Search results
1 – 10 of over 13000Tugrul Oktay, Seda Arik, Ilke Turkmen, Metin Uzun and Harun Celik
The aim of this paper is to redesign of morphing unmanned aerial vehicle (UAV) using neural network for simultaneous improvement of roll stability coefficient and maximum…
Abstract
Purpose
The aim of this paper is to redesign of morphing unmanned aerial vehicle (UAV) using neural network for simultaneous improvement of roll stability coefficient and maximum lift/drag ratio.
Design/methodology/approach
Redesign of a morphing our UAV manufactured in Faculty of Aeronautics and Astronautics, Erciyes University is performed with using artificial intelligence techniques. For this purpose, an objective function based on artificial neural network (ANN) is obtained to get optimum values of roll stability coefficient (Clβ) and maximum lift/drag ratio (Emax). The aim here is to save time and obtain satisfactory errors in the optimization process in which the ANN trained with the selected data is used as the objective function. First, dihedral angle (φ) and taper ratio (λ) are selected as input parameters, C*lβ and Emax are selected as output parameters for ANN. Then, ANN is trained with selected input and output data sets. Training of the ANN is possible by adjusting ANN weights. Here, ANN weights are adjusted with artificial bee colony (ABC) algorithm. After adjusting process, the objective function based on ANN is optimized with ABC algorithm to get better Clβ and Emax, i.e. the ABC algorithm is used for two different purposes.
Findings
By using artificial intelligence methods for redesigning of morphing UAV, the objective function consisting of C*lβ and Emax is maximized.
Research limitations/implications
It takes quite a long time for Emax data to be obtained realistically by using the computational fluid dynamics approach.
Practical implications
Neural network incorporation with the optimization method idea is beneficial for improving Clβ and Emax. By using this approach, low cost, time saving and practicality in applications are achieved.
Social implications
This method based on artificial intelligence methods can be useful for better aircraft design and production.
Originality/value
It is creating a novel method in order to redesign of morphing UAV and improving UAV performance.
Details
Keywords
The purpose of this paper is to present a degenerated simplex search method to optimize neural network error function. By repeatedly reflecting and expanding a simplex, the…
Abstract
Purpose
The purpose of this paper is to present a degenerated simplex search method to optimize neural network error function. By repeatedly reflecting and expanding a simplex, the centroid property of the simplex changes the location of the simplex vertices. The proposed algorithm selects the location of the centroid of a simplex as the possible minimum point of an artificial neural network (ANN) error function. The algorithm continually changes the shape of the simplex to move multiple directions in error function space. Each movement of the simplex in search space generates local minimum. Simulating the simplex geometry, the algorithm generates random vertices to train ANN error function. It is easy to solve problems in lower dimension. The algorithm is reliable and locates minimum function value at the early stage of training. It is appropriate for classification, forecasting and optimization problems.
Design/methodology/approach
Adding more neurons in ANN structure, the terrain of the error function becomes complex and the Hessian matrix of the error function tends to be positive semi‐definite. As a result, derivative based training method faces convergence difficulty. If the error function contains several local minimum or if the error surface is almost flat, then the algorithm faces convergence difficulty. The proposed algorithm is an alternate method in such case. This paper presents a non‐degenerate simplex training algorithm. It improves convergence by maintaining irregular shape of the simplex geometry during degenerated stage. A randomized simplex geometry is introduced to maintain irregular contour of a degenerated simplex during training.
Findings
Simulation results show that the new search is efficient and improves the function convergence. Classification and statistical time series problems in higher dimensions are solved. Experimental results show that the new algorithm (degenerated simplex algorithm, DSA) works better than the random simplex algorithm (RSM) and back propagation training method (BPM). Experimental results confirm algorithm's robust performance.
Research limitations/implications
The algorithm is expected to face convergence complexity for optimization problems in higher dimensions. Good quality suboptimal solution is available at the early stage of training and the locally optimized function value is not far off the global optimal solution, determined by the algorithm.
