• Open Access close
• Publications close

This study explores the application of various machine learning models to predict vehicle fuel consumption using the Auto MPG dataset. It examines the effectiveness of algorithms such as Decision Tree Regressors, Random Forests, Support Vector Regressors, and neural network-based models like LSTM and GRU. The study aims to enhance fuel efficiency prediction by analyzing factors like engine specifications, driving habits, and vehicle design. The models' performance is evaluated using metrics such as R-squared (R2), Root Mean Square Error(RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) to ensure accuracy and minimize error.

This research investigates the application of machine learning models in the banking sector, specifically focusing on the classification of bank marketing datasets. We explore the use of feature reduction techniques, including Principal Component Analysis (PCA) and SelectKBest, to enhance the performance of various models such as Multi-Layer Neural Networks (MLNN), K-Nearest Neighbors (KNN), Random Forest(RF), and Linear Discriminant Analysis (LDA). Our study reveals the pivotal role of these reduction techniques in addressing the challenges posed by high-dimensional data and imbalanced distributions in customer behavior prediction. Through comparative analysis, we demonstrate how PCA and SelectKBest, through F-Value and Chi-Squared methods, influence model accuracy and efficiency, providing insights into the effectiveness of these models in strategic bank marketing efforts.

This study focuses on pediatric appendicitis, a leading cause of hospital admissions due to abdominal pain in children, characterized by a substantial risk of perforation, especially in younger patients. Traditional diagnostic methods, while effective, often lack specificity and are supplemented by varying laboratory and imaging techniques. This research introduces a novel application of machine learning (ML), specifically a multi-output neural network model, to address the complexities of diagnosing appendicitis, determining its severity, and guiding management strategies in pediatric cases. The model, with its unique architecture, has been trained and tested on a comprehensive dataset from Children’s Hospital St. Hedwig in Regensburg, Germany, which includes a wide array of clinical data and ultrasound images. The results demonstrate remarkable accuracy in classifying management approaches, severity levels, and diagnosis, highlighting the model's potential in supporting clinical decision-making. While not a replacement for clinical judgment, this model serves as a promising tool in the ongoing efforts to improve pediatric appendicitis care, offering a glimpse into the future of AI-enhanced medical diagnostics and treatment planning.

The term "emotion" refers to an individual's response to an event, person, or condition. In recent years, there has been an increase in the number of papers that have studied emotion estimation. In this study, a dataset based on three different emotions, utilized to classify feelings using EEG brainwaves, has been analysed. In the dataset, six film clips have been used to elicit positive and negative emotions from a male and a female. However, there has not been a trigger to elicit a neutral mood. Various classification approaches have been used to classify the dataset, including MLP, SVM, PNN, KNN, and decision tree methods. The Bagged Tree technique which is utilized for the first time has been achieved a 98.60 percent success rate in this study, according to the researchers. In addition, the dataset has been classified using the PNN approach, and achieved a success rate of 94.32 percent.

Light electric vehicles provide significant advantages in reducing environmental pollution and increasing efficiency in urban transportation. The performance of the motor directly affects the overall performance of electric vehicles. This study investigates the performance analysis of asynchronous motors designed for light electric vehicles used in urban transportation. The initial design parameters of the motor are specified, and various motor structures designed with changes in the rotor slot number are presented. Additionally, the effects of the slot number on the motor's magnetic circuit and performance are discussed. Finite Element Analysis (FEA) is used to investigate the motor's performance. Performance parameters such as efficiency, magnetic flux density, weight, starting torque, and power factor are obtained for different slot numbers. The results indicate that the rotor slot number is a critical design parameter affecting motor performance. In particular, it is stated that maximum efficiency can be achieved with a certain slot number, but an excessive increase in the slot number may have adverse effects on performance.

With the increasing demand for energy today, diversification of resources and meeting this demand has become crucial. Environmentally friendly alternative solutions have been the subject of research. Especially investments in renewable energy sources have increased in this regard. The power required by low-power sensor technologies can be met by harvesters. For this purpose, the design and Finite Element Analysis (FEA) of the toroid core electromagnetic harvester have been carried out in the study. The material of the toroidal core is determined by selecting Nickel-steel, M19, and nanocrystalline, and the effect of induced voltage and mutual inductance on the core material has been identified. In addition, the line current was determined as a variable and its effect on both flux density and voltage was determined.

Consciousness is said to be associated with neuronal activity in the brain, but how this relationship works is still unknown. There are different theories and opinions on whether consciousness is a biological phenomenon or a physical process. The question of whether consciousness can be created in artificial intelligence systems has also been raised. In this article, current artificial neural network models that attempt to mimic the workings of the brain have been discussed and evaluated for their adequacy in addressing the issue of consciousness.

In the control of DC-DC converters, pulse width modulation (PWM) is commonly used. In converters operating with PWM control, the switches operate under hard-switching conditions, resulting in increased switching losses, current and voltage stresses on the switching elements, and electromagnetic interference (EMI) noise as the operating frequency increases. Achieving higher power density and faster transient response in DC-DC converters is possible only by increasing the switching frequency. Therefore, reducing these losses and noises while increasing the switching frequency is only possible with soft switching techniques. Particularly in cases of variable loads, such as batteries, and when a smoother output voltage is required, the series-parallel LCC-type circuit topology from resonant converter topologies is employed. In this study, a simple algorithm has been developed to rapidly control the output voltage and switching frequency of the Full-Bridge Isolated LCC SeriesParallel Resonance circuit based on the current drawn by the changing load over time. The circuit has been successfully operated in the range of 100-130 kHz.

Electric power systems are structures that should operate stable in all scenarios. Unified power flow controller (UPFC), a flexible alternating current transmission system (FACTS) device, is one of the main assistants to achieve this necessity. In this study a control strategy for power flow optimization that based on the combined Fast-Decoupled (FD) method and UPFC is proposed. A detailed model was designed under MATLAB/Simulink platform in association with MATLAB editor. The IEEE-30 bus system was used to validate the model, and the results were addressed in terms of power loss values and optimization. According to the obtained results, it is observed that proposed model has ability to regulate system parameters for various conditions.

In today's rapidly developing and changing landscape, PLC technology, widely used in the field of industrial automation, offers users various solutions. In industry, management, and scientific technical jobs, the execution of tasks without human labor is achieved through automation and machines. In this context, Asynchronous motors are preferred over other electrical machines due to their lower cost and being the most widely used machine in the industry. In this study, the control of an Asynchronous motor was realized using a PLC with a VFD driver. In the established experimental system, the speed of the Asynchronous motor was controlled using a Proportional Integral Derivative (PID) controller algorithm. Different control PID values were experimented with constant speed trials to achieve the best results. The obtained results were interpreted through system graphs.