Mardin Meslek Yüksekokulu

Permanent URI for this communityhttps://hdl.handle.net/20.500.12514/28

Browse

Now showing 1 - 20 of 74

Analysis of Resource Consumption Accounting by TAS-2 Inventories Standard: An Application in A Manufacturing Company
(Üçüncü Sektör Sosyal Ekonomi, 2022) Güneş, Mehmet; Gutnu, Mehmet Murat
TAS-2 inventories standard is based on normal cost method, instead of full costing method. The aim of this study is to examine the Resource Consumption Accounting (RCA) method, which has emerged as an important management accounting technique in calculating the idle capacity in recent years, within the framework of TAS- 2 inventories standard. For this purpose, both the normal cost management method based on the TAS-2 inventories standard and the RCA method are applied to a production facility. The findings suggest that the RCA method estimates the idle capacity costs accurately, reliably and realistically as proposed by the standard. Therefore, for businesses that have to apply the standards, the RCA method can be easily integrated within their own systems.
Analysis of solar inverter THD according to PWM’s carrier frequency
(ICRERA, 2015) Cangi Hasan; Adak, Süleyman
Solar PV systems are usually used in the generation of power systems. Electricity produced in Photovoltaic systems in the form of direct current. In order to convert direct current to alternating current used converters, which are harmonic source. In this thesis study, output distortion currents of solar inverter t are analyzed for various PWM’s carrier frequency. Analytical expressions related to obtained numerical results, which was found by curve fitting method. Simulations are implemented in MATLAB and Simulink software. R-L inductive load is implemented in hardware to show the effectiveness of the proposed system.
An Applıcatıon Of Exergoeconomic Analysıs For Power Plants
(Vinča Institute of Nuclear Sciences, 2018) Ünal, Fatih
Currently, energy resources are rapidly consumed. Therefore, scientists and engineers study the effective use of energy. In the present study, a thermodynamic and exergoeconomic analysis was performed in a thermal power plant in Turkey. The study involved determining the thermodynamic properties of 27 node points in a thermal power plant unit, and this was followed by calculating energy and exergy values of every node. Mean exergy costs were calculated by establishing energy and exergy balances of the equipment with respect to the calculated results. Subsequently, lost and damaged energies and exergies were calculated, and exergoeconomic factors were determined. The equipments were compared with each other on a graph based on the obtained results. The maximum rate of exergy loss and cost of exergy destruction corresponded to 79.5% and 886,66 $/h, respectively. The maximum exergy losses in a thermal power plant occurred in the boiler, turbine groups, condenser, heating group, pumps, and auxiliary groups. The highest and second highest law efficiencies of the studied thermal power plant corresponded to 32.3% and 28.5%, respectively. The study also involved presenting suggestions for improvement. Additionally, exergoeconomic analyses were conducted while considering the power plants’ investment and equipment maintenance costs. It is expected that the calculation method and the obtained results can be applied to other thermal power plants.
Applications of mid-IR spectroscopy for identification of wine and olive yeasts and characterization of antimicrobial activities of phenolics on yeasts
(2015) Canal, Canan; Ozen, Banu; Baysal, A. Handan
The aim of this study was application of mid-IR spectroscopy in combination with multivariate statistical analysis for characterization of yeasts from two fermented products, wine and olive, in comparison with cultural and molecular tests and characterization of antimicrobial effects induced by olive phenolics on yeasts. Totally 19 wine yeasts were molecularly identified as M. pulcherrima (11%), P. membranifaciens (16%), H. uvarum (5%) and S. cerevisiae (68%). According to FTIR spectroscopic data of wine samples, S. cerevisiae isolates formed a cluster which were generally separated from all other yeasts. Totally 182 olive yeasts were identified from naturally debittered Hurma and a common olive variety and their leaves. The most common yeasts were Metschnikowia sp. (39%) and Aureobasidium sp (78%) in the first and the second harvest years, respectively. Since only Aureobasidium sp. was the common yeast isolated from Hurma during both years, any link between natural debittering of Hurma and the yeast population of this olive type might be related to Aureobasidium sp. Molecularly identified yeast types generally formed different clusters and showed spectral differences. For antimicrobial activity tests, all phenolic compounds were found effective on both S. cerevisiae and A. pullulans; however, A. pullulans was observed to be more sensitive. Antimicrobial activity was differentiated with respect to treatment time and phenol concentration with statistical treatment of FTIR data. As a complementary technique, FTIR could be successfully used for identification of yeasts and characterization of antimicrobial activity of phenolics against yeasts.
