Aydın, Yıldız; Türkeş, Muhammed Kerem

The facial expression recognition system, which contributes to the processes to be more effective and faster in many fields such as medicine, education and security, plays an important role in various applications. For example, while emotional and psychological states can be monitored thanks to facial expression recognition in the health field, it can be used in critical applications such as lie detection in the security sector. In education, students' instant facial expressions are analyzed to contribute to the learning processes. The problem of emotion recognition from facial expressions, which is related to many fields, is of great importance in obtaining accurate and reliable results. Therefore, in order to increase the performance of emotion recognition from facial expressions, a hybrid approach combining deep learning and classical machine learning methods is considered in this study. In the proposed method, the ResNet50 model is used as a feature and Support Vector Machines (SVM) is used as a classifier. In this study, a hybrid approach consisting of the combination of ResNet50 and SVM methods is proposed-to increase the performance of emotion recognition from facial expressions. In order to analyze facial expressions, six basic emotions are classified as happiness, sadness, anger, fear, surprise and disgust using the CK+48 dataset. Experimental results show that the proposed hybrid approach has high accuracy in emotion recognition and outperforms traditional machine-learning algorithms.

Geçmez, Hacer; Deveci, Hamza Arda

In this study, it is aimed to obtain the highest dimensional stability against temperature changes in fiber-reinforced hybrid composite laminates considering eight different composite materials: Aramid/Epoxy, AS4/Epoxy, Boron/Epoxy, E-Glass/Epoxy, IM6/Epoxy, GY70/Epoxy, Kevlar49/Epoxy, and Spectra/Epoxy. The study focuses on finding the optimum continuous and traditional fiber angle orientations for the hybrid composite plates that would provide the lowest coefficients of thermal expansion. For this purpose, two different laminate sequences were investigated, each including two materials. A hybrid algorithm combining genetic algorithm and generalized pattern search algorithm was used in the optimization. A great number of hybrid design problems were solved repeatedly, and their results were compared both within themselves and to the optimum non-hybrid laminate results. Furthermore, the thermal durability of the selected optimum hybrid designs was evaluated by Tsai-Wu failure and Hashin-Rotem criteria. The results reveal that substantial increase in dimensional stability can be achieved by stacking sequence optimization of hybrid composite laminates with multiple material selection, and this hybrid design approach can offer the desired laminated composite structures for aerospace applications required to withstand extreme temperature changes.

Altun Çolak, Deniz; Bayğu, Gürhan

Nowadays, plant extract-mediated biosynthesis of nanoparticles has gained prominence as a pivotal research domain. Silver nanoparticles are traditionally synthesized using highly toxic and ecologically hazardous chemical and physical methods. The emerging green synthesis approach offers more eco-friendly alternatives while reducing production costs. Hence, the present study opted for a nature-friendly green synthesis method to produce silver nanoparticles. Silver nanoparticles were characterized using UV-visible spectroscopy (UV-VIS), scanning electron microscopy (SEM), X-ray diffraction (XRD), and Fourier transform infrared spectroscopy (FT-IR). The reaction involved the treatment of AgNO3 (5 mM) with an aqueous extract of Karaerik grape leaf. Subsequently, the potentially toxic, genotoxic, and antioxidant effects of purchased chemically produced silver nanoparticles (AgNP(c)) and silver nanoparticles (AgNP(b)) that we synthesized using the green method were investigated on Drosophila melanogaster transheterozygous larvae. The study employed 72 ± 4 hour-old larvae bearing the recessive flr3 and mwh determinant genes on their third chromosomes. Exposure scenarios included 1 mM Ethyl methanesulfonate (EMS), AgNPs (1.25, 2.5, and 5 mg/mL), and EMS+ AgNPs. Interestingly, the EMS+ AgNPs combination reduced total oxidant status while increasing total antioxidant status significantly compared to EMS alone. To assess genotoxic effects, mutant trichomes resulting from genetic changes in the development of wing imaginal discs were examined. Furthermore, the AgNP synthesized through green synthesis demonstrated antioxidant properties and displayed no genotoxicity. In conclusion, the research highlights the promising potential of green-synthesized silver nanoparticles, which provide an eco-friendly and safe method for various applications.

