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
 43   44   45   46   47 
Classification of Hand Gestures Using Random Forest and MediaPipe in an Educational Mathematics Game M. Ridha Ansari Adriansyah; Agus Suhendar
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.v8i2.3172

Abstract

Conventional mathematics learning at the elementary level often lacks interactivity, leading to low student motivation. This issue hinders the development of foundational analytical skills, despite significant time allocation in the curriculum. This research addresses this pedagogical problem by developing an educational game that replaces traditional input methods with kinesthetic interaction, aiming to directly enhance student engagement. The proposed method is a real-time hand gesture detection system built on a desktop platform. The system utilizes the MediaPipe framework to accurately extract 21 key hand landmarks from a live video feed, which serve as robust features for analysis. These features are then classified using a Random Forest algorithm, chosen for its efficiency and high performance in handling complex data, with an undersampling technique applied to ensure a balanced dataset. The performance evaluation showed that the developed classification model achieved a high accuracy of up to 98% on the test data. The resulting functional prototype allows users to answer addition and subtraction problems intuitively through hand gestures, featuring direct visual feedback and a score-tracking mechanism. This study successfully demonstrates that digital image processing can be effectively leveraged to create an engaging and adaptive mathematics learning experience. This approach not only addresses motivation in mathematics but also demonstrates the potential of gesture-based kinesthetic learning for designing a new class of engaging educational tools across various subjects, highlighting its broader impact on future educational game design.
Mobile-Based Book Recommendation System Based on Film Preferences Using Content-Based Filtering Nabil Anshari; Retno Mumpuni; Budi Mukhamad Mulyo
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.v8i2.3177

Abstract

The low reading interest among the Indonesian population remains one of the main challenges in improving national literacy quality. One contributing factor is the difficulty in finding reading materials that align with individual interests. Conversely, the increasing public interest in films can be leveraged as a bridge to foster reading habits. This study discusses the development of a mobile-based book recommendation system based on users’ film preferences to facilitate the discovery of books relevant to their favorite films. The proposed method here employs a Content-Based Filtering approach using Term Frequency–Inverse Document Frequency (TF-IDF) and Cosine Similarity to measure the similarity between film synopsis and book descriptions. Data are retrieved in real time through the integration of The Movie Database (TMDB) API and Google Books API. System evaluation was conducted using User Acceptance Testing (UAT) with ISO 9126 as the evaluation framework, focusing on functionality, usability, and reliability aspects. The results show that the application successfully provides relevant book recommendations based on users’ selected films, achieving functionality, usability, and reliability scores of 88%, 84%, and 86%, respectively. Therefore, the system is considered feasible for use and has the potential to serve as a literacy enhancement medium based on film preference.
Implementation of the Brocleanx Application for Optimizing Android Based Shoe Cleaning Management Ervin Khoirus Syifa' Uddin; Sulistyo Dwi Sancoko
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.v8i2.3179

Abstract

This research addresses operational inefficiencies within local service SMEs by detailing the development of a mobile booking application for the Brocleanx case study. The pre existing manual booking system resulted in significant inefficiencies and a lack of real time tracking. The innovation of this research lies in its integrated approach, which combines Location Based Service (LBS) for booking logistics accuracy with end to end service transparency through real time order status tracking. This study adopts a structured waterfall development methodology, encompassing requirements analysis, system design, implementation, and functional testing using the Black Box method. The resulting application enables customers to book pick up and delivery services, specify their location accurately via LBS for efficient logistics, and track order status in real time. Supporting features include transaction history and automated notifications. Developed using Flutter for the UI and Supabase as a Backend as a Service (BaaS), the application was validated through functional testing. This testing confirmed the successful operation of core functionalities, achieving an 85.7% pass rate. Findings indicate that the application successfully transformed manual business processes into a centralized digital system, significantly improving operational efficiency by addressing the previous 15% order data error rate and 10 minute administrative work time order, while simultaneously enhancing customer convenience through transparent monitoring. This study concludes that the LBS-integrated mobile booking application is an effective solution for improving service quality at Brocleanx. Furthermore, this implementation serves as a practical model for other local service SMEs seeking to digitize their operations by enhancing logistics efficiency and customer transparency.
Fuzzy C-Means Clustering of Regencies and Cities Based on Total Sanitation Society Ananda Azra Razali; Eva Yulia Puspaningrum; Henni Endah Wahanani
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.v8i2.3180

