In this paper, models of data envelopment analysis (DEA) were investigated with the aim of measuring the efficiency of production chains in Iran's poultry industry. DEA tool can determine the efficiency frontier and the reference production chain to improve the performance of the poultry industry. Statistical data were collected for 28 active production chains and 8 variables including: Material cost, human resource cost, equipment and facilities cost, transport cost, number of poultry, poultry price, profit, and cost of slaughter. Then, the relative efficiency of each chain was measured using traditional and network DEA. Finally, cross efficiency method was used to rank efficient chains. Traditional DEA results showed 25% of production chains to be efficient. Meanwhile, this percentage was equal to 10.7% in the proposed model of the paper (two-stage DEA). Therefore, the scientific accuracy of the reference production chain will be higher in the network model. The rest of the results and their details were presented and discussed. The results of this paper can be useful in the decision-making and policies of poultry industry managers and also improve the performance of production chains in this industry. Manuscript profile

Environmental issues are unavoidable in supply chain management. Providing different level of green products is a major subject in this area for distinctive customer segments. In this research, a capacitated network design problem with different levels of green products for their specific demands is considered. This network has different levels with multiple products. The forward/reverse network consists of plants, hybrid warehouse/disposal centers, and customers. Two types of vehicles are considered to transport the products among the network. Each customer segment has specific needs based on their attitude to the greenness subject and their willingness to pay more money in order to attain a product with higher degree of greenness. A quadratic function is assumed for extra money to produce green products. To evaluate the reliability of the model, a real example proposed. Large size sample problems are solved using an efficient Lagrangian relaxation method. The results presents that the proposed method solved large size sample problems in a reasonable time. Manuscript profile

Nowadays, improving quality is advocated as a strategy to increase market share, and failing to address this crucial issue results in exclusion from the competitive landscape. Most studies undertaken in recent years have investigated and optimized continuous response variables while ignoring categorical characteristics. This necessitates a change in statistical methods in this discipline to ones that take categorical responses into account. Statistical techniques have always provided researchers with estimates of parameters that are subject to uncertainty. Hence, considering uncertainty in modeling is essential for reducing errors and minimizing costs while increasing quality. In this study, we deal with the robust design of quality characteristics in categorical response problems to reach optimal levels of control variables, which can minimize the error caused by modeling and implementation and provide more accurate estimates. A portion of the uncertainty is considered while estimating the model parameters. However, the proposed approach assumes that the optimal settings of design variables during the implementation phase will also experience oscillations. Finally, in the optimization phase, multiple equations relating to response levels are modeled and solved using the goal programming approach. The results showed that our approaches could achieve solutions with robustness against the two main sources of errors. Manuscript profile

Computational intelligence methods, such as fuzzy logic and deep neural networks, are robust models to solve real-world problems. In many dynamic and complex problems, statistical attributes frequently change over the time. Recurrent neural networks (RNN) are suitable to model dynamic high-dimensional and non-linear state-space systems. Nevertheless, the RNN is incapable of modelling long-term dependencies in temporal data, and its learning using gradient descent is a complex and difficult task. Long Short-Term Memory (LSTM) networks were introduced to overcome the RNN issues, but coping with uncertainty is still a major challenge for the LSTM models. This research presents a Hybrid Type-2 Fuzzy LSTM (HHT2FLSTM) deep approach to learn long-term dependencies in order to obtain a reliable prediction in uncertain time series circumstances. The proposed model was applied to the air quality prediction problem to evaluate the model’s robustness in handling uncertainties in a real-world application. The proposed model has been evaluated on a real dataset that contains the outdoor pollutants from July 2011 to October 2020 in Tehran and Beijing by a 10-fold cv with an average area under the ROC curve of 97 % with a 95% confidence interval [95-97] %. Manuscript profile

The supply chain requires a distribution network between customers and suppliers. This distribution network can be multifaceted. Combining these two problems into a single problem increases the efficiency of the distribution network and ultimately increases the efficiency of the supply chain. Establishing a window of time to deliver goods to customers also increases their satisfaction and, as a result, more profitability in the long run. Therefore, in this research, an attempt has been made to present a routing-location problem in the multimodal transportation network. A time window is also included in this model. To solve such a model, especially in large dimensions, exact solution methods cannot be used. Based on this, a combined meta-heuristic algorithm (genetic optimization algorithm and neural network) has been proposed to solve the model, and the result has been compared with two gray wolf optimization algorithms and grasshopper optimization algorithms. The presented results indicate the effectiveness of the proposed algorithm. Manuscript profile

