Showing 121 results for Genetic Algorithm
Volume 5, Issue 2 (6-2015)
Abstract
Taking advantage of geometry has been always a current base in Iranian traditional architecture for accommodate survey among form, stability and coordination. Recognition of components’ geometrical behavior along organic :union: making’s direction among skeleton, space and background systems causes integrated feedback formation among effective elements in collection’s stability. Based on existing geometrical limitations in their structures and coordination, Iranian girih as modular units are capable of developing in x and y axes by considering visual values and actionable efficiency. According to controlled process of Iranian girih s’ structure in mentioned axes, transferring this discipline in z axis for -3dimensional action’s maintenance of structure collection is also discussed. So, firstly current article has considered usage method of girih geometry productive parameters by Grasshopper graphical coding software, and then resulting collection of various forms from girih geometry is introduced as a population of analyzable genes by genetic algorithm method. Thereby, supports’ optimized location is developed by -3dimentional action among components for reaching an efficient form of girih’s geometry. Adapted to survey, prevalent population of introduced genes collections is selected after simultaneously analysis of form and mechanism by Karamba addition and the most optimized status of supports’ location is selected in circumstances that structure’s components has the minimum stress. Then, the optimized state and organized sample in supports’ location are considered to explore about resulting behavior in both states toward load transferring to case foundation. According to this study results, it can be concluded that by defining certain legislations, geographical mechanism of Iranian girih causes an integrated behavior’s controlling and multi-dimensional action among quality parameters such as cladding structures’ designing and quantity parameters such as proper behavior toward forces. This coordinating feedback between architecture and structure in supports’ optimized location which results from genetic algorithm method, decreases stress in structures’ components and also maximizes structure’s stability besides economic advantage in used materials. So, firstly current article has considered usage method of girih geometry productive parameters by Grasshopper graphical coding software, and then resulting collection of various forms from girih geometry is introduced as a population of analyzable genes by genetic algorithm method. Thereby, supports’ optimized location is developed by -3dimentional action among components for reaching an efficient form of girih’s geometry. Adapted to survey, prevalent population of introduced genes collections is selected after simultaneously analysis of form and mechanism by Karamba addition and the most optimized status of supports’ location is selected in circumstances that structure’s components has the minimum stress. Then, the optimized state and organized sample in supports’ location are considered to explore about resulting behavior in both states toward load transferring to case foundation. According to this study results, it can be concluded that by defining certain legislations, geographical mechanism of Iranian girih causes an integrated behavior’s controlling and multi-dimensional action among quality parameters such as cladding structures’ designing and quantity parameters such as proper behavior toward forces. Based on existing geometrical limitations in their structures and coordination, Iranian girih as modular units are capable of developing in x and y axes by considering visual values and actionable efficiency. According to controlled process of Iranian girih s’ structure in mentioned axes, transferring this discipline in z axis for -3dimensional action’s maintenance of structure collection is also discussed. So, firstly current article has considered usage method of girih geometry productive parameters by Grasshopper graphical coding software, and then resulting collection of various forms from girih geometry is introduced as a population of analyzable genes by genetic algorithm method. Thereby, supports’ optimized location is developed by -3dimentional action among components for reaching an efficient form of girih’sgeometry. Adapted to survey, prevalent population of introduced genes collections is selected after simultaneously analysis of form and mechanism by Karamba addition and the most optimized status of supports’ location is selected in circumstances that structure’s components has the minimum stress. Then, the optimized state and organized sample in supports’ location are considered to explore about resulting behavior in both states toward load transferring to case foundation. According to controlled process of Iranian girih s’ structure in mentioned axes, transferring this discipline in z axis for -3dimensional action’s maintenance of structure collection is also discussed. So, firstly current article has considered usage method of girih geometry productive parameters by Grasshopper graphical coding software, and then resulting collection of various forms from girih geometry is introduced as a population of analyzable genes by genetic algorithm method. Thereby, supports’ optimized location is developed by -3dimentional action among components for reaching an efficient form of girih’s geometry. Adapted to survey, prevalent population of introduced genes collections is selected after simultaneously analysis of form and mechanism by Karamba addition and the most optimized status of supports’ location is selected in circumstances that structure’s components has the minimum stress. Then, the optimized state and organized sample in supports’ location are considered to explore about resulting behavior in both states toward load transferring to case foundation. According to controlled process of Iranian girih s’ structure in mentioned axes, transferring this discipline in z axis for -3dimensional action’s maintenance of structure collection is also discussed. So, firstly current article has considered usage method of girih geometry productive parameters by Grasshopper graphical coding software, and then resulting collection of various forms from girih geometry is introduced as a population of analyzable genes by genetic algorithm method. Thereby, supports’ optimized location is developed by -3dimentional action among components.
