Journal of Pharmaceutical and Biomedical Analysis, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
pharmacy 4.1.2. Understanding of patient data 4.1.3. Preparation of patient data for analysis 4.1... more pharmacy 4.1.2. Understanding of patient data 4.1.3. Preparation of patient data for analysis 4.1.3.1. Prescription cleaning and derivation of new attributes 4.1.3.2. Classification of drugs 4.1.3.3. Transformation of patient data to tabular format 4.1.4. The processing of Apriori algorithm 4.2. The Application of Multi-Dimensional Scaling Analysis 4.2.1. Scaling of drug groups CHAPTER 5: FINDINGS AND RESULTS
Research on integration of supply chain and scheduling is relatively recent, and number of studie... more Research on integration of supply chain and scheduling is relatively recent, and number of studies on this topic is increasing. This study provides a comprehensive literature survey about Integrated Supply Chain Scheduling (ISCS) models to help identify deficiencies in this area. For this purpose, it is thought that this study will contribute in terms of guiding researchers working in this field. In this study, existing literature on ISCS problems are reviewed and summarized by introducing the new classification scheme. The studies were categorized by considering the features such as the number of customers (single or multiple), product lifespan (limited or unlimited), order sizes (equal or general), vehicle characteristics (limited/sufficient and homogeneous/heterogeneous), machine configurations and number of objective function (single or multi objective). In addition, properties of mathematical models applied for problems and solution approaches are also discussed.
The information sector is changing and developing very rapidly with the effect of the technologie... more The information sector is changing and developing very rapidly with the effect of the technologies it contains. It is very important for companies to keep up with this change in order to compete with their competitors and provide customer satisfaction. Therefore, in order for companies to continue their activities, they need to progress smoothly and innovatively in information technology infrastructure. This is especially critical for companies operating in the banking and finance sectors. In these sectors where competition is intense, it is important that the type and quality of the service provided is easily accessible. Mobile applications, the ability to make transactions over the internet, chatbotlar increase customer satisfaction of companies in this sector, as well as self-service applications saves the cost of operational labor. In this study, the characteristics and success criteria of 4 different software development projects which use different project management methods such as Scrum, Kanban, and Waterfall and located in the different functions of a mobile application of a leading company in operating in the banking sector in Turkey were analyzed. The main and sub-criteria that these four projects need to be successful are determined according to expert opinions. The weighting coefficient for the criteria was determined by AHP method, which is one of the multi-criteria decision making methods frequently used in the literature, and then success ranking was performed by TOPSIS method. As a result of the study, it is seen that the projects that implement agile project management methods such as Scrum and Kanban in the software development department are highly successful in terms of all criteria.
Ulke ekonomisi ve refah seviyesinin yanisira savunma guvenligi ve stratejik hedefler yonunden ene... more Ulke ekonomisi ve refah seviyesinin yanisira savunma guvenligi ve stratejik hedefler yonunden enerji planlamasi buyuk oneme sahiptir. Bu nedenle, enerji talebinin en dogru sekilde tahmini, ulke politikalari acisindan kritik bir konudur. Son yillarda, gelecekteki enerji talep seviyelerini en dogru sekilde tahmin edebilmek icin cesitli yontemler kullanilmaktadir. Bununla birlikte, farkli tahmin yontemleri arasindan en uygun olanin secilmesi gerekmektedir. Bu calismada, Turkiye'de yillik ulasim kaynakli enerji talebinin (UKET) modellenmesi ve tahmin edilmesi icin hibrit bir yontem olan Uyarlamali Ag Tabanli Bulanik Cikarim Sistemleri (Adaptive-Network Based Fuzzy Inference Systems, ANFIS) ile Parcacik Suru Optimizasyon (PSO) algoritmasi birlikte kullanilmistir. Modellerin gelistirilmesinde gayri safi yurtici hâsila (GSYIH), nufus, yillik toplam tasit-km parametreleri ve yillik trafige cikan tasit sayisi model girdileri olarak alinmistir. Modellerin egitim ve test asamalari icin 197...
