This research is entitled "Development of AI-Based Interactive Infographics on the Tonarigumi Social Institution During the Japanese Occupation at SMA Negeri Plus 2 Banyuasin III." The problem in this research focuses on how to develop interactive infographic media based on Artificial Intelligence that meets the criteria for validity and practicality as a history learning medium. The purpose of…
This study aims to analyze the effectiveness of plenary meetings held by the Trial and Legislation Section at the Bangka Regency DPRD Secretariat. The research problem stems from the postponement and cancellation of meetings, which impact the regularity of the agenda and the effectiveness of decision-making. The analysis used Stephen P.Robbins' (1990) Systems Approach, which assesses effectiven…
The rapid advancement of computer vision and deep learning has greatly improved image classification performance. However, maintaining consistent accuracy across diverse datasets and visual conditions remains challenging. This study proposes a soft voting ensemble learning approach for image classification using three fine-tuned Convolutional Neural Networks (CNNs): ResNet, EfficientNet, and De…
Pengelolaan keuangan pada Homeschooling Sriwijaya Kids sebelumnya masih sangat bergantung pada ketelitian pegawai, sehingga berisiko menimbulkan kesalahan pencatatan, data ganda, keterlambatan rekapitulasi, serta kesulitan dalam penyusunan laporan keuangan. Penelitian ini bertujuan untuk merancang dan membangun aplikasi pengelolaan keuangan berbasis web yang dapat membantu proses pencatatan, pe…
The development of an interactive learning media assisted by Google Sites on the topic of plane figures for fourth-grade elementary school students SDN 10 Talang Kelapa aims to determine the development stages, assess the validity level, and evaluate the media practicality. This study employed the Research and Development (R&D) method using the ADDIE model, which consists of the Analyze, Design…
Social media is widely used today for communication and information exchange. One of the most popular social media platforms is Instagram. The comments section on an Instagram post creates discussions among users regarding issues that are currently being widely discussed. One of the issues that is currently being widely discussed is the free lunch program, which is a new program created by the …
Type 2 diabetes is a chronic disease that requires early detection to reduce the risk of complications. This study aims to design a web-based prototype Clinical Decision Support System (CDSS) to predict diabetes risk using the XGBoost algorithm and improve interpretability through the SHAP method. The dataset used was obtained from Kaggle and consisted of approximately 100,000 records with eigh…
Most current flood prediction studies rely on secondary data with limited temporal resolution and Deep Learning models with high computational demands. This research addresses this gap by designing an early warning system that is computationally efficient, utilizing direct physical sensor data within a controlled simulation. The objectives are to measure water flow velocity (m/s) using an optoc…
Traffic accidents are a road safety issue that can result in fatalities. This study aims to compare the performance of machine learning models namely, Random Forest, XGBoost and LightGBM and to explain the prediction results of the best model using the Explainable Artificial Intelligence (XAI) approach, with SHapley Additive exPlanations (SHAP) employed as the interpretation method. The data us…
Traffic accidents are one of the transportation issues that require distribution analysis to identify areas with different accident characteristics. This study aims to compare the K-Means, DBSCAN, and Hierarchical Clustering methods in clustering traffic accident data based on geographical location and accident severity. The dataset used is derived from traffic accident data in the United Kingd…
Electrocardiogram (ECG) signals represent the electrical activity of the heart and are used to record disorders such as arrhythmia and heart failure. Due to their non-stationary nature, ECG signals require a time-frequency domain approach to capture their dynamic characteristics more accurately. This study aims to develop and evaluate machine learning-based heart disorder classification models …
Congenital heart disease (CHD) in children, such as atrial septal defects (ASD), ventricular septal defects (VSD), and atrioventricular septal defects (AVSD), requires accurate diagnosis through dynamic analysis. However, existing methods for analyzing echocardiographic video are often limited to frame-by-frame analysis and are not yet capable of consistently tracking temporal changes. This stu…
Image captioning is a task in the fields of computer vision (CV) and natural language processing (NLP) that aims to generate textual descriptions from an image. In this study, various combinations of encoder–decoder architectures were designed and evaluated to improve captioning performance on cervical medical images from the International Agency for Research on Cancer (IARC). The encoders us…
Cervical cancer is one of the leading causes of morbidity and mortality among women, making early detection of precancerous lesions essential. However, lesion segmentation in cervical images still faces several challenges, including unclear object boundaries, illumination variations, imaging artifacts, and class imbalance between lesion and background, which reduce the performance of deep learn…
This study aims to develop a deep learning-based object detection system using the YOLOv11n algorithm to identify foreign objects on coal conveyor belt systems. The study is motivated by the limitations of manual inspection methods in maintaining detection consistency and accuracy within mining environments characterized by high visual complexity, such as dust, uneven illumination, motion blur,…
