According to the World Health Organization, cough is one of the most prominent symptoms of the COVID-19 disease declared as a global pandemic. The symptom is seen in 68% to 83% of people with COVID-19 who come to the clinic for medical examination. Therefore, during the pandemic, cough plays an important role in diagnosing of COVID-19 and distinguishing patients from healthy individuals. This study aims to distinguish the cough sounds of COVID-19 positive people from those of COVID-19 negative, thus providing automatic detection and support for the diagnosis of COVID-19. For this aim, “Virufy” dataset containing cough sounds labeled as COVID-19 and Non COVID-19 was included. After using the ADASYN technique to balance the data, independent modes were obtained for each sound by utilizing the Variational Mode Decomposition (VMD) method and various features were extracted from every mode. Afterward, the most effective features were selected by ReliefF algorithm. Following, ensemble machine learning methods, namely Random Forest, Gradient Boosting Machine and Adaboost were prepared to identify cough sounds as COVID-19 and Non COVID-19 through classification. As a result, the best performance was obtained with the Gradient Boosting Machine as 94.19% accuracy, 87.67% sensitivity, 100% specificity, 100% precision, 93.43% F-score, 0.88 kappa and 93.87% area under the ROC curve.
{"title":"VARYASYONEL MOD AYRIŞTIRMASIYLA ÖKSÜRÜK SESLERİNDEN KOVİD-19 TESPİTİ","authors":"Fatma Zehra SOLAK","doi":"10.36306/konjes.1110235","DOIUrl":"https://doi.org/10.36306/konjes.1110235","url":null,"abstract":"According to the World Health Organization, cough is one of the most prominent symptoms of the COVID-19 disease declared as a global pandemic. The symptom is seen in 68% to 83% of people with COVID-19 who come to the clinic for medical examination. Therefore, during the pandemic, cough plays an important role in diagnosing of COVID-19 and distinguishing patients from healthy individuals. This study aims to distinguish the cough sounds of COVID-19 positive people from those of COVID-19 negative, thus providing automatic detection and support for the diagnosis of COVID-19. For this aim, “Virufy” dataset containing cough sounds labeled as COVID-19 and Non COVID-19 was included. After using the ADASYN technique to balance the data, independent modes were obtained for each sound by utilizing the Variational Mode Decomposition (VMD) method and various features were extracted from every mode. Afterward, the most effective features were selected by ReliefF algorithm. Following, ensemble machine learning methods, namely Random Forest, Gradient Boosting Machine and Adaboost were prepared to identify cough sounds as COVID-19 and Non COVID-19 through classification. As a result, the best performance was obtained with the Gradient Boosting Machine as 94.19% accuracy, 87.67% sensitivity, 100% specificity, 100% precision, 93.43% F-score, 0.88 kappa and 93.87% area under the ROC curve.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Damla KARAGOZLU, John Karima MACHARIA, Tolgay KARANFİLLER
The paper aims to carry out a systematic literature review to determine what computer vision techniques are prevalent in the field of precision agriculture, specifically for weed control. The review also noted what situations the techniques were best suited to and compared their various efficacy rates. The review covered a period between the years 2011 to 2022. The study findings indicate that computer vision in conjunction with machine learning and particularly Convolutional Neural Networks were the preferred options for most researchers. The techniques were generally applicable to all situations farmers may face themselves with a few exceptions, and they showed high efficacy rates across the board when it came to weed detection and control.