Akar, Funda; Genç, Muhittin

Lung cancer stands out as a high mortality, fatal disease worldwide. Early diagnosis is crucial for effective treatment of this disease; however, treatment options can be limited when it is often diagnosed in advanced stages. This study examines the role of artificial intelligence (AI) techniques in early diagnosis of lung cancer and emphasizes the advantages it provides. Particularly, the ability of deep learning algorithms to extract meaningful features from complex datasets indicates significant potential for detecting early stages of lung cancer. In this context, it is anticipated that AI-supported diagnostic systems have the potential to significantly improve lung cancer diagnostic methods by reducing the workload of radiologists and increasing accuracy rates. In this study, a total of 6 datasets were obtained by applying Gabor filter and Histogram Equalization+CLAHE filter to original datasets. The results obtained in the diagnosis of lung cancer using Convolutional Neural Networks (CNN) and YOLO algorithms are evaluated in two different categories. One of these categories is the investigation of the effect of image preprocessing methods. The other is the investigation of the effect of dataset partitioning into training, testing, and validation on success. According to the results obtained, the highest success rate in terms of F1 Score for the CNN model was achieved in both dataset partitioning (70%-20%-10% and 60%-20%-20%) with the datasets subjected to Histogram Equalization+CLAHE filter. It was obtained as 99%. For the YOLO model, the highest success rate was determined as 96% F1 Score with the same preprocessing technique and dataset partition. The effect of image preprocessing and dataset partitioning on success is not as high in the YOLO model as it is in the CNN model.

Yavuz, Sevtap Çaglar

Cynarin (1,3-o-dicaffeoylquinic acid) is one of the biologically active functional food components which is the most well-known caffeoylquinic acid derivative found in artichoke. The structural and electronic features of cynarin compound were investigated theoretically using density functional theory (DFT). The highest occupied molecular orbital (HOMO) and the least occupied molecular orbital (LUMO) are the most significant orbitals in molecules, these orbitals are quite helpful to know several molecular features such as the chemical reactivity, kinetic stability, electronegativity, chemical potential, electrophilicity index, chemical hardness and softness and electronegativity. Molecular orbital analysis HOMO-LUMO was used to explore the stability of the molecule. Moreover, physicochemical properties, drug-likeness, and toxicity estimation of the cynarin compound were appraised owing to ADMET (including absorption, distribution, metabolism, excretion, and toxicology). Molecular docking was carried out to examine the biological activity of the cynarin compound. 5A19, a liver cancer biomarker, is human methionine adenosyl-transferase enzymes. Cynarin-methionine adenosyl-transferase enzyme binding energy value was calculated as -7.9 kcal/mol. As a result, this in silico study confirmed that cynarin has the potential to be a drug by revealing its protective effect against liver diseases.

Aydın, Yıldız

Twitter sentiment classification is an artificial approach for examining textual information and figuring out what people's publicly tweets from a variety of industries are experiencing or thinking. For instance, a large number of tweets containing hashtags are posted online every minute from one user to some other user in the commercial and politics fields. It can be challenging for scientists to correctly comprehend the context in which specific tweet terms are used, necessitating a challenge in determining what is actually a positive or negative comment from the vast database of twitter data. The system's authenticity is violated by this issue and user dependability may be significantly diminished. In this study, twitter data sent to interpret movies were classified using various classifier and feature methods. In this context, the IMDB database consisting of 50000 movie reviews was used. For the purpose of anticipating the sentimental tweets for categorization, a huge proportion of twitter data is analyzed. In the proposed method, bag of words and word2vec methods are given by combining them instead of giving them separately to the classifier. With both the suggested technique, the system's effectiveness is increased and the data that are empirically obtained from the real world situation may be distinguished well. With experimental efficiency of 90%, the suggested approach algorithms' output attempts to assess the reviews tweets as well as be able to recognize movie reviews.

