Global optimization methods play an important role to solve many real-world problems. FLOWER POLLINATION ALGORITHM (FP) is a new nature-inspired ALGORITHM, based on the characteristics of FLOWERing plants. In this paper, a new hybrid optimization method called hybrid FLOWER POLLINATION ALGORITHM (FPPSO) is proposed. The method combines the standard FLOWER POLLINATION ALGORITHM (FP) with the particle swarm optimization (PSO) ALGORITHM to improve the searching accuracy. The FPPSO ALGORITHM is used to solve constrained optimization problems. Experimental results showed that the accuracy of finding the best solution and convergence speed performance of the proposed ALGORITHM is significantly better compared to those achieved by the existing ALGORITHMs.

In recent years, the use of renewable energy systems has grown significantly, among which photovoltaic systems have received much attention. Solar cells are known as the building blocks of a photovoltaic system. Because of the nonlinear nature of solar cells and the continuous changes in atmospheric conditions, maximum power point tracking (MPPT) is essential to extract the maximum power of a photovoltaic system. In this study, in order to achieve the maximum power, it was proposed to apply FLOWER POLLINATION ALGORITHM (FPA) combined with a comprehensive selection ALGORITHM, named as improved FPA. In addition, to evaluate the proposed ALGORITHM, its performance was compared with genetic ALGORITHM (GA) and standard FPA under rapid changes in atmospheric conditions. The calculated results showed that the improved FPA has a better accuracy than GA; moreover it has a higher convergence rate as compared with other applied ALGORITHMs.

In recent years, production of text documents has seen an exponential growth, which is the reason why their proper classification seems necessary for better access. One of the main problems of classifying text documents is working in high-dimensional feature space.Feature Selection (FS) is one of the ways to reduce the number of text attributes. So, working with a great bulk of the feature space without FS increases the computational cost which is a function of the length of the vector, and also, it helps to remove irrelevant attributes. The general approach in this paper combines the hybrid of FLOWER POLLINATION ALGORITHM (FPA) with Ada-Boost ALGORITHM. The FPA is used for FS and the Ada-Boost is used for classification of text documents. Tests were conducted on Reuters-21578, WEBKB and CADE 12 datasets. The results show that the hybrid model has higher detection accuracy in FS compared with Ada-Boost ALGORITHM with model. And comparisons are indicative of higher detection accuracy of the proposed model compared with KNN-K-Means, NB-K-Means and learning models.

The purpose of clustering is to identify natural categories in a large data set, which, by summarizing and simplifying, provides the possibility of analyzing a huge amount of data for other applications. So far, many ALGORITHMs have been presented to solve the clustering problem, but no single ALGORITHM performs well under different conditions and with different types of data. Each ALGORITHM has its advantages and disadvantages. Therefore, the subject of current research is the design of hybrid ALGORITHMs to exploit the advantages of two or more ALGORITHMs in a single ALGORITHM. The features of different ALGORITHMs are complementary. To achieve this goal, a hybrid meta-heuristic ALGORITHM based on FLOWER POLLINATION and Big Bang-Big Crunch ALGORITHMs is presented in this thesis. In the proposed ALGORITHM, the FLOWER POLLINATION ALGORITHM is used to search the problem space and find the optimal clusters, and the Big Bang-Big Crunch ALGORITHM is used to solve the local optimal problem and the early convergence of the FLOWER POLLINATION ALGORITHM. The results of the simulations show the high efficiency of the proposed hybrid ALGORITHM compared to non-hybrid ALGORITHMs.

