Hybrid Flower Pollination Algorithm Research Articles

Improved Artificial Neural Network Classification Model based Metaheuristic Optimization for Handwritten Character Recognition

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analysed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

An Efficient Fault Diagnosis Framework for Digital Twins Using Optimized Machine Learning Models in Smart Industrial Control Systems

In recent times, digital twins (DT) is becoming an emerging and key technology for smart industrial control systems and Industrial Internet of things (IIoT) applications. The DT presently supports a significant tool that can generate a huge dataset for fault prediction and diagnosis in a real-time scenario for critical industrial applications with the support of powerful artificial intelligence (AI). The physical assets of DT can produce system performance data that is close to reality, which delivers remarkable opportunities for machine fault diagnosis for effective measured fault conditions. Therefore, this study presents an intelligent and efficient AI-based fault diagnosis framework using new hybrid optimization and machine learning models for industrial DT systems, namely, the triplex pump model and transmission system. The proposed hybrid framework utilizes a combination of optimization techniques (OT) such as the flower pollination algorithm (FPA), particle swarm algorithm (PSO), Harris hawk optimization (HHO), Jaya algorithm (JA), gray wolf optimizer (GWO), and Salp swarm algorithm (SSA), and machine learning (ML) such as K-nearest neighbors (KNN), decision tree (CART), and random forest (RF). The proposed hybrid OT–ML framework is validated using two different simulated datasets which are generated from both the mechanized triplex pump and transmission system models, respectively. From the experimental results, the hybrid FPA–CART and FPA–RF models within the proposed framework give acceptable results in detecting the most relevant subset of features from the two employed datasets while maintaining fault detection accuracy rates exemplified by the original set of features with 96.8% and 85.7%, respectively. Therefore, the results achieve good and acceptable performance compared to the other existing models for fault diagnosis in real time based on critical IIoT fields.

Optimization of one-dimensional bin packing problem using a hybrid flower pollination algorithm

Optimization of one-dimensional bin packing problem using a hybrid flower pollination algorithm

Design and area optimization of CMOS operational amplifier circuit using hybrid flower pollination algorithm for IoT end-node devices

CMOS operational amplifiers are widely used in internet of things (IoT) systems due to their excellent performance at low input voltage. However, the design and optimization of high-performance operational amplifiers are time-consuming processes, even for experienced analog circuit designers. For circuit designer, it is also difficult to quickly evaluate the feasibility of a given specification in a technology node. This paper presents an optimal sizing of operational amplifiers based on the swarm intelligence method. A hybrid version of the Flower Pollination Algorithm (HFPA) was introduced to solve an analog circuit transistor sizing problem effectively and also efficiently reduce the design search space. The proposed method was employed to reduce the transistor size of an operational amplifier to fit for end-node IoT devices. The simulation results show that the HFPA algorithm improved circuit performance in respect of area, power dissipation, and gain compared with other two existing methods. In addition to simulation results, spice validation through cadence is also employed to validate the specifications of the proposed circuit. Therefore the proposed amplifier design is mostly suitable of IoT end-node devices.

Reactive Power and Voltage Optimization of New-Energy Grid Based on the Improved Flower Pollination Algorithm

In order to solve the reactive power and voltage control problem caused by the high proportion of new energy connected to the power grid, this paper takes the minimum voltage deviation, minimum network loss and maximum dynamic reactive power margin of the whole system as the comprehensive optimization objectives and establishes a reactive power and voltage optimization model by considering the reactive power regulation ability of SVC (Static Var Compensator) and new energy units. In view of the continuous and discrete variables in the model, the traditional continuous FPA (Flower Pollination Algorithm) is discretized to form an improved continuous-discrete hybrid FPA, and the tournament selection mechanism is adopted to speed up the convergence. Through the example analysis of the IEEE-39 bus system, the feasibility of the proposed reactive power and voltage optimal control method in the new energy grid is verified. Compared with GA (Genetic Algorithm), the results show that the improved FPA has high optimization accuracy, which is suitable for solving the reactive power and voltage optimization problem of the new energy grid.

An enhanced HFPA‐IHS‐ORP‐based optimization mechanism for efficient bandwidth allocation in software‐defined networks

SummaryNowadays, due to the increased amount of network users and resources, some emerging technologies like big data and cloud have been developed. But managing these types of networks is more complex; in order to solve this issue, a software‐defined network (SDN) is developed for managing the network in a comfortable manner, in which maintaining load balance and energy efficiency of network is highly important to satisfy the requirements of quality of service (QoS). For these reasons, various optimization‐based algorithms are developed in the traditional works, but these lack with the limitations of increased network traffic and energy consumption. In order to solve these issues, an enhanced hybrid flower pollination algorithm (HFPA) with improved harmony search (IHS) is developed in this paper. It intends to obtain an improved resource utilization and reduced network load and delay by efficiently allocating the bandwidth to the network. Moreover, an optimal routing protocol (ORP) is employed to perform the data transmission with condensed network traffic. During experimentation, the performance results of the proposed algorithm are examined and compared with some traditional methodologies. From the results, it is noted that the proposed HFPA‐IHS‐ORP provides the better results than the existing methods.

