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
 46   47   48   49   50 
Intelligent Detection of Spermatozoa Motility Using YOLOv5: Toward Efficient and Accurate Male Fertility Analysis Christina Halim; Wahyu Syaifullah JS; Kartika Maulida Hindrayani; I Gede Susrama Mas Diayasa
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.v8i2.3231

Abstract

Detecting multiple spermatozoa in microscopic videos remains a complex challenge due to their small size, high velocity, frequent overlap, and inconsistent illumination. This study introduces an enhanced real-time detection framework using the YOLOv5 deep learning algorithm, representing a significant advancement over previous Computer-Assisted Sperm Analysis (CASA) systems that primarily relied on classical image processing or earlier YOLO versions (e.g., YOLOv3, YOLOv4). Unlike these predecessors, the proposed YOLOv5-based model integrates Cross Stage Partial (CSP) architecture and optimized feature pyramid networks, allowing for superior detection of small, fast-moving spermatozoa with reduced computational complexity and model size. A curated dataset of sperm motility videos was processed through standardized steps—frame extraction, contrast enhancement, and manual annotation—to ensure uniformity and data quality. The model, trained via transfer learning on images of 640×640 pixels over 50 epochs, achieved a precision of 0.6333, recall of 0.627, and mAP@0.5 of 0.618, while maintaining real-time performance at 93 frames per second (FPS). Compared to YOLOv4, the proposed framework reduced training time by two-thirds (from 3 hours to 1 hour) and decreased model size from 244 MB to 13.8 MB, without compromising accuracy. These improvements establish YOLOv5 as a lightweight and scalable AI model for sperm detection, enabling automated, objective, and reproducible motility assessment. Clinically, this approach enhances the precision and consistency of male fertility diagnostics, paving the way toward AI-driven reproductive health evaluation and more accessible fertility screening solutions in both advanced and resource-limited laboratory settings.
Optimizing the ResNet50 Model with Five Optimizers for Detecting Rice Leaf Diseases Muchammad Syamsu Huda; Henni Endah Wahanani; Fetty Tri Anggraeny
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.v8i2.3232

Abstract

Rice (Oryza sativa) productivity is frequently threatened by foliar diseases such as Bacterial Leaf Blight, Brown Spot, Blast, and Tungro, which are often visually indistinguishable. This study achieved a high classification accuracy of 97.05% in detecting these diseases by optimizing the ResNet50 architecture with five optimizers Adam, Nadam, Adamax, RMSprop, and SGD and identifying Adamax as the most effective. Using transfer learning with ImageNet weights and data augmentation, the model was trained and validated on 4,400 labeled images from Kaggle, partitioned in a 70:20:10 ratio for training, validation, and testing. The methodological framework integrates three layers of innovation: (1) optimizing a deep residual CNN with comparative adaptive and non-adaptive optimizers; (2) employing transfer learning to accelerate convergence and reduce overfitting; and (3) deploying the best-performing model into an Android-based mobile application for real-time field detection. Results demonstrate that adaptive optimizers substantially enhance ResNet50’s learning stability and generalization compared to traditional methods. The Adamax variant exhibited the most stable convergence and minimal validation loss, proving effective for fine-grained visual differentiation between similar disease patterns. This research advances the current state-of-the-art in agricultural image classification by providing a systematic optimizer evaluation within a CNN transfer learning framework and extending its practical usability through mobile deployment. Future studies should address model compression, real-time inference optimization, and cross-crop generalization to strengthen the scalability of AI-assisted disease diagnosis in precision agriculture.
Black Hat SEO Detection Using Ensemble Learning and Multi-Dimensional Web Content Analysis Akhmad Zaqi Riyadi; Sri Wulandari
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.v8i2.3238