Heart disease is a prevalent and life-threatening condition that poses significant challenges to healthcare systems worldwide. Accurate and timely diagnosis of heart disease is crucial for effective treatment and patient management. In recent years, machine learning algorithms have emerged as powerful tools for predicting and identifying individuals at risk of heart disease. This article highlights the importance of heart disease diagnosis and explores the potential of machine learning algorithms in enhancing the diagnosis of heart disease accuracy. This article presents a study to develop a model for predicting heart disease in the Cleveland patient dataset. The innovation of this research involved identifying and handling outlier data using Winsorized and Logarithmic transformation methods. We also used Wrapper and Embedded methods to determine the most critical features for diagnosing heart disease. In addition to the usual features, Exercise-induced angina and No. of major vessels were found to be important. We then compared the performance of four machine learning algorithms, including KNN, Naïve Bayes' Classifier, Decision Tree, and Support Vector Classifier to determine the best algorithm for predicting heart disease. The findings showed that the Decision Tree algorithm had the best performance with an accuracy of 97.95%. Manuscript profile

Heart disease is a prevalent and life-threatening condition that poses significant challenges to healthcare systems worldwide. Accurate and timely diagnosis of heart disease is crucial for effective treatment and patient management. In recent years, machine learning algorithms have emerged as powerful tools for predicting and identifying individuals at risk of heart disease. This article highlights the importance of heart disease diagnosis and explores the potential of machine learning algorithms in enhancing the diagnosis of heart disease accuracy. This article presents a study to develop a model for predicting heart disease in the Cleveland patient dataset. The innovation of this research involved identifying and handling outlier data using Winsorized and Logarithmic transformation methods. We also used Wrapper and Embedded methods to determine the most critical features for diagnosing heart disease. In addition to the usual features, Exercise-induced angina and No. of major vessels were found to be important. We then compared the performance of four machine learning algorithms, including KNN, Naïve Bayes' Classifier, Decision Tree, and Support Vector Classifier to determine the best algorithm for predicting heart disease. The findings showed that the Decision Tree algorithm had the best performance with an accuracy of 97.95%. Manuscript profile

In this paper, models of data envelopment analysis (DEA) were investigated with the aim of measuring the efficiency of production chains in Iran's poultry industry. DEA tool can determine the efficiency frontier and the reference production chain to improve the performance of the poultry industry. Statistical data were collected for 28 active production chains and 8 variables including: Material cost, human resource cost, equipment and facilities cost, transport cost, number of poultry, poultry price, profit, and cost of slaughter. Then, the relative efficiency of each chain was measured using traditional and network DEA. Finally, cross efficiency method was used to rank efficient chains. Traditional DEA results showed 25% of production chains to be efficient. Meanwhile, this percentage was equal to 10.7% in the proposed model of the paper (two-stage DEA). Therefore, the scientific accuracy of the reference production chain will be higher in the network model. The rest of the results and their details were presented and discussed. The results of this paper can be useful in the decision-making and policies of poultry industry managers and also improve the performance of production chains in this industry. Manuscript profile

Nowadays, improving quality is advocated as a strategy to increase market share, and failing to address this crucial issue results in exclusion from the competitive landscape. Most studies undertaken in recent years have investigated and optimized continuous response variables while ignoring categorical characteristics. This necessitates a change in statistical methods in this discipline to ones that take categorical responses into account. Statistical techniques have always provided researchers with estimates of parameters that are subject to uncertainty. Hence, considering uncertainty in modeling is essential for reducing errors and minimizing costs while increasing quality. In this study, we deal with the robust design of quality characteristics in categorical response problems to reach optimal levels of control variables, which can minimize the error caused by modeling and implementation and provide more accurate estimates. A portion of the uncertainty is considered while estimating the model parameters. However, the proposed approach assumes that the optimal settings of design variables during the implementation phase will also experience oscillations. Finally, in the optimization phase, multiple equations relating to response levels are modeled and solved using the goal programming approach. The results showed that our approaches could achieve solutions with robustness against the two main sources of errors. Manuscript profile

Today, the problem of non-infectious diseases has overshadowed many health beliefs and has attracted the attention of scientific communities. In the past, the main problem of society and people was infectious diseases and the high mortality caused by these diseases, while today, due to the control of infectious diseases, the development of urbanization, the advancement of industry and machine life, in other words, the change in the quality and lifestyle of people, the spread of diseases Non-communicable diseases have increased and gradually contagious diseases have given their place to non-communicable diseases, so that today the most important causes of death in societies are non-communicable diseases, especially cardiovascular diseases, cancers and accidents. Diabetes mellitus is a chronic disease that is very expensive, complicated and debilitating. By the end of 2017, more than 425 million people between the ages of 20 and 79 were suffering from diabetes, which will reach 619 million people by 2045. For this reason, it is very important to provide diabetes control solutions. In this paper, a new method for simulating control in diabetic patients is presented. For this purpose, the technique of fuzzy expert system has been used in MATLAB software to analyze the data. Manuscript profile

The supply chain requires a distribution network between customers and suppliers. This distribution network can be multifaceted. Combining these two problems into a single problem increases the efficiency of the distribution network and ultimately increases the efficiency of the supply chain. Establishing a window of time to deliver goods to customers also increases their satisfaction and, as a result, more profitability in the long run. Therefore, in this research, an attempt has been made to present a routing-location problem in the multimodal transportation network. A time window is also included in this model. To solve such a model, especially in large dimensions, exact solution methods cannot be used. Based on this, a combined meta-heuristic algorithm (genetic optimization algorithm and neural network) has been proposed to solve the model, and the result has been compared with two gray wolf optimization algorithms and grasshopper optimization algorithms. The presented results indicate the effectiveness of the proposed algorithm. Manuscript profile

