Huseyin Ceylan

A new solution algorithm for improving performance of ant colony optimization

This study proposes an improved solution algorithm using ant colony optimization (ACO) for finding global optimum for any given test functions. The procedure of the ACO algorithms simulates the decision-making processes of ant colonies as they forage for food and is similar to other artificial intelligent techniques such as Tabu search, Simulated Annealing and Genetic Algorithms. ACO algorithms can be used as a tool for optimizing continuous and discrete mathematical functions. The proposed algorithm is based on each ant searches only around the best solution of the previous iteration with @b. The proposed algorithm is called as ACORSES, an abbreviation of ACO Reduced SEarch Space. @b is proposed for improving ACOs solution performance to reach global optimum fairly quickly. The ACORSES is tested on fourteen mathematical test functions taken from literature and encouraging results were obtained. The performance of ACORSES is compared with other optimization methods. The results showed that the ACORSES performs better than other optimization algorithms, available in literature in terms of minimum values of objective functions and number of iterations.

Hybridizing the harmony search algorithm with a spreadsheet ‘Solver’ for solving continuous engineering optimization problems

In this article, a hybrid global–local optimization algorithm is proposed to solve continuous engineering optimization problems. In the proposed algorithm, the harmony search (HS) algorithm is used as a global-search method and hybridized with a spreadsheet ‘Solver’ to improve the results of the HS algorithm. With this purpose, the hybrid HS–Solver algorithm has been proposed. In order to test the performance of the proposed hybrid HS–Solver algorithm, several unconstrained, constrained, and structural-engineering optimization problems have been solved and their results are compared with other deterministic and stochastic solution methods. Also, an empirical study has been carried out to test the performance of the proposed hybrid HS–Solver algorithm for different sets of HS solution parameters. Identified results showed that the hybrid HS–Solver algorithm requires fewer iterations and gives more effective results than other deterministic and stochastic solution algorithms.

Harmony Search Algorithm for Transport Energy Demand Modeling

The transport sector is one of the major consumers of energy production throughout the world. Thus, the estimation of medium and long-term energy consumption based on socio-economic and transport related indicators is a critical issue on a global scale. This chapter reviews the harmony search (HS) applications to transport energy modeling problems. The models reviewed in this chapter are in the form of linear, exponential and quadratic mathematical expressions, and they are applied to transportation sector energy consumption. Convergence behavior of the HS during the modeling is tested. Performance of each HS model is compared according to an absolute error between observed data and predicted data. Results showed the HS method can be applied to the transport energy modeling issues.

An Artificial Neural Networks Approach to Estimate Occupational Accident: A National Perspective for Turkey

Occupational accident estimation models were developed by using artificial neural networks (ANNs) for Turkey. Using these models the number of occupational accidents and death and permanent incapacity numbers resulting from occupational accidents were estimated for Turkey until the year of 2025 by the three different scenarios. In the development of the models, insured workers, workplace, occupational accident, death, and permanent incapacity values were used as model parameters with data between 1970 and 2012. 2-5-1 neural network architecture was selected as the best network architecture. Sigmoid was used in hidden layers and linear function was used at output layer. The feed forward back propagation algorithm was used to train the network. In order to obtain a useful model, the network was trained between 1970 and 1999 to estimate the values of 2000 to 2012. The result was compared with the real values and it was seen that it is applicable for this aim. The performances of all developed models were evaluated using mean absolute percent errors (MAPE), mean absolute errors (MAE), and root mean square errors (RMSE).

Optimal Design of Signal Controlled Road Networks Using Differential Evolution Optimization Algorithm

This study proposes a traffic congestion minimization model in which the traffic signal setting optimization is performed through a combined simulation-optimization model. In this model, the TRANSYT traffic simulation software is combined with Differential Evolution (DE) optimization algorithm, which is based on the natural selection paradigm. In this context, the EQuilibrium Network Design (EQND) problem is formulated as a bilevel programming problem in which the upper level is the minimization of the total network performance index. In the lower level, the traffic assignment problem, which represents the route choice behavior of the road users, is solved using the Path Flow Estimator (PFE) as a stochastic user equilibrium assessment. The solution of the bilevel EQND problem is carried out by the proposed Differential Evolution and TRANSYT with PFE, the so-called DETRANSPFE model, on a well-known signal controlled test network. Performance of the proposed model is compared to that of two previous works where the EQND problem has been solved by Genetic-Algorithms- (GAs-) and Harmony-Search- (HS-) based models. Results show that the DETRANSPFE model outperforms the GA- and HS-based models in terms of the network performance index and the computational time required.

