abbas toloie eshlaghy

Load forecasting is a key component of electric utility operations and planning. Because of today's highly developed electricity markets and rapidly growing power systems, load forecasting is becoming an essential part of power system operation scheduling. This paper proposes a new short-term load forecasting model based on the large margin nearest neighbor (LMNN) classification algorithm to improve prediction accuracy. The accuracy of many classification methods, such as k-nearest neighbor (k-NN), is significantly influenced by the technique used to calculate sample distances. The Mahalanobis distance is one of the most widely used methods for calculating distance. Numerous techniques have been used to enhance k-NN performance in recent years, including LMNN. Our proposed approach aims to solve the local optimum problem of LMNN, compute data similarities, and optimize the cost function that establishes the distances between instances. Before using gradient descent to determine the ideal parameter values for the cost function, we employ a genetic algorithm to shrink the size of the solution space. Additionally, our method's forecasting errors are contrasted with those of the BPNN and ARMA models. The comparative findings show how well the recommended forecasting model performs in short-term load forecasting.

Inventory management as a live subset of whole organization would be organize the expectation of supply chain base on an intelligent platform. This article was created with the aim of facing the challenges of industrial big data on data which are effective in decision-making based on historical records, but are not linear data due to the valuable content they have.As consequence, it is obvious that are not exploited by traditional methods such as time series for forecasting and decision-making. Accordingly, in this article, to present a strategic model based on artificial intelligence techniques, long short-Term Memory (LSTM), while we discussed the use of industrial big data, which enables the ability to use non-linear data to predict orders. Moreover, the methods of economic order quantity (EOQ) and economic production quantity model (EPQ) in order to prepare and training data have been used. In continue for getting better processing in order to identify strengths and weaknesses in inventory management, "ABC" analysis has also been used. The findings show that the integration of the traditional approach with deep learning method improves learning performance for complex big data analysis tasks. Many evaluations of the proposed deep network have reached an acceptable error value. Finally, this model has provided promising results for predicting expectation of fields that related to controlling amount of production based on objective in inventory management sector.

The purpose of this research is the dynamic analysis of the foreign exchange policies of the Central Bank of Iran. In this regard, the concepts, dimensions, and indicators of the final model were identified using the meta-integration method, which can be used as a suitable tool to evaluate the central bank's currency policies and changes in macroeconomic variables. After simulating the desired model, the results show that with the improvement of economic factors, its sub-components are improved, which increases the efficiency and effectiveness of the central bank's foreign exchange policies, and this will continue as a dynamic cycle over time. Also, the lack of improvement in economic and legal factors is one of the most important obstacles to efficiency, effectiveness, and improvement in the implementation of the Central Bank's foreign exchange policies. Based on the results of simulation and examination of different policies and scenarios, we come to the conclusion that for the central bank's currency policies to be effective and successful, it is necessary to increase internal and external trust and participation in economic investment, improve monetary and budgetary factors, and export growth. Social, managerial and political factors are in the next stage.

In this article, a health service delivery model based on the Internet of Things (IoT) under uncertainty is presented. The considered model includes a set of patients, doctors, vehicles, and services that should be provided in the shortest time and cost. The most important decisions of the network include the allocation of specialist doctors to patients, the routing of vehicles, and doctors to provide health services. The dataset of the problem has been provided to the hospital and centers using IoT tools and an integration framework has been designed for this problem. The results of solving the numerical examples show that to reduce the service delivery time and the distance traveled by vehicles, the design costs of the model should be increased. Also, the increase in the rate of uncertainty during service delivery leads to an increase in total costs in the health system. In this article, Non-Dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Particle Swarm Optimization (MOPSO), and Multi-objective imperialist Competitive algorithm (MOICA) were proposed to solve the model, and the results showed that the proposed methods are more efficient than the exact methods. These algorithms have achieved close to optimal results in the shortest possible time. Also, the calculation results in large numerical examples show the high efficiency of the MOICA.