Journal of the Institute of Science and Technology, 2021
Hızlı kentleşme ve nüfus artışından dolayı raylı ulaşım sisteminin kullanımı giderek artmaktadır.... more Hızlı kentleşme ve nüfus artışından dolayı raylı ulaşım sisteminin kullanımı giderek artmaktadır. Ancak, raylı ulaşım sistemlerin şehir içi taşımacılıkta yaygın kullanımı beraberinde büyük boyutlu ve çözülmesi zor problemlere sebep olmaktadır. Özellikle, tren seferlerinin düzenlenmesinde dengesizlikler, makinistlerin vardiya planlamasının ve çalışma-dinlenme sürelerinin uygun şekilde ayarlanamaması gibi pek çok sorun ortaya çıkmaktadır. Bu nedenle, bu sistemlerin planlanması, işletilmesi ve sürekliliğin sağlanması için sorunlara hızlı ve uygun çözümler üretilmesi zorunlu hale gelmiştir. Bu çalışmada, hafif raylı ulaşım sisteminde hizmet eden bir işletmenin tüm makinistlerinin toplam çalışma süresini ve vardiya sayısını eşitleyerek adil bir görev çizelgesi oluşturulması hedeflenmektedir. Mevcut durumda işletmede makinist görev çizelgesinin manuel olarak yapılması zaman kaybına sebep olmaktadır. Ayrıca, oluşturulan çizelgede eşit iş dağılımının sağlanamaması çalışan memnuniyetsizliğine yol açmaktadır. Bu nedenle, bu çalışmada, söz konusu işletmede makinist çizelgeleme problemi için hedef programlama modeli geliştirilmiş ve GAMS/CPLEX programı ile çözülmüştür. Önerilen matematiksel model ile adil görev ataması sağlanmış ve çalışanların artan motivasyon ve memnuniyeti ile hizmet kalitesinin artması beklenmektedir.
Individual Pension System (IPS) is a personal future investment system that allows individuals to... more Individual Pension System (IPS) is a personal future investment system that allows individuals to regularly save for their retirement. IPS is enacted by the law and supported by the government through state contribution. In Turkey, IPS entered into force on October 27, 2003 and it achieved an impressive progress over the last years. This improvement has caused increase in amount of raw data stored in databases. However, accumulated data are complicated and big to be processed and cannot be analyzed by classical methods. Data mining is becoming an essential tool to discover hidden and potentially useful knowledge from raw data. For this reason, application of data mining techniques on Individual Pension Savings and Investment system is necessary. In this study, one of the data mining techniques, decision tree classification, was used to determine customers’ profile. SPSS Clementine 12.0 software was used to develop a classification model. Analyses were performed by various decision t...
Bu calismada, beyaz esya sektorunde faaliyet gosteren bir firmanin boyahane bolumunde sira bagiml... more Bu calismada, beyaz esya sektorunde faaliyet gosteren bir firmanin boyahane bolumunde sira bagimli hazirlik sureli tek makine cizelgeleme problemi uzerinde calisilmistir. Boyanacak her bir urunun islem suresi, teslim suresi ve renk degisiminden kaynaklanan hazirlik suresi dikkate alinarak en uygun siralamanin olusturulmasi hedeflenmistir. Son isin tamamlanma zamanini ve toplam gecikme suresini en aza indirmeyi amaclayan hedef programlama modeli gelistirilmis ve GAMS/CPLEX programinda cozulmustur. Problem NP-zor yapida oldugu icin buyuk boyutlu problemlerin cozumunde LEKIN programi kullanilarak, literaturde cokca kullanilan SPT (en kisa islem suresi), LPT (en uzun islem suresi), EDD (en erken teslim suresi) ve FCFS (ilk gelen ilk servis gorur) gibi farkli oncelik kurallarina basvurulmustur. Matematiksel modelden elde edilen sonuclar; kurallardan elde edilen sonuclar ile karsilastirilarak yorumlanmistir.