Determining On-Street Parking Places in Urban Road Networks Using Meta-Heuristic Harmony Search Algorithm

This study aims to develop a simulation/optimization model for the solution to the problem of determining on-street parking places in urban road networks. The problem is dealt within the Discrete Network Design (DND) context due to the binary decision variables and the bi-level programming technique is used for the solution of the problem. The upper level represents the determination of on-street parking places while the reaction of drivers’ to the design is handled in user equilibrium manner in the lower level. The upper level problem is formulized as a non-linear mixed integer programming problem and the meta-heuristic Harmony Search (HS) optimization technique is employed for the solution. In the proposed model, VISUM traffic analysis software is utilized as the simulation tool for solving the lower level problem. The performance of the proposed model is tested on Sioux-Falls road network which has widely been used on DND studies in the previous works. Results show that determining optimal or near-optimal on-street parking places may be achieved by using the proposed model.

Estimating Transport Energy Demand Using Ant Colony Optimization

Abstract This study proposes a heuristic algorithm based on ant colony optimization for estimating the transport energy demand (TED) of Turkey using gross domestic product, population, and vehicle-km. Three forms of the improved ant colony optimization transport energy demand estimation (IACOTEDE) models are used for improving estimating capabilities of TED models. Performance of IACOTEDE is compared with the Ministry of Energy and Natural Resources (MENR) projections. Sensitivity analysis is also carried out for testing the effects of the parameters. The quadratic form provided a better-fit solution to the observed data, and it underestimates Turkeys TED by about 28% less than the MENR projection in year 2025. Thus, it may be used with a highest correlation coefficient and considerably lower relative error according as the MENR projection in the testing period. It is also expected that this study will be helpful in developing highly applicable and productive planning for transport energy policies.

Modeling and Forecasting Car Ownership Based on Socio-Economic and Demographic Indicators in Turkey

Since car ownership is an important determinant to analyze car travel behavior especially in developing countries, this paper deals with modeling and forecasting car ownership in Turkey based on socio-economic and demographic indicators such as Gross Domestic Product (GDP) per capita, Gasoline Price (GP), car price and number of employees by using multiple nonlinear regression analysis. Although most of the studies on this subject prefer using annual data, we use monthly data for the analysis of car ownership since all explanatory variables and exchange rates used for the modeling are unstable and vary even in a short period in developing countries such as Turkey. Thus, it may be possible to reflect the effects of socio-economic and demographic indicators on car ownership more properly. During the modeling process, exponential and polynomial nonlinear regression models are set up and then tested to investigate their applicability for car ownership forecasting. Based on results of the Kolmogorov-Smirnov test, the polynomial models has been selected to forecast car ownership for the year 2035. In order to reveal the possible different trends of the independent variables in future, car ownership is forecasted along the scenarios which are related to the GDP per capita and GP. Results show that Turkey’s car ownership may vary between 230 and 325 per thousand capita in 2035 depending on economic achievements, global oil prices and national taxation policies. The lowest and the highest values of the car ownership may provide insight to car producers and transport planners in Turkey. Another significant result presented in this study is that car ownership rate will be substantially lower in Turkey than that in the European Union countries despite it has an increasing trend in the past two decades.

Using accessibility measures in transit network design

Transit planning scenarios may lead to the different Objective Function (OF) values since each scenario has different transit travel times, frequencies and fleet sizes. Change on those variables leads to the different accessibility values for each route set. Therefore, the actual performance of a route set may be unforeseen since the accessibility values are out of evaluation criteria. This study tries to generate techniques, which handle the relation between accessibility and transportation in the scope of public transit. The accessibility measures, which have direct relation with land use and transportation, are utilized in transit route set decision. Accessibility measures have been utilized in the decision-making process of transit network design. Conventional OFs, which are used to determine the most effective route sets are combined with accessibility based OFs and the decision-making process of transit network design is strengthened. In this context, the effects of accessibility measures in decision-making process of transit network design have been represented on an 8-node example transit network. The results showed the accessibility measures could effectively improve the planners’ decision accuracy. First published online 12 April 2017

Relation Between Land Use and Transportation Planning in the Scope of Smart Growth Strategies: Case Study of Denizli, Turkey

In the decision-making process of planning residential areas in developing countries, importance of the commercial areas and need for a sustainable urban transportation infrastructure have generally been ignored based on several sociopolitical reasons. Meanwhile, decision-making periods of location choice and determining areal densities are conducted without quantitative spatial/technical analyses. Those urban matters bring along new planning paradigms like smart growth (SG) and new urbanism. SG is a land use planning paradigm which indicates that traffic problems should be minimized by transit alternatives, effective demand management and providing a balance between land use and transportation planning. This study aims to apply SG strategies to the land use planning process and evaluate the accuracy of land use planning decisions in the perspective of sustainable transportation. In order to reveal the effects of land use planning decisions on the available transportation infrastruc‐ ture, two scenarios are investigated for 2030. In the first scenario “do nothing” option is considered, while the residential area densities and trip generation rates are regulated based on SG strategies in the second scenario. The results showed that the land use and traffic impact analyses should simultaneously be conducted before land use configu‐ ration process.