In today's world, due to the existence of several criteria in every decision, budgeting has become a complex issue. Applying decision-making methods significantly helps to make optimal decisions. Multiple criteria decision making (MCDM) is a branch of operational research dealing with finding optimal results in complex scenarios including various indicators, conflicting objectives, criteria, and various indicators. The paper presents a location-allocation decision-making problem resulting in the selection of the most desirable location for the consulting service center in the Qazvin state of Iran. In the first stage, different location criteria are determined. Then, the decision-making matrix preparation is completed based on the criteria dimension and expert opinions. The decision problem is formulated as a multiple criteria ranking problem (MCDM). In the second stage, the decision-making is performed by using all three models of the PROMETHEE method. Finally, considered locations are ranked from the best choice to the worst one with the application of the PROMETHEE MCDM/A method. Manuscript profile

Computational intelligence methods, such as fuzzy logic and deep neural networks, are robust models to solve real-world problems. In many dynamic and complex problems, statistical attributes frequently change over the time. Recurrent neural networks (RNN) are suitable to model dynamic high-dimensional and non-linear state-space systems. Nevertheless, the RNN is incapable of modelling long-term dependencies in temporal data, and its learning using gradient descent is a complex and difficult task. Long Short-Term Memory (LSTM) networks were introduced to overcome the RNN issues, but coping with uncertainty is still a major challenge for the LSTM models. This research presents a Hybrid Type-2 Fuzzy LSTM (HHT2FLSTM) deep approach to learn long-term dependencies in order to obtain a reliable prediction in uncertain time series circumstances. The proposed model was applied to the air quality prediction problem to evaluate the model’s robustness in handling uncertainties in a real-world application. The proposed model has been evaluated on a real dataset that contains the outdoor pollutants from July 2011 to October 2020 in Tehran and Beijing by a 10-fold cv with an average area under the ROC curve of 97 % with a 95% confidence interval [95-97] %. Manuscript profile

Today, to satisfy the needs of customers in the supply chain, there have been considered the design and optimization of the logistic networks. The transfer pricing is one of the most important and the most complex issues that multinational companies faced to it. This article provides a multi-objective mathematical model in order to design a logistic network by considering the transfer pricing and the transportation cost allocation. There has been used the mixed integer nonlinear programming to model the problem. This network has three levels: the supplier, distribution center and the retailer. To deal with the uncertainty in the parameters of the model, there has been used the robust optimization approach and eventually phased solution approach by TH method. Today, to satisfy the needs of customers in the supply chain, there have been considered the design and optimization of the logistic networks. The transfer pricing is one of the most important and the most complex issues that multinational companies faced to it. This article provides a multi-objective mathematical model in order to design a logistic network by considering the transfer pricing and the transportation cost allocation. There has been used the mixed integer nonlinear programming to model the problem. Manuscript profile

Environmental issues are unavoidable in supply chain management. Providing different level of green products is a major subject in this area for distinctive customer segments. In this research, a capacitated network design problem with different levels of green products for their specific demands is considered. This network has different levels with multiple products. The forward/reverse network consists of plants, hybrid warehouse/disposal centers, and customers. Two types of vehicles are considered to transport the products among the network. Each customer segment has specific needs based on their attitude to the greenness subject and their willingness to pay more money in order to attain a product with higher degree of greenness. A quadratic function is assumed for extra money to produce green products. To evaluate the reliability of the model, a real example proposed. Large size sample problems are solved using an efficient Lagrangian relaxation method. The results presents that the proposed method solved large size sample problems in a reasonable time. Manuscript profile

In the recent years, traditional revenue management (RM) models are shifting from them from quantity-based to price-based techniques and incorporating individuals’ decisions within optimization models. In this paper, we have replaced, quantity-based with price-based techniques and proposed the MNL to capture more choice probabilities Computation results indicate the obtained revenue by using proposed model for deciding about the most appropriate product for offering to the customersIn the recent years, traditional revenue management (RM) models are shifting from them from quantity-based to price-based techniques and incorporating individuals’ decisions within optimization models. In this paper, we have replaced, quantity-based with price-based techniques and proposed the MNL to capture more choice probabilities Computation results indicate the obtained revenue by using proposed model for deciding about the most appropriate product for offering to the customers.In the recent years, traditional revenue management (RM) models are shifting from them from quantity-based to price-based techniques and incorporating individuals’ decisions within optimization models. In this paper, we have replaced, quantity-based with price-based techniques and proposed the MNL to capture more choice probabilities Computation results indicate the obtained revenue by using proposed model for deciding about the most appropriate product for offering to the customers. Manuscript profile