Practical implications
Traditional simplex faces convergence difficulty to train ANN error function since during training simplex can't maintain irregular shape to avoid degeneracy. Simplex size becomes extremely small. Hence convergence difficulty is common. Steps are taken to redefine simplex so that the algorithm avoids the local minimum. The proposed ANN training method is derivative free. There is no demand for first order or second order derivative information hence making it simple to train ANN error function.
Originality/value
The algorithm optimizes ANN error function, when the Hessian matrix of error function is ill conditioned. Since no derivative information is necessary, the algorithm is appealing for instances where it is hard to find derivative information. It is robust and is considered a benchmark algorithm for unknown optimization problems.
Details
Keywords
Houlai Lin, Liang Li, Kaiqi Meng, Chunli Li, Liang Xu, Zhiliang Liu and Shibao Lu
This paper aims to develop an effective framework which combines Bayesian optimized convolutional neural networks (BOCNN) with Monte Carlo simulation for slope reliability…
Abstract
Purpose
This paper aims to develop an effective framework which combines Bayesian optimized convolutional neural networks (BOCNN) with Monte Carlo simulation for slope reliability analysis.
Design/methodology/approach
The Bayesian optimization technique is firstly used to find the optimal structure of CNN based on the empirical CNN model established in a trial and error manner. The proposed methodology is illustrated through a two-layered soil slope and a cohesive slope with spatially variable soils at different scales of fluctuation.
Findings
The size of training data suite, T, has a significant influence on the performance of trained CNN. In general, a trained CNN with larger T tends to have higher coefficient of determination (R2) and smaller root mean square error (RMSE). The artificial neural networks (ANN) and response surface method (RSM) can provide comparable results to CNN models for the slope reliability where only two random variables are involved whereas a significant discrepancy between the slope failure probability (Pf) by RSM and that predicted by CNN has been observed for slope with spatially variable soils. The RSM cannot fully capture the complicated relationship between the factor of safety (FS) and spatially variable soils in an effective and efficient manner. The trained CNN at a smaller the scale of fluctuation (λ) exhibits a fairly good performance in predicting the Pf for spatially variable soils at higher λ with a maximum percentage error not more than 10%. The BOCNN has a larger R2 and a smaller RMSE than empirical CNN and it can provide results fairly equivalent to a direct Monte Carlo Simulation and therefore serves a promising tool for slope reliability analysis within spatially variable soils.
Practical implications
A geotechnical engineer could use the proposed method to perform slope reliability analysis.
Originality/value
Slope reliability can be efficiently and accurately analyzed by the proposed framework.
Details
Keywords
This paper aims to examine regime switching behaviour of the nominal exchange rate in Uganda to shed light on the necessity (as well as efficacy) of the participation of the…
Abstract
Purpose
This paper aims to examine regime switching behaviour of the nominal exchange rate in Uganda to shed light on the necessity (as well as efficacy) of the participation of the central bank market.
Design/methodology/approach
The homogenous two‐state Markov chain methodology was employed to investigate the possibility of regime changes in the nominal exchange rate. The maximum likelihood parameter estimates were obtained using the Broyden‐Fletcher‐Goldfarb‐Shanno iteration algorithm.
Findings
The results validate the expectation of the two distinct state spaces characterized as sharp and disruptive but short‐lived depreciations as well as small appreciations occurring through a long period. The central bank intervention actions are shown to be largely successful in mitigating the disruptive effects of the sharp depreciations.
Practical implications
The paper lends empirical support to the intervention actions of the Bank of Uganda. In face of the numerous disruptions to the short‐term exchange rate process, failure to intervene may cause rational panic and given the nature of investor behavior, this may quickly spread and even cause further disruptions. It is important for the central bank to send signals that these disruptions are temporary.
Originality/value
The homogenous Markov chain specification employed in this study makes it possible to avoid the pitfalls that may arise by attempting to specify a structural model for the exchange rate. In addition, inference about the different possible state spaces is made on the basis of all available information.