The purpose of customer relationship management is to develop profitable customer relationships and increase company value. Based on this, this research identifies factors affecting competitive advantage. The current research is applied in terms of purpose and in terms of survey method with model development approach. The time frame of the research is five years (2016-2016). For this purpose, information on the indices of 33 factors affecting competitive advantage in Tejarat Bank were entered into Bayesian averaging models (BMA), (TVP-DMA) and (TVP -DMS) Based on the error rate, the BMA model had the highest accuracy. After estimating the model, 8 main variables were identified. which includes the long-term account balance; the amount of use of mobile bank; the amount of internet bank usage; real customers; legal clients; special or normality of the customer; The type of job and education. In the next step, customers are entered into the LRFM model and categorized based on these variables, finally, the effect of non-fragile variables in the Markov switching model on profitability was analyzed. The results indicated that the majority of the variables have a positive and significant effect on the level of profitability, and by moving from the high prosperity to the deep recession, the impact of the variables has increased. As a result, it can be said that profitability in the state of economic recession has a higher sensitivity to explanatory variables.

Efficient and effective customer relationship management increases customer satisfaction and retention. Customer relationship management helps organizations evaluate profitability and customer loyalty using criteria such as repeat purchases, money spent, and durability. The main goal of this research was the dynamic modeling of communication with customers and the dynamic analysis of this model. The current research is applied in terms of purpose and in terms of survey method with model development approach. The time frame of the research is five years (2017-2021). For this purpose, information on the indices of 33 factors affecting competitive advantage in Tejarat Bank were entered into Bayesian averaging models (BMA), dynamic moving average model with parameters that can be changed over time (TVP-DMA) and dynamic selection model with parameters that can be changed over time (TVP). -DMS) Based on the error rate, the BMA model had the highest accuracy. After estimating the model, 8 main variables were identified. which consists of: long-term account balance; the amount of use of mobile bank; the amount of internet bank usage; real customers; legal clients; special or normality of the customer; Type of job and education. These 8 main identified variables were entered into the dynamic model and then the model was validated based on boundary adequacy tests, structure evaluation, integration error and sensitivity analysis.

Iranian Commercial banks are always considered as one of the most important institutions active in the money and capital market, due to the economic structure of the country and the lack of development of the capital markets, which makes them in charge of financing the economic sectors of the country. However, these banks are not successful in fulfilling their mission. High level of banks' reserves shows that they do not pay enough attention to risk management and credit portfolio management. There are several models such as linear programming, integer programming, zero and one programming that can provide an optimal combination of the elements that make up the facility basket. However, entering financial information into mathematical planning by considering all conditions is not straightforward to achieve such a goal. In this research, using data mining to optimize the multi-objective model of facility allocation is done using neural network. First, the effective variables were extracted from the bank database and after preparation, the most important features were identified using different algorithms such as random forest algorithm, MARS, and step-wise regression. Then, these methods were compared with each other and the best method was selected. In order to cluster the customers, k-means and k-medoids models have been used. Using different criteria, including the silhouette and the best number of clusters, two clusters have been estimated and customers have been identified in two low-risk and high-risk categories. And finally, by using convolutional neural network, the risk and profit of each customer has been predicted.

Human capital is considered as a valuable and competitive capital of organizations, and managers who are aware of the importance of human resources will be able to create a competitive advantage for the future of the organization and the economic development and growth of the country. The purpose of this research is to provide a model for measuring national human capital. The current research is applied in terms of purpose, descriptive-survey approach, and quantitative in terms of research method. The statistical population of the research is two parts. To collect information, in the qualitative section, after extracting a conceptual model from the research literature, the model was confirmed through a survey of experts and professors of human resource management using the Delphi technique. A small part were managers and human resources experts of government organizations of the Ministry of Cooperation, Labor and Social Welfare, and the statistical sample was determined with the help of Morgan's table. The data was collected with the help of a questionnaire from experts and employees, and the validity of the questionnaire was confirmed with the experts' opinions and its reliability was confirmed with Cronbach's alpha, and the data was analyzed using the structural equation approach. Based on the findings of the research, the dimensions of the national human capital measurement model were personal dimension, occupational dimension, organizational dimension, spiritual capital, intellectual capital. The research results indicate the applicability of the national human capital measurement model in the Ministry of Cooperation, Labor and Social Welfare.