An Assessment of Post-Earthquake Issues in UNESCO (United Nations Educational, Scientific and Cultural Organization) Gastronomic Cities Gaziantep, Hatay and Şanlıurfa in Turkey
(2023) Kızılgeçi, çiğdem
estinations catering to tourists with specific gastronomic preferences or diverse motivations may experience occasional disruptions in the range of offerings available. This scenario may arise due to anthropogenic factors or natural phenomena that result in varying degrees of environmental degradation. The literature commonly reports that regions experiencing disasters such as wars, floods, epidemics, earthquakes, and hurricanes are susceptible to significant life, property, and economic losses. The seismic events thatcommenced on February 6th, 2023 and persist to the present have engendered a consequential phenomenon within the nation of Turkey. The present research has been conducted to examine the prospective impacts of the Gaziantep/Kahramanmaraş earthquakes of 2023 on Gastronomy tourism and to propose viable remedies for any associated issues. The study employed qualitative research methods, specifically observation and literature review, to gather data. The data that was acquired was subjected to analysis using the descriptive analysis methodology. In summary, based on the scientific literature review and contemporary scientific assessments of gastronomic tourism, it has been observed that this phenomenon can be leveraged as a tourism asset in the future, despite certain criticisms. Upon evaluating both domestic and foreign visual and printed media, it is apparent that there is a prevalence of favorable news regarding gastronomy tourism. Based on the literature and observational data gathered in the study, it is believed that the impact of the earthquake on the gastronomic tourism of Gaziantep, Hatay, and Şanlıurfa, which are recognized as UNESCO (United Nations Educational, Scientific and Cultural Organization) gastronomic cities, can be mitigated through appropriate measures. With multidimensional planning, the gastronomy of these cities is expected to emerge even stronger from the aftermath of the earthquake
Automatic Detection of Brain Tumors With the Aid of Ensemble Deep Learning Architectures and Class Activation Map Indicators by Employing Magnetic Resonance Images
(Elsevier, 2024) Turk, Omer; Ozhan, Davut; Acar, Emrullah; Akinci, Tahir Cetin; Yilmaz, Musa; Türk, Ömer
Today, as in every life-threatening disease, early diagnosis of brain tumors plays a life-saving role. The brain tumor is formed by the transformation of brain cells from their normal structures into abnormal cell structures. These formed abnormal cells begin to form in masses in the brain regions. Nowadays, many different techniques are employed to detect these tumor masses, and the most common of these techniques is Magnetic Resonance Imaging (MRI). In this study, it is aimed to automatically detect brain tumors with the help of ensemble deep learning architectures (ResNet50, VGG19, InceptionV3 and MobileNet) and Class Activation Maps (CAMs) indicators by employing MRI images. The proposed system was implemented in three stages. In the first stage, it was determined whether there was a tumor in the MR images Tumor) were detected from MR images (Multi-class Approach). In the last stage, CAMs of each tumor group were created as an alternative tool to facilitate the work of specialists in tumor detection. The results showed that the overall accuracy of the binary approach was calculated as 100% on the ResNet50, InceptionV3 and MobileNet architectures, and 99.71% on the VGG19 architecture. Moreover, the accuracy values of 96.45% with ResNet50, 93.40% with VGG19, 85.03% with InceptionV3 and 89.34% with MobileNet architectures were obtained in the multi-class approach.
BEHAVIOUR, DESIGN AND STRENGTHENING TECHNIQUES OF MASONRY STRUCTURES AGAINST EARTHQUAKE EFFECTS
(Iksad Publications, 2020) Ateş, Tahir
Turkey, especially in masonry recently experienced an earthquake of this intensity has been shown in several instances that they create the overall effects on masonry structures. In these examples, there are masonry buildings that are not engineered, especially in rural areas, and the damage of these buildings has been pointed out. In particular, strengthening techniques that can be applied to both these damaged buildings and the earthquake-resistant design of undamaged or newly constructed masonry buildings are presented. Strengthening techniques stated in terms of applicability are the results of studies conducted in various universities, and it is known that these strengthening techniques are supported by laboratory experimental results.