Details
Keywords
The purpose of this paper is to address the issue of optimal management of ecosystems by developing a dynamic model of strategic behavior by users/communities of an ecosystem such…
Abstract
Purpose
The purpose of this paper is to address the issue of optimal management of ecosystems by developing a dynamic model of strategic behavior by users/communities of an ecosystem such as a lake, which is subject to pollution resulting from the users. More specifically, it builds a model of two ecosystems that are spatially connected.
Design/methodology/approach
The paper uses the techniques of optimal control theory and game theory.
Findings
The paper uncovers sufficient conditions under which the analysis of the dynamic game can be converted to an optimal problem for a pseudo authority. It is shown that if the discount rate on the future is high enough relative to ecological self‐restoration parameters then multiple stable states appear. In this case, if the pollution level is high enough it is too costly in terms of what must be given up today to restore the damaged system. By using computational methods, the paper evaluates the relative strengths of lack of coordination, strength of ecosystem self‐cleaning forces, size of discount rates, etc.
Originality/value
The methodology as well as findings can help to devise an optimal management strategy over time for ecosystems.
Details
Keywords
Henry Egbezien Inegbedion, Emmanuel Edo Inegbedion, Eseosa David Obadiaru, Abiola John Asaleye, Adebanji Ayeni and Charity Aremu
The study examined policy improvement and cassava attractiveness. The purpose was to determine the optimum rewards using three strategies: selling of farm produce to harvesters…
Abstract
Purpose
The study examined policy improvement and cassava attractiveness. The purpose was to determine the optimum rewards using three strategies: selling of farm produce to harvesters, making wholesale of harvested outputs and retailing harvested outputs.
Design/methodology/approach
Three hundred and sixty (360) cassava farmers were surveyed in three local government areas in Edo South senatorial district of Nigeria. From their responses, probabilities were assigned to rewards for each strategy from each of the locations. Subsequently, dynamic programming was employed in data analysis. Specifically, Howard policy improvement technique was used to forecast expected rewards to cassava farmers in the three local government areas using the three strategies.
Findings
Cassava farmers in Edo South senatorial district of Edo state, Nigeria, can maximize their earnings from cassava by retailing at the local markets in Oredo and Egor local government areas and by making wholesales at Ikpoba Okha local government area. Using this policy, they will realize approximately N2360 per basin and approximately N33040 per plot of 100 × 100 ft. This will translate to N143724 per acre (4.35 plots of 100 ft2).
Research limitations/implications
Availability of storage facilities as well as technical constraints to cassava production.
Social implications
Provision of jobs to the unemployed, thereby reducing the level of unemployment in the country.
Originality/value
Suggestion of the sales strategy that will yield optimum returns to cassava farmers, using policy iteration technique, and the projected estimates of the likely turnover when the strategy is adopted. This is a point of departure from previous studies. Thus, the study used operations research methodology to model solutions, through involvement in agriculture, to Nigeria's economic/financial problems, thus making it unique. In broad terms the study demonstrates that investment in agriculture will help to reduce unemployment and enhance the country's national income.
Details
Keywords
Himanshukumar R. Patel and Vipul A. Shah
The two-tank level control system is one of the real-world's second-order system (SOS) widely used as the process control in industries. It is normally operated under the…
Abstract
Purpose
The two-tank level control system is one of the real-world's second-order system (SOS) widely used as the process control in industries. It is normally operated under the Proportional integral and derivative (PID) feedback control loop. The conventional PID controller performance degrades significantly in the existence of modeling uncertainty, faults and process disturbances. To overcome these limitations, the paper suggests an interval type-2 fuzzy logic based Tilt-Integral-Derivative Controller (IT2TID) which is modified structure of PID controller.
Design/methodology/approach
In this paper, an optimization IT2TID controller design for the conical, noninteracting level control system is presented. Regarding to modern optimization context, the flower pollination algorithm (FPA), among the most coherent population-based metaheuristic optimization techniques is applied to search for the appropriate IT2FTID's and IT2FPID's parameters. The proposed FPA-based IT2FTID/IT2FPID design framework is considered as the constrained optimization problem. System responses obtained by the IT2FTID controller designed by the FPA will be differentiated with those acquired by the IT2FPID controller also designed by the FPA.
