Makale Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe A novel hybrid model for automated analysis of cardiotocograms using machine learning algorithms(İsmail SARITAŞ, 2021) Avuçlu, EmreIn this study, a new hybrid model was presented for the prediction of fetal state from fetal heart rate (FHR) and the uterine contraction (UC) signals obtained from cardiotocogram (CTG) recordings. CTG monitoring of FHR and uterine contractions during pregnancy and delivery provides information on the physiological status of the fetus to identify hypoxia. The precise information obtained from these records provides some ideas for interpreting the pathological condition of the fetus. Thus, with early intervention, it allows to prevent any negative situation that will occur in the fetus in the future. In this study, due to the importance of this subject, a new hybrid model was developed which can perform high rate accurate diagnosis using Machine Learning (ML) algorithms. In the hybrid model, 4 different ML algorithms (k Nearest Neighbors (k-NN), Decision Tree (DT), Naive Bayes (NB) and Support Vector Machine (SVM)) were used. While the diagnosis without the hybrid model was low, the improved hybrid model increased the accuracy by 34%. As a result of this hybrid model, 100% success was achieved for classification, test success, Accuracy, Sensitivity and Specificity with NB and DT ML algorithms.Öğe Classification Of Pistachio Images With The ResNet Deep Learning Model(Selçuk Üniversitesi Ziraat Fakültesi, 2023) Avuçlu, EmrePistachio, which is grown in many parts of the world today, has an important place in the agricultural economy. In order to maintain this economic value, the post-harvest industrial classification process is very important to obtain efficiency from this harvest. In the process of separating pistachios, an efficient classification process is needed in order for different pistachio species to appeal to different markets. For this reason, the classification process of pistachios is very important. In this study, Kirmizi and Siirt pistachio classification with 2148 images was made using ResNet architecture. After the statistical experimental studies, the highest classification accuracy was obtained from fold-1 as 88.5781% and the Accuracy value was 0.86168 after the classification process.Öğe Evaluating vision transformer models for breast cancer detection in mammographic imaging(Bitlis Eren Üniversitesi Rektörlüğü, 2025) Demiroğlu, Uğur; Şenol, Bilal; Kerim, EnginBreast cancer is a leading cause of mortality among women, with early detection being crucial for effective treatment. Mammographic analysis, particularly the identification and classification of breast masses, plays a crucial role in early diagnosis. Recent advancements in deep learning, particularly Vision Transformers (ViTs), have shown significant potential in image classification tasks across various domains, including medical imaging. This study evaluates the performance of different Vision Transformer (ViT) models—specifically, base-16, small-16, and tiny-16—on a dataset of breast mammography images with masses. We perform a comparative analysis of these ViT models to determine their effectiveness in classifying mammographic images. By leveraging the self-attention mechanism of ViTs, our approach addresses the challenges posed by complex mammographic textures and low contrast in medical imaging. The experimental results provide insights into the strengths and limitations of each ViT model configuration, contributing to an informed selection of architectures for breast mass classification tasks in mammography. This research underscores the potential of ViTs in enhancing diagnostic accuracy and serves as a benchmark for future exploration of transformer-based architectures in the field of medical image classification.Öğe Sorting and counting of almond kernels on conveyor belt using computer vision and deep learning techniques(Elsevier B.V., 2025) Aktaş, Hakan; Karagöz, ÖmerThe classification and sorting of agricultural products, such as almonds, are critical processes in ensuring quality and meeting market demands. Sorting process is done in machines with computer vision technology. However, the output of these machines is never 100 %. The products coming out of these machines are finally sorted again on the conveyor belt. In this study, deep learning and computer vision techniques were used to perform the final sorting and counting on the conveyor belt. A self-curated dataset containing 1200 images divided into three distinct classes: whole almond kernels, damaged kernels, and broken shells was created to facilitate the study. We evaluated the performance of four CNN architectures: ResNet50, InceptionV3, VGG16, and EfficientNetB3 using both RGB and grayscale image datasets. Among these, EfficientNetB3 achieved the highest accuracy of 99.44 % with RGB images and 98.33 % with grayscale images. Field tests with new samples validated the model's robustness, achieving 97.14 % accuracy on RGB images and 95.71 % on grayscale images. These results demonstrate the potential of the proposed method to automate almond classification and sorting on the conveyor belt and calculate the operating accuracy of sortex machines with its counting feature.