Abstract

The integrity of search engines is significantly threatened by manipulative Black Hat SEO (BSEO) tactics, particularly the hidden injection of illicit content such as online gambling. This issue is critically urgent in Indonesia, where attackers frequently compromise government domains (.go.id). By September 2023, over 9,000 such sites had been infiltrated using stealthy defacement and semantic confusion highlighting a gap in existing detection systems that rely on single-dimensional features or ignore real-world class imbalance. To address this, we propose an ensemble learning based detection system combining Random Forest (RF) and Support Vector Machine (SVM), supported by multi-dimensional feature engineering from URLs, meta-tags, hidden CSS/HTML elements, and high-risk keywords (e.g., “slot”, “judi”). Our manually annotated dataset comprises 582 .go.id URLs with a natural 4:1 class imbalance, mitigated via Random Oversampling during training. Evaluation on a balanced test set (146 samples) shows 93.8% ensemble accuracy, 99.6% AUC-ROC, and most critically 100% recall for the Black Hat class, ensuring minimal false negatives. The system also incorporates an internal “override logic” that flags evasion tactics like cloaking or hidden keyword injection, enhancing interpretability. Unlike deep learning alternatives that require large data and computational resources, our approach balances performance, efficiency, and transparency making it suitable for deployment by national cybersecurity agencies. This work advances both academic research and practical defense capabilities against sophisticated BSEO threats targeting public-sector websites.
Development of a Web-Based Information System to Digitalize Florist SME Operations Marlinda Marlinda; Khusnul Khotimah
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.v8i2.3239

Abstract

Small and medium enterprises (SMEs) often face inefficiencies due to manual business processes that result in data redundancy, high error rates, and delayed service delivery. Queen Flower Shop in North Lampung exemplifies these challenges, as it continues to record transactions and inventory manually, reducing productivity and decision-making accuracy. This study addresses this problem by developing a web-based information system designed to digitalize florist operations and enhance overall business performance. The system was developed using the Waterfall model, comprising five sequential stages—requirements analysis, design, implementation, testing, and maintenance. Implemented through the CodeIgniter 4 framework based on the Model–View–Controller (MVC) architecture and supported by a MySQL database, the system integrates modules for user authentication, product management, online ordering, and automated reporting. Black-box testing validated that all features operated as expected, achieving a 100% success rate. Quantitatively, system implementation reduced average transaction processing time by approximately 45% and eliminated recurring data duplication errors. These outcomes demonstrate that the developed system significantly improves operational efficiency, data accuracy, and user satisfaction while ensuring modularity and scalability for future enhancements. The study contributes a practical and replicable model for SME digitalization, particularly in the creative and retail sectors, promoting transparency, competitiveness, and long-term sustainability in the digital economy.
Online Catering Booking Application Based on Web-Based and Mobile Budget Amanda Aprilina; 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.v8i2.3240

Abstract

The rapid advancement of information technology has encouraged digital transformation across various service industries, including the catering sector. Many small and medium enterprises (SMEs) still rely on manual ordering systems that often lead to data inaccuracies and inefficient service operations. To address these challenges, digital-based solutions are needed to streamline transactions, improve service accuracy, and enhance customer experience. This study aims to develop an integrated web and mobile-based catering ordering information system equipped with a budget-based ordering feature that allows users to select menus according to their financial capacity. The system was developed using the Waterfall model as the main framework, encompassing stages of requirement analysis, system design, implementation, and testing. The backend was built with Laravel framework, while the mobile application used React Native, ensuring real-time synchronization through a centralized API. The interface design applied Bootstrap and CSS to achieve responsiveness and usability across devices. System testing was conducted using the Blackbox Testing method to evaluate functional accuracy from the user’s perspective. Unlike previous systems that focus only on integration, this study introduces a budget-based filtering mechanism that dynamically adjusts menu recommendations to user-defined spending limits, enhancing personalization and affordability. The implementation results show that the system operates effectively and consistently across both platforms, enabling seamless order, payment, and confirmation processes. In conclusion, the proposed system successfully combines cross-platform integration with budget-based personalization, providing an efficient, reliable, and adaptable model for digital transformation in catering service management.
Implementation of PSO Optimization on the LightGBM Algorithm for Air Pollution Classification Muchamad Dicky Alifiansyah; Ani Dijah Rahajoe; Eva Yulia Puspaningrum
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.v8i2.3243