Abstract

The Community Based Total Sanitation (STBM) program is a national initiative designed to enhance public health by promoting clean and healthy living habits. However, its implementation in several regions, including East Java Province, continues to encounter a number of challenges, as several sanitation indicators have yet to reach the desired targets. This study aims to group the sanitation performance of regencies and cities in East Java using the Fuzzy C Means (FCM) algorithm and visualize the outcomes through thematic maps to provide clearer and more informative spatial insights. Six key indicators. Six key indicators CTPS, PAMMRT, PSRT, PLCRT, PKURT, and Healthy Home Access were analyzed as percentages, with variable selection and normalization conducted using the Min Max Scaler to ensure comparable value ranges across datasets. The clustering validity was assessed using the Davies Bouldin Index (DBI), where the lowest value of 0.9134 was achieved for three clusters, indicating the most optimal grouping configuration. The resulting clusters represent regions with high, medium, and low sanitation achievement levels, while spatial visualization reveals that lower-performing regions are largely concentrated in the eastern part and the Madura area. From a practical standpoint, the findings of this study can serve as a foundation for policy formulation, intervention prioritization, and more efficient resource allocation to improve regional sanitation performance in a focused and sustainable manner.
Integration Content-Based and Collaborative Filtering in AI-Based Culinary Recommendation For Community of Tangerang City Suwitno Suwitno; Ardie Halim Wijaya; Wiyono Wiyono
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.v8i2.3182

Abstract

The rapid growth of digital technology and the culinary industry in Tangerang presents new challenges for the community in finding suitable food options. Many users experience difficulties selecting restaurants or dishes that match their individual preferences, creating a need for a more intelligent and adaptive recommendation system. To address this problem, this study develops an AI-based culinary recommendation model that integrates CBF (Content-Based Filtering) and CF (Collaborative Filtering) approaches. The proposed hybrid system combines user behavior patterns with food attributes such as dish type, main ingredients, taste, and price. Data were collected from 90 respondents in Tangerang through questionnaires and interviews, containing user reviews, ratings, and restaurant information. Several hybrid strategies were implemented, including weighted, switching, feature combination, and cascade hybrid methods. Evaluation of system performance used Precision (73%), Recall (76.9%), MAE (0.49), and MSE (0.256). In addition, UAT(User Acceptance Testing) was applied to ensure that the developed system meets functional, usability, and business workflow requirements. The UAT result of 81.86% indicates that the system performs well, is easy to use, and aligns with user expectations. The resulting AI-driven recommendation model successfully provides more accurate, relevant, and personalized culinary suggestions for users. This research contributes to advancing the development of recommendation systems by addressing the limitations of standalone CBF and CF techniques. The proposed hybrid framework offers a practical solution to enhance user experience and strengthen the digital ecosystem of the culinary industry in Tangerang City.
IoT-Based Reverse Vending Machine with Deep Learning for Bottle Waste Management Asep Marzuki; Abdul Zaky; Bobi Handoko; Dela Qurota Mustieni; Novita Risyadi
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.v8i2.3183

Abstract

The escalating volume of waste, driven by insufficient public awareness and the lack of effective waste management systems, has become a significant environmental challenge. Improper waste disposal, particularly of non-biodegradable materials like plastics and metals, contributes notably to environmental pollution. In Riau Province, Indonesia, where the annual waste generation reaches 862,013 tons, only 60.71% is effectively managed. Despite the presence of 267 waste bank units, much of the plastic bottle and aluminum can waste remains improperly discarded. The high cost of commercially available Reverse Vending Machines (RVMs) further limits their widespread adoption, especially in regions like Riau. This study addresses these issues by proposing a cost-effective RVM that integrates Internet of Things (IoT) technology and a deep learning-based image classification model. The system enables users to exchange waste bottles for rewards through the Ecocycle mobile application, thus promoting waste sorting and recycling. The proposed model, tested on plastic and aluminum bottles, achieved 100% classification accuracy. Notably, this research bridges a critical gap by combining automated classification with IoT communication and incentive distribution in a low-cost, scalable system. The potential for this system to be expanded globally is evident, as it provides a feasible solution for large-scale waste management, particularly in regions lacking advanced waste infrastructure. Through both technological and behavioral approaches, this study contributes uniquely to the field of waste management by advancing accessible, effective solutions to foster environmental sustainability.
Comparison of Naive Bayes and Support Vector Machine in Sentiment Analysis of Siwaslu Application Trio Saputro; Arief Hermawan
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.v8i2.3184

Abstract

The 2024 General Election (PEMILU) in Indonesia introduced the SIWASLU application, which generated a large volume of unstructured user feedback on the Google Play Store. Efficiently analyzing this public sentiment is crucial for guiding rapid application enhancements, yet the sheer volume of raw data poses a significant challenge. The purpose of this study is to evaluate the performance of two classifications, Naive Bayes and Support Vector Machine (SVM), to identify the most effective model for sorting review sentiment into positive, neutral, and negative categories. This research offers novelty as it is applied to a comprehensive multi-class scheme, differing from previous research focused on binary classification and its evaluation of a hybrid feature approach for SVM. The methodology began with the collection of 3,632 reviews, followed by pre-processing and lexicon-based labeling. The naive bayes model was trained using CountVectorizer features, while the SVM model was trained using a combination of TF-IDF features, additional engineered features, and a weighting technique to handle imbalanced data. Evaluation results demonstrate that the SVM model was significantly superior, achieving 85% accuracy and a macro-average F1-score of 0.72, outperforming the NB model (78% accuracy and 0.60 F1-score). The superiority of SVM was evident in its ability to identify the minority class, achieving a 0.75 Recall score for neutral sentiment. Practically, the developed SVM model is robust enough to be integrated into a real-time monitoring dashboard for BAWASLU, providing an automated system to categorize public concerns and enable faster, data-driven improvements.
Implementation of Facebook Prophet Algorithm in Population Prediction Raditya Dimas Libriawan; Anggraini Puspitasari Sari; Henni Endah Wahanani
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.v8i2.3190