Volume 5, Issue 3 (12-2015)
Abstract
In recent existing environment one of the major challenges that planners and managers are grappling with is customer recognition, and distinguishing between different groups of customers in the field of banking services. It is obvious that using an appropriate model gives the bank the opportunity to fit valuable suggestions along with demands for targeted sectors and provides design and thus improves bank performance from different perspectives. The aim of this study is using and appropriate model for clustering customers based on indexes including novelty, number of transaction and financial factors. In this paper, for clustering data, the genetic algorithm combining with fuzzy C-means is used to overcome problems such as being sensitive to the initial value and getting trapped in the local optimum. The simple random sampling method is used to obtain the sample. The findings show that the first cluster of customers due to its high performance in "novelty", "number of transaction" and "financial factors" index are loyal customers and the second cluster of customers because of low performance in "novelty" index, mean performance in "number of transaction" index and high performance in "financial factors" are among those customers who are turning away from bank.
Volume 6, Issue 1 (12-2006)
Abstract
Voltage stability may be improved by various control functions. In this paper, it is shown that how High Side Voltage Control (HIVC) may be employed for this purpose. Two test systems, namely a 22- bus and IEEE U8-bus systems are used to demonstrate the proposed tuning strategy for HSVC control parameters.
Volume 6, Issue 1 (12-2006)
Abstract
This paper presents a framework for long term transmission expansion planning in competitive, electricity markets. Transmission lines and phase shifters are taken into account as expansion options.
Maximization of the network users' benefits, with satisfying security constraints are considered as the criterion for transmission expansion planning. The elements of the objective function are the benefits of each network. The proposed model is as a non-linear mixed-integer programming (NLMIP) optimization problem. A GA (Genetic Algorithm) based method and quadratic programming (QP) approach is used to solve the problem. The discrete decision-making variables of the expansion plan are optimized by genetic algorithm, while QP optimizes the continuous variables.
Volume 7, Issue 0 (0-2007)
Abstract
This paper investigates the islands formation in initial stages of restoration process in blackout condition and studies the impacts of islands number variation on the process execution. In addition, a method is proposed to determining each island optimal boundaries. Then the effects of transmission lines Thyistor Controlled Series Compensators (TCSC) to facilitate restoration process and improvement of optimal solutions are studied. Energy Not supplied (ENS) index minimization is the objective function and the optimization method is Genetic Algorithm. The test network modeling has been done using a special appropriate chromosome coding. Various operational constraints such as voltage margins in buses, transmission lines capacities and generators loading limits have been considered in optimization process and final solution evaluation. The IEEE-118 bus network has been used as test system to assess the capabilities of the proposed method. Some obtained results have been given in the case study section.
.
Volume 7, Issue 0 (0-2007)
Abstract
In some mobile systems, intelligent antennas are used to increase efficiency in a wide frequency band and different environmental and electromagnetic conditions. Environmental factors, such as position of nearby objects, antenna mobility and even user type, can vary the antenna input impedance appreciably. Therefore, it is necessary to incorporate an adaptive impedance matching circuit between the antenna array elements and the transceiver to maximize the antenna radiation power.
