (CBF) with the Random Forest algorithm. The system generates personalized recommendations by analyzing novel attributes such as title, genre, score, and popularity. The methodology involves extracting features from textual data using Term Frequency-Inverse Document Frequency (TF-IDF), followed by the calculation of cosine similarity to assess title relevance. These similarity scores are then combined with popularity predictions derived from the Random Forest model to produce final recommendations that reflect both content similarity and statistical relevance. The proposed system demonstrates strong performance, achieving an accuracy of 94.0%, precision of 81.4%, recall of 80.3%, and an F1-score of 80.8%. These results underscore the system’s capability to deliver accurate and diverse suggestions. By enhancing personalization and addressing the limitations of conventional CBF systems, this hybrid approach offers practical value for digital novel platforms. It serves as an effective tool for improving content discovery, increasing reader satisfaction, and supporting user retention in content-rich environments.
Adoption of ShopeePay Among Indonesian Gen Z Women: A UTAUT-Based Evaluation Anidew, Nadilla; Arista Pratama; Asif Faroqi
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2840

Abstract

This study investigates factors influencing the adoption and utilization of ShopeePay, a digital wallet integrated within the Shopee e-commerce platform, among Generation Z women in Indonesia. Given this demographic group's active engagement in digital transactions, identifying key behavioral factors underlying their adoption of mobile payment technologies is essential. Guided by the Unified Theory of Acceptance and Use of Technology (UTAUT), this research examines core determinants of behavioral intention toward ShopeePay, additionally incorporating trust, perceived security, and network externalities into the analytical framework. Employing a quantitative research methodology, the study utilized an online structured survey involving 160 female respondents aged between 18 and 27 years who actively use ShopeePay. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS version 4.1.0.9. Findings demonstrate that performance expectancy, social influence, and perceived security significantly and positively affect behavioral intention to adopt ShopeePay. Trust indirectly influences intention through its impact on performance expectancy. Interestingly, effort expectancy and facilitating conditions did not demonstrate significant direct effects on behavioral intention. These results underscore that Gen Z female users prioritize application performance, social recommendations, and perceived safety when selecting digital payment solutions. Practically, these insights inform e-wallet developers and marketing professionals in designing targeted functionalities and marketing strategies aligned with user expectations and digital habits. Moreover, this study contributes to existing academic literature on mobile payment adoption and offers strategic implications for enhancing user acceptance, particularly among young female consumers in Indonesia.
Implementation of IOT-based Motorcycle Security System with Cut Off Engine and Mobile Application Insany, Gina Purnama; Alawiyah, Sindi Aulia; Somantri; Septian, Deni Ramdan; Iyusmani
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2841

Abstract

The increasing rate of motorcycle theft highlights the limitations of conventional security systems such as mechanical alarms and double locks, which often fail to provide proactive protection. This research proposes an Internet of Things (IoT)-based motorcycle security system integrating an engine cut-off feature, GPS tracking, vibration detection, and real-time notifications via a custom mobile application. Unlike previous solutions that commonly rely on SMS gateways or third-party services, this system leverages the Wemos D1 Mini microcontroller and Firebase Realtime Database to enable high-speed, two-way communication between the vehicle and the user. The system allows real-time vehicle location monitoring, remote engine control, and immediate detection of suspicious activities through the SW-420 vibration sensor connected to an audible buzzer alarm. The Android application, developed independently using the Kodular platform, not only provides digital vehicle location mapping but also enables quick engine deactivation and emergency alerts within seconds. Laboratory and field tests confirm a response time of less than one second for the engine cut-off function and accurate GPS tracking with an average deviation of under 10 meters. The primary innovation of this study lies in the full integration of IoT components, mobile interfaces, and cloud databases into a single platform without external dependencies, thereby enhancing efficiency, reliability, and system flexibility. The results demonstrate the system’s potential to deliver adaptive and modular vehicle security solutions, with opportunities for future enhancements such as geofencing, biometric authentication, and hybrid connectivity for improved resilience.
Building a School Guest Book Information System Using the Waterfall Method Subhana, Muhammad
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2847

Abstract

The increasing volume of data on human activities has resulted in a growing number of visitors to schools, particularly in the western part of Rangkasbitung, Lebak, Banten. Prospective parents visit the RA (Raudhatul Athfal) institution to enroll their children in school, pay monthly administration fees, and engage in educational activities with various general visitors. This influx poses several challenges for school administration and security, especially since visit records are still maintained manually, leading to data loss, difficulties in accessing visit histories, and limitations in monitoring guests, including parents and vendors. This issue impacts the transparency of school activity records. To address this, the research proposes a web-based school booking system to record visitor data based on the purpose of the visit, thus allowing for more effective data access and preliminary analysis in the event of an incident. This system is developed using the waterfall method, which is chosen for its structured concept, suitable for small to medium-sized school environments. Each phase consists of needs analysis, design, implementation, testing, and maintenance, carried out sequentially. Evaluation using a Likert scale from 104 respondents (determined by Slovin's formula) showed the Daily Report feature scored highest at 3.81, while the Weekly Report was lowest at 3.04. Maintenance tests found input validation and weekly report printing less smooth (2.84 and 2.69). Overall, the system effectively supports visitor monitoring with accessible features.
Comparative Analysis of Machine Learning Algorithms for Predicting LQ45 Stock Index Prices Hidayat, Amin; Ade Putra Prima Suhendri
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2853

Abstract

An essential metric for assessing the success of the country's capital markets is the LQ45 index, which is made up of 45 stocks with the biggest market capitalization and liquidity on thb e Indonesia Stock Exchange. Stock price prediction, particularly in volatile markets, remains complex challenge that benefits from advanced analytical approaches. While machine learning (ML) techniques have demonstrated significant promise in financial forecasting, comprehensive comparative evaluations across multiple algorithms and preprocessing strategies remain limited. In order to evaluate the predictive performance of nine machine learning algorithms Random Forest, Decision Tree, AdaBoost, Support Vector Classifier (SVC), XGBoost, Naive Bayes, K-Nearest Neighbors (KNN), Logistic Regression, and Artificial Neural Networks (ANN) in predicting the direction of movements of the LQ45 index, this study presents a structured comparative framework. The models are trained using a 10-year historical dataset, incorporating both continuous and binary representations of technical indicators. Three data preprocessing approaches are explored: raw trading data, unsmoothed indicators, and smoothed indicators. Accuracy, precision, recall, F1-score, and ROC AUC are all important factors in model evaluation. The findings show that when applied to continuous data with smoothed technical indications, Random Forest and XGBoost produce the best prediction results. For binary classification tasks, Naive Bayes emerges as the most effective model. These results demonstrate how important data representation and preprocessing in particular, smoothing are to enhancing the accuracy and robustness of models.  Research aids in the creation of trustworthy, data-driven stock prediction tools that are suited for developing markets.  Financial analysts, portfolio managers, and algorithmic traders looking to improve investment strategies through well-informed model selection and preprocessing design can benefit from the findings.