The new challenge for business managers is to model and simulate an efficient and effective perishable foods supply chain network that is resilient enough to deal with different disruptions. Therefore, this research aims to model a resilient supply chain for unnecessary perishable foods using an agent-based simulation to deal with future disruptions. To confirm the strategies and model, the statistical population and sample include 7 prominent university professors and 11 managers of various departments of companies producing perishable foods (sales department; production department; planning and warehouse department; laboratory and quality control department; and commercial department). NetLogo software has been utilized to test the agent-based model. The simulation environment in this study includes the behavior and interactions between the members of the supply chain of unnecessary perishable foods and the consumers in Shiraz City. The simulation results indicate that the use of strategies such as consumer behavior tracking, discount, awareness of product safety, robotics, the use of blockchain among the levels of distributors and retailers, and the activation of several supporting suppliers, leads to a resilience supply chain of unnecessary perishable foods under different disruptions. In addition, among the different scenarios, the 30% discount and 40% robotics have been the most effective in the resilience of the supply chain of unnecessary perishable foods under different disruptions.

Global competition, dynamic markets, and rapidly shrinking innovation and technology cycles, all have imposed significant challenges on the financial, banking, and insurance industries and the need to data analysis for improving decision-making processes in these organizations has become increasingly important. In this regard, the data stored in the databases of these organizations are considered as valuable sources of information and knowledge needed for organizational decisions. In the present research, the researchers focus on the common customers of the bank and insurance industry. The purpose is to provide a methodology to predict the performance of new customers based on the behavior of previous customers. To this end, a hybrid model based on support vector machine and genetic algorithm is used. The support vector machine is responsible for modeling the relationship between customer performance and their identity information and the genetic algorithm is responsible for tuning and optimizing the parameters of the support vector machine. The results obtained from customer classification using the proposed model in this research led to customer classification with a high accuracy of 99%.

This study presents the elements and methodology of the reinforcement learning model according to the agent-based conceptual model of hospital accreditation in Iran. The elements and methodology of the mentioned model will create a favorable study base for creating a smart and multi-agent hospital accreditation system and environment simulation trends to provide efficient guidelines to relevant agents and policymakers. Also, this study intends to provide an appropriate answer to the main research questions in which there are uncertainties related to the reinforcement learning elements and how to choose the reinforcement learning methodology in a multi-agent system of the socio-technical systems type.

To collect the information needed to know the elements and identify the hospital accreditation processes, agents, environment, and interaction between them, the systematic review of sources, review of scientific documents, and semi-structured interviews, through experts, to The face-to-face method has been used. Summarizing the interviews was done using grounded-theory-based methods, and a sequential and systematic approach. The sources for collecting the characteristics of the machine learning process using the systematic review method were from the document "Iran Hospital Accreditation Guide 2022". Also, the process of selecting the mentioned features was done through the correct selection of the output features of the model, which are the actions of the agent. The list of agent actions was extracted from the conceptual content of the document above in the form of a general non-binary tree based on the classification of the tree structure.

The extracted reinforcement learning model will seek to find the optimal chains of operational actions, in the conditions where the quantitative data of the hospital is available. The most important elements of the mentioned model are:Set of states: set of hospital accreditation factors such as input variables, output variables, indicators, parameters, and fixed numbers related to the metrics of each conceptual agent in the document "Iran Hospital Accreditation Guide 2022".Set of actions: actions of intelligent agents in each reinforcement learning episode, paths from the hierarchically clustered binary tree are operational actions that can be performed in the hospital and per set of state features.Reward function: "Obtaining the highest possible score in the hospital ranking system by performing the least number of necessary actions and actions."Policy function: Based on the learning process of each agent, it is based on a DQN deep neural network and gradient reduction algorithm.Operational Agents: the operational goal of each of the conceptual agents, is "maximizing the accreditation points of the metrics of the relevant field by recommending the least measures."The general cycle of the model: in this structure, each of the intelligent agents, a subset of the 9 conceptual agents, has a multi-layered neural network within its scope, and the characteristics of related states are entered into this neural network and Output, based on the definition of the special policy function of that agent, a map of optimal actions will be created according to the agent's current conditions and states.Neural network model: The neural network of the intelligent agent is derived from the conceptual agent "management and leadership" in which the input, hidden, and output layers of the network are specified.