In this research note, the design of adaptive matching circuit for intelligent quadrifilar helical antenna in the UHF band (for GSM) is presented. The GA algorithm is used to optimize the results. The designed circuit can decrease the VSWR from 20 to less than 2 at any frequency within the GSM bandwidth.
Volume 7, Issue 4 (1-2008)
Abstract
The focus of this paper is on standard Markowitz mean–variance model and its traditional approach to solve portfolio selection problem (Quadratic Planning). For this goal we have applied a meta-heuristic method based on genetic algorithms (GA) in order to trace out the efficient frontier associated with the portfolio selection problem under cardinality and bounding constraints. These constraints ensure the investment in a given number of different assets and limit the amount of capital to be invested in each asset. We have presented some experimental results in two samples from Iranian stock market and overseas ones and compare the GA result with unconstrained quadratic results. Finally, we have found out which proposed GA can optimize portfolio selection problem under cardinality and bounded constrains
Volume 8, Issue 1 (0-2008)
Abstract
In this paper, power system restoration in the presence of SVC and TCSC in partial outage conditions is considered and a new method for maximum load restoration using different control variables is presented. Control variables are tap of transformers, generation rescheduling and operating points of FACTS devices. Objective function is restored load (to be maximized) and constraints are voltage magnitudes in buses, carrying load in lines and power generation limits in generators. Also SPA limits in voltage angles in both sides of circuit breakers before closing are considered. With respect to the number of control variables, optimization is done using Genetic Algorithm with IEEE-118bus network as the test system.
Volume 8, Issue 3 (10-2020)
Abstract
Aims: Due to the terrible effects of 2019 novel coronavirus (COVID-19) on health systems and the global economy, the necessity to study future trends of the virus outbreaks around the world is seriously felt. Since geographical mobility is a risk factor of the disease, it has spread to most of the countries recently. It, therefore, necessitates to design a decision support model to 1) identify the spread pattern of coronavirus and, 2) provide reliable information for the detection of future trends of the virus outbreaks.
Materials & Methods: The present study adopts a computational intelligence approach to detect the possible trends in the spread of 2019-nCoV in China for a one-month period. Then, a validated model for detecting future trends in the spread of the virus in France is proposed. It uses ANN (Artificial Neural Network) and a combination of ANN and GA (Genetic Algorithm), PSO (Particle Swarm Optimization), and ICA (Imperialist Competitive Algorithm) as predictive models.
Findings: The models work on the basis of data released from the past and the present days from WHO (World Health Organization). By comparing four proposed models, ANN and GA-ANN achieve a high degree of accuracy in terms of performance indicators.
Conclusion: The models proposed in the present study can be used as decision support tools for managing and controlling of 2019-nCoV outbreaks.
Volume 9, Issue 1 (1-2009)
Abstract
Transmission expansion planning (TEP) is one of the most important parts in power systems. Restructuring of power system has changed the traditional planning objectives and introduced new challenges in the field of TEP. In this new environment, the comprehensive and precise design based on electricity market criteria in planning horizon is indispensable. In this paper a new algorithm is proposed for dynamic transmission expansion planning in deregulated environment. In this method, investment cost and operation cost are considered as market based economic criteria, and average load curtailment cost in contingencies is considered as a reliability criterion from market players' viewpoint. Congestion cost is also used as a competition index between market participants. The combination of Genetic Algorithm (GA) and fuzzy satisfying method is used for solving TEP problem. At last the proposed method has been tested on 8-bus network and IEEE 30-bus network.
Volume 9, Issue 1 (10-2019)
Abstract
Customers’ purchase behavior is one of the main criteria and critical success factors of e-commerce and online businesses which is similar to traditional businesses with some differences. Therefore, this study tries to reach a model for analyzing the online re-purchasing intention in B2C transactions. This research has been done in the framework of interpretive philosophical paradigm, with inductive approach, in qualitative method and the theme analysis technique using interviewing tools. Accordingly, an interview was conducted with 36 people including 6 e-commerce experts, 13 brokers in Internet business and 17 re-purchasing customers. After coding the interviews, 120 codes were reached at the first stage and final codes had been retrieved which were classified in 21 basic themes. After final analysis, the basis themes were divided into four organizing theme: psychological theme, technological theme, institutional and customer-orientation theme. Among these four themes, the concept of technology in e-commerce has the greatest emphasis. Organizational issues, customer-orientation and psychological issues are at the next rankings, which can also be considered as important which can be considered by as e-commerce managers.
