Artificial Bee Colony Optimization Method Research Articles

Ensembled CNN with artificial bee colony optimization method for esophageal cancer stage classification using SVM classifier.

Esophageal cancer (EC) is aggressive cancer with a high fatality rate and a rapid rise of the incidence globally. However, early diagnosis of EC remains a challenging task for clinicians. To help address and overcome this challenge, this study aims to develop and test a new computer-aided diagnosis (CAD) network that combines several machine learning models and optimization methods to detect EC and classify cancer stages. The study develops a new deep learning network for the classification of the various stages of EC and the premalignant stage, Barrett's Esophagus from endoscopic images. The proposed model uses a multi-convolution neural network (CNN) model combined with Xception, Mobilenetv2, GoogLeNet, and Darknet53 for feature extraction. The extracted features are blended and are then applied on to wrapper based Artificial Bee Colony (ABC) optimization technique to grade the most accurate and relevant attributes. A multi-class support vector machine (SVM) classifies the selected feature set into the various stages. A study dataset involving 523 Barrett's Esophagus images, 217 ESCC images and 288 EAC images is used to train the proposed network and test its classification performance. The proposed network combining Xception, mobilenetv2, GoogLeNet, and Darknet53 outperforms all the existing methods with an overall classification accuracy of 97.76% using a 3-fold cross-validation method. This study demonstrates that a new deep learning network that combines a multi-CNN model with ABC and a multi-SVM is more efficient than those with individual pre-trained networks for the EC analysis and stage classification.

Techno-economic analysis and optimization of hybrid energy systems based on hydrogen storage for sustainable energy utilization by a biological-inspired optimization algorithm

Wind energy resources based on hydrogen energy storage systems are recognized as clean alternative sources from the perspective of sustainable development. A low-cost hydrogen energy storage system is recognized as a cornerstone of a renewables-hydrogen economy. The hybridization of wind turbines, as a non-dispatchable resource, and hydrogen storage system, as energy storage, can provide a promising hybrid energy system. The main outlook of the present paper is to develop a biological-inspired optimization algorithm for the optimal design of an off-grid wind power generator considering a hydrogen energy storage system. The parameters of the system are optimized with respect to two objective functions, namely the total cost, and load loss of the system. To obtain an efficient optimum capability, an artificial bee colony optimization method is introduced. Its results are compared with the results of the particle swarm optimization algorithm. Eight different small horizontal-axis wind turbines are used for the optimal design of an off-grid system. A sensitivity analysis is conducted by varying the capital cost of the components to determine how total cost and load loss are affected by the change of the input variables. Simulation results show that at load loss = 0 and 20 %, the cost of energy (COE) is around 0.6907 and 0.3771 $/kWh, respectively. The variation of wind turbine (WT) and hydrogen storage system capital costs have a significant impact on total cost value. Among the investigated systems, the Fortis-WT- hydrogen storage system with 0.5987 $/kWh COE has the minimum cost and maximum reliability (100 %). The superiority of the proposed algorithm compared to the particle swarm optimization algorithm is confirmed.

DC-link voltage control of three-phase PWM rectifier by using artificial bee colony based type-2 fuzzy neural network

The pulse width modulation (PWM) rectifiers are nonlinear systems due to semiconductor switches in their structure. Therefore, these rectifiers draw a distorted current from AC supply. Many different improvements have been proposed to overcome problems caused by PWM rectifiers. In this paper, DC-link voltage of three-phase PWM rectifier is regulated by using a Type-2 Fuzzy Neural Network (T2FNN) controller that parameters are optimized by using Artificial Bee Colony (ABC) optimization method. The parameters in antecedent and consequent parts of T2FNN are optimized by ABC optimization method. The performance of ABC-T2FNN controller is analyzed under different operating conditions through simulation model based on MATLAB. The operating conditions are considered as constant input, set point, a step DC load change, unbalanced AC supply and regenerative mode. The simulation results obtained from the proposed controller are verified by comparing with the results of the classical T2FNN. When the results of PWM rectifiers are investigated, it is seen that PWM rectifier based on the proposed controller has better dynamic response for all operating conditions than conventional T2FNN controller.

Estimation of rigidity of concrete based on multi parameters using artificial bee colony optimization method with levy flight distribution

The rigidity of the materials used in the structures affects most deformation characteristics. Therefore, obtaining information about the rigidity of materials is essential for the behavior of the structures. In the study, 32 different equations were derived by usage of eight parameters in various combinations to estimate elastic modulus of concrete. These parameters are compressive strength, unit weight, water-cement ratio, consistency, cement amount, fine aggregate - course aggregate ratio and air content. Multidimensional nonlinear regression models were generated between equation models and test results. The optimization process is applied to solve regression models. An improved version of Artificial Bee Colony Optimization algorithm by adding levy flight distribution (ABC LF) is used as the optimization method. Estimated values are compared to test results to determine the goodness of the equations. The effectiveness of the parameters is investigated according to the comparison as well.

Discovering the Maximum Clique in Social Networks Using Artificial Bee Colony Optimization Method

Discovering the Maximum Clique in Social Networks Using Artificial Bee Colony Optimization Method

Adaptive Fuzzy Super – Twisting Sliding Mode Controller optimized by ABC for Vehicle Suspension System

In this paper, a second order Sliding Mode Controller (SMC), based on Super – Twisting algorithm, Fuzzy estimator and PID controller is presented for quarter vehicle active suspensions. Because of the chattering that appeared at the output of the system when using first order SMC, second order SMC is preferred. The proposed controller has been derived in order to achieve the convergence and the stability of the system that can improve the comfortable driving and vehicles safety against different road disturbances. The Artificial Bee Colony optimization method has been utilized to find the optimal values of the proposed controller parameters.The obtained results of the simulations have been verified the efficiency and the ability of the proposed control scheme to suppress the oscillations and give the stability of the suspension system in the presence of uncertainty and different road disturbances.