Summarizing the background of related research showed that the approach to designing hospital accreditation models can be divided into two groups: "conceptual models without using intelligent agents" and "conceptual models using Intelligence and operating systems" should be divided. The investigations showed that these studies had the expected results and that the efficiency and effectiveness of the models and processes proposed by them had the necessary validity.

Considering that the users are the main focus of immersive journalism, any study in this field without understanding and recognizing them is incomplete. The quality of the VR news experience depends on many parameters, the most important of which are related to the cognitive and behavioral science of the users, apart from the technological factors that are prerequisites for making VR. In this regard, through interviews with experts in journalism and cognitive sciences, this research identified the categories that influence the depth of user’s immersion based on the Grounded Theory methodology and finally presented a conceptual model. The phenomenon of the model is “user involvement”. This category is affected by contextual factors such as "user’s demographic characteristics" and "type of news", as well as the intervening factors of "trauma" and "preventing factors of using virtual reality". In addition, the three categories of "cognition", "narrative" and "crafting pieces" provided the causal conditions that are the basis for the immersion in the news narrative. Finally, "focusing on user’s cognitive factors" in creating VR pieces is the interaction strategy that brought two consequences of "increasing immersion" and "changing norms and behaviors".

Recently,social networks have attracted special attention. In various social networks, users are constantly expressing their public as well as private opinions on various topics. Twitter is one of these social networks that has become very popular in the last decade. This social network provides organizations with a fast and effective way to analyze customers' feelings, views, and criticisms of market success. Emotional analysis is a process in which people's opinions, feelings, and attitudes about a particular subject are extracted. There has been a lot of research on emotion analysis based on user comments, documents and articles. Analysis of what is being said is very different from Twitter data, because Twitter tweets are limited to 280 characters and force users to express their feelings concisely. The best results in emotion classification are obtained from machine learning techniques such as simple Bayes and support vector machine. In this research, a method for analyzing emotions in social networks is presented. In this regard, we have tried to improve the classification of text by Bayesian method to some extent by focusing on the stages of data preprocessing and feature selection.users' feelings are analyzed. The classification problem has been formulated and solved using the latest achievements in the field of machine learning. . To evaluate the proposed method in this dissertation is from the Twitter data set scenario. The proposed method is compared with other classification methods. Has shown the best performance.

The issue of increasing tax revenues and possible ways for this increase is an attractive issue for governments. Especially in a single product economy like Iran, whose main source of income is volatile and unpredictable oil income. Today, tax revenues play an important role in financing governments so that tax is considered as a legitimizing factor for a government. After introducing the presented models and classifying them, this research aims to investigate and identify the effective factors in increasing tax revenues and evaluating public trust and participation in the field of tax with a meta- synthesis approach. The main components of this dynamic model include economic, cultural factors and political factors. Then, in order to better understand the variables affecting this relationship and understand the existing dynamics, a model has been presented for evaluating trust and public participation in the field of tax using the approach of system dynamics modeling and drawing causal-loop diagrams (CLD). Finally, the simulation has been done by Vensim software. Three basic scenarios for increasing the main components and one scenario for simultaneous increase of all the main components were analyzed as levers of the model. The simulation results indicate the positive effect of economic factors on trust and public participation in the field of tax. The point is that the effect of economic factors is greater when all simultaneous components are applied.