Öğe A Review of Traditional and Advanced MPPT Approaches for PV Systems Under Uniformly Insolation and Partially Shaded Conditions(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Endiz, Mustafa Sacid; Gökkuş, Göksel; Coşgun, Atıl Emre; Demir, HasanSolar photovoltaic (PV) is a crucial renewable energy source that converts sunlight into electricity using silicon-based semiconductor materials. However, due to the non-linear characteristic behavior of the PV module, the module’s output power varies according to the solar radiation and the ambient temperature. To address this challenge, maximum power point tracking (MPPT) techniques are employed to extract the maximum amount of power from the PV modules. This paper offers a comprehensive review of widely used traditional and advanced MPPT approaches in PV systems, along with current developments and future directions in the field. Under uniform insolation, these methods are compared based on their strengths and weaknesses, including sensed parameters, circuitry, tracking speed, implementation complexity, true MPPT, accuracy, and cost. Additionally, MPPT algorithms are evaluated in terms of their performance in reaching maximum power point (MPP) under partial shading condition (PSC). Existing research clearly demonstrates that the advanced techniques exhibit superior efficiency in comparison to traditional methods, although at the cost of increased design complexity and higher expenses. By presenting a detailed review and providing comparison tables of widely used MPPT techniques, this study aims to provide valuable insights for researchers and practitioners in selecting appropriate MPPT approaches for PV applications.Öğe Analytical approach in designing PID controller for complex fractional order transfer function(John Wiley and Sons Ltd, 2025) Demiroğlu, Uğur; Şenol, Bilal; Matušů, RadekThe study focuses on the fractional complex order plant model, which has gained popularity in applied mathematics, physics, and control systems. A significant contribution of this research lies in discussing the physical phenomena associated with complex plant models and their impact on system stability and robustness. The main purpose of the method presented in this paper is to tune the controller parameters to ensure the stability and robustness of the system. There are methods presented in the literature for this purpose. One of these methods is to keep the phase curve in the system frequency response flat within a certain range. However, this process is based on equating the derivative of the phase value to zero at a certain frequency and adds great mathematical complexity to the calculations. In this study, reliable analytical formulas are presented for the same purpose using a graphical approach. Since the fractional complex order plant model represents the most general mathematical form, it enables easy creation of other plant models, including integer order and fractional order plant. The reason why this plant is chosen is that this structure can be named as the universal plant, which all other structures can be built by making little variations. For instance, a transfer function having integer, real and/or complex number coefficients and/or orders can be obtained by proper determination of the parameters of the universal plant. A time delay can also be added towards researcher's desire. The main inspiration comes from studying on an inclusive plant. The method in this paper intends to tune the well-known classical Proportional Integral Derivative controller. Thus, effectiveness of the integer order controller on various plants will be shown. This approach provides analytical calculation equations for the physical modifications of plants with integer, fractional, and/or complex coefficients and/or orders. The effectiveness of the method is demonstrated visually with different examples that include these different possible situations. The results observed in the changes of the parameters in the transfer functions were also examined. Thus, pros and cons of the variations of integer, fractional, and complex numbers on system parameters have been shown.Öğe Analyzing complex fractional order systems physical phenomena in IOPI controller design(John Wiley and Sons Inc, 2024) Şenol, Bilal; Demiroğlu, UğurThe Fractional Complex Order Plant model, which has lately gained popularity in applied physics and control systems, is the main subject of this study. The major contribution of this study to the literature is the discussion of the physical phenomena of complex plant models and how they affect the stability and robustness of the systems. Because the Fractional Complex Order Plant model is the most general mathematical form, other plant models covering the Integer Order Plant and the Fractional Order Plant can be easily created with this benefit. The proposed approach using the classical Proportional Integral controller which is recalled as the Integer-Order PI controller in this paper gives the calculation equations of the physical alterations of plants having integer, fractional, and complex orders. Along with the visuals and with the aid of simulations, the consequences of the parameters on the system are described. Additionally, the advantages and disadvantages of the proposed controller designs for each of the three plant species are discussed.