Characterization of antimicrobial activities of olive phenolics on yeasts using conventional methods and mid-infrared spectroscopy
(2018) Canal, Canan; Ozen, Banu; Baysal, A. Handan
Olive fruit is very rich in terms of phenolic compounds. Antimicrobial activities of various phenolic compounds against bacteria and fungi are well established; however, their effects on yeasts have not been examined. Aim of this study was to investigate the antimicrobial effects induced by olive phenolic compounds, including tyrosol, hydroxytyrosol, oleuropein, luteolin and apigenin against two yeast species, Aureobasidium pullulans and Saccharomyces cerevisiae. For this purpose, yeasts were treated with various concentrations (12.5-1000 ppm) of phenolic compounds and reduction in yeast population was followed with optical density measurements with microplate reader, yeast colony forming units and mid-infrared spectroscopy. All phenolic compounds were effective on both yeasts, especially 200 ppm and higher concentrations have significant antimicrobial activity; however, effects of lower levels depend on the type of phenolic compound. According to mid-infrared spectral data, significant changes were observed in 1200-900 cm-1 range corresponding to carbohydrates of yeast structure as a result of exposure to all phenolic compounds except tyrosol. Spectra of tyrosol and luteolin treated yeasts also showed changes in 1750-1500 cm-1 related to amide section and 3600-3000 cm-1 fatty acid region. Since phenolic compounds from olives were effective against yeasts, they could be used in food applications where yeast growth showed problem. In addition, FTIR spectroscopy could be successfully used to monitor and characterize antimicrobial activity of phenolic compounds on yeasts as complementary to conventional microbiological methods.
Characterization of Wine Yeasts during Wine Process using Different Techniques
(2015) Canal, Canan; Baysal, A. Handan; Ozen, Banu
Study of the microorganisms that colonise the skin of grapes has been an important topic in microbial taxonomy of especially yeasts associated with vines and vineyards. It is known that yeast microbiota on grapes and in musts is influenced by factors such as climatic conditions, geographical location of the vineyard and grape variety. Molecular methods have been used for the identification of yeasts from wines and the most relevant molecular methods used in the identification of yeast species are based on the variability of the ribosomal genes 5.8S, 18S and 26S. Previous results have demonstrated that the complex ITS regions (non-coding and variable) and 5.8S rRNA gene (coding and conserved) are useful in measuring close fungus phylogenetic relationships. Mid-infrared spectroscopy is a rapid technique which provides highly specific biochemical fingerprints of microorganisms and coupled with different chemometrics analyses offer a wide range of applications including detection, taxonomic level classification and characterization. The objective of this study was identification of yeast flora of 7 wine samples (red, rose and white) through entire wine process from must until the end of fermentation using molecular methods in comparison with cultural methods followed by mid-IR spectroscopic techniques to monitor the diversity of yeasts during a wine process. As a result, identified yeast species included M.pulcherrima (2/19, 11%), P.membranifaciens (3/19, 16%), H.uvarum (1/19, 5%) and S.cerevisiae (13/19, 68%) during the whole process. Multivariate analysis of the data showed that S.cerevisiae isolates formed a cluster which were probably starter cultures and this cluster was generally separated from the other three yeasts which were isolated at the beginning of wine process. Therefore, it was concluded that FTIR could be succesfully used as a complementary method of molecular techniques for differentiation of wine yeast species isolated at different steps of wine process and monitoring the food process microbiologically.
Characterization of yeast flora of “hurma” olives using molecular methods and mid-IR spectroscopy
(2015) Canal, Canan; Baysal, A. Handan; Özen, Fatma Banu
Among the olive varieties in Turkey, Erkence olives, grown in nearby area around Karaburun Peninsula of Izmir, go through a natural debittering phase on the tree during its ripening. As a result of this phase, the olives lose their bitter taste while still on the tree and have a dark brownish color in the inside and a wrinkled outer layer which are their differentiating appearance characteristics from olives that do not undergo this process. This naturally debittered olive type is known by the name of Hurma (Aktas et al., 2014). According to an old study performed in Greece with a similar type of olive, the debittering process was attributed to the action of a fungus, Phoma olea,which hydrolyses oleuropein, a bitter phenolic compound of olives (Kalogeras, 1932). There is no study in the literature related to the characterization of yeasts on this unique type of olive, Hurma. Until present, the characterization of yeasts associated with table olives has been made through biochemical and morphological methods, using the taxonomic keys (Kurztman and Fell, 1998). More recently, molecular methods and FTIR spectroscopy using chemometric techniques have been used for the identification of yeasts due to being rapid, easy and more precise methods for yeast identification. In order to understand the role of yeasts in maturation and debittering process of natural Hurma olives, characterization of olive yeasts from two olive types, Hurma and Gemlik, an olive variety which is commonly consumed as table olive, was aimed using molecular methods and mid-IR spectroscopy in comparison with cultural methods.