Volume 10, Issue 1 (6-2010)
Abstract
Abstracts
This paper presents how the genetic algorithm (GA) can be applied to design of cascade stilling basins. Genetic
Algorithm is adaptive method, which can be used to solve search and optimization problems over a period of
generations, based upon the principles of natural selection and survival of the fittest ones. The objective of this
research is to minimize total cost of construction effectively which is a function of height of falls and length of
stilling basins, while fulfilling the hydraulic and topographical criteria. The efficiency of GA discussed here has
been tested for a benchmark example and the result for this algorithm is compared with the other method
introduced by Vittal and Porey. The results clearly reveal superiority of the GA algorithm
Volume 10, Issue 1 (7-2020)
Abstract
As the importance of supply chain management becomes more evident to the industry owners, the role of cooperation and integration of supply chain different components has become more vivid in creating competitive advantage. This paper proposes a comprehensive mathematical model for location-inventory-routing problem of perishable products given shortage, shipping time, and environmental considerations under uncertainty. To this purpose, an accurate solution was proposed by formulating the problem as non-linear programming of mixed integer using scenario-based stochastic approach. This approach simultaneously minimizes the sum of system costs (the cost of locating centers with certain level of capacity, operational cost of centers, transportation costs, maintaining inventory, and/or shortage of combined center of production/inspection), the sum of maximum time in the chain and emission of pollutants in the whole network. As the problem is NP-hard, a genetic algorithm approach has been proposed to solve the model. For validation, the results of the proposed algorithm in the small size examples were compared to the results of precise solution method. The obtained results revealed the capability of the proposed algorithm in reaching a solution with acceptable percentage difference and in a very shorter time compared to precise solution method. Additionally, the results from algorithm performance were investigated based on standard indicators. The computational results show the efficiency of the proposed model and solution method.
Mahmood Karimi, , ,
Volume 10, Issue 4 (12-2010)
Abstract
Abstract - In this paper, an optimal trajectory planning method is presented for robot manipulators with multiple degrees of freedom in 3D space using a new analytical technique for collision avoidance in the presence of ellipsoidal obstacles. To generate the robot’s trajectory, a genetic algorithm with a fuzzy mutation rate is introduced to have a quick access to optimal solutions in a complex workspace. A cubic spline interpolation polynomial is applied to approximate trajectories in the joint space. In order to optimize the objective function, the genetic algorithm determines a number of interior points for curve fitting using interpolation polynomials. The performance of the proposed technique is demonstrated by simulations.
Mohammad Taghi Vakil Baghmisheh, , ,
Volume 10, Issue 4 (12-2010)
Abstract
Vehicles are subject to random road excitations due to road unevenness and variable velocity which causes ride discomfort and fatigue. Ride comfort could be improved by decreasing vehicle accelerations. In this paper, to evaluate the vehicle ride comfort, root mean square acceleration response (RMSAR) is calculated using power spectral density (PSD) of road excitations and these quantities are compared with the ISO2631 boundary values. Then by considering ISO2631, the vehicle’s RMSAR is minimized by optimal design of vehicle suspension viscous damping and stiffness parameters. To solve this nonlinear constrained optimization problem, we utilize genetic algorithms. Also, in the design process the physical restrictions are included. Obtained results demonstrate a considerable improvement of vehicle ride comfort and its dynamic response as a result of reduced accelerations. Comparing the obtained results with those obtained by method of nonlinear programming confirms the supremacy of genetic algorithms.