Öğe Simulation and forecasting of power by energy harvesting method in photovoltaic panels using artificial neural network(Elsevier Ltd, 2024) Demir, HasanHeat is an important efficiency reducing factor in photovoltaic systems. Although many studies in the literature are related to the removal of waste heat from photovoltaic panels, the disadvantages such as installation and maintenance of cooling systems should not be forgotten. A study has shown that with a new approach, energy can be produced with the method of energy harvesting from waste heat. The results of the study were limited to a geographical region and climatic conditions in Aksaray, Turkey. In this article, the results of the study, which was limited to a region, were extended using the finite element method analysis and the artificial neural network model. Ten different cases were determined and temperature gradient was found by finite element analysis. The forecasting algorithm was developed with artificial neural network and estimates the harvestable power based on the temperature gradient. The accuracy of the algorithm was tested with the MSE and nRMSE statistical metrics which were calculated as 59.1423 mW and 13.6189 %, respectively. The training data accuracy of the network was 0.93987 and the combined accuracy was 0.94364. The results of this study are important to be a reference for researchers who want to establish a photovoltaic panel energy harvesting system.Öğe Investigating the Effect of Albedo in Simulation-Based Floating Photovoltaic System: 1 MW Bifacial Floating Photovoltaic System Design(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Coşgun, Atıl Emre; Demir, HasanPhotovoltaic (PV) modules have emerged as a promising technology in the realm of sustainable energy solutions, specifically in the harnessing of solar energy. Photovoltaic modules, which use solar energy to generate electricity, are often used on terrestrial platforms. In recent years, there has been an increasing inclination towards the installation of photovoltaic (PV) modules over water surfaces, including lakes, reservoirs, and even oceans. The novel methodology introduces distinct benefits and complexities, specifically pertaining to the thermal characteristics of the modules. In order to accomplish this objective, a photovoltaic (PV) module system with a capacity of 1 MW was developed as a scenario in the PVsyst Program. The scenario simulation was conducted on the Mamasın Dam, situated in the Gökçe village within the Aksaray province. To conduct the efficiency analysis, a comparative evaluation was conducted between bifacial and monofacial modules, which were installed from above the water at 1 m. The comparison was made considering two different types of modules. Additionally, the albedo effect, water saving amount, and CO2 emissions of the system were also investigated. Albedo measurements were made in summer when the PV power plant will operate most efficiently. As a result of the simulations, it was found that bifacial modules produce 12.4% more energy annually than monofacial modules due to the albedo effect. It is estimated that PV power plant installation will save 19,562.695 and 17,253.475 tons of CO2 emissions in bifacial and monofacial systems, respectively.Öğe Agrivoltaic systems for sustainable energy and agriculture integration in Turkey(Elsevier Ltd, 2024) Coşgun, Atıl Emre; Endiz, M.S.; Demir, H.; Özcan, M.In recent years, the use of solar photovoltaic (PV) energy, which is one of the leading renewable energy sources, has become increasingly widespread around the world due to its numerous advantages. However, PV-based electricity generation necessitates a large amount of land. Agrivoltaic (AV) systems, an innovative approach to combining agricultural and electricity production in the same area through solar modules positioned several meters above the surface of the ground, are growing rapidly in renewable energy and farming communities. This study explores Turkey's solar power generation and agricultural activities, combining crop cultivation and electricity generation for sustainable development on the same land. Furthermore, the AV potential for the most agriculture ten cities in different climate zones in Turkey is investigated using the PVsyst program. A list of the most commonly grown crops in the ten selected cities and the types of AV systems that can be employed with these crops is provided. The results show that AV systems present a great opportunity for the optimal integration of solar power generation with food production, especially for the cities of Konya, Kayseri, and Manisa, with the most ideal conditions for agricultural and solar power production. By combining the solar power potential of the country with the production capacity of arable lands, the increasing energy needs can be met and more efficient agricultural production can be provided. This study is expected to demonstrate that in specific regions of Turkey, AV farming will be suitable for certainÖğe Smart and digital world: The technologies needed for digital twins and human digital twins(American Society of Mechanical Engineers (ASME), 2024) Coşgun, Atıl EmreThe transition to Industry 5.0 begins with the integration of the human aspect into Industry 4.0 technologies. Industry 5.0 is a human-centric design approach that aims to overcome the issues raised by Industry 4.0 and involves collaborating both with humans and robots in a shared working environment. The new idea demonstrates a great connection between technology and people, or “soft” sectors. At this point, the idea of a digital twin (DT), a novel technological innovation, appears. The digital twin is a newly developed technology that is essential for digital transformation and intelligent updates. The fundamental basis of this concept involves the amalgamation of artificial intelligence (AI) with the notion of digital twins, which refer to virtual renditions of tangible entities, systems, or procedures. Therefore, this article focuses on digital twins and the innovative concept of human digital twins (HDTs), with particular emphasis on the technological tools of AI in the usage of mentioned technology. Also, this article conducts a comprehensive political (P), economic (E), social (S), technological (T), legal (L), and environmental (E) (PESTLE) analysis of Industry 5.0, while specifically delving into the concepts of digital twin and human digital twin.