Classification is the operation of dividing various data into multiple classes where they share quantitative and qualitative similarities. Classification has many use cases in engineering fields such as cloud computing, power distribution, and remote sensing. The accuracy of many classification techniques such as k-nearest neighbor (k-NN) is highly dependent on the method used in the calculation of distances between samples. It is assumed that samples close to each other belong to the same class while samples that belong to different classes have a large distance between them. One of the popular distance calculation methods is the Mahalanobis distance. Many methods, including large margin nearest neighbor (LMNN), have been proposed to improve the performance of k-NN in recent years. Our proposed method aims to introduce a cost function to calculate data similarities while solving the local optimum pitfall of LMNN and optimizing the cost function determining distances between instances. Although k-NN is an efficient classification technique that is simple to comprehend and use, it is costly to compute for large datasets and sensitive to outlier data. Another difficult feature of k-NN is that it can only measure distance in Euclidean space. The distance metric should ideally be modified to fit the specific needs of the application. Due to the disadvantages in k-NN and LMNN methods, to optimize the objective function to calculate distances for the test data and to improve classification accuracy, we initially use the genetic algorithm to reduce the range of the solution space and then by using the gradient descent the optimal values of parameters in the cost function is obtained. Our method is carried out on different benchmark datasets with varying numbers of attributes and the results are compared to k-NN and LMNN methods. Misclassification rate, precision, f1 score, and kappa score are calculated for different values of k, mutation rate, and crossover rate. Overall, our proposed method shows superior performance with an average accuracy rate of 87.81% which is the highest among all methods. The average precision, f1 score, and kappa score of our method are 0.8453, 0.8513, and 0.6976 respectively.

The primary goal of this study is to design an agent-based model of the supply chain for perishable goods during the occurrence of specific disruptions. This study is practical in terms of aim and qualitative in terms of data collection method. To validate the model, the views of the statistical population including prominent university professors and manufacturers of perishable goods and experts with experience and expertise in the area of specific disruptions of the perishable goods supply chain were used. Additionally, the snowball method was used to select the sample. In total, the views of 18 experts were used. Agent-based modeling was done using NetLogo software. In this modeling, all supply chain disruptions of perishable goods such as disruptions at the macro level (change in consumer behavior), demand, production, supply, transportation, information, and Financial were considered. Also, according to each disruption, strategies to mitigate the effects such as blockchain, robotics, etc. were determined. The results of agent-based modeling show that the simultaneous use of different strategies in the perishable goods supply chain during the occurrence of specific disruptions significantly reduces the effects of specific disruptions on the perishable goods supply chain. Vaccination along with the application of other strategies such as the use of blockchain, robotics, discounts, subsidy, online purchase methods, non-cash payment methods, awareness of product safety, green packaging, and employee safety and health have significantly reduced the effects of specific disruptions on the perishable non-necessary goods supply chain. In addition, according to the findings of the research, among the various strategies, the discount has played the most significant role in reducing the influences of specific disruptions on the supply chain of non-necessary perishable goods.

Among the most commonly diagnosed cancers, melanoma is the second leading cause of cancer-related death. A growing number of people are becoming victims of melanoma. Melanoma is also the most malignant and rare form of skin cancer. Advanced cases of the disease may cause death due to the spread of the disease to internal organs. The National Cancer Institute reported that approximately 99,780 people were diagnosed with melanoma in 2022, and approximately 7,650 died. Therefore, this study aims to develop an optimization algorithm for predicting melanoma patients' survival.

This applied research was a descriptive-analytical and retrospective study. The study population included patients with melanoma cancer identified from the National Cancer Research Center at Shahid Beheshti University between 2008 and 2013, with a follow-up period of five years. An optimization model was selected for melanoma survival prognosis based on the evaluation metrics of data mining algorithms.

A neural network algorithm, a Naïve Bayes network, a Bayesian network, a combination of decision tree and Naïve Bayes network, logistic regression, J48, and ID3 were selected as the models used in the national database. Statistically, the studied neural network outperformed other selected algorithms in all evaluation metrics.

The results of the present study showed that the neural network with a value of 0.97 has optimal performance in terms of reliability. Therefore, the predictive model of melanoma survival showed a better performance both in terms of discrimination power and reliability. Therefore, this algorithm was proposed as a melanoma survival prediction model.

