فراابتکاری

Open Access Article

1 - Multi-period Multi-level Supply Chain Network Design in Agile Manufacturing with Tabu Search Algorithm
elahe salari mohammadreza shahraki abdollah sharifi

10.7508/jstpi.2019.02.003

Supply chain network design includes key decisions that have a major impact on the supply chain operational structure. Efficient supply chain design improves performance in organizations. This has led to the emergence of new concepts in the supply chain issue in the pas More

Supply chain network design includes key decisions that have a major impact on the supply chain operational structure. Efficient supply chain design improves performance in organizations. This has led to the emergence of new concepts in the supply chain issue in the past decade. In this study, the supply chain network design problem in agile organizations has been taken into account with multi-level and multi-period. This problem is considered under conditions of having multiple customers with a high demand volume. The decisions include the selection of companies at each level, the amount of production, storage and transportation of each company. The problem has been modeled to integrate all decision variables with the goal of minimizing overall operating costs across the entire supply chain and Satisfaction of customers' complete demand and Satisfaction with them. Since multi-period multi-level supply chain design problem solving is one of the NP-Hard issues in uncertainty conditions, it is better to use innovative and meta-algorithms to reduce problem solving time. For this reason, the algorithm for banning search algorithms, which is one of the meta-algorithms, has been used to solve the model. The results of this research show that as the number of problem-solving repetitions increases, answers with less than 3% of the difference between the optimal answer are achieved. The search algorithm is forbidden to get the optimal response compared to the Lagrange algorithm. Manuscript profile

Open Access Article

2 - Prediction of Growth of Small and Medium Enterprises with the Combination of Artificial Neural Networks and Meta-Heuristic Algorithm
حامد ابراهیم خانی مصطفی کاظمی Alireza Pooya Amir Mohammad Fakoor Saghih

The growth of a company is considered to be an important economic goal. Given that many small and medium enterprises do not grow into growth and fail in the early years of their operations, a predictive system of corporate growth can be offset by the huge costs Starting More

The growth of a company is considered to be an important economic goal. Given that many small and medium enterprises do not grow into growth and fail in the early years of their operations, a predictive system of corporate growth can be offset by the huge costs Starting businesses, entrepreneurs and companies to pay. Accordingly, the purpose of this study was to predict the growth of small and medium enterprises with the combination of neural network and meta-heuristic algorithms. The purpose of this research was applied and based on the method of doing descriptive-modeling work. Statistical population of this research was all small and medium enterprises of Zanjan province. Statistical sample size According to the growth of companies, 158 companies has been designated. In order to collect data in this study, interviews, questionnaires and documents of companies have been used. Validity and reliability of the questionnaire were verified and and using Cronbach's alpha coefficient. In order to analyze the research data using confirmatory factor analysis methods, the neural network of multilayer perceptron, neural network combined with genetic algorithm and neural network combined with particle swarm algorithm have been used. The results show that all three methods are able to predict the growth of the company. Among these three methods, the best predictive method for growth of the company is the neural network combined with the particle swarm algorithm with the least error rate compared to the other two methods. Manuscript profile

Open Access Article

3 - A Hybrid-Based Feature Selection Method for High-Dimensional Data Using Ensemble Methods
A. Rouhi H. Nezamabadi-pour

Nowadays, with the advent and proliferation of high-dimensional data, the process of feature selection plays an important role in the domain of machine learning and more specifically in the classification task. Dealing with high-dimensional data, e.g. microarrays, is as More

Nowadays, with the advent and proliferation of high-dimensional data, the process of feature selection plays an important role in the domain of machine learning and more specifically in the classification task. Dealing with high-dimensional data, e.g. microarrays, is associated with problems such as increased presence of redundant and irrelevant features, which leads to decreased classification accuracy, increased computational cost, and the curse of dimensionality. In this paper, a hybrid method using ensemble methods for feature selection of high dimensional data, is proposed. In the proposed method, in the first stage, a filter method reduces the dimensionality of features and then, in the second stage, two state-of-the-art wrapper methods run on the subset of reduced features using the ensemble technique. The proposed method is benchmarked using 8 microarray datasets. The comparison results with several state-of-the-art feature selection methods confirm the effectiveness of the proposed approach. Manuscript profile

