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
 49   50   51   52   53 
Autoimmune Skin Disease Image Classification using EfficientViT-M1 with AdamW Optimizer Hafiyan Fazagi Adnanto; Anggraini Puspita Sari; Achmad Junaidi
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.v8i2.3300

Abstract

Diagnosing autoimmune skin diseases is a clinical challenge because several conditions share overlapping visual characteristics. This study evaluates the EfficientViT-M1 model trained with the AdamW optimizer to classify images from five autoimmune skin disease categories. The dataset contains 3,336 images before augmentation and is divided into 60 percent training, 20 percent validation, and 20 percent testing to ensure stable evaluation and reduce overfitting. The model is trained for 50 epochs with a learning rate of 0.0001, and experiments using batch sizes of 64, 128, and 256 are conducted to analyze the impact of data processing on performance. Performance is measured using accuracy, precision, recall, and F1-score derived from confusion matrix results. The best performance appears at a batch size of 64, achieving 89.25 percent accuracy along with balanced precision, recall, and F1-score. These results show that EfficientViT-M1 can extract relevant lesion features while maintaining computational efficiency. A notable challenge emerges when distinguishing visually similar disease classes, particularly Psoriasis and Lichen, which often share comparable textures and color patterns that contribute to misclassification. This highlights the influence of dataset imbalance and visual overlap on prediction outcomes. The approach offers potential value for clinical practice, especially in underserved areas where automated decision support can help early screening when specialist access is limited. The model demonstrates encouraging potential as a resource-efficient tool for dermatological assessment. Future improvements may include increasing dataset diversity, incorporating clinical metadata, and exploring alternative optimization strategies to enhance diagnostic reliability.
Comparison of Batch Size Values in MobileNetV2 for Stroke Classification Using CT Scan Images Ajeng Listya Devani; Anggraini Puspita Sari; Afina Lina Nurlaili; Nurul Hidajati
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.v8i2.3301

Abstract

Stroke is still one of the world's leading causes of death and permanent disability, necessitating a quick and precise diagnosis in order to choose the best course of treatment.  The purpose of this study is to examine how different batch size configurations affect the MobileNetV2 architecture's ability to classify stroke types from CT-scan brain pictures. The dataset comprises three categories Normal, Ischemic, and Bleeding sourced from Kaggle and RSUD Haji, East Java Province. The strategy to transfer learning was used utilizing pretrained ImageNet weights, with the network fine-tuned for stroke classification tasks. Experimental testing was conducted using three batch size configurations: 16, 32, and 64, while maintaining consistent hyperparameters for other training components. Among the assessment measures were accuracy, macro F1-score, and AUC (macro) to measure performance comprehensively. The results revealed that a batch size of 16 achieved the highest overall performance, with an accuracy of 96.14%, a macro F1-score of 96.15%, and an AUC of 99.62%, outperforming larger batch configurations. These findings indicate that smaller batch sizes enhance model generalisation and improve gradient update dynamics, enabling the CNN to better capture subtle patterns within CT-scan images. Thus, our study finds that the best trade-off between convergence speed and batch size is 16., model generalisation, and diagnostic accuracy, demonstrating the effectiveness of the MobileNetV2 architecture for automated stroke detection based on CT-scan imaging
UI/UX Development of a Boarding House Reservation Application: A Design Thinking Approach in Surabaya Azizatul Fara Dibah; Abdul Rezha Efrat Najaf; Prasasti Karunia Farista Ananto
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.v8i2.3320

Abstract

Fragmented, inconsistent, and frequently outdated information about boarding-house availability, facilities, and pricing remains a persistent usability problem in existing digital platforms. Current UI/UX and reservation-system research has not sufficiently addressed these issues within the specific context of urban rental ecosystems, creating gap in designing solutions that respond to the needs of both tenants and property owners. This study addresses that gap by developing and evaluating a user-centered interface for a boarding-house reservation application using the five-stage Design Thinking framework: empathize, define, ideate, prototype, and test. Insights were gathered from 30 participants representing owners, tenants, and administrators in Surabaya, forming the basis for personas, information architecture, user flows, and low- to high-fidelity prototypes designed in Figma. Usability and interface quality were examined through task-based testing, the System Usability Scale (SUS), and Nielsen’s heuristic evaluation to integrate both user perception and normative usability standards. Initial testing produced SUS scores of 74.5 (owners), 76.5 (tenants), and 66 (administrators), indicating acceptable but improvable usability and several interface issues. Iterative refinement led to marked enhancements, with second-round SUS scores of 90, 87, and 89, accompanied by high learnability (96–97%), strong memorability (95–96%), and low error rates (0.0306–0.0800). A minor efficiency decrease was attributed to unstable network conditions rather than design flaws. Overall, the findings demonstrate that structured, iterative UI/UX development supported by heuristic auditing effectively resolves core information and interaction challenges in boarding-house reservation systems. The final prototype demonstrates high usability and provides a replicable design rationale for future implementation and scaling.
QR Code-Based Ordering and Reservation System Design to Improve Cafe Operational Efficiency Berlian Putri Zezar; Anna Dina Kalifia
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.v8i2.3325