Chemical characterization of waste tire pyrolysis products
(International Advanced Researches and Engineering Journal, 2021) Uğuz, Gediz; Ayanoğlu, Abdulkadir
The significance of tire disposal, an attractive waste to convert into burning oil or absorber etc.,has been increasing day by day. However, if it does not change into a useful form, it will damagethe nature and the living things. Thus, pyrolysis, a well-known method, which is used to convertrecycle tire waste into gas, liquid and char. On the other hand, the waste pyrolysis oil or wastetire oil (WTO) has a substantial avaliable calorific value similar to those of fossil fuels. Due topyrolysis reaction, high amount of sulfur is detected in the WTO; therefore, another step ofexplosion applied to WTO to decrease sulfur and also re-upgrade quality of oil with suchcatalysts as Calcium Oxide (CaO) and Natural Zeolite (NZ) at a ratio from 2 to 10 with anincrease of 2 for each step, individually. It is noticed that distillation test is a key analysis forseparation discrimination of rich or lean quality fuel. As a consequence of mixture of catalystWTO reactions, the best curve was observed at a 10% CaO-WTO mixture which was close todiesel#2 and the mixture was separated into two new fuels as light (Gasoline Like Fuel orabbreviated as GLF) and heavy one (Diesel Like Fuel or shortened as DLF) due to temperaturedifferences. According to distillation, FT-IR, NMR and UV–vis were used to analyze WTO,GLF and DLF for defining their characterization as well. Thus, the characterization result data ofsamples have quasi-equivalent with standard petroleum in open literature, and can be combustedin engine as well.
A Class Activation Map-Based Interpretable Transfer Learning Model for Automated Detection of ADHD from fMRI Data
(Sage Journals, 2022) Uyulan, Caglar; Erguzel, Turker Tekin; Türk, Ömer; Farhad, Shams; Metin, Bariş; Tarhan, Nevzat; Türk, Ömer
Automatic detection of Attention Deficit Hyperactivity Disorder (ADHD) based on the functional Magnetic Resonance Imaging (fMRI) through Deep Learning (DL) is becoming a quite useful methodology due to the curse of-dimensionality problem of the data is solved. Also, this method proposes an invasive and robust solution to the variances in data acquisition and class distribution imbalances. In this paper, a transfer learning approach, specifically ResNet-50 type pre-trained 2D-Convolutional Neural Network (CNN) was used to automatically classify ADHD and healthy children. The results demonstrated that ResNet-50 architecture with 10-k cross-validation (CV) achieves an overall classification accuracy of 93.45%. The interpretation of the results was done via the Class Activation Map (CAM) analysis which showed that children with ADHD differed from controls in a wide range of brain areas including frontal, parietal and temporal lobes.
Classification and analysis of epileptic EEG recordings using convolutional neural network and class activation mapping
(2021) Yildiz, Abdulnasir; Zan, Hasan; Said, Sherif; Zan, Hasan
Electrical bio-signals have the potential to be used in different applications due to their hidden nature and their ability to facilitate liveness detection. This paper investigates the feasibility of using the Convolutional Neural Network (CNN) to classify and analyze electroencephalogram (EEG) data with their time-frequency representations and class activation mapping (CAM) to detect epilepsy disease. Several types of pre-trained CNNs are employed for a multi-class classification task (AlexNet, GoogLeNet, ResNet-18, and ResNet-50) and their results are compared. Also, a novel convolutional neural network architecture comprised of two horizontally concatenated GoogLeNets is proposed with two inputs scalograms and spectrogram of the eplictic EEG signal. Four segment lengths (4097, 2048, 1024, and 512 sampling points) with three time-frequency representations (short-time Fourier, Wavelet, and Hilbert-Huang transform) are statistically evaluated. The dataset used in this research is collected at the University of Bonn. The dataset is reorganized as normal, interictal, and ictal. The maximum achieved accuracies for 4097, 2048, 1024, and 512 sampling points are 100 %, 100 %, 100 %, and 99.5 % respectively. The CAM method is used to analyze discriminative regions of time-frequency representations of EEG segments and networks' decisions. This method showed CNN models used different time and frequency regions of input images for each class with correct and incorrect predictions.