Academic transgression (AT), as any behavior, belief, or condition that violates a social and academic norm, is a serious problem threatening academic integrity, especially when committed by faculty members, who are supposed to be educational role models. Societies employ social control means to respond to, prevent or reduce transgressive acts, to maintain social order and morality. The current study aimed to examine the perceived effects of self-control, job satisfaction, and life satisfaction, as social control means, on five types of interpersonal, educational, research, organizational, and sexual ATs among faculty members, and also to measure perceived prevalence of these transgressions in Iranian higher education.

A modified version of “perceived causal relations” methodology was adopted to study the perceived relations between reciprocal pairs of the variables. Network analysis was employed to analyze the data gathered from faculty members via an online questionnaire.

The results demonstrated that faculty member participants perceived high effects of their self-control, job satisfaction, and life satisfaction on decreasing ATs, particularly interpersonal, organizational, and educational ATs.

As faculty member participants perceived high prevalence of all types of ATs in Iranian academia, there is an urge to consider new policies to employ effective social control means suggested in this research, especially self-control, to reduce, and even restrain the perpetration of these transgressions. We also suggest perceived causal relations as a useful and strong methodology to conduct research on sensitive topics, especially, transgression and crime

Efficient supply chain as well as the proper management of its components play an important role in supply chain productivity. The steel industry is one of the mother industries and needs to further enhance its chain productivity. The purpose of the present study is to identify key factors affecting the productivity of national steel supply chain. In order to identify the factors affecting steel supply chain productivity, the SCOR model has been used and its indices have been validated by CVR and CVI forms as well as by steel industry experts, based on which the designed questionnaire was distributed among the managers and experts of the steel industry and the data were collected. Finally, the data analysis was performed using confirmatory factor analysis with structural equations and PLS software. The factors affecting supply chain productivity were confirmed by 30 indices and 6 factors.The results revealed that all 6 factors influence steel supply chain efficiency, however, among these factors, the enabler’s factor

Increasing operating profit is a challenge faced by pharmaceutical distribution companies. Most of the researches conducted in this field have a cost reduction approach. The online monitoring system is one of the effective methods that can be used for managers' decision-making and improving the performance of the pharmaceutical distribution chain with the approach of reducing costs and increasing revenues. To create this system, conceptual, mathematical and computer modeling is needed. The aim of this research is to develop a mathematical model of the online monitoring system to improve the pharmaceutical distribution system based on a conceptual model using a reinforcement learning approach. The mathematical model was derived based on the factor-based conceptual model and using the multi-factorial reinforcement learning approach. After extracting the mathematical model, the effectiveness of the model was validated by comparing the results obtained from the output of the mathematical model and the actual results in a pharmaceutical distribution company. The findings of the research showed that the developed mathematical model has the ability to continuously improve the goals, decisions and performance of the pharmaceutical distribution chain processes, according to the interactions and changes in the behavior of agents and the state of the environment.

The significant growth in the amount of use of management information systems in different work departments of organizations has caused researchers in the field of information technology management to pay more attention to improving productivity in these systems. The purpose of this research is to identify the cause and effect (causal) mathematical model of the productivity of management information systems in the field of human resources.

This research has used a mixed exploratory approach. First, the conceptual model was calculated using the previous sources, and then the mathematical model of cause and effect was created using the quantitative method of Fuzzy DEMATEL (in six steps). The reliability and validity of the questionnaires of fuzzy DEMATEL pairwise comparisons have been confirmed by using the test-retest method and the content validity method of Lawshe, respectively.

Among the main productivity dimensions of the human resources management information system, the dimension of "intelligence" is the most effective dimension. The "innovation" dimension is the most effective dimension. The dimension of "innovation" has the highest degree of interaction with other dimensions and the dimension of "intelligence" has the highest degree of causality.

Since "effectiveness" is the main problem and "intelligence" is the main solution to the problem, placing the dimension of "intelligence" and the components of "organizational effect" and "individual effect" and "user satisfaction" in the focus of attention; The main priority of the management information system maintenance and development team in Naja's human resources department is to improve productivity.