Open Access Article

4 - Hyper Spherical Search Optimization Algorithm Based on Chaos Theory
Mohammad Kalantari S. Sohrabi H. Rashidy Kanan H. Karami

A Hyper Spherical Search (HSS) optimization algorithm based on chaos theory is proposed that resolves the weakness of the standard HSS optimization algorithm including the speed of convergence and the sequential increment in the number of algorithm iterations to achieve More

A Hyper Spherical Search (HSS) optimization algorithm based on chaos theory is proposed that resolves the weakness of the standard HSS optimization algorithm including the speed of convergence and the sequential increment in the number of algorithm iterations to achieve the optimal solution. For this, in the particle initiation and search steps of the proposed algorithm, random values used in the standard algorithm are replaced with the values of two mappings, Chebyshev and Liebovitch, that makes the results of the proposed algorithm definite and decreases their standard deviation. The simulation results on the standard benchmark functions show that the proposed algorithm not only has faster convergence, but also acts as a more accurate search algorithm to find the optimal solution in comparison to standard hyper spherical search algorithm and some other optimization algorithms such as genetic, particle swarm, and harmony search algorithm. Manuscript profile

Open Access Article

5 - A New Data Clustering Method Using 4-Gray Wolf Algorithm
Laleh Ajami Bakhtiarvand Zahra Beheshti

Nowadays, clustering methods have received much attention because the volume and variety of data are increasing considerably.The main problem of classical clustering methods is that they easily fall into local optima. Meta-heuristic algorithms have shown good results in More

Nowadays, clustering methods have received much attention because the volume and variety of data are increasing considerably.The main problem of classical clustering methods is that they easily fall into local optima. Meta-heuristic algorithms have shown good results in data clustering. They can search the problem space to find appropriate cluster centers. One of these algorithms is gray optimization wolf (GWO) algorithm. The GWO algorithm shows a good exploitation and obtains good solutions in some problems, but its disadvantage is poor exploration. As a result, the algorithm converges to local optima in some problems. In this study, an improved version of gray optimization wolf (GWO) algorithm called 4-gray wolf optimization (4GWO) algorithm is proposed for data clustering. In 4GWO, the exploration capability of GWO is improved, using the best position of the fourth group of wolves called scout omega wolves. The movement of each wolf is calculated based on its score. The better score is closer to the best solution and vice versa. The performance of 4GWO algorithm for the data clustering (4GWO-C) is compared with GWO, particle swarm optimization (PSO), artificial bee colony (ABC), symbiotic organisms search (SOS) and salp swarm algorithm (SSA) on fourteen datasets. Also, the efficiency of 4GWO-C is compared with several various GWO algorithms on these datasets. The results show a significant improvement of the proposed algorithm compared with other algorithms. Also, EGWO as an Improved GWO has the second rank among the different versions of GWO algorithms. The average of F-measure obtained by 4GWO-C is 82.172%; while, PSO-C as the second best algorithm provides 78.284% on all datasets. Manuscript profile

Open Access Article

6 - Stochastic Planning of Resilience Enhancement for Electric Power Distribution Systems against Extreme Dust Storms
M. Haghshenas R. Hooshmand M. Gholipour

Resilience in power systems refers to the system's ability to withstand severe disturbances with a low probability of occurrence. Because in recent years extreme dust storms have caused severe damage to Iran's electricity industry, especially in the south and southwest, More