Volume 11, Issue 1 (6-2021)
Abstract
Increasing greenhouse gas emissions and global warming and government support for renewable sources, as well as recent advances in electricity generation and related technologies, have led to the penetration of renewable energy products in the electricity supply chain. The infiltration of these resources, despite the uncertainty in their output power, has faced serious challenges in power supply chain planning. In this research, an effective and efficient method for security and probabilistic planning of power supply chain development is presented, taking into account the uncertainty of renewable energy production and the uncertainty of peak consumption. In the proposed method, a high limit for the allowable load cut is considered and the effect of existing uncertainties and changes in the high load cut limit on the investment cost of the supply chain is evaluated. The proposed method is implemented on the network by MATLAB software and solved by genetic algorithm. The final model of this method can be used effectively to plan the supply chain of the electricity network with the influence of renewable energy products.
Volume 11, Issue 2 (7-2011)
Abstract
In this paper torque ripple in switched reluctance motor is studied. The presented method in this paper for minimization of torque ripple is based on suitable machine structure obtained from the genetic algorithm (GA) and suitable machine driver. In the presented paper, the parameters of one machine are chosen as the reference machine parameters. Then some parameters of machine are chosen, which have no effects on the characteristics of mechanical, power and volume of reference machine. The desirable machine is simulated by finite element software, and then the torque characteristics are obtained for different machine structure with various machine parameters. Finally, with GA the best parameters for the design of machine with minimum torque ripple are chosen. So this paper presented for the first time an accurate method by finite element method in the process of machine design by GA. The finite element method used in the previously studies in the design of machine only for machine analysis, but in this paper finite element method is used in the process of machine design. So this method of machine design can be replaced to a conventional method. In this paper, the design of SRM driver is presented based on the best machine structure which is chosen from GA. So, the profile of machine torque for this structure has minimum deviation from the ideal torque without the ripple
Volume 11, Issue 20 (12-2007)
Abstract
This article while describing the problem and methodology of research and also reviewing briefely its theoretical basis, explains the proposed MISSQM1 moldel based on Genetic Algorithm and its major characteristics. These characteristeristics are:
1) Assurace of choice possivitity and near to optimum prioritizing of the quality measurement indexes of information systems services,
2) Providing the cooperation possibility of experts and professors in the process of defining the indexes,
3) Helping menagers to take the best or near the best decision about investing in the development of the quality of information systems services, proved by the use of analytical hierarchy process and genetic algorithm.
The scientific use of the present research in the development of theoreticel basis of information systems is discussed and some suggestions are given for future researches.
Volume 12, Issue 1 (1-2010)
Abstract
The forecasting of hydrological variables, such as streamflow, plays an important role in water resource planning and management. Recently, the development of stochastic models is regarded as a major step for this purpose. Streamflow forecasting using the ARIMA model can be conducted when unknown parameters are estimated correctly because parameter estimation is one of the crucial steps in modeling process. The main objective of this research is to explore the performance of parameter estimation methods in the ARIMA model. In this study, four parameter estimation methods have been used: (i) autocorrelation function based on model parameters; (ii) conditional likelihood; (iii) unconditional likelihood; and (iv) genetic algorithm. Streamflow data of Ouromieh River basin situated in Northwest Iran has been selected as a case study for this research. The results of these four parameter estimation methods have been compared using RMSE, RME, SE, MAE and minimizing the sum squares of error. This research indicates that the genetic algorithm and unconditional likelihood methods are, respectively, more appropriate in comparison with other methods but, due to the complexity of the model, genetic algorithm has high convergence to a global optimum.
Mostafa Ranjbar, Steffen Marburg,
Volume 12, Issue 2 (6-2012)
Abstract
This paper introduces a new approach for the reduction of sound radiation from the mechanical structures. A combination of genetic algorithm method and geometry modification concept minimizes the root mean square level of structure borne sound for a square plate over a specific frequency range. The structure’s local geometry modification values at the selected surface key-points considered as design variables. The model is under three non-symmetric harmonic excitations. An iterative approach is used to develop new modified model until when a termination criterium is rached. The results show that this approach could produce significant reduction in the value of radiated sound power level of the structure.