The effect of the COVID-19 pandemic on crude oil prices just faded; at this moment, the Russia–Ukraine war brought a new crisis. In this paper, a new application is developed that predicts the change in crude oil prices by incorporating these two global effects. Unlike most existing studies, this work uses a dataset that involves data collected over twenty-two years and contains seven different features, such as crude oil opening, closing, intraday highest value, and intraday lowest value. This work applies cross-validation to predict the crude oil prices by using machine learning algorithms (support vector machine, linear regression, and rain forest) and deep learning algorithms (long short-term memory and bidirectional long short-term memory). The results obtained by machine learning and deep learning algorithms are compared. Lastly, the high-performance estimation can be achieved in this work with the average mean absolute error value over 0.3786.

Today, the increase in the number of people, advances in industry and technology cause an increase in the number of wastes generated with the acceleration of production. It is important for the future of our country and the world that these wastes are more easily identified and recycled. In the process of recycling wastes, the classification of wastes as well as their collection requires costly energy and manpower. Wastes are basically separated into paper, plastic, glass and metal. Various studies have been carried out to complete these processes in a shorter and easier way with technologies such as artificial intelligence, deep learning and image processing. In this study, a dataset of paper, plastic and food and beverage wastes that are common in the environment was created. In this dataset, paper cups, plastic water bottles and fast food wastes were detected from different locations in nature and photographed. These images were labeled and trained and tested with YoloV3 in deep learning algorithms. In addition, in order to compare the performance of the new dataset, studies were conducted on a global dataset used in the literature. As a result of the studies, it was observed that it was successful in classifying the newly created dataset and the global dataset.

Multiple screen addiction is a growing public health problem, especially among young people. Early detection and classification of screen addiction are important for the prevention of neurological complaints. The current study aimed to determine the status of multiple screen addiction with machine learning and to identify the relationship between multiple screen addiction and neurological complaints. This cross-sectional and correlational study was conducted with 406 participants. The data were collected from November 13, 2023, to March 4, 2024, in the neurology outpatient clinic of a training and research hospital. The dataset created in the study was trained with machine learning algorithms, and classification was provided. K-Nearest Neighbors (KNN), Ensemble, Support Vector Machine (SVM), Decision Tree machine learning algorithms, and Confusion Matrix were used for classification. In the study, KNN was the algorithm with the highest classification performance, while Decision Tree was the algorithm with the worst performance. Moreover, it was determined that multiple screen addiction and neurological complaints were related, and these complaints were successfully evaluated through machine learning classification. Multi-screen addiction is closely linked to numerous neurological complaints, and machine learning can effectively uncover and analyze this association. As a foundational step, this study paves the way for family physicians and healthcare professionals to utilize machine learning in calculating individuals' addiction scores, monitoring addiction patterns, and providing personalized recommendations.