Classification of electroencephalogram records related to cursor movements with a hybrid method based on deep learning
(Wiley Online Library, 2021) Türk, Ömer; Türk, Ömer
In brain computer interface (BCI), many transformation methods are used whenprocessing electroencephalogram (EEG) signals. Thus, the EEG can be represen-ted in different domains. However, designing an EEG-based BCI system withoutany transformation technique is a challenge. For this purpose, in this study, aBCI model is proposed without any transformation. The classification of cursordown and cursor up movements using the EEG signals received from the brain isaimed at in the proposed model. The EEG patterns were classified using twomethods. Firstly, EEG signals were classified by classic convolutional neural net-work (CNN). Secondly, proposed hybrid structure obtained the EEG features,which were classified by k-NN and SVM, using CNN. Classification with CNNarchitecture gave a result of 68.15% while the hybrid method using k-NN andSVM classifiers yielded 97.55% and 97.61% respectively. The hybrid proposedmethod were more successful than the studies in the literature.
Classification of Epilepsy Types from Electroencephalogram Time Series Using Continuous Wavelet Transform Scalogram-Based Convolutional Neural Network
(ASTM International, 2020) Türk, Ömer; Akpolat, Veysi; Varol, Sefer; Aluçlu, Mehmet Ufuk; Özerdem, Mehmet Siraç; Türk, Ömer
During the supervisory activities of the brain, the electrical activities of nerve cell clusters produce oscillations. These complex biopotential oscillations are called electroencephalogram (EEG) signals. Certain diseases, such as epilepsy, can be detected by measuring these signals. Epilepsy is a disease that manifests itself as seizures. These seizures manifest themselves in different characteristics. These different characteristics divide epilepsy seizure types into two main groups: generalized and partial epilepsy. This study aimed to classify different types of epilepsy from EEG signals. For this purpose, a scalogram-based, deep learning approach has been developed. The utilized classification process had the following main steps: the scalogram images were obtained by using the continuous wavelet transform (CWT) method. So, a one-dimension EEG time series was converted to a two-dimensional time-frequency data set in order to extract more features. Then, the increased dimension data set (CWT scalogram images) was applied to the convolutional neural network (CNN) as input patterns for classifying the images. The EEG signals were taken from Dicle University, Neurology Clinic of Medical School. This data consisted of four classes: healthy brain waves, generalized preseizure, generalized seizure, and partial epilepsy brain waves. With the proposed method, the average accuracy performance of three of the EEG records' classes (healthy, generalized preseizure, and generalized seizure), and that of all four classes of EEG records were 90.16 % (± 0.20) and 84.66 % (± 0.48). According to these results, regarding the specific accuracy ratings of the recordings, the healthy EEG records scored 91.29 %, generalized epileptic seizure records were at 96.50 %, partial seizure EEG records scored 89.63 %, and the preseizure EEG records had a 90.44 % rating. The results of the proposed method were compared to the results of both similar studies and conventional methods. As a result, the performance of the proposed method was found to be acceptable.
Comparison of Energy and Cost Analysis of Two Different Industrial Corn Drying Plants Using Solid Fuel
(IJARSET, 2018) ÜNAL, Fatih; BULUT, Hüsamettin; KAHRAMAN, Ahmet
In this study, the energy and cost analyzes of two different corn drying plants using solid fuel in the heating of drying air are performed. In the evaluated drying processes, corn which has high humidity, dried to a value below 15% relative humidity which is the storage humidity. In the drying process, thermodynamic properties such as temperature, relative humidity and air velocity of the node points determined in the systems were measured. The continuous operating temperatures of the facilities specified for analyzes were taken into account. In the analyzes, measurements were made for the drying air inlet temperatures of drying plants which was drying temperature of 70°C and 112°C. Based on the results obtained at the determined nodes, the influences on the inlet temperature of the drying air, the thermal value of the fuel, the fuel consumption, the energy efficiency and the unit drying cost have been evaluated. As a result, it has been found that the increase in inlet air temperature reduces boiler efficiency and energy efficiency, increases unit drying cost and fuel consumption. It has been found that high thermal value fuel usage has an important role in decreasing drying time as it allows working at high temperatures.