{"title":"COMPUTER VISION IN PRECISION AGRICULTURE FOR WEED CONTROL: A SYSTEMATIC LITERATURE REVIEW","authors":"Damla KARAGOZLU, John Karima MACHARIA, Tolgay KARANFİLLER","doi":"10.36306/konjes.1097969","DOIUrl":"https://doi.org/10.36306/konjes.1097969","url":null,"abstract":"The paper aims to carry out a systematic literature review to determine what computer vision techniques are prevalent in the field of precision agriculture, specifically for weed control. The review also noted what situations the techniques were best suited to and compared their various efficacy rates. The review covered a period between the years 2011 to 2022. The study findings indicate that computer vision in conjunction with machine learning and particularly Convolutional Neural Networks were the preferred options for most researchers. The techniques were generally applicable to all situations farmers may face themselves with a few exceptions, and they showed high efficacy rates across the board when it came to weed detection and control.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study introduces the modeling and analysis of the extraction process of bioactive compounds from fenugreek seeds in different solid-to-solvent ratios (0.5-60 g/L) and extraction times. Maceration was applied with agitation for the extraction processes and total phenolic compounds, total flavonoid content and antioxidant activity of the extracts were measured as experimental data. The amount of extractable phenolic compounds having antioxidant effect was increased by adjusting the solid-to-solvent ratio. According to obtained results, the highest values were determined as 12564.08±376.88 mg gallic acid/100 g dry sample, 7540.44±39.67 mg quercetin/100 g dry sample and 1904.80±17.43 mM Trolox/100 g dry sample for total phenolic compounds, total flavonoid content, and antioxidant activity, respectively. The extraction process was modeled using standard Artificial Neural Networks (ANN) and Pi-Sigma Neural-Networks (PSNN). The PSNN model had a higher prediction efficiency with lower RMSE (%) values varied between 0.94% and 1.30% for both training and testing.
{"title":"EXTRACTION OF PHENOLIC COMPOUNDS FROM FENUGREEK SEEDS: MODELLING AND ANALYSIS USING ARTIFICIAL NEURAL NETWORKS","authors":"Selami BEYHAN, Hilal İŞLEROĞLU","doi":"10.36306/konjes.1208658","DOIUrl":"https://doi.org/10.36306/konjes.1208658","url":null,"abstract":"This study introduces the modeling and analysis of the extraction process of bioactive compounds from fenugreek seeds in different solid-to-solvent ratios (0.5-60 g/L) and extraction times. Maceration was applied with agitation for the extraction processes and total phenolic compounds, total flavonoid content and antioxidant activity of the extracts were measured as experimental data. The amount of extractable phenolic compounds having antioxidant effect was increased by adjusting the solid-to-solvent ratio. According to obtained results, the highest values were determined as 12564.08±376.88 mg gallic acid/100 g dry sample, 7540.44±39.67 mg quercetin/100 g dry sample and 1904.80±17.43 mM Trolox/100 g dry sample for total phenolic compounds, total flavonoid content, and antioxidant activity, respectively. The extraction process was modeled using standard Artificial Neural Networks (ANN) and Pi-Sigma Neural-Networks (PSNN). The PSNN model had a higher prediction efficiency with lower RMSE (%) values varied between 0.94% and 1.30% for both training and testing.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cihanbeyli (Konya) sınırları içerisinde bulunan Kuşça bölgesindeki peribacası türündeki jeolojik oluşumlar, doğal güzellik yönünden görülmeye değer olup bölge turizmi açısından çok yüksek potansiyele sahiptir. Doğal miras özelliği bulunan bu tür jeolojik oluşumların ayrıntılı bir şekilde araştırılarak turizm potansiyellerinin belirlenmesi ve bölgeye bir jeopark statüsünün kazandırılmasının sağlanması önemli bir konudur. Bu amaç doğrultusunda bu çalışmada, bölgede bulunan peri bacası oluşumlarından alınan kayaç örnekleri üzerinde bazı fiziksel ve mekanik deneyler yapılmış ve sonuçları değerlendirilmiştir. Bu sayede peri bacaları oluşumları hakkında önemli bilgiler edinilmiş ve koruma çalışmaları adına ilk adımlar atılmıştır. Yapılan çalışma ile bölgenin tanıtımı amaçlanmış ve bölgenin jeoljik yapısının jeopark olarak nitelendirilme potansiyeli belirlenmiştir.
