Data distribution changes over time have become one of the main challenges in the application of machine learning to intelligent transportation systems. This phenomenon, known as concept drift, can lead to performance degradation when the testing data exhibit characteristics that differ from those of the training data. This study aims to analyze the robustness of machine learning algorithms aga…
In this study, the feature selection method employed is the Genetic Algorithm (GA), while the classification method used is the Support Vector Machine (SVM), with the aim of improving the performance of myocardial infarction disease classification. The study utilizes the Myocardial Infarction Complications dataset, which consists of 123 features. The research process includes several preprocess…
Myocardial infarction complications require early, accurate prediction for clinical intervention. This study optimizes the K-nearest neighbor (KNN) algorithm to classify these complications using Z-Score normalization and three feature selection methods: Information Gain, Gain Ratio, and Symmetrical Uncertainty.Using a dataset from the UCI Machine Learning Repository, preprocessing included mea…
The development of blockchain technology has increased cryptocurrency transaction activities, especially Ethereum, whose daily transaction volume is highly fluctuating. This condition makes transaction volume prediction important for understanding network activity patterns. This study aims to develop a prediction model for daily Ethereum transaction volume using the XGBoost Regressor algorithm.…
Accurate mental state identification is important across various fields, and EEG is a biomedical signal widely used for this purpose as it can directly and non-invasively record brain electrical activity. However, the complex, nonlinear, and high-dimensional characteristics of EEG signals require effective classification methods. This study aims to implement and compare the performance of Logis…
Talent Scouting in sports is a systematic process of finding, identifying, and evaluating individuals who show potential for achievement from an early age, so that their talents can be developed through a tiered training program to achieve optimal performance. The use of classification methods is one effective solution to support this process. Classification is the main method in machine learni…
The high school dropout rate in public high schools remains a significant problem in Indonesia due to various factors, such as socioeconomic conditions, educational facilities, and the ratio of teachers to students. This study aims to group provinces in Indonesia based on the indicator of high school dropout rates in 2024/2025 using the K-Means Clustering algorithm. The data used were obtained …
Salary is an important aspect in the employment sector as it reflects job value and employee welfare. Along with the rapid growth of salary data availability, effective analytical methods are required to transform raw data into meaningful information. However, salary data are often complex and unlabeled, making direct analysis difficult. This study aims to group salary data using the K-Means al…
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…
Classifying rainfall events can be challenging when the available data is incomplete or contains missing values. Several imputation methods can be used to address missing data, such as the mean imputation method and the K-Nearest Neighbors Imputation method. For classification purposes, many techniques can be utilized, one of which is the Adaptive Boosting (AdaBoost) method. AdaBoost is designe…
Infused water or spa water is water that is added with pieces of fruit and left to stand for a few hours until the juice comes out, then ready to be consumed, thus providing flavor and health benefits. The lime peel of an orange contains more than 60% flavonoids and 170 different types of phytonutrients. Processing lime as an infused water drink can be an alternative to overcome acidity in citr…
The vast diversity of Indonesian cuisine often leads to information overload and the "paradox of choice" for users. Existing conventional search systems are unable to understand specific personal preferences, necessitating an intelligent recommendation system. This research aims to (1) design and build a hybrid Indonesian food recommendation system model combining the Long Short-Term Memory (LS…
Facial paralysis is a condition characterized by the loss of motor function in the facial muscles and requires accurate clinical evaluation. Conventional visual assessments are often subjective, creating variability in diagnosis; therefore, a more consistent image-based assistance system is needed. This study develops an automated classification system for facial paralysis severity using the VG…
Traffic congestion is a recurring issue in Palembang City and significantly affects the daily activities of its residents. Social media, particularly Facebook, serves as a platform for the public to express their opinions and complaints regarding traffic conditions. This study aims to analyze public sentiment toward traffic congestion in Palembang City using the Random Forest algorithm. The res…
Good water quality is one of the leading indicators in supporting the life of living things. However, pollution from industrial, domestic, and agricultural waste has resulted in a decline in water quality, which has the potential to cause environmental and health problems. Rapid technological advancements have made machine learning algorithms a viable alternative for classifying water quality. …