Öğe Automatically Finding the Biggest Fold Value for More Accurate Classification and Diagnosis in Machine Learning Algorithms(Springer, 2024) Avuçlu, EmreCorrect diagnosis in medicine is of great importance as it is one of the most important issues in medicine. Today, researchers have embarked on many new searches to make an accurate medical diagnosis. In order for any disease to be cured, it is necessary to define it precisely early and accurately. In this study, a new method was proposed to make a more accurate medical diagnosis. This method is based on automatically selecting the fold with the best accuracy rate after k-fold crossvalidation is performed in any database. In this way, scientific studies that lead to more accurate results will be carried out by using the fold with the highest accuracy in both classification and medical diagnosis procedures. This method has been applied on two different databases, Ecoli and Wisconsin Breast Cancer Diagnostic (WBCD) databases, which are used in scientific studies by many researchers in the literature. The statistical measurements of each fold values of both databases used have been examined in detail. Diagnostics for these databases were carried out using 7 different Machine Learning Algorithms (MLA), (k nearest neighbor (k-NN), Decision Tree (DT), Random Forest (RF), Multinominal Logistic Regression (MLR), Naive Bayes (NB), Support Vector Machine (SVM), Minumum (Mean) Distance Classifier (MMDC)). In the test procedures for Ecoli dataset, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively; 0.8485, 0.8358, 0.9848, 0.8182, 0.6667, 0.8636, 0.7424. For the WBCD database, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively; 0.9856, 0.9568, 0.9784, 0.9856, 0.9856, 0.9856, 0.9784. Other results were given in detail in the experimental studies section. It is of great importance to choose the most accurate MLAs to be used in medical diagnosis for human life. Thus, in the studies to be done with MLAs in medicine or any field in the literature, how the best score that can be obtained from MLAs will be introduced to the literature. In this study, an original study was conducted on how to make the correct medical diagnosis, which is one of the most important issues for human life.Öğe Assessing the potential of solar power generation in Turkey: A PESTLE analysis and comparative study of promising regions using PVsyst software(Elsevier Ltd, 2023) Endiz, Mustafa Sacid; Coşgun, Atıl EmreRenewable energy sources have a tremendous amount of potential in Turkey. In the previous year, 43.2% of the country's electricity was generated from renewable energy sources. Solar photovoltaic (PV) energy accounted for 4.7% of the electricity generation and the installed capacity was 9.425 GW with 9353 solar power plants of various types. This paper provides an overview of the current state of solar PV potential in Turkey, evaluates its capacity to meet the country's energy demand, and discusses its future prospects. The PESTLE analysis is performed based on political (P), economic (E), social (S), technological (T), legal (L), and environmental (E) factors to study the sustainable development of solar energy potential in Turkey. Furthermore, a comparative analysis of the solar energy potential between the Konya and Diyarbakır regions which are recognized as promising areas for harnessing the country's abundant solar resources has been conducted using the PVsyst software. The electricity consumption in Turkey will be 380.2 TWh in 2025, 455.3 TWh in 2030, and 510.5 TWh in 2035, according to the Turkey National Energy Plan. Hence, it is essential to maximize the use of solar energy capacity in the production of electricity to meet the increased energy demand. The main objective of this study is to help strategic and systematic evaluation of the solar energy resource potential affecting large and small-scale solar power projects in Turkey.Öğe A fused electrocardiography arrhythmia detection method(Springer, 2024) Demiroğlu, Uğur; Şenol, Bilal; Matuš?, RadekRecently, Electrocardiography (ECG) signals are commonly used in diagnosing the cardiac arrhythmia that shows up with the loss of the regular movement of the heart. Approximately 5% of the world population have cardio motor disorders. Therefore, usage of the ECG signals in biomedical signal processing algorithms and machine learning methods for automated diagnosis of this widespread health problem is a popular research topic. In this paper, the Particle Swarm Optimization (PSO) technique is implemented to tune the parameters of Tunable Q-Factor Wavelet Transform (TQWT) and the new generation feature generator Hamsi Hash Function (Hamsi-Pat) is used to obtain the characteristics of the signal. Sub-signals of 10 s obtained from the original ECG signal are divided into their sub-bands of 25 levels with PSO and TQWT. Each of these low pass filters generates 536 dimensional features by applying Hamsi-Pat and statistical methods. Then, all these features are combined and 536 × 25 = 13400-dimensional feature set is obtained. The features in the set are reduced and the best of them are selected by using the Iterative Neighborhood Component Analysis (INCA) method. Finally, the k-Nearest Neighbors (kNN) classification method is applied to the best features according to the City Block measurement criterion. All studies cited to compare the results in this paper also use the MIT-BIH Arrhythmia ECG database. Hence, the difference could be observed in the used techniques. In contrast to the existing studies, this study shows its superior performance by classifying all 17 classes simultaneously by applying a “fused” approach. The method in the paper reached 98.5% classification accuracy on the 17 classes of the MIT-BIH Arrhythmia ECG database. The results indicate that the proposed method showed better rates from the existing studies related to arrhythmia diagnosis using ECG signals in the literature.