New Optimization Algorithms for Application to Environmental Economic Load Dispatch in Power Systems

DOI: 10.5152/iujeee.2018.1825 The determination of the most economical generation dispatch in an electrical power system has become a very important issue globally. However, economical dispatch can no longer be considered alone because of environmental problems that are derived from emissions such as nitrogen oxide, carbon dioxide, and sulfur dioxide. In this study, the problem of environmental economic load dispatch (EELD) in a power system of six generators is addressed both by neglecting and including line transmission losses using a modified genetic algorithm and a modified artificial bee colony optimization method. The results of these modified algorithms are compared with those of the unmodified versions. The results demonstrate that the proposed new methods have better economic and environmental distribution performances. Accordingly, it can be concluded that the new methods are more effective and should be adopted.

Power System Restoration Planning Strategy Based on Optimal Energizing Time of Sectionalizing Islands

Common power system restoration planning strategy is based on a ‘build up’ approach, where a blackout system is sectionalized among several islands for parallel restoration prior to resynchronization. In order to speed up the resynchronization of the islands, each island must have similar energizing times. However, there is a huge number of possible combinations of islands that can be formed. Thus, this paper proposes a method to determine optimal islands that have similar energizing times. The method involves identifying transmission lines that should not be connected to form the islands. The proposed method is based on the combination of heuristic and discrete optimization methods. The heuristic technique is proposed to find initial solution that is close to the optimal solution. This solution will guide the optimization technique, which is the discrete Artificial Bee Colony optimization method, to find the optimum solution. The proposed method also considers restoration constraints including black start generator availability, load-generation balance, and the maintenance of acceptable voltage magnitude within each island. The proposed method is validated via simulation using IEEE 39, 118-bus and 89-bus European systems. The advantage of the proposed method in terms of restoration time is demonstrated through a comparison with other literature.

Thermodynamic Optimization of a Geothermal- Based Organic Rankine Cycle System Using an Artificial Bee Colony Algorithm

Geothermal energy is a renewable form of energy, however due to misuse, processing and management issues, it is necessary to use the resource more efficiently. To increase energy efficiency, energy systems engineers carry out careful energy control studies and offer alternative solutions. With this aim, this study was conducted to improve the performance of a real operating air-cooled organic Rankine cycle binary geothermal power plant (GPP) and its components in the aspects of thermodynamic modeling, exergy analysis and optimization processes. In-depth information is obtained about the exergy (maximum work a system can make), exergy losses and destruction at the power plant and its components. Thus the performance of the power plant may be predicted with reasonable accuracy and better understanding is gained for the physical process to be used in improving the performance of the power plant. The results of the exergy analysis show that total exergy production rate and exergy efficiency of the GPP are 21 MW and 14.52%, respectively, after removing parasitic loads. The highest amount of exergy destruction occurs, respectively, in condenser 2, vaporizer HH2, condenser 1, pumps 1 and 2 as components requiring priority performance improvement. To maximize the system exergy efficiency, the artificial bee colony (ABC) is applied to the model that simulates the actual GPP. Under all the optimization conditions, the maximum exergy efficiency for the GPP and its components is obtained. Two of these conditions such as Case 4 related to the turbine and Case 12 related to the condenser have the best performance. As a result, the ABC optimization method provides better quality information than exergy analysis. Based on the guidance of this study, the performance of power plants based on geothermal energy and other energy resources may be improved.

A Model of Automatic Block Reallocation in the Land Consolidation Projects Using Artificial Bee Colony Algorithm

Equitably reallocating of blocks among land owners has been one of the most important tasks in Land Consolidation studies. This task has to be fairly solved among landholdings for a land. This complicated problem is difficult to solve using linear methods. Therefore, a method is needed to solve this non-linear problem among land owners impartially. There are many applications employing optimization algorithms for solving the complicated and non-linear problems in literature. When we examine the literature, it is seen that Genetic Algorithm has been only used to overcome the block reallocation problem. Artificial Bee Colony (ABC) algorithm is one of the optimization algorithms that have been used to solve the non-linear and complicated problems in literature. Furthermore, this method has better performance when it is compared with the other optimization algorithms. In this study, we have aimed to fairly reallocate the landholding areas to blocks in a land by developing an algorithm using Artificial Bee Colony optimization method. When we develop the steps of the algorithm, we give priority to landholdings preferences and places of fixed installations. Data tables have been arranged by taking land consolidation data of DOT Village in Adiyaman, Turkey that into consideration. DOT Village land consolidation project includes 143 blocks and 225 landholders. Consequently, we have introduced the steps of an algorithm solving the block reallocation problem automatically using ABC for a sample land. Also, we have observed the applicability of the proposed method for automatic block reallocation problem in this study. This study is a preliminary study helping us to develop software providing to automatically solve complicated block reallocation problem in real time land consolidation process.

A Kriging-based hybrid optimization algorithm for slope reliability analysis

Abstract First, the artificial bee colony (ABC) algorithm was used to optimize the Kriging model. A typical example was given to validate a good function fitting performance of the ABC-optimized Kriging model. Next, a structural reliability optimization method was proposed on the basis of the Kriging surrogate model, combined with the artificial bee colony optimization method and penalty function method. A nonlinear limit-state function example was provided to validate the accuracy and efficiency of the hybrid algorithm by comparing the algorithm’s solution with the exact solution of the example. Finally, the proposed method was applied to earth slope reliability analysis using a commercial finite difference program to calculate the slope’s factor of safety. Comparison of the results between the proposed method and the other methods shows that the proposed algorithm is the most suitable for slope reliability analysis.