Abstract

The number of populations in a country is a very important aspect because it has a direct effect on various aspects of life. Indonesia is in the fourth position of the country with the largest population in the world. It is recorded in the Indonesian Central Statistics Agency (BPS) that by mid-2024, the population in Indonesia will reach 281.603.800 people. The ever-increasing population will drive increased energy demand. Therefore, monitoring and controlling population growth is a crucial and indispensable step, one of which is by utilizing machine learning to conduct time series forecasting. This study contributes by optimizing FB Prophet’s parameter configuration for population forecasting in Indonesia, achieving improved accuracy compared to traditional models. The purpose of this study is to determine the level of accuracy and error of the model with evaluation metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results obtained from forecasting using the Prophet algorithm were that Indonesia increased by 1.5% by the end of 2025, with the value of the MAE evaluation metric of 0.0244, RMSE of 0.0256, and MAPE of 2.65%, which indicates a highly accurate prediction level for annual population data.
Fine-Tuning YOLOv11 Architecture for Real-Time Object Detection on Mobile Devices for Visually Impaired Arsya Prima Al Azmi; Muhammad Fachrie
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.v8i2.3191

Abstract

Visual impairment presents significant challenges in daily navigation and environmental interaction, impacting personal independence and safety. This research addresses these challenges by developing "AllScan," a mobile application designed as a real-time visual assistant for the visually impaired. The system leverages the You Only Look Once version 11 (YOLOv11) architecture, a state-of-the-art object detection framework renowned for its balance of speed and accuracy, making it highly suitable for on-device implementation. To optimize performance, a comparative study was conducted by fine-tuning two model variants, YOLOv11n and YOLOv11m, on a specialized dataset specifically curated from Open Images V7. This dataset comprises 20 common object classes, with 1,000 images per class, and was used to evaluate the models under three distinct experimental conditions. The application, developed using the Flutter framework, processes a live camera feed, performs on-device inference with a TensorFlow Lite model, and provides auditory feedback via a Text-to-Speech (TTS) engine, enabling users to identify detected objects through real-time sound cues. Experimental results demonstrate that the fine-tuned YOLOv11m model, trained without data augmentation, achieved superior performance, scoring a mean Average Precision (mAP50) of 76.2% (a metric for general detection accuracy) and an mAP50-95 of 57.8% (a stricter metric for precise object localization). The final application provides a robust and efficient solution that can demonstrably enhance situational awareness and independence for visually impaired individuals in real-world environments.
Rice Leaf Disease Classification Using EfficientNetV2 with Hyperparameter Tuning Rizal Harjo Utomo; Mohammad Idhom; Trimono Trimono
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.v8i2.3194

Abstract

Rice is a strategic food commodity and a primary source of food security in many countries, including Indonesia. However, rice productivity often declines due to leaf diseases that remain difficult for farmers to identify manually with consistent accuracy. Deep learning–based artificial intelligence offers a promising solution for automatically detecting and classifying plant diseases in a more objective and reliable manner. This study implements the EfficientNetV2 model for classifying rice leaf disease images and enhances its performance through systematic hyperparameter tuning. The dataset includes rice leaf images obtained from field observations in Lamongan Regency combined with supplementary data from an open-access platform, representing several major rice diseases such as blast, bacterial leaf blight, brown spot, tungro disease, and healthy leaves. The model is trained using a transfer learning approach and evaluated using accuracy, precision, recall, and F1-score to ensure comprehensive performance assessment. The experimental results from this study demonstrate that hyperparameter tuning substantially improves model performance compared to the untuned baseline. The optimized EfficientNetV2 model achieves a final accuracy of 99%, with precision, recall, and F1-scores consistently reaching 0.97–1.00 across all classes, indicating strong robustness and generalization capability. This research contributes to the development of an automated diagnostic system capable of assisting farmers in identifying rice leaf diseases more quickly and effectively, while also supporting broader applications in smart agriculture. The findings underscore the potential of deep learning to enhance sustainable agricultural productivity through early detection and rapid decision-making support.

Page 45 of 65 | Total Record : 642

 43   44   45   46   47 

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