Jurnal Informatika: Jurnal Pengembangan IT
Not a member yet
437 research outputs found
Sort by
Optimasi Faktor Friksi dan Dinamis dengan Hibrida GA-ACO pada Estimasi Usaha Perangkat Lunak Agile
No full textEffort estimation remains a critical challenge in Agile Software Development due to the high dynamics of requirement changes and the reliance on friction factors (FF) and dynamic factors (DF) that are inherently subjective, often leading to significant deviations between estimated and actual project effort. This study aims to improve the accuracy of Agile software effort estimation by optimizing FF and DF parameters using a hybrid metaheuristic approach based on Genetic Algorithm and Ant Colony Optimization (GACO). The proposed method integrates a pheromone-based guided search mechanism from Ant Colony Optimization to generate high-quality initial populations, which are subsequently refined through the evolutionary process of Genetic Algorithm to achieve more stable and systematic parameter optimization. Experimental evaluation was conducted using two datasets, namely the Ziauddin dataset representing Agile projects and the Maxwell dataset encompassing cross-domain software projects. The results demonstrate that the GACO approach consistently outperforms the conventional Genetic Algorithm, as indicated by a substantial reduction in Mean Absolute Error from 616.38 to 354.81. Furthermore, statistical validation using the Wilcoxon Signed-Rank Test confirms that the performance difference between the two approaches is statistically significant. These findings indicate that integrating Ant Colony Optimization into Genetic Algorithm effectively enhances the accuracy, stability, and robustness of software effort estimation, thereby supporting more reliable resource planning in Agile software development
Penerapan Metode Canny Edge Untuk Deteksi Pelat Nomor Kendaraan Area Parkir PLN Mabar
No full textVehicle license plate detection is an essential component in modern parking management, particularly in institutional areas like PLN Mabar, which necessitate fast and accurate identification systems. This study focuses on applying the Canny Edge Detection method to accurately identify the edges of vehicle license plates under specific environmental settings, specifically lighting conditions of 100115 lux and a camera height of 40 cm, evaluated across various threshold levels. Widely regarded as an optimal edge detection algorithm, the Canny Edge method offers significant advantages, including high-precision edge detection, robust noise interference minimization, and the generation of clear object boundaries. The research findings demonstrate that this method delivers excellent performance for vehicle detection in parking facilities when operating under controlled lighting and camera parameters. Specifically, the test results reveal that within a threshold range of 50 to 500, the system achieves a flawless 100% detection accuracy. This highlights the method's effectiveness in capturing crucial object edges under the tested conditions. Conversely, increasing the threshold beyond 500 leads to a gradual decline in system accuracy, dropping to 20% at a threshold of 9001000. This decline indicates that excessively high threshold values cause the system to discard vital contours necessary for accurate detection. Ultimately, the system successfully detects license plate edges with a high success rate and stable processing times, proving its viability for practical implementation within the vehicle identification system at the PLN Mabar parking area
Pemanfaatan Teknologi Augmented Reality dengan Marker-Based Tracking sebagai Media Pengenalan Kabupaten Muara Enim
No full textThe development of digital technology has increased the demand for more interactive information media, including those used to present regional potential. Muara Enim Regency is rich in culture, industry, and tourism, all of which need to be introduced through more engaging media for both younger generations and the wider community. This study aims to develop an Augmented Reality–based application for introducing Muara Enim Regency using the Marker-Based Tracking method as a response to the need for more immersive and accessible information media. The development process follows the Multimedia Development Life Cycle (MDLC) method, which includes the Concept, Design, Material Collecting, Assembly, Testing, and Distribution phases. The application is implemented using Unity and Vuforia, integrating 3D objects, information panels, and an interactive quiz feature. Functional testing through Black-box Testing shows that all features operate according to specifications without significant issues. User Acceptance Testing (UAT) produced results categorized as very good, indicating that the application is positively received in terms of operational ease, informational clarity, stability, and interaction experience. Therefore, this application is considered suitable as an alternative medium for introducing the potential of Muara Enim Regency and has promising opportunities for further development through additional content and enhanced interactivity
Studi Komparatif Dampak Layanan Cloud Gaming terhadap Kinerja Jaringan Rumah Berbasis Ethernet dan WLAN