Abstract

The survival of living things is highly dependent on the important role of air. Clean air that is free from pollution is a standard for a quality environment that supports life. The Machine Learning approach can be an alternative in conducting data-based air pollution monitoring to assist in making the right decisions to deal with air pollution early on. This research aims to optimize the performance of the Light Gradient Boosting Machine (LightGBM) algorithm in air pollution classification combined with PSO optimization. The LightGBM or Light Gradient Boosting Machine algorithm is a Gradient Boosting algorithm that has decision tree-based learning, but in its application, LightGBM is prone to overfitting because it is sensitive to hyperparameters. Therefore, optimization techniques are needed to maximize performance. Particle Swarm Optimization (PSO) is an optimization method inspired by the movement of flocks of birds searching for optimal solutions. The data used is the Air Pollution Standard Index data. The research method includes data collection, data preprocessing, splitting the data, PSO optimization, model training, and model evaluation. The results show that PSO optimization can improve the performance of the LightGBM model. The LightGBM model with PSO optimization produced an evaluation matrix with an accuracy of 0.9510, precision of 0.9256, recall of 0.9261, and F1-score of 0.9247, demonstrating the model's ability to accurately classify air pollution. Meanwhile, the LightGBM model without optimization produced an evaluation matrix with an accuracy of 0.9455, precision of 0.9201, recall of 0.9170, and F1-score of 0.9182.
Implementation of a Web-Based Inventory Management Information System Ani Yoraeni; Asima Margaret; Muhimatul Ifadah; Ade Mulyono
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.v8i2.3245

Abstract

The use of internet technology in business processes is increasingly encouraging organizations to adopt digital systems that can improve operational efficiency and support data-driven decision-making. However, PT. Jodo Global still calculates inventory records manually, which causes data inconsistencies, loss of information, reporting delays, and limited inventory records. This problem indicates a significant research gap, as the lack of an integrated inventory system has significantly impacted operational accuracy and the effectiveness of managerial decision-making. This study aims to address these issues by developing a web-based inventory information management system capable of providing real-time stock monitoring, structured transaction recording, and automated report generation. The system was developed using a structured methodology encompassing requirements analysis, system design, implementation, and validation through black-box testing. The testing phase focused on evaluating the system's core functions such as stock updates, transaction recording, user authentication, and report generation-based on predetermined performance indicators, including accuracy, system responsiveness, and minimal functional errors. The results showed measurable performance improvements after the system was implemented. Inventory update processing time decreased by approximately 60%, recording errors were reduced by 83%, and the reporting process became fully automated, supporting faster and more reliable managerial decision-making. Overall, the system provides a scientifically proven digital solution that improves operational efficiency, accuracy, and productivity at PT. Jodo Global.
Classification of Sentiment Tokopedia and Shopee App Reviews on Google Playstore Using Naive Bayes Robait Tajuddin; Yudie Irawan; R. Rhoedy Setiawan
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.v8i2.3246