Comparison of near sets by means of a chain of features
(2016) Özcan, A. Fatih; Bağırmaz, Nurettin
If the number of features of objects in a perceptual system, is large, then the objects can be known better and comparable. In this paper basically, we form a chain of feature sets that describe objects and then by means of this chain of feature sets, we investigate the nearness of sets and near sets in a perceptual system
A comprehensive review on detection of cyber-attacks: Data sets, methods, challenges, and future research directions
(ScienceDirect, 2022) Ahmetoglu, Huseyin; Das, Resul
Rapid developments in network technologies and the amount and scope of data transferred on networks are increasing day by day. Depending on this situation, the density and complexity of cyber threats and attacks are also expanding. The ever-increasing network density makes it difficult for cyber-security professionals to monitor every movement on the network. More frequent and complex cyber-attacks make the detection and identification of anomalies in network events more complex. Machine learning offers various tools and techniques for automating the detection of cyber attacks and for rapid prediction and analysis of attack types. This study discusses the approaches to machine learning methods used to detect attacks. We examined the detection, classification, clustering, and analysis of anomalies in network traffic. We gave the cyber-security focus, machine learning methods, and data sets used in each study we examined. We investigated which feature selection or dimension reduction method was applied to the data sets used in the studies. We presented in detail the types of classification carried out in these studies, which methods were compared with other methods, the performance metrics used, and the results obtained in tables. We examined the data sets of network attacks presented as open access. We suggested a basic taxonomy for cyber attacks. Finally, we discussed the difficulties encountered in machine learning applications used in network attacks and their solutions.
CONDENSATION ANALYSIS OF THE INSULATION OF WALLS IN MARDIN PROVINCE ACCORDING TO DIFFERENT LOCATIONS
(2019) Ünal, Fatih
In this study, condensation and vapor diffusion caused by different positioned insulation in the wall were analyzed for Mardin province. In the analysis, according to the 2008 standard of TS 825, the MATLAB calculation program was used with the Glaser graphing method and graphical user interface (GUI). Extruded polyurethane foam was used as the insulation material and normal unreinforced concrete was chosen as the wall. Evaporation and condensation values were determined by creating 6 different wall models with the same insulation thickness of 20 cm and an unreinforced concrete wall was covered with 2 cm plaster on the inside with a 3 cm thickness on the outside. The data obtained for 2 cm and 4 cm insulation thicknesses are presented in tables and the results are interpreted for Mardin province. Consequently, it was seen that the worst wall structure in terms of condensation and evaporation was obtained in the middle insulated wall and later in the interior insulated wall structure. The externally insulated wall did not show any condensation.
The convolutional neural network approach from electroencephalogram signals in emotional detection
(Concurrency Computation, 2021) Türk, Ömer; Özerdem, Mehmet Siraç; Türk, Ömer
Although brain-computer interfaces (BCI) progress rapidly, the desired success has not been achieved yet. One of these BCI is to detect emotional states in humans. An emotional state is a brain activity consisting of hormonal and mental reasons in the face of events. Emotions can be detected by electroencephalogram (EEG) signals due to these activities. Being able to detect the emotional state from EEG signals is important in terms of both time and cost. In this study, a method is proposed for the detection of the emotional state by using EEG signals. In the proposed method, we aim to classify EEG signals without any transform (Fourier transform, wavelet transform, etc.) or feature extraction method as a pre-processing. For this purpose, convolutional neural networks (CNNs) are used as classifiers, together with SEED EEG dataset containing three different emotional (positive, negative, and neutral) states. The records used in the study were taken from 15 participants in three sessions. In the proposed method, raw channel-time EEG recordings are converted into 28 × 28 size pattern segments without pre-processing. The obtained patterns are then classified in the CNN. As a result of the classification, three emotion performance averages of all participants are found to be 88.84%. Based on the participants, the highest classification performance is 93.91%, while the lowest classification performance is 77.70%. Also, the average f-score is found to be 0.88 for positive emotion, 0.87 for negative emotion, and 0.89 for neutral emotion. Likewise, the average kappa value is 0.82 for positive emotion, 0.81 for negative emotion, and 0.83 for neutral emotion. The results of the method proposed in the study are compared with the results of similar studies in the literature. We conclude that the proposed method has an acceptable level of performance.

Browse

Browsing Mardin Meslek Yüksekokulu by Language "en"