Cervical cancer is a leading cause of death among women. The subjectivity of Visual Inspection with Acetic Acid (VIA) screening encourages the use of Artificial Intelligence (AI) for medical image segmentation automation. However, limited datasets frequently cause model overfitting. This research aims to improve the segmentation performance of cervical precancerous images on the YOLOv11-seg mod…
Visual diagnosis via colposcopy is prone to observer subjectivity, making a more objective computational system necessary. This study explores two approaches: hybrid feature engineering (color, texture, contour) using machine learning (ML) via a rule-based system that adapts the Sweden score method, and end-to-end architectures based on YOLO (v8, v11, v12, v26). The dataset is sourced from the …
This study aims to classify normal and abnormal puncta lacrimal images using deep learning methods and to analyze the impact of data augmentation strategies on model performance. The dataset consisted of 61 images, including 30 normal and 31 abnormal images, which underwent a preprocessing stage by resizing all images to 256 × 256 pixels. Nine deep learning architectures were evaluated, includ…
The increasing use of Android devices has led to a rise in security threats, particularly spyware attacks that threaten user privacy. Conventional signature-based detection methods have limitations in detecting new spyware variants. This study aims to classify Android spyware attacks using the Convolutional Neural Network (CNN) method. The dataset used is CIC-MalMem2022, consisting of memory du…
The rapid development of the Internet of Things (IoT) has accelerated the implementation of smart home systems connected to the internet. However, this advancement also increases the risk of cyberattacks, particularly SSL Pinning Bypass, which threatens communication security, and Distributed Denial of Service (DDoS), which disrupts service availability. This study aims to detect both types of …
Cyber Threat Intelligence (CTI) is essential to support cyber threat detection and mitigation, particularly for Advanced Persistent Threat (APT) activities that are commonly reported in unstructured text. This condition makes critical information difficult to utilize automatically without an entity extraction process. This study aims to analyze the performance of Named Entity Recognition (NER) …
The development of information technology has increased cyber attack threats, especially Advanced Persistent Threat (APT), so appropriate methods are needed to detect attacks based on Cyber Threat Intelligence (CTI) data. The main problems in this study are data imbalance and the difficulty in determining the most important features to improve detection results. To address these problems, this …
Alzheimer's disease is a slowly progressing neurodegenerative disorder characterized by memory decline, visual-spatial impairment, executive function impairment, and personality and behavioral changes. Early detection of this disease is crucial for proper treatment. This study used MRI images to detect Alzheimer's disease, as MRI can provide a more detailed picture of brain structure and networ…
Flight departure delays affect operational efficiency and the quality of air transportation services. This study compares the performance of the Artificial Neural Network (ANN), ANN optimized using Particle Swarm Optimization (ANN-PSO), and ANN optimized using Genetic Algorithm (ANN-GA) for flight delay classification using a two-class dataset, namely on-time and delayed flights, based on opera…
This research was conducted because departure delays on the Light Rail Transit can reduce passenger comfort and satisfaction. Therefore, a predictive model that can estimate delays accurately is needed. The purpose of this study is to implement, compare, and determine the best machine learning algorithm for predicting LRT departure delays in Canberra. The dataset used consists of static and rea…
Traffic accidents are a serious public safety issue that requires data-driven analytical approaches. This study aims to classify traffic accident severity into three classes, namely fatal, serious, and slight, using machine learning algorithms. Four algorithms are evaluated: Random Forest, Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). M…
The rapid adoption of Cyber-Physical Systems (CPS) has improved operational efficiency across critical sectors but has simultaneously increased exposure to cyber threats, particularly Man-in-the-Middle (MITM) attacks that covertly intercept and manipulate communication. In CPS environments, such attacks pose serious risks to system reliability and operational safety, thereby requiring security …
Cloud computing provides dynamic computing resources over a network. However, an increasing number of user requests can lead to higher server workloads and decreased service performance. This study aims to analyze the performance of load balancing using the Least Connection method with HAProxy as the load balancer. The system was implemented in a VMware-based virtual machine environment consist…
The classification of articles into several categories has been done using the Naive Bayes method, with an F1-score result of 98% on balanced data based on titles and abstracts. The results show a high level of classification accuracy, with a processing time of less than 60 minutes. Similarity detection between articles was carried out using the Cosine Similarity method, and a similarity score …
The evolution of technology roles attracted cyber security threats not only compromise stable technology but also cause significant financial loss for organizations and individuals. As a result, organizations must create and implement a comprehensive cybersecurity strategy to minimize further loss. The founding of a cybersecurity surveillance center is one of the optimal adopted strategies, kno…