Resilience in power systems refers to the system's ability to withstand severe disturbances with a low probability of occurrence. Because in recent years extreme dust storms have caused severe damage to Iran's electricity industry, especially in the south and southwest, in this paper proposed a new scenario-based stochastic planning model for enhancement of power distribution systems resilience against extreme dust storms. In proposed model, in the first stage, the investment costs to improve the distribution system resilience against extreme dust storms are minimized due to the financial constraints, and in the second stage, the expected operating costs in dust storm conditions are minimized due to the operating constraints. Because network's insulation equipment are major cause of distribution system vulnerabilities in the dust storms, measures in the planning stage include replacement of porcelain insulators with silicon-rubber type, installation of automatic tie switches and installation of emergency generators. In the second stage, the measures are divided into preventive actions and corrective actions, and coordination between stages 1 and 2 is implemented in such a way that the results of each stage depend on the decision variables of the other stage. The simulation results for IEEE 33-bus test system and a 209 bus radial distribution network located in Khuzestan province, Iran, confirm the efficiency of the proposed model in different financial conditions. Manuscript profile

Open Access Article

7 - Novel AI-Based Metaheuristic Optimization Approaches for Designing INS Navigation Systems
علی محمدی Farid Sheikholeslam Mehdi Emami

Soft computing techniques in engineering sciences have covered a large amount of research. Among them is the design and optimization of navigation systems for use in land, sea, and air transportation systems. Therefore, in this paper, an attempt is made to take advantag More

Soft computing techniques in engineering sciences have covered a large amount of research. Among them is the design and optimization of navigation systems for use in land, sea, and air transportation systems. Therefore, in this paper, an attempt is made to take advantage of novel approaches of intelligent metaheuristic optimization for designing integrated navigation systems. For this purpose, the inclined planes system optimization algorithm with several modified and new versions have been used along with two well-known methods of genetic algorithm and particle swarm optimization. Considerations are made on an INS/GNSS problem with IMU MEMS inertia measurement modules. Process and measurement noise covariance matrices are considered as design variables and the sum of mean-squares-error as an objective function in the form of a single-objective minimization problem. Outputs are presented in terms of statistical and performance indicators such as runtime, fitness, convergences, angular-velocity accuracy, latitude, longitude, altitude, roll, pitch, yaw, and routing along with the ranking of algorithms. The overall assessment indicated the correctness of the performance and the relative superiority of the IPO and IIPO over the competitors and competitive performance of the assumed algorithms in comparison with the volume of considerations and calculations of the base problem. Manuscript profile

Open Access Article

8 - Metaheuristic Optimization of Competencies of Strategic Managers in State Organizations
Gholamreza Abbaspasha davood kia kojoree Mohammad javad Taghipourian Gilani

10.52547/istd.31557.8.31.273

The aim of the present research was to optimize the competencies of strategic managers in state organizations. This applied research was conducted quantitatively to collect the data. A researcher-made questionnaire was used to determine the level of consensus among res More

The aim of the present research was to optimize the competencies of strategic managers in state organizations. This applied research was conducted quantitatively to collect the data. A researcher-made questionnaire was used to determine the level of consensus among respondents on the priority of the proposed indicators for the competency of strategic managers. The relationship between the components of the metaheuristic model was determined by 122 senior and middle managers who were selected by random stratified sampling from the studied organizations: Tehran Governor's Office, Administrative and Recruitment Affairs Organization, Supreme Audit Court, Welfare Organization, Iran Health Insurance Organization (IHIO). Data were analyzed using the metaheuristic approach method based on genetic algorithm and decision tree, using the WEKA and RAPIDMINER software programs. Based on the results of the Shannon’s method, ethics earned the highest priority. Furthermore, 11 out of the 16 extracted factors affecting competency were selected as the optimal characteristics of strategic managers in state organizations using metaheuristic algorithms. These were knowledge competencies, skill competencies, basic competencies, psychological competencies, ethics, general competencies, interactions and communications, resource management, strategic thinking, transformism, and leadership. The findings also show that the most effective factors must be examined to identify and evaluate the competencies of strategic managers in state organizations. Manuscript profile

Open Access Article

9 - Presenting a Network-on-Chip Mapping Approach Based on Harmony Search Algorithm
Zahra Bagheri Fatemeh Vardi Alireza Mahjoub

In network-on-chip implementation, mapping can be considered as an important step in application implementation. The tasks of an application are often represented in the form of a core graph. The cores establish a link between themselves using a communication platform a More