The pharmacy is one of the most extensively used facility in healthcare where a large amount of m... more The pharmacy is one of the most extensively used facility in healthcare where a large amount of money is spent for purchasing medicinal items. In pharmacies, various drugs are being stored for supporting the therapy of patients. Due to the variety of pharmaceutical items, it is a difficult task to control and manage the quantity of drug. However, for a better and effective service management in a pharmacy, required drug must be provided continually at correct time and quantity to sustain steady in supply. This can be accomplished by efficient inventory management of pharmacy by providing control on important drugs, and deciding on priorities in purchase and distribution. Therefore, the inventory management ensures significant improvement for both patient care and optimal use of resources. In this study, annual drug sale data of a pharmacy was analyzed to identify the categories of drugs needing strict management control. Three important methods regarding inventory management practic...
Summary Due to the extraordinary impact of the Coronavirus Disease 2019 (COVID‐19) and the result... more Summary Due to the extraordinary impact of the Coronavirus Disease 2019 (COVID‐19) and the resulting lockdown measures, the demand for energy in business and industry has dropped significantly. This change in demand makes it difficult to manage energy generation, especially electricity production and delivery. Thus, reliable models are needed to continue safe, secure, and reliable power. An accurate forecast of electricity demand is essential for making a reliable decision in strategic planning and investments in the future. This study presents the extensive effects of COVID‐19 on the electricity sector and aims to predict electricity demand accurately during the lockdown period in Turkey. For this purpose, well‐known machine learning algorithms such as Gaussian process regression (GPR), sequential minimal optimization regression (SMOReg), correlated Nyström views (XNV), linear regression (LR), reduced error pruning tree (REPTree), and M5P model tree (M5P) were used. The SMOReg algorithm performed best with the lowest mean absolute percentage error (3.6851%), mean absolute error (21.9590), root mean square error (29.7358), and root relative squared error (36.5556%) values in the test dataset. This study can help policy‐makers develop appropriate policies to control the harms of not only the current pandemic crisis but also an unforeseeable crisis.
Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
ABSTRACT Knowing the properties of coal, which is still the most widely used among primary energy... more ABSTRACT Knowing the properties of coal, which is still the most widely used among primary energy sources, is critical for determining the application area and the technology to be applied. The ultimate analysis results contain important information for the estimation of the gas product composition to be released to the environment as a result of the combustion process. This study aims to make a comparative study using different machine learning models, namely, Support Vector Regression (SVR), Regression Trees (RT), the Ensemble of Trees (ET), Gaussian Process Regression (GPR) for predicting the elemental composition of coal. The moisture, ash, volatile matter, and fixed carbon contents were used as input variables to predict carbon, hydrogen, and oxygen contents of coal. 70% of 6339 coal samples (4437 data) containing different quality coal types were for the training of the models, whereas the remaining 30% sets of data (1902 data) were used to evaluate the prediction performance of the developed models. Analysis results proved that the GPR-exponential model performs best among all models. In the training stage, the correlation of determination (R2), mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute deviation (MAD) values were obtained as 0.9970, 0.7525%, 0.6492, 0.4635 for Carbon content; 0.9900, 0.5712%, 0.0646, 0.0297 for Hydrogen content; 0.9951, 4.0664%, 0.7910, 0.4152 for Oxygen content, respectively. Reported indices showed that the GPR-exponential model is a promising procedure for achieving high accuracy and can be used as a reliable model to predict the coal elemental components successfully.