{"title":"Investigation of Fairy Chimneys of Cihanbeyli-Celil Strait (Konya) and Determination of Physico-Mechanical Properties","authors":"Niyazi BİLİM, Bilgehan KEKEÇ, Emre KARAKAYA, Özer KARAKAYACI","doi":"10.36306/konjes.1048798","DOIUrl":"https://doi.org/10.36306/konjes.1048798","url":null,"abstract":"Cihanbeyli (Konya) sınırları içerisinde bulunan Kuşça bölgesindeki peribacası türündeki jeolojik oluşumlar, doğal güzellik yönünden görülmeye değer olup bölge turizmi açısından çok yüksek potansiyele sahiptir. Doğal miras özelliği bulunan bu tür jeolojik oluşumların ayrıntılı bir şekilde araştırılarak turizm potansiyellerinin belirlenmesi ve bölgeye bir jeopark statüsünün kazandırılmasının sağlanması önemli bir konudur. Bu amaç doğrultusunda bu çalışmada, bölgede bulunan peri bacası oluşumlarından alınan kayaç örnekleri üzerinde bazı fiziksel ve mekanik deneyler yapılmış ve sonuçları değerlendirilmiştir. Bu sayede peri bacaları oluşumları hakkında önemli bilgiler edinilmiş ve koruma çalışmaları adına ilk adımlar atılmıştır. Yapılan çalışma ile bölgenin tanıtımı amaçlanmış ve bölgenin jeoljik yapısının jeopark olarak nitelendirilme potansiyeli belirlenmiştir.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Firdevs ÇİRLİ, Gülcihan GÜZEL KAYA, Hüseyin DEVECİ
Hydrogels are cross-linked polymeric networks which retain large amounts of water. The hydrogels with response capability to various stimuli such as pH and temperature have received great attention in many fields. In this study, hydrogels were synthesized by free radical solution polymerization through optimization of acrylamide/sodium acrylate mole ratio and ethylene glycol dimethacrylate content. With the addition of sepiolite as filler into the hydrogel network which had highest swelling percent, hydrogel composites were obtained. In the presence of 10 wt% sepiolite, maximum swelling percent was determined as approximately 10600%. Swelling properties of the hydrogel composite including 10 wt% sepiolite was investigated depending on pH, salt effect and temperature. With increasing pH value, swelling percent of the hydrogel composite showed an increase. At high temperatures, the hydrogel composite exhibited higher swelling percent. Swelling tests in 0.1 M NaCl, CaCl2 and FeCl3 solutions revealed that the lowest swelling percent was observed in 0.1 M FeCl3 solution. Fourier transform infrared spectroscopy (FTIR) analyses verified successfully preparation of the hydrogel composites. Regular layers of the sepiolite in the hydrogel network which made water diffusion easily were shown by scanning electron microscopy (SEM) analyses. Thermogravimetric analyses (TGA) indicated that thermal stability of the hydrogel network was increased with the addition of sepiolite.
水凝胶是交联的聚合物网络，可以保留大量的水。具有对pH、温度等多种刺激响应能力的水凝胶在许多领域受到广泛关注。本研究通过优化丙烯酰胺/丙烯酸钠的摩尔比和乙二醇二甲基丙烯酸酯的含量，采用自由基溶液聚合法制备了水凝胶。在膨胀率最高的水凝胶网络中加入海泡石作为填料，得到了水凝胶复合材料。当海泡石含量为10%时，最大溶胀率约为10600%。研究了含10%海泡石的水凝胶复合材料在pH、盐效应和温度下的溶胀特性。随着pH值的增加，水凝胶复合材料的溶胀率增加。在高温下，水凝胶复合材料表现出较高的溶胀率。在0.1 M NaCl、CaCl2和FeCl3溶液中进行溶胀试验，发现0.1 M FeCl3溶液溶胀率最低。傅里叶变换红外光谱(FTIR)分析成功地验证了水凝胶复合材料的制备。扫描电镜(SEM)分析表明，海泡石在水凝胶网络中呈规则层状，使水易于扩散。热重分析(TGA)表明，海泡石的加入提高了水凝胶网络的热稳定性。
{"title":"INVESTIGATION OF PHYSICOCHEMICAL AND THERMAL PROPERTIES OF CLAY-HYDROGEL COMPOSITES","authors":"Firdevs ÇİRLİ, Gülcihan GÜZEL KAYA, Hüseyin DEVECİ","doi":"10.36306/konjes.1218991","DOIUrl":"https://doi.org/10.36306/konjes.1218991","url":null,"abstract":"Hydrogels are cross-linked polymeric networks which retain large amounts of water. The hydrogels with response capability to various stimuli such as pH and temperature have received great attention in many fields. In this study, hydrogels were synthesized by free radical solution polymerization through optimization of acrylamide/sodium acrylate mole ratio and ethylene glycol dimethacrylate content. With the addition of sepiolite as filler into the hydrogel network which had highest swelling percent, hydrogel composites were obtained. In the presence of 10 wt% sepiolite, maximum swelling percent was determined as approximately 10600%. Swelling properties of the hydrogel composite including 10 wt% sepiolite was investigated depending on pH, salt effect and temperature. With increasing pH value, swelling percent of the hydrogel composite showed an increase. At high temperatures, the hydrogel composite exhibited higher swelling percent. Swelling tests in 0.1 M NaCl, CaCl2 and FeCl3 solutions revealed that the lowest swelling percent was observed in 0.1 M FeCl3 solution. Fourier transform infrared spectroscopy (FTIR) analyses verified successfully preparation of the hydrogel composites. Regular layers of the sepiolite in the hydrogel network which made water diffusion easily were shown by scanning electron microscopy (SEM) analyses. Thermogravimetric analyses (TGA) indicated that thermal stability of the hydrogel network was increased with the addition of sepiolite.