Findings
As the results, it was found that the IT2FTID can provide the very satisfactory tracking and regulating responses of the conical two-tank noninteracting level control system superior as compared to IT2FPID significantly under the actuator and system component faults. Additionally, statistical Z-test carried out for both the controllers and an effectiveness of the proposed IT2FTID controller is proven as compared to IT2FPID and existing passive fault tolerant controller in recent literature.
Originality/value
Application of new metaheuristic algorithm to optimize interval type-2 fractional order TID controller for nonlinear level control system with two type of faults. Also, proposed method will compare with other method and statistical analysis will be presented.
Details
Keywords
– The purpose of this paper is to investigate the phenomena of convergence and stability of leverage reported by Lemmon et al. (2008).
Abstract
Purpose
The purpose of this paper is to investigate the phenomena of convergence and stability of leverage reported by Lemmon et al. (2008).
Design/methodology/approach
A dynamic trade-off model of the firm was used to simulate investment, leverage, and payout decisions for different types of firms. From an econometric standpoint, the Efficient Method of Moments was used to recover the structural parameters.
Findings
The structural model generates a leverage ratio that oscillates around a long-run, time-invariant level and consistently reproduces the convergence and stability of leverage reported by Lemmon et al. (2008). The model also suggests the causes of those observed properties of the data. That is, convergence is due to the mean-reversion of profits while stability is due to the different fundamental characteristics (e.g. capital elasticity, volatility of profits, etc.) of the firm.
Practical implications
Determining the optimal capital structure of a firm is a complex problem that has challenged academics and practitioners for a long time. Understanding leverage decisions is of great importance not only for financial managers, but also for investors, such as banks, debt-holders, equity-holders, and other capital providers, who need to understand how firms make capital structure decisions in order to achieve an efficient allocation of funds.
Originality/value
The author shows that the firm-specific fixed effects in leverage regressions are not related to the usual determinants (e.g. profitability, market-to-book ratio), but to the primitive characteristics of the firm (e.g. elasticity of capital in the production function, the volatility of profits, the capital depreciation rate, the income tax rate, etc.)
Details
Keywords
The purpose of this paper is to infer the welfare of heterogeneous agents using a representative agent model.
Abstract
Purpose
The purpose of this paper is to infer the welfare of heterogeneous agents using a representative agent model.
Design/methodology/approach
It does so by partitioning the household into subunits and allocating consumption to each subunit proportionally to the income the subunit generates through wages and capital returns.
Findings
The author shows that for a simple dynamic general equilibrium model with immigration, the steady state utilities of these subunits correspond very closely to the utilities for an equivalent heterogeneous agent model. This is particularly true when labor–leisure decisions are made using slightly modified Euler equations.
Originality/value
More complicated models can be solved and simulated using fewer computational resources using this technique.
Details
Keywords
Danilo Ferreira de Carvalho and Carmelo José Albanez Bastos‐Filho
Particle swarm optimization (PSO) has been used to solve many different types of optimization problems. In spite of this, the original version of PSO is not capable to find…
Abstract
Purpose
Particle swarm optimization (PSO) has been used to solve many different types of optimization problems. In spite of this, the original version of PSO is not capable to find reasonable solutions for some types of problems. Therefore, novel approaches to deal with more sophisticated problems are required. Many variations of the basic PSO form have been explored, targeting the velocity update equation. Other approaches attempt to change the communication topology inside the swarm. The purpose of this paper is to propose a topology based on the concept of clans.
Design/methodology/approach
First of all, this paper presents a detailed description of its proposal. After that, it shows a graphical convergence analysis for the Rosenbrock benchmark function. In the sequence, a convergence analysis for clan PSO with different parameters is performed. A comparison with star, ring, focal, von Neumann and four clusters topologies is also performed.
Findings
The paper's simulation results have shown that the proposal obtained better results than the other topologies for the benchmark functions selected for this paper.
Originality/value
The proposed topology for PSO based on clans provides a novel form for information distribution inside the swarm. In this approach, the topology is determined dynamically during the search process, according to the success rate inside each clan.
Details