SDGs score prediction is important in assisting the planning and evaluation of policies to achieve these global targets. This study aims to compare the performance of several regression algorithms in predicting the SDGs score: Polynomial Regression, Support Vector Regression, Random Forest Regression, and Gradient Boosting Regressor. The dataset used consists of data on country names, years, SD…
The development of online transportation applications such as Maxim has increased the need for sentiment analysis to understand user opinions from reviews on the Google Play Store. The main challenges in this analysis are language diversity, variations in writing style, and data imbalance, which affect model accuracy. This study aims to evaluate the performance of the Support Vector Machine (SV…
Understanding user sentiment from e-commerce reviews is essential for platform improvement and business strategy. This study compares three machine learning algorithms—Logistic Regression, Random Forest, and XGBoost—for sentiment classification of Indonesian-language Tokopedia reviews. A dataset of 6,822 user reviews was preprocessed through tokenization, stopword removal, and TF-IDF vector…
Diabetes merupakan salah satu penyakit tidak menular yang prevalensinya terus meningkat secara global maupun nasional. Kondisi ini menimbulkan risiko komplikasi serius seperti penyakit jantung, stroke, hingga gagal ginjal apabila tidak terdeteksi sejak dini. Oleh karena itu, dibutuhkan metode prediksi berbasis data yang mampu membantu proses deteksi awal secara cepat, akurat, dan efisien. Penel…
Dalam beberapa tahun terakhir, pertumbuhan e-commerce di Indonesia menunjukkan peningkatan yang signifikan, menjadikan ulasan konsumen sebagai acuan utama dalam menilai kualitas layanan dan pengalaman pengguna. Tokopedia, sebagai salah satu platform e-commerce terbesar, menerima jutaan ulasan yang merefleksikan opini serta pengalaman pelanggan terhadap berbagai produk dan layanan. Karena berben…
The rapid growth of the cosmetics industry on e-commerce platforms has intensified competition, creating a critical need for effective, data-driven marketing strategies. This study aims to conduct a comparative analysis of machine learning algorithms to predict the sales categories (High, Medium, Low) of cosmetic products on the Tokopedia marketplace. Four classification models; Random Forest, …
Rice is a primary staple food in Indonesia, particularly in South Sumatra Province. In February 2024, BBC News Indonesia reported that the price of premium rice surged to Rp18,000 per kilogram, marking the highest price in the country’s history. To anticipate and predict similar spikes in the future, this study applies a Knowledge Discovery approach and compares three machine learning models:…
Indonesia’s film industry is rapidly expanding with diverse genres and new titles, creating a need for fast, data-driven mapping of audience sentiment. This study maps social media X users’ sentiment toward the film “Sore: Istri dari Masa Depan,” which carries an unconventional theme, while addressing limited manual labels on short and noise tweets. Support Vector Machine (SVM) is selec…
This study aims to obtain a course schedule based on graph coloring with the Welch Powell algorithm. The coloring method used is vertex coloring. This study uses data from 37 courses in the odd semester of 2022/2023, consisting of 20 compulsory courses, 17 elective courses, and 23 lecturer-directed courses. Collecting data on the list of odd semester courses and the names of the lecturers in ch…
Earthquakes occur due to the impact of volcanic activity in mountainous areas. Sumatra Island is one of the islands that has earthquake activity that occurs quite frequently, especially in the South Sumatra region. This research aims to get accurate results based on the best algorithm in predicting earthquakes in Southern Sumatra to determine the prediction of earthquakes in Southern Sumatra us…
This study explores the implementation of the Greedy algorithm in FIFA 23, particularly within the Coach Career mode, to determine the most effective tactics and player formations. The Greedy algorithm is chosen for its ability to make fast, locally optimal decisions without considering long term consequences. The developed system evaluates various tactical and formation combinations and select…
Automatic image classification of fruits and vegetables plays a crucial role in enhancing efficiency in the agricultural and retail sectors, yet it faces challenges due to visual complexities such as intra-class variation and inter-class similarity. This research aims to implement and evaluate the effectiveness of the You Only Look Once version 11 (YOLOv11) algorithm, specifically the YOLOv11s-…
The air quality in a region significantly impacts the health of its residents. The Indonesian government has established the Air Quality Index (AQI) as a parameter to assess air quality and its effects on the health of individuals exposed to the air for several hours to several days. Several studies have found that machine learning methods, particularly the Random Forest algorithm, can be used …
The rapid growth of online gambling in Indonesia poses significant challenges insocial, economic, and network security aspects. This study aims to visualize networktraffic patterns of online gambling sites using machine learning approaches,specifically the K-Means and DBSCAN algorithms. Data were collected throughnetwork tapping with Wireshark during access to online gambling sites andapplicati…