Öğe Regions of robust relative stability for PI controllers and LTI plants with unstructured multiplicative uncertainty: A second-order-based example(Elsevier Ltd, 2023) Matuš?, Radek; Şenol, Bilal; Peka?, Liborhis example-oriented article addresses the computation of regions of all robustly relatively stabilizing Proportional-Integral (PI) controllers under various robust stability margins ? for Linear Time-Invariant (LTI) plants with unstructured multiplicative uncertainty, where the plant model with multiplicative uncertainty is built on the basis of the second-order plant with three uncertain parameters. The applied graphical method, adopted from the authors’ previous work, is grounded in finding the contour that is linked to the pairs of P–I coefficients marginally fulfilling the condition of robust relative stability expressed using the H? norm. The illustrative example in the current article emphasizes that the technique itself for plotting the boundary contour of robust relative stability needs to be combined with the precondition of the nominally stable feedback control system and with the line for which the integral parameter equals zero in order to get the final robust relative stability regions. The calculations of the robust relative stability regions for various robust stability margins ? are followed by the demonstration of the control behavior for two selected controllers applied to a set of members from the family of plants.Öğe Classification of computerized tomography images to diagnose non-small cell lung cancer using a hybrid model(Springer, 2023) Demiroğlu, Uğur; Şenol, Bilal; Yıldırım, Muhammed; Eroğlu, YeşimLung cancer arises from the abnormal and uncontrolled reproduction of parenchymal cells. Among all cancer cases, lung cancer is one of the prevailing types. Prevalence and death rates of the cancer increases day by day. From this point of view, early diagnosis and treatment of this cancer increases survival times and rates. The main idea in the development of the method presented in this publication is to increase the rate of early diagnosis. Computerized Tomography (CT) is the major screening method when encountered with suspicious symptoms. The cancer can be determined with CT and besides subtyping can be done. Diagnosing the disease with the human eye can sometimes lead to the emergence of deficiencies. This is one of the problems faced today. In this direction, the study in this paper presents a hybrid method to predict and diagnose the lung cancer from CT images to minimize potential human errors. Using the method, feature maps of the CT images of the dataset are obtained using the previously trained DarkNet-53 and DenseNet-201 deep model architectures. DarkNet-53 and DenseNet-201 architectures were chosen because they gave the best feature extraction results among 7 different architectures. The purpose of using the two architectures is to combine two high-performance models to create a hybrid classification method with high accuracy. Feature concatenation is applied to increase the diagnosis accuracy. To optimize the performance and computation cost of the proposed method, the Neighborhood Component Analysis (NCA) optimization method is used in determining and analysis of the features with more information. Therefore, features with less contribution in the accuracy are eliminated. Next, new feature maps are achieved by grading all features upon their weights and applying an elimination using a threshold value. The new feature maps are classified using Classical Machine Learning (CML) classifiers. Classification accuracies on DarkNet-53 architecture were calculated as 69.11% with SoftMax and 96.25% with Ensemble Classifiers and Nearest Neighbor Classifiers respectively. Similarly, accuracies on DenseNet-201 architecture were calculated as 68.29% with SoftMax and 97.39% with Ensemble Classifiers and Nearest Neighbor Classifiers respectively. With the proposed hybrid model, the Ensemble Classifiers reached the accuracy of 98.69% and the highest accuracy is achieved by using k-Nearest Neighbor Classifier (kNN) with the value of 98.86%. The results are supported with detailed illustrations.