Abstract

The increasing demand for service efficiency and digital interaction in the food and beverage industry has driven businesses to adopt technological innovations that streamline ordering processes. Manual order-taking often results in long queues, inaccurate recording, and reduced customer satisfaction, emphasizing the need for digital transformation. This study aims to design and implement a QR Code-based ordering and reservation system that enhances operational efficiency and minimizes human error in café service management. The research employs a Prototyping development method consisting of five stages: data collection, system requirement analysis, interface design, prototype implementation, and functional testing. The system is developed as a web-based application that allows customers to place orders and make reservations independently through QR Code scanning. Testing results show that the system functions effectively across all core features, reducing customer waiting time and eliminating manual recording errors. The integrated reservation feature also improves table management and staff coordination. Unlike most prior QR Code-based systems that focus only on menu ordering, this study introduces an integrated, responsive web platform combining ordering and reservation in a unified workflow. The developed prototype addresses inefficiencies in manual service operations while demonstrating measurable improvements in speed, accuracy, and user satisfaction. This integration represents the main contribution of the research, providing a distinctive model for enhancing digital café operations through user-centered design. The study contributes to the advancement of digital ordering systems and offers both practical and academic implications for future F&B digitalization initiatives
An Optimized Demand Response-ARMA Model for Inventory Management Under Intermittent Product Demand Vedano Gustine; Sandi Tendean; Jimmy Tjen
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.v8i2.3326

Abstract

Forecasting accuracy serves a crucial role in supply chain management, especially in calculating safety stock and purchase limit, particularly under demand fluctuations such as those observed for air filter products, which are characterized as slow moving and intermittent. The DR-ARMA method was designed to model sparse data effectively, despite the model heavily relies on manual tuning factor selection. In this case, the model still face limitation in handling intermittent demand. To address such methodological gap, this study proposes an optimized version of the Demand Response-ARMA (DR-ARMA) model which is able to handle intermittent demand, named Optimized Demand Response-ARMA (ODR-ARMA) by applying optimization problems that lead to an adaptive error multiplier factor. Using air filter sales data with a sparsity level of 62.3% and a varying lead time assumption from a company located in Pontianak. The comparative analysis of ODR-ARMA against LSTM, GBRT, and DR-ARMA reveals that the ODR-ARMA model demonstrates the best performance for both safety stock and purchase limit calculations with an average accuracy of 81.11% and 96.09%, respectively. The optimization results in a significant improvement, as the DR-ARMA model achieves an average accuracy of 51.26% for safety stock calculation and 30.48% for purchase limit calculation. As the ODR-ARMA model has the capability to generate an accurate demand forecast and requires low computational resources, this model can be used as a basis for enterprises, especially SMEs in decision making related to inventory management, which allows enterprises to avoid the risks of stockout, excess stock, and dead stock.
Application of the First Come First Served Method in the Mobile-Application System Muhammad Andi Syaifullah; Lilis Nur Hayati; Lutfi Budi Ilmawan
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.v8i2.3331

Abstract

Royal Cafe Makassar still relies on a manual system for managing queues and processing orders, which leads to long waiting lines, delayed service, and frequent recording errors. This study aims to design and implement a mobile-based queue management application using the First Come First Served (FCFS) method to create a more efficient, structured, and transparent ordering process. System development follows the Waterfall model, consisting of requirement analysis, system design, implementation, testing, and maintenance phases. The application provides features for registration and login, digital menu browsing, ordering, payment processing, queue monitoring, and a role-based workflow involving administrators, baristas, and waiters. Functional validation is conducted using black-box testing, while usability evaluation employs the System Usability Scale (SUS). The results show that every major function of the application operates according to the specified requirements. The SUS evaluation, involving 73 respondents, yields an average score of 82.35, which falls into the “very good” and “acceptable” categories, indicating high usability and user satisfaction. The FCFS mechanism effectively addresses operational issues by ensuring fair and consistent service order based on customer arrival time, reducing manual workload, and minimizing ordering errors. Overall, the developed system provides a practical digital solution for improving café service efficiency and can serve as a reference model for similar small-scale businesses adopting queue management applications.
Web-Based Citrus Fruit Disease Detection Application Using MobileNet V2 for Agricultural Quality Assurance Nasrul Hidayah; Adam Muiz; Dede Sunandar
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.v8i2.3338

Abstract

Precision disease detection in citrus commodities has become increasingly essential within the framework of Agriculture 4.0, particularly for small-scale vendors who still rely on manual visual inspection that is often inconsistent and error-prone. This study develops and evaluates a web-based citrus fruit disease detection system using the MobileNet V2 Convolutional Neural Network architecture. The methodological novelty of this work lies in the integration of an optimized MobileNet V2 model enhanced through targeted data augmentation and lightweight fine-tuning into an end-to-end web ecosystem that supports two inference modes: static image upload and real-time webcam-based detection, tailored to the operational needs of small vendors. The system classifies citrus fruit images into four categories: Black-Spot, Citrus Canker, Greening (Huanglongbing), and Fresh, using more than 1,000 augmented images standardized to 224×224 pixels with an 80:20 train–test split. Experimental results show that the model achieves an accuracy of 96.21%, with consistently high precision and recall across disease classes, while the Fresh class exhibits relatively higher misclassification due to visual similarity with early-stage symptoms. The Flask-based web application demonstrates stable performance under black-box testing and delivers rapid, high-confidence predictions. These findings affirm the effectiveness of lightweight CNN approaches in improving fruit quality inspection accuracy, reducing sorting errors, and supporting more efficient workflows for local vendors.
An SMOTE-Optimized MLP Approach for Classification of Diabetes Health Status Ferry Trilaksana Putra; Eva Yulia Puspaningrum; Muhammad Muharrom Al Haromainy
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.v8i2.3340