International Journal of Intelligent Systems and Applications in Engineering
Breast cancer is one of the most common types of cancer and is the second main cause of cancer de... more Breast cancer is one of the most common types of cancer and is the second main cause of cancer death in females. Early detection of breast cancer is crucial for the survival of a patient as well as for the quality of life throughout cancer treatment. The aim of this study is to develop improved machine learning models for early diagnosis of breast cancer with high accuracy. In this context, a performance comparison of machine learning algorithms including Support Vector Machines, Decision Trees, Naive Bayes, K-Nearest Neighbor, and Ensemble Classifiers was performed on a dataset consisting of routine blood analysis combined with anthropometric measurements to diagnose breast cancer. Neighborhood component analysis was applied as a feature selection method to reveal relevant biomarkers that can be used in breast cancer prediction. In order to assess the performance of each proposed classifier model, two different data division procedures such as hold-out and 10-fold cross-validation were employed. Bayesian Optimization algorithm was applied to all classifiers for the maximizing the prediction accuracy. Different performance criteria such as accuracy, precision, sensitivity, specificity, and Fmeasure were used to measure the success of each classifier. Experimental results showed that the Bayesian optimization-based K-Nearest Neighbor performs better than other machine learning algorithms under the hold-out data division protocol with an accuracy of 95.833%. The results obtained in this study may provide a new perspective on the application of improved machine learning techniques for the early detection of breast cancer.
In this study, a new coordinated scheduling problem is proposed for the multi-stage supply chain ... more In this study, a new coordinated scheduling problem is proposed for the multi-stage supply chain network. A multi-product and multi-period supply chain structure has been developed, including a factory, warehouses, and customers. Furthermore, the flexible job shop scheduling problem is integrated into the manufacturing part of the supply chain network to make the structure more comprehensive. In the proposed problem, each product includes a sequence of operations and is processed on a set of multi-functional machines at the factory to produce the final product. Final products are delivered to the warehouses to meet customers’ demands. If the demands of customers are not fulfilled, the shortage in the form of backorder may occur at any period. The problem is expressed as a bi-objective mixed-integer linear programming (MILP) model. The first objective function is to minimize the total supply chain costs. On the other hand, the second objective function aims to minimize the makespan in all periods. A numerical example is presented to evaluate the performance of the proposed MILP model. Five multi-objective decision-making (MODM) methods, namely weighted sum, goal programming, goal attainment, LP metric, and max–min, are used to provide different alternative solutions to the decision-makers. The performance of the methods is evaluated according to both objective function values and CPU time criteria. In order to select the best solution technique, the displaced ideal solution method is applied. The results reveal that the weighted sum method is the best among all MODM methods.
Journal of Pharmaceutical and Biomedical Analysis, 2020
This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
pharmacy 4.1.2. Understanding of patient data 4.1.3. Preparation of patient data for analysis 4.1... more pharmacy 4.1.2. Understanding of patient data 4.1.3. Preparation of patient data for analysis 4.1.3.1. Prescription cleaning and derivation of new attributes 4.1.3.2. Classification of drugs 4.1.3.3. Transformation of patient data to tabular format 4.1.4. The processing of Apriori algorithm 4.2. The Application of Multi-Dimensional Scaling Analysis 4.2.1. Scaling of drug groups CHAPTER 5: FINDINGS AND RESULTS
Research on integration of supply chain and scheduling is relatively recent, and number of studie... more Research on integration of supply chain and scheduling is relatively recent, and number of studies on this topic is increasing. This study provides a comprehensive literature survey about Integrated Supply Chain Scheduling (ISCS) models to help identify deficiencies in this area. For this purpose, it is thought that this study will contribute in terms of guiding researchers working in this field. In this study, existing literature on ISCS problems are reviewed and summarized by introducing the new classification scheme. The studies were categorized by considering the features such as the number of customers (single or multiple), product lifespan (limited or unlimited), order sizes (equal or general), vehicle characteristics (limited/sufficient and homogeneous/heterogeneous), machine configurations and number of objective function (single or multi objective). In addition, properties of mathematical models applied for problems and solution approaches are also discussed.