Summary In this study, for inversion of surface wave dispersion curves, a new modified FLOWER POLLINATION ALGORITHM (MFPA) is introduced. The goal of the proposed ALGORITHM is to find the unknown parameters of the problem, i. e., the thicknesses and shear wave velocities of the soil layers. The performance of the ALGORITHM has been evaluated by synthetic models and also actual dataset. The results, in both of synthetic models and experimental data, represent the acceptable performance of the proposed ALGORITHM. The MFPA inversion method is a suitable technique for reducing the non-uniqueness of the surface wave inversion task. Introduction The inversion of the surface wave dispersion curves is one of the practical issues in identifying the subsurface layers and shear wave velocities structures. Shear wave velocity is one of the most important parameters in geotechnical studies that is used to evaluate soil properties, including site effects and seismic microzonation. Typically, surface waves are used to estimate the shear wave velocity. Linear inversion methods are not very reliable due to the nonlinear nature of the problem. With the development of computer sciences and the development of intelligent optimization methods, rapid and easy techniques for inversion of surface waves could be used. In this paper, a new modified FLOWER POLLINATION ALGORITHM (MFPA) for inversion of Rayleigh wave dispersion curves is introduced. In the proposed ALGORITHM in comparison to standard FLOWER POLLINATION ALGORITHM (FPA), the exploration ability of the ALGORITHM is improved. Methodology and Approaches In order to process surface waves and find an adequate shear wave velocity structure, a new hybrid metaheuristic ALGORITHM that adds a dynamic factor to mutation operator of the standard FPA, called MFPA, is applied. In this study, the mutation rate increases gradually from 𝑊 𝑚 𝑖 𝑛 (1/number of FLOWERs) to 𝑊 𝑚 𝑎 𝑥 (1/ number of subsurface layers) as the number of iterations is increased. The MFPA approach could accelerate the convergence speed in comparison to the standard FBA. The code of the MFPA inversion method has been written in MATLAB environment. Then, the proposed technique has been tested on a synthetic dataset. To more explore the reliability of the applied method, 10 percent noise has also been added to the synthetic dataset. The results of synthetic dataset show the capability of the MFPA technique in the absence and presence of noise. For further evaluation of the proposed method, the MFPA has been applied on an actual dataset for geotechnical assessment in an area in the city of Tabriz, northwest of Iran. The results of the experimental data indicate a three-layer model that is in a good agreement with the geological evidence of the study area. Results and Conclusions In this study, a new surface wave inversion ALGORITHM, i. e. MFPA is proposed. Then, capability of this technique is tested by synthetic and actual datasets. The results show that the applied method is a fast and powerful technique in the inversion of surface wave dispersion curves. Moreover, the performance of MFPA has been compared with standard FPA. Because of strong exploration ability of MFPA, this ALGORITHM in estimation of the model parameters has higher convergence and accuracy than FPA.

Surface quality is a technical prerequisite in the field of manufacturing industries and can be treated as a quality index for machined parts. Attainment of appropriate surface finish plays a key role during functional performance of machined part. It is typically influenced by the machining parameters. Consequently, enumerating the good relation between surface roughness (Ra) and machining parameters is a highly focused task. In the current work, response surface methodology (RSM) based regression models and FLOWER POLLINATION ALGORITHM (FPA) based sparse data model were developed to predict the minimum value of surface roughness in hard turning of AISI 4340 steel (35 HRC) using a single nanolayer of TiSiN-TiAlN PVD-coated cutting insert. The results obtained from this approach had good harmony with experimental results, as the standard deviation of the estimated values was simply 0.0804 (for whole) and 0.0289 (for below 1 µm Ra). When compared with RSM models, the proposed FPA based model showed the least percentage of mean absolute error. The model obtained the strongest correlation coefficient value of 99.75% among the other models values. The behavior of machining parameters and its interaction against surface roughness in the developed models were discussed with Pareto chart. It was observed that the feed rate was highly significant parameter in swaying machining surface roughness. In inference, the FPA sparse data model is a better choice over the RSM based regression models for prognosis of surface roughness in hard turning of AISI 4340 steel (35 HRC). The model developed using FPA based sparse data for surface roughness during hard turning operation in the current work is not reported to the best of author’s knowledge. This model disclosed a more dependable estimation over the multiple regression models.

Olive (Olea europaeaL.) is an evergreen plant which belongs to Oleaceae family. In an attempt to investigate the impact of POLLINATION and branch direction as well as the interaction effect of these two treatments on the quality and quantity of fruit in two varieties of yellow and Mary olive in the region of Fars, an experiment was carried out during 2005-2006. The experiment was conducted with three treatments of POLLINATION (i.e. self-POLLINATION, open POLLINATION, and wind POLLINATION without the interference of pollinating insects) in four replications following a randomized complete block design by means of net in four main geographical directions of yellow and Mary olive trees. The results indicated that in comparison to self-POLLINATION, open POLLINATION significantly increased the yield level at P<0.01 in the two cultivars. Self-POLLINATION resulted in an increase in the number of parthenogenetic and unnatural fruits which reduced the yield and quality of these fruits in comparison to the open treatment. The variance analysis of yields demonstrated genetic differences between cultivars as an indication of production power. The comparison of open POLLINATION treatment and wind POLLINATION without the interference of pollinating insects was not significant. The highest and the lowest percentages of full FLOWERing were respectively observed in the southern and northern directions. An increase in full FLOWERing in the southern part resulted in an increase in the amount of initial fruit. However, after the primary and secondary FLOWER loss, no significant difference was observed in the final fruit formation.

The complexity of engineering problems and the existence of various constraints on these issues, encourage the researchers to use of innovative methods based on a heuristic ALGORITHM to find the optimal solution for practical problems at a cost-effective time and non-consistency tolerance. A distinction has been made between various issues and, therefore, extensive research has been done to improve heuristic ALGORITHMs in order to enhance their ability to solve engineering and practical problems. In this paper, due to the ability to global search some of the metaheuristic search patterns (such as the EMA ALGORITHM) and the ability to local search for some meta-heuristic search patterns (such as the FPA ALGORITHM), a novel combination method is proposed to use the ability of both types of ALGORITHMs. Then, using the proposed method, a hybrid search pattern with new abilities is presented, whose abilities are proven on standard benchmark testing functions as well as solving engineering problems.