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Several constant breadth curves are defined that can be used as cam profiles in constant breadth cam mechanisms that are closed cam mechanisms. There are two objectives for this study. One of them is to study the kinematic analysis of different type of constant breadth cam mechanisms. The other objective is to obtain a dwell period for constant breadth cam driven linkages that is impossible for a standard cam mechanism. A general kinematic analysis of a constant breadth cam mechanism with translating flat-faced follower was carried out with the principle of kinematic inversion. With the results, the kinematic analyses of the constant breadth cam driven inverted slider crank mechanism and four bar mechanism were examined in detail and a general method is given for all constant breadth cam profiles and cam driven linkages. It has been seen that a dwell period of 45° (with the fixed joint coordinates as x_n = 18 mm and y_n= 8.5 mm) and 40° (with the fixed joint coordinates as x_n = 18.5 mm and y_n= 8.5 mm) can be obtained in designed cam driven four bar and inverted slider crank mechanism respectively. After the displacement analysis, some velocity and acceleration analysis examples are given by taking the derivative of displacement. Similar kinematic analyses are possible for cam-driven mechanisms with more links. Also, it has been seen that changing the location of fixed joint of the cam profile can affect the displacement, velocity and acceleration graphics of the mechanism. With this, the dwell period can be changed too.
{"title":"KINEMATIC ANALYSIS OF CONSTANT BREADTH CAM DRIVEN LINKAGES","authors":"Mert Eren AYĞAHOĞLU, Ziya ŞAKA","doi":"10.36306/konjes.1249830","DOIUrl":"https://doi.org/10.36306/konjes.1249830","url":null,"abstract":"Several constant breadth curves are defined that can be used as cam profiles in constant breadth cam mechanisms that are closed cam mechanisms. There are two objectives for this study. One of them is to study the kinematic analysis of different type of constant breadth cam mechanisms. The other objective is to obtain a dwell period for constant breadth cam driven linkages that is impossible for a standard cam mechanism. A general kinematic analysis of a constant breadth cam mechanism with translating flat-faced follower was carried out with the principle of kinematic inversion. With the results, the kinematic analyses of the constant breadth cam driven inverted slider crank mechanism and four bar mechanism were examined in detail and a general method is given for all constant breadth cam profiles and cam driven linkages. It has been seen that a dwell period of 45° (with the fixed joint coordinates as x_n = 18 mm and y_n= 8.5 mm) and 40° (with the fixed joint coordinates as x_n = 18.5 mm and y_n= 8.5 mm) can be obtained in designed cam driven four bar and inverted slider crank mechanism respectively. After the displacement analysis, some velocity and acceleration analysis examples are given by taking the derivative of displacement. Similar kinematic analyses are possible for cam-driven mechanisms with more links. Also, it has been seen that changing the location of fixed joint of the cam profile can affect the displacement, velocity and acceleration graphics of the mechanism. With this, the dwell period can be changed too.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135675792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, ground state properties of Ni2ZnAl alloy in L21 phase from Heusler family were optimized. The calculated parameters are in harmony with the available literature data. Elastic constants were calculated using optimized parameters. The calculated elastic constants were found to meet the Born mechanical stability criteria. By using these constants, some mechanical and thermodynamic properties of the material such as elastic modulus, Vicker hardness, anisotropic nature, melting temperature were investigated in detail. Calculations showed that the Ni2ZnAl alloy is ductile, soft, and anisotropic. As such, it is a candidate material for applications that do not require hardness. The free energy, vibrational energy, entropy, and heat capacity of the Ni2ZnAl alloy were investigated using a semi- harmonic approach in the range of 0-800 K. All the total energy calculations were performed using the open-source Quantum Espresso software and ab-initio pseudopotential method based on the density functional theory (DFT) scheme within a generalized gradient approximation (GGA). According to the data obtained because of the study, Ni2ZnAl alloy is a potential candidate for industrial use.