The information sector is changing and developing very rapidly with the effect of the technologie... more The information sector is changing and developing very rapidly with the effect of the technologies it contains. It is very important for companies to keep up with this change in order to compete with their competitors and provide customer satisfaction. Therefore, in order for companies to continue their activities, they need to progress smoothly and innovatively in information technology infrastructure. This is especially critical for companies operating in the banking and finance sectors. In these sectors where competition is intense, it is important that the type and quality of the service provided is easily accessible. Mobile applications, the ability to make transactions over the internet, chatbotlar increase customer satisfaction of companies in this sector, as well as self-service applications saves the cost of operational labor. In this study, the characteristics and success criteria of 4 different software development projects which use different project management methods such as Scrum, Kanban, and Waterfall and located in the different functions of a mobile application of a leading company in operating in the banking sector in Turkey were analyzed. The main and sub-criteria that these four projects need to be successful are determined according to expert opinions. The weighting coefficient for the criteria was determined by AHP method, which is one of the multi-criteria decision making methods frequently used in the literature, and then success ranking was performed by TOPSIS method. As a result of the study, it is seen that the projects that implement agile project management methods such as Scrum and Kanban in the software development department are highly successful in terms of all criteria.
Ulke ekonomisi ve refah seviyesinin yanisira savunma guvenligi ve stratejik hedefler yonunden ene... more Ulke ekonomisi ve refah seviyesinin yanisira savunma guvenligi ve stratejik hedefler yonunden enerji planlamasi buyuk oneme sahiptir. Bu nedenle, enerji talebinin en dogru sekilde tahmini, ulke politikalari acisindan kritik bir konudur. Son yillarda, gelecekteki enerji talep seviyelerini en dogru sekilde tahmin edebilmek icin cesitli yontemler kullanilmaktadir. Bununla birlikte, farkli tahmin yontemleri arasindan en uygun olanin secilmesi gerekmektedir. Bu calismada, Turkiye'de yillik ulasim kaynakli enerji talebinin (UKET) modellenmesi ve tahmin edilmesi icin hibrit bir yontem olan Uyarlamali Ag Tabanli Bulanik Cikarim Sistemleri (Adaptive-Network Based Fuzzy Inference Systems, ANFIS) ile Parcacik Suru Optimizasyon (PSO) algoritmasi birlikte kullanilmistir. Modellerin gelistirilmesinde gayri safi yurtici hâsila (GSYIH), nufus, yillik toplam tasit-km parametreleri ve yillik trafige cikan tasit sayisi model girdileri olarak alinmistir. Modellerin egitim ve test asamalari icin 197...
Journal of the Institute of Science and Technology, 2021
Hızlı kentleşme ve nüfus artışından dolayı raylı ulaşım sisteminin kullanımı giderek artmaktadır.... more Hızlı kentleşme ve nüfus artışından dolayı raylı ulaşım sisteminin kullanımı giderek artmaktadır. Ancak, raylı ulaşım sistemlerin şehir içi taşımacılıkta yaygın kullanımı beraberinde büyük boyutlu ve çözülmesi zor problemlere sebep olmaktadır. Özellikle, tren seferlerinin düzenlenmesinde dengesizlikler, makinistlerin vardiya planlamasının ve çalışma-dinlenme sürelerinin uygun şekilde ayarlanamaması gibi pek çok sorun ortaya çıkmaktadır. Bu nedenle, bu sistemlerin planlanması, işletilmesi ve sürekliliğin sağlanması için sorunlara hızlı ve uygun çözümler üretilmesi zorunlu hale gelmiştir. Bu çalışmada, hafif raylı ulaşım sisteminde hizmet eden bir işletmenin tüm makinistlerinin toplam çalışma süresini ve vardiya sayısını eşitleyerek adil bir görev çizelgesi oluşturulması hedeflenmektedir. Mevcut durumda işletmede makinist görev çizelgesinin manuel olarak yapılması zaman kaybına sebep olmaktadır. Ayrıca, oluşturulan çizelgede eşit iş dağılımının sağlanamaması çalışan memnuniyetsizliğine yol açmaktadır. Bu nedenle, bu çalışmada, söz konusu işletmede makinist çizelgeleme problemi için hedef programlama modeli geliştirilmiş ve GAMS/CPLEX programı ile çözülmüştür. Önerilen matematiksel model ile adil görev ataması sağlanmış ve çalışanların artan motivasyon ve memnuniyeti ile hizmet kalitesinin artması beklenmektedir.