Öğe An examination of complex fractional order physical phenomena in IOPD controller design(John Wiley and Sons Ltd, 2023) Demiroğlu, Uğur; Şenol, Bilal; Matuš?, RadekThis research focuses on the fractional complex order plant (FCOP). The significant contribution is the role of complex plant models in system stability and robustness and associated physical phenomena. A general transfer function is studied in the paper. Other plant models may be built with this structure since the FCOP is a general mathematical form covering integer order plant (IOP) and fractional order plant (FOP). Using the equations produced with the proposed technique and the recommended integer order proportional derivative (IOPD controller, physical changes in integer, fractional and complex coefficients, and orders are observed within this paper. Analysis of the plant controlled with an IOPD controller is done by applying an integrator to reveal the differences. The effects of the parameters are discussed together with the visuals, supported by simulations. The aim is to tune the controller parameters to achieve the phase and specifications as the researcher desired. It is observed that the integrator greatly takes part in reducing the steady-state error. The IOP with the integrator showed the lowest steady-state error, and also, the settling and overshoot time were enhanced. Increase in the phase margin also caused an increase in the phase crossover frequency. It is also observed that the fractional order affected the phase crossover frequency comparing with the IOP, and the complex order modification also had an effect comparing to the fractional order version. The complex order of the system is considered with its conjugate components in the imaginary part thus, the results are found separately for each case.Öğe Fractional order PD controller design for third order plants ıncluding time delay(Pamukkale Üniversitesi, 2023) Demiroğlu, Uğur; Şenol, Bilal; Matuš?, RadekDue to the lack of integral operator, proportional derivative controllers have difficulties in providing stability and robustness. This difficulty is especially felt in higher order systems. In this publication, analytical design method of fractional proportional derivative controllers is presented to ensure the stability of third order systems with time delay. In this method, it is aimed to achieve the frequency characteristics of a standard control system to ensure stability. It is aimed to provide the desired gain crossover frequency, phase crossover frequency and phase margin properties of the system. In this way, the stability and robustness of the system can be obtained by choosing the appropriate values. The reason for choosing a fractional order controller is that the controller parameters to provide these features can be tuned more accurately. In order for the obtained stability to be robust to unexpected external effects, it is aimed to flatten the system phase. In the literature, phase flattening is performed by setting the phase derivative to zero at a specified frequency value. This can lead to mathematical complexity. In this publication, the phase flattening process is provided graphically by correctly selecting the frequency characteristics given above. Thus, an accurate and reliable controller design method is presented, avoiding mathematical complexity. The effectiveness of the proposed method has been demonstrated on three different models selected from the literature. The positive contribution of the method to the system robustness has been proven by changing the system gain at certain rates.Öğe Designing a dynamic system to control building components and computers with voice commands for disabled individuals(Springer, 2023) Avuçlu, Emre; Özçifçi, Ayhan; Elen, AbdullahNowadays, with the development of technology, there have been many innovations in human life. Technology has made many things easier in human life depending on these innovations. In this study, an application has been developed to more easily solve the needs of people in their daily lives. The developed application is designed to control the internal units of the house with voice commands. The doors, windows, lamps, etc. that we use daily in our house can be controlled by voice commands through wireless headphones. Voice commands can be sent from inside or outside the house. In addition to these external units, all applications on the personal computer are controlled by voice commands without using a keyboard and mouse. The application developed in C # programming language, provides control of newly installed programs to the computer without coding. To do so, it is enough to add that program and voice command to the interface. Moreover, the application provides a lot of convenience for disabled-aged citizens and some dangerous situations in the industrial environment.Öğe A new hybrid model for classification of corn using morphological properties(Springer Science and Business Media Deutschland GmbH, 2023) Avuçlu, Emre; Taşdemir, Şakir; Köklü, MuratAutomated classification of corn is important for corn sorting in intelligent agriculture. Corn classification process is a necessary and accurate process in many places in the world today. Correct corn classification is important to identify product quality and to distinguish good from bad. In this study, a hybrid model was proposed to classify the 3 corn species belonging to the Zea mays family. In the hybrid model, 12 different morphological features of corn were obtained. These morphological features were used for the classification process in the hybrid model created using machine learning (ML) algorithms. When morphological features were given as input to ML algorithms for normal classification, the test score was 96.66% for Decision Tree (DT), 97.32% for Random Forest (RF) and 96.66% for Naive Bayes (NB). With the proposed hybrid model, this rate has reached 100% test score in all three algorithms. Test processes were measured by statistical models. While Accuracy was 97.67% as a result of normal classification, this rate was 100% in hybrid model. The experimental results demonstrated the effectiveness of the proposed corn classification system.