{"title":"Ni2ZnAl BİLEŞİĞİNİN İLK PRENSİPLER YÖNTEMİ İLE İNCELENMESİ","authors":"Tahsin ÖZER","doi":"10.36306/konjes.1171749","DOIUrl":"https://doi.org/10.36306/konjes.1171749","url":null,"abstract":"In this study, ground state properties of Ni2ZnAl alloy in L21 phase from Heusler family were optimized. The calculated parameters are in harmony with the available literature data. Elastic constants were calculated using optimized parameters. The calculated elastic constants were found to meet the Born mechanical stability criteria. By using these constants, some mechanical and thermodynamic properties of the material such as elastic modulus, Vicker hardness, anisotropic nature, melting temperature were investigated in detail. Calculations showed that the Ni2ZnAl alloy is ductile, soft, and anisotropic. As such, it is a candidate material for applications that do not require hardness. The free energy, vibrational energy, entropy, and heat capacity of the Ni2ZnAl alloy were investigated using a semi- harmonic approach in the range of 0-800 K. All the total energy calculations were performed using the open-source Quantum Espresso software and ab-initio pseudopotential method based on the density functional theory (DFT) scheme within a generalized gradient approximation (GGA). According to the data obtained because of the study, Ni2ZnAl alloy is a potential candidate for industrial use.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Çevresel faaliyetlerin sonuçlarını tahmin edebilecek ve aynı zamanda bu faaliyetlerin ortamı hakkında bilgi edinile bilinmesi için ses verisinin kullanılması çok önemlidir. Kentlerde meydana gelen gürültü kirliliği, güvenlik sistemleri, sağlık hizmetleri ve yerel hizmetler gibi faaliyetlerin işleyişini ve temel bilgilerini elde etmek için ses verisinden faydalanılmaktadır. Bu anlamda Çevresel Seslerin Sınıflandırması (ÇSS) kritik önem kazanmaktadır. Artan veri miktarı ve çözümlemedeki zaman kısıtlamalarından dolayı anlık otomatik olarak seslerin tanımlanmasını sağlayan yeni ve güçlü yapay zekâ yöntemlerine ihtiyaç duyulmaktadır. Bu sebeple yapılan çalışmada iki farklı ÇSS veri setinin sınıflandırılması için yeni bir yötem önerilmiştir. Bu yöntemde ilk olarak sesler görüntü formatına çevrilmiştir. Daha sonra görüntü formatındaki bu sesler için özgün Evrişimsel Sinir Ağları (ESA) modelleri tasarlanmıştır. Her bir veri seti için özgün olarak tasarlanan birden fazla ESA modelleri içerisinden en yüksek doğruluk oranına sahip ESA modelleri elde edilmiştir. Bu veri setleri sırasıyla ESC10 ve UrbanSound8K veri setleridir. Bu veri setlerindeki ses kayıtları 32x32x3 ve 224x224x3 boyutuna sahip görüntü formatına çevrilmiştir. Böylelikle toplamda 4 farklı görüntü formatında veri seti elde edilmiştir. Bu veri setlerini sınıflandırılması için geliştirilen özgün ESA modelleri sırasıyla, ESC10_ESA32, ESC10_ESA224, URBANSOUND8K_ESA32 ve URBANSOUND8K_ESA224 olarak isimlendirilmiştir. Bu modeller veri setleri üzerinde 10-Kat Çapraz Doğrulama yapılarak eğitilmiştir. Elde edilen sonuçlarda, ESC10_ESA32, ESC10_ESA224, URBANSOUND8K_ESA32 ve URBANSOUND8K_ESA224 modellerinin ortalama doğruluk oranları sırasıyla %80,75, %82,25, %88,60 ve %84,33 olarak elde edilmiştir. Elde edilen sonuçlar aynı veri setleri üzerinde literatürde yapılan diğer temel çalışmalarla karşılaştırıldığında önerilen modellerin daha iyi sonuçlar elde ettiği görülmüştür.