Abstract

Diabetes mellitus requires accurate classification systems to support early detection and clinical decision-making. Prior research has explored the use of Multilayer Perceptron combined with SMOTE, yet the methodological gap remains in evaluating its effectiveness on multiclass clinical datasets with significant class imbalance, particularly for the Prediabetes category. This study addresses that gap by examining the performance of an MLP model enhanced with SMOTE to improve overall accuracy and minority-class detection. The dataset includes age, gender, blood pressure, random blood glucose, weight, and height as clinical predictors. The preprocessing pipeline consists of label encoding for categorical variables, feature standardization, and the application of SMOTE to balance class distribution. The evaluation follows a consistent 80 10 10 split for training, validation, and testing, with three repeated experimental runs to ensure result stability. On the original imbalanced dataset, the MLP achieved an accuracy of 85 percent and showed limited capability in identifying Prediabetes. After applying SMOTE, accuracy increased to 91 percent, accompanied by notable improvements in recall and F1 score across all health status categories. These results demonstrate that SMOTE enables the model to capture non-linear patterns in minority classes and strengthens overall generalization. The proposed model can be integrated into clinical screening workflows as a decision-support tool. Its predictions can help clinicians identify at-risk individuals earlier, prioritize follow-up actions, and enhance patient management in healthcare settings.
Design and Development of a Web-Based Boarding House Management Information System Using RAD Method Mohamad Ilham Praditya Arifatul Nesta; Abdul Rezha Efrat 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.v8i2.3342

Abstract

The rapid growth of urban migration in Indonesia, particularly among students and workers, has increased the demand for efficient and integrated boarding house management systems. However, many boarding house businesses still rely on manual processes for tenant registration, payment tracking, and data recording, leading to inefficiencies and data inaccuracies. This study aims to design and develop a web-based boarding house management information system to optimize operational performance and enhance service quality for both owners and tenants. The system was developed using the Rapid Application Development (RAD) method, which emphasizes iterative prototyping, user involvement, and rapid feedback to ensure functional alignment with user requirements. The application was built with ReactJS for the frontend, ExpressJS for the backend, and PostgreSQL as the database, integrated with the Midtrans payment gateway to enable secure, real-time transactions. A key contribution of this study is the combination of RAD methodology with Midtrans integration, providing a scalable and user-friendly solution for small-scale property management. The system’s functionality was tested using Black Box Testing, confirming that all features operated correctly according to design specifications. The results demonstrate that the system successfully streamlines management workflows, reduces human error by 25%, and improves the user experience by reducing administrative processing time by 30%. This study contributes to the digital transformation of small-scale property management by demonstrating the feasibility of using low-cost, scalable technologies to enhance operational efficiency and service transparency.
Application of Transfer Learning for Breast Tumor Classification Adinda Putri Budi Saraswati; Anggraini Puspita Sari; Afina Lina Nurlaili
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.v8i2.3343

Abstract

Breast tumor classification from mammogram images plays an essential role in supporting clinical decision-making, particularly because manual interpretation is often challenged by variations in breast tissue density and suboptimal image quality. This study develops a three-class classification model for normal, benign and malignant categories using the ResNet50 architecture with a transfer learning strategy on the mini-MIAS dataset, which contains 322 images with an imbalanced class distribution. Three optimizers are compared, namely Adam, RMSProp and SGD. Adam represents an adaptive moment-based optimization approach. RMSProp emphasizes stable updates under fluctuating gradients. SGD with momentum serves as a conventional baseline relying on direct gradient updates. The model is trained using a 60 percent training and 40 percent validation split with class weighting and evaluated through accuracy, AUC and F1-score metrics. Experimental results show that Adam achieves the highest performance with 68.27 percent accuracy, 88.58 percent AUC and an F1-score of 0.68. RMSProp attains 58.63 percent accuracy, 76.05 percent AUC and an F1-score of 0.59. SGD yields the lowest performance with 44.18 percent accuracy, 61.33 percent AUC and an F1-score of 0.44. Confusion matrix analysis for the Adam configuration indicates reasonably consistent recognition across all classes, although misclassification remains present. The findings demonstrate that adaptive optimizers are more effective for training ResNet50 on small and imbalanced mammogram datasets. This study provides a foundation for developing more reliable computer-aided diagnostic systems for early breast cancer detection.

Page 51 of 65 | Total Record : 642

 49   50   51   52   53 

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