Vol. 2 No. 1 (2023)

Vol. 2 No. 1 (2023)
  • Hadice OKAY, Abidin Çalışkan
    1-4

    Heart disease is a disease that is difficult to diagnose and leaves serious damage to individuals like many other diseases today. It is not known whether the risk of this disease is carried or not, and it is observed that there is an increase in the number of individuals at risk today. This increase; It requires accelerating the diagnosis of the disease to humanity by making early intervention and risk analysis together with developing technologies. Machine learning methods are developing rapidly in this field, facilitating early diagnosis in medicine. Diagnosing the disease with the developed methods provides a great advantage in terms of time cost. With the developments made, the diagnosis of diseases related to more than one parameter is carried out in a very short and reliable way. In this study; with the dataset consisting of the parameters and values of carrying the risk of heart attack, the classification of the risk of heart attack with high / low probability was made using Logistic Regression, which is one of the machine learning methods. By referring to what the parameters are, the distribution and values of these parameters on the dataset are determined. Obtained values; The effect of the parameters on the result status was analyzed using visualization methods. The main purpose of these analyzes is to determine the need for corrections on the dataset before training the network. As a result of the experimental analysis, 97% overall accuracy was achieved with the proposed approach.

  • Çağrı Batuhan OĞUZ, Emre AVCI, Salih Barış ÖZTÜRK
    22-26

    Maximum Power Point Tracking (MPPT) systems enable photovoltaic (PV) panels to work at their Maximum PowerPoint (MPP). To do this, several algorithms have been developed, including conventional, intelligent, and meta-heuristic. Once a partial shading condition (PSC) occurs, more than one peak emerges in the power-voltage curve of photovoltaic arrays. Under PSCs, conventional algorithms get stuck at the local maximum point and fail to reach the global maximum point. Being an alternative method, Particle Swarm Optimization (PSO) algorithm has been frequently employed for MPPT systems under PSCs. This algorithm has some parameters that affect its performance to reach the global MPP of the PV panel.  Therefore, with well-tuned parameters, the effectiveness of the PSO will increase for the different PSCs.  In this study, the effects of the cognitive learning and social learning parameters of the PSO algorithm are investigated under different PSCs. To achieve this, an MPPT system, including a boost-type DC-DC converter, is created in MATLAB®/Simulink®. Simulation studies show that the PSO algorithm fails to track global MPP with constant cognitive and social learning parameters under changing partial shading conditions. Furthermore, the results show that these two parameters affect the time to reach the MPP of the PSO algorithm.

  • Omar Soufi, Fatima-zahra Belouadha
    27-34

    Recently, several technological solutions based on deep learning have been developed for the processing of multispectral satellite images. These solutions have broadened the scope of spatial remote sensing and further explored the earth and space by avoiding human efforts in heavy manual tasks. However, even though this progress gives even better performance it is difficult to design an efficient deep-learning pipeline for satellite image processing in the absence of a well-developed standard. Thus, we propose a new framework to design and implement a machine-learning model for satellite image processing through a set of machine-learning methods in the form of a protocol adapted to the context of space imagery. The choice of the dataset adapted metrics, exploitation of the product format, data enrichment, spatiotemporal indexing and analysis, contrast enhancement and noise reduction/suppression, network parameterization, model scalability, data normalization, spectral dependency, and processing complexity reduction are among the methods adapted to the processing of multispectral satellite images by deep learning. All these methods are analyzed in depth in order to understand their usefulness and their contribution to the performance of learning models before testing them on real use cases. This method constitutes the first standard framework for the use of deep learning in the processing of multispectral satellite images.

  • Mert Demir
    35-41

    Today, traffic problems are important factors that cause loss of life and property. The fact that the drivers are not instantly unaware of the changing road and traffic conditions prevents taking early measures and triggers traffic problems. As an alternative to the deficiencies in the existing traffic cameras and observation systems, the model has been developed with each vehicle on the road as a unit of measurement. In the study, it is aimed to evaluate and share the road and traffic conditions between vehicles with a low-budget vehicle network module and to take early measures against possible problems. In this study, an early accident prevention method is presented by using multi-factor structures to monitor vehicle flow in traffic, detect road problems and take early precautions. The road hazard detection model was developed by making the prototype of the proposed system, and the model developed for the studies, experiments and early warning system to prevent possible traffic accidents was recommended for the prevention of traffic accidents in the future.

  • Muthana ALISAWI, Nursel YALÇIN
    5-21

    The seven basic facial expressions are the most important indicator of a person's psychological state, regardless of gender, age, culture, or nationality. These expressions are an involuntary reaction that shows up on the face for a short time. They show how the person is feeling—sad, happy, angry, scared, disgusted, surprised, or neutral. The visual system and brain automatically detect a person's emotion through facial expressions. Most computer vision researchers struggle to automate facial expression recognition. Human emotion-detection pioneers have also tried to mimic human automatic detection. Thus, deep learning techniques are the closest to mimicking human intelligence. Despite deep learning techniques, creating a system that can accurately distinguish between facial expressions is still difficult due to the diversity of faces and the convergence of some expressions that express different emotions. This systematic review presents a scientifically rich paper on deep learning-based facial expression emotion detection methods. From 2019 to the present, PRISMA was used to search and select research on real-time emotions. The study collected datasets from the mentioned period that were used to train, test, and verify the models presented in the relevant studies. Each dataset was fully explained in terms of number of items, type of data, etc. The study also compared relevant studies and identified the best technique. Furthermore, challenges to systems that detect emotions through facial expressions have been identified.