No full textCloud gaming has transformed the digital gaming landscape by offloading rendering and computational processes to cloud servers, enabling users to play resource-intensive games on low-specification devices. However, in practice, there remains a critical issue regarding differences in performance and stability of home network connections in supporting cloud gaming services, particularly between Ethernet and Wireless Local Area Network (WLAN) connections. This study aims to analyze the impact of cloud gaming services, using NVIDIA GeForce NOW as a case study, on the performance of home networks under two different configurations: high-speed Ethernet and low-speed WLAN. Network traffic data were captured in real time using Wireshark over a total of 18 hours of gameplay sessions conducted across three days for each network type. Quality of Service (QoS) parameters, including latency, jitter, packet loss, and throughput, were extracted and analyzed using Python-based scripts. The results indicate that Ethernet connections provide more stable latency and jitter, experience no packet loss, and deliver more consistent throughput. In contrast, WLAN exhibits higher variability in latency and jitter, with fluctuating and less stable throughput. These findings confirm that while both network types can support cloud gaming under certain conditions, Ethernet offers superior performance and consistency. This study contributes practical insights for selecting and optimizing home network configurations to ensure a more reliable and seamless cloud gaming experience
Penerapan Transfer Learning VGG-16 untuk Mendeteksi Penyakit Mata Manusia Berbasis Citra Fundus
No full textEye disorders represent a serious global health issue that can lead to a decline in quality of life and even permanent blindness. Early diagnostic for eye diseases such as glaucoma, diabetic retinopathy, age-related macular degeneration, cataract, myopia, and hypertension is crucial to prevent more severe complications. The objective of this study is to develop an image classification model for fundus images using a transfer learning approach with the VGG-16 architecture. The dataset used is ODIR-5K, which includes eight classes of eye diseases. The research stages involve image preprocessing, data augmentation, class balancing using SMOTE, and CNN for training the model. The model training process was conducted over 80 epochs with a combination of freezing layers, fine-tuning, and hyperparameter tuning. Model evaluation was carried out using metrics such as accuracy, precision, recall, F1-score, confusion matrix, and ROC AUC curve. The results show that the developed model achieved an accuracy of 89% compared to the previous study which only reached 45%, with a macro average F1-score of 0.89. The model demonstrated excellent performance in classes such as Hypertension, Glaucoma, and Myopia, although challenges remain in distinguishing the Diabetes and Normal classes. Therefore, the VGG-16-based approach has proven effective for multi-class classification of fundus images, and the results of this study may serve as a foundation for developing deep learning-based diagnostic support systems in the field of ophthalmology
Sistem Informasi Keuangan dengan Prediksi Pendapatan Menggunakan Regresi Linier
No full textFinancial management and forecasting are critical aspects in supporting decision-making within an organization, particularly amid the increasing demand for fast and accurate data analysis. In general, many companies in Indonesia still face challenges in utilizing historical financial data to optimally predict revenue. This issue is also encountered by a company that continues to rely on manual record-keeping using spreadsheet-based systems, which makes it difficult to conduct analysis and forecast future financial conditions. This study aims to implement a linear regression method to predict revenue based on historical financial transaction data. The methodology employed follows the CRISP-ML(Q) framework, which includes business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The modeling process is carried out by developing a linear regression model using independent and dependent variables. The results indicate that the constructed linear regression model is capable of generating revenue predictions with a relatively low error rate, thereby effectively representing patterns within the historical data. Model evaluation using error metrics demonstrates that the model performs adequately within the context of the dataset used. In conclusion, the linear regression method is effective for revenue prediction and can support data-driven decision-making processes. Future research is recommended to enhance the model by incorporating more complex variables and applying alternative prediction methods to improve accuracy
Kombinasi Model ARIMA dan KNN Dalam Peramalan Harga Produk