利用声音数据来预测环境活动的结果，同时获取这些活动的环境信息，这一点非常重要。声音数据可用于获取城市中发生的噪声污染、安全系统、卫生服务和地方服务等活动的基本运行信息。从这个意义上说，环境声音分类（ESC）变得至关重要。由于数据量不断增加，分析时间有限，因此需要新的、强大的人工智能方法来即时自动识别声音。为此，本研究提出了一种新方法，用于对两个不同的 CSR 数据集进行分类。在这种方法中，首先将声音转换成图像格式。然后，针对这些图像格式的声音设计独特的卷积神经网络（DNN）模型。对于每个数据集，从为每个数据集独特设计的多个 ESA 模型中选出准确率最高的 ESA 模型。这些数据集分别是 ESC10 数据集和 UrbanSound8K 数据集。这些数据集中的音频被转换成 32x32x3 和 224x224x3 尺寸的图像格式。因此，总共获得了 4 种不同的图像格式数据集。为对这些数据集进行分类而开发的原始 ESA 模型分别命名为 ESC10_ESA32、ESC10_ESA224、URBANSOUND8K_ESA32 和 URBANSOUND8K_ESA224。这些模型通过 10 倍交叉验证在数据集上进行了训练。结果显示，ESC10_ESA32、ESC10_ESA224、URBANSOUND8K_ESA32 和 URBANSOUND8K_ESA224 模型的平均准确率分别为 80.75%、82.25%、88.60% 和 84.33%。将所获得的结果与文献中针对相同数据集的其他基本研究结果进行比较，可以发现所提出的模型取得了更好的结果。
{"title":"ÇEVRESEL SESLERİN EVRİŞİMSEL SİNİR AĞLARI İLE SINIFLANDIRILMASI","authors":"Yalçın DİNÇER, Özkan İNİK","doi":"10.36306/konjes.1201558","DOIUrl":"https://doi.org/10.36306/konjes.1201558","url":null,"abstract":"Çevresel faaliyetlerin sonuçlarını tahmin edebilecek ve aynı zamanda bu faaliyetlerin ortamı hakkında bilgi edinile bilinmesi için ses verisinin kullanılması çok önemlidir. Kentlerde meydana gelen gürültü kirliliği, güvenlik sistemleri, sağlık hizmetleri ve yerel hizmetler gibi faaliyetlerin işleyişini ve temel bilgilerini elde etmek için ses verisinden faydalanılmaktadır. Bu anlamda Çevresel Seslerin Sınıflandırması (ÇSS) kritik önem kazanmaktadır. Artan veri miktarı ve çözümlemedeki zaman kısıtlamalarından dolayı anlık otomatik olarak seslerin tanımlanmasını sağlayan yeni ve güçlü yapay zekâ yöntemlerine ihtiyaç duyulmaktadır. Bu sebeple yapılan çalışmada iki farklı ÇSS veri setinin sınıflandırılması için yeni bir yötem önerilmiştir. Bu yöntemde ilk olarak sesler görüntü formatına çevrilmiştir. Daha sonra görüntü formatındaki bu sesler için özgün Evrişimsel Sinir Ağları (ESA) modelleri tasarlanmıştır. Her bir veri seti için özgün olarak tasarlanan birden fazla ESA modelleri içerisinden en yüksek doğruluk oranına sahip ESA modelleri elde edilmiştir. Bu veri setleri sırasıyla ESC10 ve UrbanSound8K veri setleridir. Bu veri setlerindeki ses kayıtları 32x32x3 ve 224x224x3 boyutuna sahip görüntü formatına çevrilmiştir. Böylelikle toplamda 4 farklı görüntü formatında veri seti elde edilmiştir. Bu veri setlerini sınıflandırılması için geliştirilen özgün ESA