Yildirim, Nalan; Dartar, Muhammed Semih

Because of the increasing need for agricultural products in the world, the use of pesticides, which are used to increase yield, is increasing day by day. Herbicides constitute a large part of the total amount of pesticides used, such as 20%. It is known that herbicides have toxic effects and irreversibly disrupt DNA and gene expression. Pendimethalin is a widely used herbicide against weeds in the production of grains, legumes, and vegetables. Ascorbic acid has an antioxidant effect. Molecular markers are frequently used to determine genotoxic and mutagenic effects at the DNA level. It was aimed to determine the curative effect of ascorbic acid on the negative effects of pendimethalin. IRAP and ISSR molecular markers were used. It was found that the GTS ratio decreased as a result of increasing the dose of pendimethalin applied in wheat, resulting in DNA damage and the positive effect of applied ascorbic acid on DNA damage.

Kalkan, Orhan

High power Light Emitting Diodes (LED)s are preferred in places that produce intense light output and have overheating problems because they work with high currents. Therefore, efficient thermal management is essential to ensure optimal performance and longevity. In the present study, a numerical analysis is conducted on a high-power Light Emitting Diode (LED) circuit with a Circuit on Board (COB) design featuring a radial heat sink. Additionally, a multi-objective optimization approach using the Desirability Function Approach (DFA) is introduced for the modeled radial heat sink. Two performance parameters, namely the maximum junction temperature and the cost of the radial heat sink, are defined as the objective functions, and the aim is to minimize both of these parameters. The independent variables for the objective functions are the geometrical parameters of the radial heat sink, namely the base radius (R), fin length (L), and heat sink height (H). The Response Surface Method (RSM) is applied to minimize sample numbers of the Design of Experiment (DOE) while still obtaining accurate response values. Furthermore, Analysis of Variance (ANOVA) is utilized to assess the fitting of the real response equations with the representative answer equations. The minimum prediction R2 is calculated to be 0.9748%, indicating a good agreement between the models. The optimum design for the radial heat sink is obtained, with the following dimensions: R=25 mm, L=15 mm, and H=55.36 mm. The response values for this optimal design are validated with a low error rate of 0.25% using numerical analysis.

Aslay, Fulya

In this day where quality personnel employment is also important for the production of quality products and services, the organizations evaluate the performances by their performance management systems within the organization and try to achieve their targeted business performance by determining appropriate training and development programs. Development activities are spread over a longer period, as they are individual and continuous, and require the implementation of individual development activities. When the studies in the literature are examined, it is observed that standardized development activities are generally applied to the employees in this process and mostly socio-psychological factors are not taken into consideration. In this study, a decision support system, in which the employees' knowledge and skills, psychological status, communication skills, job satisfaction and demographic characteristics can be evaluated, has been developed in order to assist managers in their decision-making during the job placement and development processes of the employees. It will be possible to obtain the maximum efficiency and work performance with minor cost and time by planning the development activities in accordance with the needs and situation of each personnel thanks to the system developed in the study.

Yangılar, Filiz; Gülhan, Barış

The study evaluated the antibacterial effect of stinging nettle extract by the liquid microdilution method to obtain quantitative results. Unlike other studies in the literature, minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) values showing bacteriostatic and bactericidal effects were investigated for four different bacterial concentrations. Six pathogen strains were studied, including Staphylococcus aureus ATCC 29213, Enterococcus faecalis ATCC 29212, Streptococcus pneumoniae ATCC 45615, Klebsiella pneumoniae ATCC 70063, Escherichia coli ATCC 25922, Pseudomonas aeruginosa ATCC 27853 and different levels of antimicrobial effects were determined. While the extract does not affect the Klebsiella pneumoniae ATCC 70063 strain at any level, Pseudomonas aeruginosa ATCC 27853 in strains with MIC values 1.5x105 and 1.5x104 cfu/mL were found at concentrations, but no effect was observed at the MBC level. While MIC and MBC values were found at the concentrations of Staphylococcus aureus ATCC 29213 except for the 1.5x107 concentration, the remaining standard strains had different MIC and MBC values at all concentrations. The standard strain Streptococcus pneumoniae ATCC 45615 was the most effective with the extract's lowest MIC and MBC values. This study showed that nettle extract (Urtica dioica) would contribute to the research results in the scientific literature on its antimicrobial effect.