The aims of this study is to provide a conceptual model of hospital accreditation in Iran through qualitative research. The grounded theory model was compiled using the results of the analysis of the interviews. Then, with the help of the grounded theory model and the results of qualitative analysis, a state diagram was obtained. Using the state diagram, initial sampling, systematic review of sources and results of interviews, 9 conceptual agents "governance organizations, management and leadership, clinical personnel, support personnel, hospital infrastructure, assessor, standards, assessment method and service recipient" were identified. Finally, the conceptual model of agent-based, environment, behavioral rules of agents and their input and output interactions was presented. In future researches, reinforcement learning models can be designed according to the conceptual model of this study, so that by using it, software developers can develop a suitable framework for solving complex problems in the field of hospital accreditation. Because the field of hospital management systems is one of the desirable types of socio-technical systems that have high capacities.

Melanoma is one of the most commonly diagnosed cancers and the second cause of cancer-related death among people. This disease is the rarest and most malignant type of skin cancer. In advanced conditions, it has the ability to spread to internal organs and can lead to death. In Iran, for several years, significant data about melanoma have been collected either manually or electronically, due to its prevalence and the high costs it leaves on the country's healthcare system, but despite these valuable data, the health system is still unaware of the high potential of data mining in predicting the survival of patients with melanoma. Therefore, the aim of this study was to design an intelligent system to predict the survival of these patients.

This study was practical in terms of nature and descriptive-analytical and retrospective in terms of method. The research population consisted of patients with melanoma cancer from the database of the National Cancer Research Center affiliated to Shahid Beheshti University, located in Tajrish Martyrs Hospital, Tehran, Iran (between 2007 and 2012), who were followed up for 5 years (n = 4118). SPSS and Weka software were used to design the support system for melanoma cancer survival prediction. The final model for predicting melanoma cancer survival was selected based on the evaluation indices of data mining algorithms.

Neural network algorithms, simple Bayes, Bayesian network (BN) and combination of decision tree with simple Bayes, logistic regression, J48, and ID3 were selected as the used models of the country's database. Based on the findings, the neural network performed better with a value of 0.97 in terms of accuracy and 91.03 in terms of features.

The performance of the neural network in all evaluation indices was statistically higher than other selected algorithms. Therefore, this algorithm was chosen as a support system for predicting melanoma cancer survival.

Optimization problems are becoming more complicated, and their resource requirements are rising. Real-life optimization problems are often NP-hard and time or memory consuming. Nature has always been an excellent pattern for humans to pull out the best mechanisms and the best engineering to solve their problems. The concept of optimization seen in several natural processes, such as species evolution, swarm intelligence, social group behavior, the immune system, mating strategies, reproduction and foraging, and animals’ cooperative hunting behavior. This paper proposes a new Meta-Heuristic algorithm for solving NP-hard nonlinear optimization problems inspired by the intelligence, socially, and collaborative behavior of the Qashqai nomad’s migration who have adjusted for many years. In the design of this algorithm uses population-based features, experts’ opinions, and more to improve its performance in achieving the optimal global solution. The performance of this algorithm tested using the well-known optimization test functions and factory facility layout problems. It found that in many cases, the performance of the proposed algorithm was better than other known meta-heuristic algorithms in terms of convergence speed and quality of solutions. The name of this algorithm chooses in honor of the Qashqai nomads, the famous tribes of southwest Iran, the Qashqai algorithm.

Over the past decade, solving complex optimization problems with metaheuristic algorithms has attracted many experts and researchers.There are exact methods and approximate methods to solve optimization problems. Nature has always been a model for humans to draw the best mechanisms and the best engineering out of it and use it to solve their problems. The concept of optimization is evident in several natural processes, such as the evolution of species, the behavior of social groups, the immune system, and the search strategies of various animal populations. For this purpose, the use of nature-inspired optimization algorithms is increasingly being developed to solve various scientific and engineering problems due to their simplicity and flexibility. Anything in a particular situation can solve a significant problem for human society. This paper presents a comprehensive overview of the metaheuristic algorithms and classifications in this field and offers a novel classification based on the features of these algorithms.