modelleri sırasıyla, ESC10_ESA32, ESC10_ESA224, URBANSOUND8K_ESA32 ve URBANSOUND8K_ESA224 olarak isimlendirilmiştir. Bu modeller veri setleri üzerinde 10-Kat Çapraz Doğrulama yapılarak eğitilmiştir. Elde edilen sonuçlarda, ESC10_ESA32, ESC10_ESA224, URBANSOUND8K_ESA32 ve URBANSOUND8K_ESA224 modellerinin ortalama doğruluk oranları sırasıyla %80,75, %82,25, %88,60 ve %84,33 olarak elde edilmiştir. Elde edilen sonuçlar aynı veri setleri üzerinde literatürde yapılan diğer temel çalışmalarla karşılaştırıldığında önerilen modellerin daha iyi sonuçlar elde ettiği görülmüştür.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ihlamur bünyesinde önemli bioaktif maddelerden (antioksidan, fenolik bileşikler) dolayı hem sağlık hem de içeçek olarak tüketilmektedir. Kurutulduktan sonra özellikle çay olarak tüketimi oldukça yaygındır. Bu çalışmada, konvektif (KK) ve imal edilen sıcaklık kontrollü mikrodalga (SKM) kurutma fırınlarında 40, 45 ve 50 ºC sıcaklıklarında ıhlamur kurutulmuştur. Kurutma işlemlerinde ıhlamur örnekleri 3.21±0.19 nem değerinden 0.12±0.02 g nem/g kuru madde nem değerine kadar kurutulmuştur. KK işleminde belirtilen sıcaklıklar için ıhlamur örnekleri sırasıyla 23.5, 15 ve 8.5 saatte kurumuştur. SKM işleminde ise belirtilen sıcaklıklar için sırasıyla 495, 225 ve 135 dakikada kurumuştur. KK işleminde tespit edilen ortalama kuruma oranı değerleri 0.004025-0.008274 g nem/g kuru madde.dakika, SKM işleminde ise bu değer ortalama 0.006178-0.0228 g nem/g kuru madde.dakika değerleri arasında değiştiği belirlenmiştir. Efektif difüzyon değerleri KK işleminde 1.46x10-5-6.02x10-6 m2/s arasında, SKM işleminde ise bu değer 1.06x10-6-2.35x10-7 m2/s arasında değiştiği belirlenmiştir. Aktivasyon enerji değerleri KK ve SKM işlemleri için sırasıyla 74.50 ve 122.47 kJ/mol olarak hesaplanmıştır. Renk kalitesi açısından en uygun (p<0.05) kurutma işlemi olarak SKM yöntemi tespit edilmiştir. Buharlaşma enerji değerleri açısından KK ve SKM işlemleri için sırasıyla 0.6998-0.8312 ve 0.5267-0.6497 kWh değerleri arasında değiştiği tespit edilmiştir. Bu çalışmada imal edilen sıcaklık kontrollü mikrodalga (SKM) kurutma işlemi ıhlamurun kuruma kinetiği, renk kalitesi ve buharlaşma enerji parametreleri açısından kurutma yöntemi olarak uygun olduğu önerilmektedir.