In network-on-chip implementation, mapping can be considered as an important step in application implementation. The tasks of an application are often represented in the form of a core graph. The cores establish a link between themselves using a communication platform and often the network on the chip. For finding proper mapping for an application, developers have proposed various algorithms. In most cases, due to the complexity, exact search methods are used to find the mapping. However, these methods are suitable for networks with small dimensions. As the size of the network increases, the search time also increases exponentially. This article, from the perspective of a heuristic approach, uses the harmony search method to decide when to connect cores to routers. Our approach uses an improved version of the harmony search algorithm with a focus on reducing power consumption and delay. Algorithm complexity analysis reveals a more appropriate solution compared to similar algorithms with respect to application traffic pattern. Compared to similar methods, the algorithm achieves 39.98% less delay and 61.11% saving in power consumption. Manuscript profile

Open Access Article

10 - A review of the application of meta-heuristic algorithms in load balancing in cloud computing
Mehdi Morsali Abolfazl Toroghi Haghighat Sasan Hosseinali-Zade

By widespread use of cloud computing, the need to improve performance and reduce latency in the cloud increases. One of the problems of distributed environments, especially clouds, is unbalanced load which results in reducing speed and efficiency and increasing delay in More

By widespread use of cloud computing, the need to improve performance and reduce latency in the cloud increases. One of the problems of distributed environments, especially clouds, is unbalanced load which results in reducing speed and efficiency and increasing delay in data storage and retrieval time. Various methods for load balancing in the cloud environment have been proposed, each of which has addressed the issue from its own perspective and has its advantages and disadvantages. In this research, we first provide some criteria for measuring load balance in the cloud and then examine the use of Metaheuristic methods in load balancing in the cloud environment. After introducing Metaheuristic load balancing methods, we have compared them based on the aforementioned criteria and discussed the advantages and disadvantages of each. Ant Colony Algorithms, Artificial Ant Colony, Bee Colony, Artificial Bee Colony, Bee Foraging Algorithm, Particle Swarm, Cat Swarm, Simulated Annealing, Genetic Algorithm, Tabu Search, Fish Swarm and Hybrid Algorithms and etc. examined in this research. Manuscript profile

Open Access Article

11 - Improvement of intrusion detection system on Industrial Internet of Things based on deep learning using metaheuristic algorithms
mohammadreza zeraatkarmoghaddam majid ghayori

Due to the increasing use of industrial Internet of Things (IIoT) systems, one of the most widely used security mechanisms is intrusion detection system (IDS) in the IIoT. In these systems, deep learning techniques are increasingly used to detect attacks, anomalies or i More

Due to the increasing use of industrial Internet of Things (IIoT) systems, one of the most widely used security mechanisms is intrusion detection system (IDS) in the IIoT. In these systems, deep learning techniques are increasingly used to detect attacks, anomalies or intrusions. In deep learning, the most important challenge for training neural networks is determining the hyperparameters in these networks. To overcome this challenge, we have presented a hybrid approach to automate hyperparameter tuning in deep learning architecture by eliminating the human factor. In this article, an IDS in IIoT based on convolutional neural networks (CNN) and recurrent neural network based on short-term memory (LSTM) using metaheuristic algorithms of particle swarm optimization (PSO) and Whale (WOA) is used. This system uses a hybrid method based on neural networks and metaheuristic algorithms to improve neural network performance and increase detection rate and reduce neural network training time. In our method, considering the PSO-WOA algorithm, the hyperparameters of the neural network are determined automatically without the intervention of human agent. In this paper, UNSW-NB15 dataset is used for training and testing. In this research, the PSO-WOA algorithm has use optimized the hyperparameters of the neural network by limiting the search space, and the CNN-LSTM neural network has been trained with this the determined hyperparameters. The results of the implementation indicate that in addition to automating the determination of hyperparameters of the neural network, the detection rate of are method improve 98.5, which is a good improvement compared to other methods. Manuscript profile

List of Articles فراابتکاری

Rimag

Links

Related Centers

Technical Support

Official pages