Abstract

The rapid growth of e-commerce in Indonesia has led to an increase in user reviews that reflect satisfaction and experiences with applications such as Tokopedia and Shopee. The large volume of reviews makes manual analysis inefficient, thus requiring an automated method to identify user sentiments. This study aims to analyze and classify the sentiment of Tokopedia and Shopee reviews using the Naïve Bayes algorithm. The dataset consists of 10,000 Indonesian-language reviews collected from the Google Play Store. The analysis stages include data cleaning, stopword removal, stemming, and tokenization before classifying the reviews into positive and negative categories. The results show that the Naïve Bayes model performs well in sentiment classification. For Tokopedia data, the model achieved an accuracy of 81.84%, weighted precision of 84.44%, weighted recall of 81.84%, and weighted F1-score of 81.57%. Meanwhile, for Shopee data, the model performed better with an accuracy of 86%, weighted precision of 85.96%, weighted recall of 86%, and weighted F1-score of 83.25%. The word cloud visualization reveals that negative sentiments on Tokopedia are dominated by complaints about products and delivery, while on Shopee, they relate to late orders. Positive sentiments in both platforms highlight transaction convenience and affordable prices. These results demonstrate that Naïve Bayes is effective for sentiment analysis of e-commerce user reviews.
Validating a Delay Tolerant Network Architecture for Urban Opportunistic Contact Using Long Range Bisma Putra Sulung; Agussalim Agussalim; Andreas Nugroho Sihananto
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.v8i2.3248

Abstract

Traditional communication infrastructures are vulnerable to failure during natural disasters in dense urban areas, hindering early warning dissemination. Delay Tolerant Network (DTN) offers a resilience, yet most studies relies on simulations, overlooking physical layer constraints affecting on opportunistic routing in real-world urban scenarios. This study addresses that specific gap by empirically validating a DTN-LoRa prototype-based communication system for flood data monitoring in Surabaya. A 4-node field test simulated the Store-Carry-Forward mechanism. A fixed node in the Dukuhpakis flood zone (TMP) transmitted bundles to mobile nodes on public transport routes (FD9, FD4). These data mules relayed the bundles via an opportunistic contact at Marmoyo Shelter, delivering them to a gateway node at the BPBD Command Post (PMI Surabaya). Performance was evaluated by Packet Delivery Ratio (PDR) and Latency under varying LoRa parameters (Spreading Factor, Coding Rate). The experiment validated the functional DTN architecture, achieving 100% PDR in the optimal configuration (SF7, CR4/7). The key finding was a "Contact Window Bottleneck" as a critical failure factor. LoRa configurations with high Time on Air (ToA) failed to transfer the entire data bundle within the narrow opportunistic contact window between mobile nodes, causing PDR to drop as low as 60%. Implementation success depends on the physical layer throughput that must be high enough to complete data transfer during brief opportunistic contacts, rather than merely maximizing signal range. These findings provide a critical performance baseline for disaster management agencies, demonstrating a feasible, low-cost architecture that can enhance the reliability of urban disaster response communication.
Early Detection of Skin Cancer Using Transfer Learning on Convolutional Neural Networks Zahra Arba Mihora; Ana 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.v8i2.3255

Abstract

Skin cancer remains one of the most common and serious global health problems, with cases continuing to increase annually. Early and accurate detection is essential for improving patient survival; however, conventional diagnostic methods often depend on manual visual assessment, which can be subjective and inconsistent. Hence, the development of an automated and reliable detection system is vital to support healthcare professionals in early diagnosis. This study proposes an intelligent diagnostic model for early skin cancer detection using dermatoscopic images, integrating transfer learning with Convolutional Neural Network (CNN) techniques. The model employs the HAM10000 dataset from the International Skin Imaging Collaboration (ISIC), which contains high-resolution dermatoscopic images classified into three malignant skin cancer types: Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), and Malignant Melanoma (MM). The CNN framework was built using pre-trained models optimized to enhance classification accuracy. Experimental results showed that the model achieved an accuracy of 96.67% and an F1-score of 0.97, demonstrating strong capability in identifying multiple malignant lesions. These findings indicate that the model can assist dermatologists and clinicians in improving diagnostic precision and reducing examination time in clinical practice. In conclusion, integrating transfer learning within a CNN architecture significantly improves classification efficiency even with limited data, and with further validation, the model shows strong potential for real-world implementation as an accurate, efficient, and accessible computer-aided diagnostic tool for early skin cancer detection.

Page 48 of 65 | Total Record : 642

 46   47   48   49   50 

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