Individual Pension System (IPS) is a personal future investment system that allows individuals to... more Individual Pension System (IPS) is a personal future investment system that allows individuals to regularly save for their retirement. IPS is enacted by the law and supported by the government through state contribution. In Turkey, IPS entered into force on October 27, 2003 and it achieved an impressive progress over the last years. This improvement has caused increase in amount of raw data stored in databases. However, accumulated data are complicated and big to be processed and cannot be analyzed by classical methods. Data mining is becoming an essential tool to discover hidden and potentially useful knowledge from raw data. For this reason, application of data mining techniques on Individual Pension Savings and Investment system is necessary. In this study, one of the data mining techniques, decision tree classification, was used to determine customers’ profile. SPSS Clementine 12.0 software was used to develop a classification model. Analyses were performed by various decision t...
Bu calismada, beyaz esya sektorunde faaliyet gosteren bir firmanin boyahane bolumunde sira bagiml... more Bu calismada, beyaz esya sektorunde faaliyet gosteren bir firmanin boyahane bolumunde sira bagimli hazirlik sureli tek makine cizelgeleme problemi uzerinde calisilmistir. Boyanacak her bir urunun islem suresi, teslim suresi ve renk degisiminden kaynaklanan hazirlik suresi dikkate alinarak en uygun siralamanin olusturulmasi hedeflenmistir. Son isin tamamlanma zamanini ve toplam gecikme suresini en aza indirmeyi amaclayan hedef programlama modeli gelistirilmis ve GAMS/CPLEX programinda cozulmustur. Problem NP-zor yapida oldugu icin buyuk boyutlu problemlerin cozumunde LEKIN programi kullanilarak, literaturde cokca kullanilan SPT (en kisa islem suresi), LPT (en uzun islem suresi), EDD (en erken teslim suresi) ve FCFS (ilk gelen ilk servis gorur) gibi farkli oncelik kurallarina basvurulmustur. Matematiksel modelden elde edilen sonuclar; kurallardan elde edilen sonuclar ile karsilastirilarak yorumlanmistir.
The pharmacy is one of the most extensively used facility in healthcare where a large amount of m... more The pharmacy is one of the most extensively used facility in healthcare where a large amount of money is spent for purchasing medicinal items. In pharmacies, various drugs are being stored for supporting the therapy of patients. Due to the variety of pharmaceutical items, it is a difficult task to control and manage the quantity of drug. However, for a better and effective service management in a pharmacy, required drug must be provided continually at correct time and quantity to sustain steady in supply. This can be accomplished by efficient inventory management of pharmacy by providing control on important drugs, and deciding on priorities in purchase and distribution. Therefore, the inventory management ensures significant improvement for both patient care and optimal use of resources. In this study, annual drug sale data of a pharmacy was analyzed to identify the categories of drugs needing strict management control. Three important methods regarding inventory management practic...
Summary Due to the extraordinary impact of the Coronavirus Disease 2019 (COVID‐19) and the result... more Summary Due to the extraordinary impact of the Coronavirus Disease 2019 (COVID‐19) and the resulting lockdown measures, the demand for energy in business and industry has dropped significantly. This change in demand makes it difficult to manage energy generation, especially electricity production and delivery. Thus, reliable models are needed to continue safe, secure, and reliable power. An accurate forecast of electricity demand is essential for making a reliable decision in strategic planning and investments in the future. This study presents the extensive effects of COVID‐19 on the electricity sector and aims to predict electricity demand accurately during the lockdown period in Turkey. For this purpose, well‐known machine learning algorithms such as Gaussian process regression (GPR), sequential minimal optimization regression (SMOReg), correlated Nyström views (XNV), linear regression (LR), reduced error pruning tree (REPTree), and M5P model tree (M5P) were used. The SMOReg algorithm performed best with the lowest mean absolute percentage error (3.6851%), mean absolute error (21.9590), root mean square error (29.7358), and root relative squared error (36.5556%) values in the test dataset. This study can help policy‐makers develop appropriate policies to control the harms of not only the current pandemic crisis but also an unforeseeable crisis.
Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
ABSTRACT Knowing the properties of coal, which is still the most widely used among primary energy... more ABSTRACT Knowing the properties of coal, which is still the most widely used among primary energy sources, is critical for determining the application area and the technology to be applied. The ultimate analysis results contain important information for the estimation of the gas product composition to be released to the environment as a result of the combustion process. This study aims to make a comparative study using different machine learning models, namely, Support Vector Regression (SVR), Regression Trees (RT), the Ensemble of Trees (ET), Gaussian Process Regression (GPR) for predicting the elemental composition of coal. The moisture, ash, volatile matter, and fixed carbon contents were used as input variables to predict carbon, hydrogen, and oxygen contents of coal. 70% of 6339 coal samples (4437 data) containing different quality coal types were for the training of the models, whereas the remaining 30% sets of data (1902 data) were used to evaluate the prediction performance of the developed models. Analysis results proved that the GPR-exponential model performs best among all models. In the training stage, the correlation of determination (R2), mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute deviation (MAD) values were obtained as 0.9970, 0.7525%, 0.6492, 0.4635 for Carbon content; 0.9900, 0.5712%, 0.0646, 0.0297 for Hydrogen content; 0.9951, 4.0664%, 0.7910, 0.4152 for Oxygen content, respectively. Reported indices showed that the GPR-exponential model is a promising procedure for achieving high accuracy and can be used as a reliable model to predict the coal elemental components successfully.
International Journal of Intelligent Systems and Applications in Engineering
Breast cancer is one of the most common types of cancer and is the second main cause of cancer de... more Breast cancer is one of the most common types of cancer and is the second main cause of cancer death in females. Early detection of breast cancer is crucial for the survival of a patient as well as for the quality of life throughout cancer treatment. The aim of this study is to develop improved machine learning models for early diagnosis of breast cancer with high accuracy. In this context, a performance comparison of machine learning algorithms including Support Vector Machines, Decision Trees, Naive Bayes, K-Nearest Neighbor, and Ensemble Classifiers was performed on a dataset consisting of routine blood analysis combined with anthropometric measurements to diagnose breast cancer. Neighborhood component analysis was applied as a feature selection method to reveal relevant biomarkers that can be used in breast cancer prediction. In order to assess the performance of each proposed classifier model, two different data division procedures such as hold-out and 10-fold cross-validation were employed. Bayesian Optimization algorithm was applied to all classifiers for the maximizing the prediction accuracy. Different performance criteria such as accuracy, precision, sensitivity, specificity, and Fmeasure were used to measure the success of each classifier. Experimental results showed that the Bayesian optimization-based K-Nearest Neighbor performs better than other machine learning algorithms under the hold-out data division protocol with an accuracy of 95.833%. The results obtained in this study may provide a new perspective on the application of improved machine learning techniques for the early detection of breast cancer.
In this study, a new coordinated scheduling problem is proposed for the multi-stage supply chain ... more In this study, a new coordinated scheduling problem is proposed for the multi-stage supply chain network. A multi-product and multi-period supply chain structure has been developed, including a factory, warehouses, and customers. Furthermore, the flexible job shop scheduling problem is integrated into the manufacturing part of the supply chain network to make the structure more comprehensive. In the proposed problem, each product includes a sequence of operations and is processed on a set of multi-functional machines at the factory to produce the final product. Final products are delivered to the warehouses to meet customers’ demands. If the demands of customers are not fulfilled, the shortage in the form of backorder may occur at any period. The problem is expressed as a bi-objective mixed-integer linear programming (MILP) model. The first objective function is to minimize the total supply chain costs. On the other hand, the second objective function aims to minimize the makespan in all periods. A numerical example is presented to evaluate the performance of the proposed MILP model. Five multi-objective decision-making (MODM) methods, namely weighted sum, goal programming, goal attainment, LP metric, and max–min, are used to provide different alternative solutions to the decision-makers. The performance of the methods is evaluated according to both objective function values and CPU time criteria. In order to select the best solution technique, the displaced ideal solution method is applied. The results reveal that the weighted sum method is the best among all MODM methods.
Uploads
Papers by Zeynep CEYLAN