{"title":"KONVEKTİF VE İMAL EDİLEN SICAKLIK KONTROLLÜ MİKRODALGA FIRINLARLA KURUTULAN IHLAMURUN FİZİKO-KİMYASAL VE BUHARLAŞMA ENERJİ DEĞERLERİNİN TESPİT EDİLMESİ","authors":"Hakan POLATCI, Muhammed TAŞOVA","doi":"10.36306/konjes.1219960","DOIUrl":"https://doi.org/10.36306/konjes.1219960","url":null,"abstract":"Ihlamur bünyesinde önemli bioaktif maddelerden (antioksidan, fenolik bileşikler) dolayı hem sağlık hem de içeçek olarak tüketilmektedir. Kurutulduktan sonra özellikle çay olarak tüketimi oldukça yaygındır. Bu çalışmada, konvektif (KK) ve imal edilen sıcaklık kontrollü mikrodalga (SKM) kurutma fırınlarında 40, 45 ve 50 ºC sıcaklıklarında ıhlamur kurutulmuştur. Kurutma işlemlerinde ıhlamur örnekleri 3.21±0.19 nem değerinden 0.12±0.02 g nem/g kuru madde nem değerine kadar kurutulmuştur. KK işleminde belirtilen sıcaklıklar için ıhlamur örnekleri sırasıyla 23.5, 15 ve 8.5 saatte kurumuştur. SKM işleminde ise belirtilen sıcaklıklar için sırasıyla 495, 225 ve 135 dakikada kurumuştur. KK işleminde tespit edilen ortalama kuruma oranı değerleri 0.004025-0.008274 g nem/g kuru madde.dakika, SKM işleminde ise bu değer ortalama 0.006178-0.0228 g nem/g kuru madde.dakika değerleri arasında değiştiği belirlenmiştir. Efektif difüzyon değerleri KK işleminde 1.46x10-5-6.02x10-6 m2/s arasında, SKM işleminde ise bu değer 1.06x10-6-2.35x10-7 m2/s arasında değiştiği belirlenmiştir. Aktivasyon enerji değerleri KK ve SKM işlemleri için sırasıyla 74.50 ve 122.47 kJ/mol olarak hesaplanmıştır. Renk kalitesi açısından en uygun (p&lt;0.05) kurutma işlemi olarak SKM yöntemi tespit edilmiştir. Buharlaşma enerji değerleri açısından KK ve SKM işlemleri için sırasıyla 0.6998-0.8312 ve 0.5267-0.6497 kWh değerleri arasında değiştiği tespit edilmiştir. Bu çalışmada imal edilen sıcaklık kontrollü mikrodalga (SKM) kurutma işlemi ıhlamurun kuruma kinetiği, renk kalitesi ve buharlaşma enerji parametreleri açısından kurutma yöntemi olarak uygun olduğu önerilmektedir.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mustafa ÇATALTAŞ, Büşra ÜSTÜNEL, Nurdan AKHAN BAYKAN
As Covid-19 pandemic affected everyone in various aspects, people have been expressing their opinions on these aspects mostly on social media platforms because of the pandemic. These opinions play a crucial role in understanding the sentiments towards the pandemic. In this study, Turkish tweets on Covid-19 topic were collected from March 2020 to January 2021 and labelled as positive, negative, or neutral in terms of sentiment using BERT which is a pre-trained text classifier model. Using this labelled dataset, a set of experiments were carried out with SVM, Naive Bayes, K-Nearest Neighbors, and CNN-LSTM model machine learning algorithms for binary and multi-class classification tasks. Results of these experiments have shown that CNN-LSTM model outperforms other machine learning algorithms which are used in this study in both binary classification and multi-class classification tasks.
{"title":"COVID-19 Hakkındaki Türkçe Tweetlerde LSTM Ağı Kullanılarak Duygu Sınıflandırması","authors":"Mustafa ÇATALTAŞ, Büşra ÜSTÜNEL, Nurdan AKHAN BAYKAN","doi":"10.36306/konjes.1173939","DOIUrl":"https://doi.org/10.36306/konjes.1173939","url":null,"abstract":"As Covid-19 pandemic affected everyone in various aspects, people have been expressing their opinions on these aspects mostly on social media platforms because of the pandemic. These opinions play a crucial role in understanding the sentiments towards the pandemic. In this study, Turkish tweets on Covid-19 topic were collected from March 2020 to January 2021 and labelled as positive, negative, or neutral in terms of sentiment using BERT which is a pre-trained text classifier model. Using this labelled dataset, a set of experiments were carried out with SVM, Naive Bayes, K-Nearest Neighbors, and CNN-LSTM model machine learning algorithms for binary and multi-class classification tasks. Results of these experiments have shown that CNN-LSTM model outperforms other machine learning algorithms which are used in this study in both binary classification and multi-class classification tasks.","PeriodicalId":17899,"journal":{"name":"Konya Journal of Engineering Sciences","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135674278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：