No full textThis study proposes a product price forecasting model for PT ABC by integrating the Autoregressive Integrated Moving Average (ARIMA) model and the K-Nearest Neighbor (KNN) method into a hybrid predictive approach. The company faces recurring challenges related to product price fluctuations and stock availability caused by unstable market conditions and irregular supply distribution. To address these issues, a data-driven forecasting model is required to support inventory planning and price stabilization strategies. The dataset used in this study consists of historical cement purchase records from January 2023 to September 2025, obtained from the company’s ERP system. The research process includes data cleansing, transformation, monthly price aggregation, and the application of ARIMA, KNN, and a hybrid ARIMA–KNN model designed to improve forecasting accuracy. The evaluation results indicate that the hybrid ARIMA–KNN model outperforms the standalone ARIMA model in short-term price forecasting. Based on three performance metrics, the hybrid model achieved a Mean Absolute Error (MAE) of 1604.94, a Root Mean Square Error (RMSE) of 2299.37, and a Coefficient of Determination (R²) of 0.2881. These results suggest that while the model captures a portion of price variability, it still faces limitations in modeling non-linear fluctuations and sudden extreme changes. Nevertheless, the hybrid approach demonstrates improved stability by reducing extreme prediction variations, maintaining trend continuity, and generating smoother prediction curves that more closely align with actual price movements. This research contributes practically by providing PT ABC with a forecasting tool to support future price estimation, improve inventory management, and maintain market price stability. Additionally, the findings offer a foundation for future research on advanced non-linear and deep learning–based forecasting models
Perbandingan Kinerja Algoritma Random Forest dan Convolutional Neural Network (CNN) Untuk Klasifikasi Citra Kucing
No full textCat breed classification is a significant challenge in the field of computer vision due to the high visual similarity between breeds (fine-grained classification) and pattern variations within a single breed. This study aims to compare the performance of two different machine learning approaches, namely Random Forest (RF) based on manual features and Convolutional Neural Network (CNN) based on automatic features. The research focuses on three cat breeds: Bombay, Siamese, and Persian. The research methodology uses a public dataset from Kaggle, divided in a ratio of 80:10:10. The RF pathway applies manual feature extraction through a combination of Histogram of Oriented Gradients (HOG) and Color Histogram. In contrast, the CNN pathway uses Transfer Learning techniques with the ResNet50V2 architecture. The test results show that CNN significantly outperforms RF with an accuracy of 93.33%, while RF only reaches 68.33%. The analysis shows that manual features in RF have difficulty capturing complex texture details in the Persian breed, while CNN is able to generalize well. It is concluded that the Deep Learning (CNN) approach is much more effective than traditional methods for animal breed classification
Pipeline NLP End-to-End untuk Peringkasan Abstraktif dan Ekstraksi Entitas Berita Berbahasa Indonesia Berbasis Model Transformer
No full textThe rapid growth of online news content poses challenges for readers to capture the core information quickly and accurately. This research proposes and implements an automated end-to-end pipeline that integrates three main stages: data acquisition, abstractive text summarization, and Named Entity Recognition (NER). The mT5 model is employed to generate coherent and concise summaries, while the BERT model is applied to extract key entities, including persons, organizations, and locations. The pipeline was evaluated using 100 news articles from the Egindo portal. Experimental results show that the system achieves an average text reduction of 62.47%, with a ROUGE-1 F1 score of 0.473. For NER tasks, the pipeline reached a Micro-F1 score close to 0.70, outperforming traditional approaches such as TextRank and CRF. These results demonstrate that the integration of Transformer-based models within a structured pipeline significantly improves summarization quality and entity extraction accuracy. The study contributes a practical NLP solution for the Indonesian language, providing a functional prototype that can be applied to online media analysis and media intelligence applications
Pemanfaatan Metode Agile dalam Pengembangan Aplikasi CISEA pada PT. Bukit AsamTbk
No full textKey Performance Indicator (KPI) management is a crucial aspect in measuring and evaluating organizational performance in a systematic and sustainable manner. However, KPI management processes that are still conducted manually may lead to several issues, such as verification delays, lack of data integration, and low accuracy in performance reporting. This study aims to develop an Electronic Balanced Scorecard (e-BSC) module within the CISEA application to support integrated and digital-based KPI management. The system development method employed in this study is Agile, which consists of planning, design, development, testing, documentation, and deployment stages. During the planning stage, system requirements were analyzed through observations and discussions with relevant stakeholders. The design stage utilized Unified Modeling Language (UML) to model the system, database structure, and user interface. System implementation was carried out using PHP as the programming language and MySQL as the database management system, with the user interface developed using HTML and CSS. System testing was conducted using the black box testing method to ensure that all system functions operated in accordance with user requirements. The results of this study indicate that the developed e-BSC module is capable of facilitating KPI input, verification, approval, and performance reporting processes in a more systematic, integrated and structured manner. Therefore, the system is expected to enhance the quality of organizational performance management and support accurate and timely managerial decision-making