Hybrid Flower Pollination Algorithm with Sequential Quadratic Programming Technique for Solving Dynamic Combined Economic Emission Dispatch Problem

This paper presents the solution of highly complex, non-linear, multi-objective Dynamic Combined Economic Emission Dispatch (DCEED) problem. DCEED is a power system optimization problem with conflicting objectives of fuel cost and emission. DCEED includes constraints like valve point loading effect, Transmission Losses and Ramp Rate limits. Solution of DCEED problem is given by a novel Hybridized Flower Pollination Algorithm (FPA) with Sequential Quadratic Programming (SQP). FPA is a nature inspired population based meta-heuristic optimization technique that models its search on the flower pollination process. The non-convex nature of generation because of numerous operational, physical and dynamic constraints, makes search space highly multi model and complex. This makes DCEED a challenging as well as an attractive problem for research. The effectiveness of FPA-SQP is tested and validated by applying it on IEEE Standard 5-unit and 10-unit non-convex test system in MATLAB environment for the time interval of 24 hours. The results achieved by this algorithm show significant reduction in cost and emission as compared to other available techniques in the literature.

Hybrid Flower Pollination Algorithm and Binary Particle Swarm Optimization Algorithm for Osteosarcoma Detection

Hybrid Flower Pollination Algorithm and Binary Particle Swarm Optimization Algorithm for Osteosarcoma Detection

FPAES: A Hybrid Approach for the Optimal Placement and Sizing of Reactive Compensation in Distribution Grids

Reactive power compensation with Capacitor Banks (CBs) is one of the most successful approaches used in distribution systems, mainly due to their versatility, long-term acceptance in the power industry, and reduced costs. Most allocation methods, however, lack specific strategies to handle the limited discrete nature of CBs sizes seeking to improve the overall optimization and computational performance. We present an algorithm for the Optimal Placement of Capacitor Banks (OPCB) in distribution systems by means of a hybrid Flower Pollination Algorithm (FPA)–Exhaustive Search (ES) approach. The pollination process itself determines the sets of buses for placement, while CBs sizes and the final fitness values of each pollen are selected after a full-search is conducted in the sizing space. As the sizing phase works on the limited search space of predetermined discrete bank values, the computational effort to find the optimum CB capacity is greatly reduced. Tests were performed on distribution systems of 10, 34, and 85 buses with respect to the objective function, final losses, and voltage profile. The algorithm offers an excellent compromise between solution quality and computational effort, when compared to similar approaches.

New hybrid flower pollination algorithm with dragonfly algorithm and jaccard index to enhance solving university course timetable problem

University course timetable problem (UCTP) is one of the problems on which many researches have been conducted over the years because of its importance in academic institutions. A nature-inspired metaheuristic optimization algorithm, Flower Pollination Algorithm (FPA) has been adapted, so-called Adapted FPA (AFPA), to cope with UCTP in the previous work. However, AFPA suffers from the stagnation problem because of the non-diversity in the population. To improve the diversity of the population, this work introduces new Hybrid FPA with two variants: JFPA provided the Jaccard index to determine similarities among categorical data and the greedy selection mechanism to improve the selection of the random solution, and DFPA applied the navigational characteristics of the Dragonfly Algorithm (DA) to help in the neighborhood relationship. The results in this study indicate that the proposed algorithms have better exploration ability and fast convergence rate in comparison; JFPA outperforms AFPA in 3 out of 4 datasets for both small and large datasets, and DFPA outperforms AFPA and GA in all datasets while it outperforms PSO in 3 out of 4 small datasets and 2 complex large datasets.

Person identification using EEG channel selection with hybrid flower pollination algorithm

Recently, electroencephalogram (EEG) signal presents a great potential for a new biometric system to deal with a cognitive task. Several studies defined the EEG with uniqueness features, universality, and natural robustness that can be used as a new track to prevent spoofing attacks. The EEG signals are the graphical recording of the brain electrical activities which can be measured by placing electrodes (channels) in various positions of the scalp. With a large number of channels, some channels have very important information for biometric system while others not. The channel selection problem has been recently formulated as an optimisation problem and solved by optimisation techniques. This paper proposes hybrid optimisation techniques based on binary flower pollination algorithm (FPA) and β-hill climbing (called FPAβ-hc) for selecting the most relative EEG channels (i.e., features) that come up with efficient accuracy rate of personal identification. Each EEG signals with three different groups of EEG channels have been utilized (i.e., time domain, frequency domain, and time-frequency domain). The FPAβ-hc is measured using a standard EEG signal dataset, namely, EEG motor movement/imagery dataset with a real world data taken from 109 persons each with 14 different cognitive tasks using 64 channels. To evaluate the performance of the FPAβ-hc, five measurement criteria are considered:accuracy (Acc), (ii) sensitivity (Sen), (iii) F-score (F_s), (v) specificity (Spe), and (iv) number of channels selected (No. Ch). The proposed method is able to identify the personals with high Acc, Sen., F_s, Spe, and less number of channels selected. Interestingly, the experimental results suggest that FPAβ-hc is able to reduce the number of channels with accuracy rate up to 96% using time-frequency domain features. For comparative evaluation, the proposed method is able to achieve results better than those produced by binary-FPA-OPF method using the same EEG motor movement/imagery datasets. In a nutshell, the proposed method can be very beneficial for effective use of EEG signals in biometric applications.

VNE strategy based on chaos hybrid flower pollination algorithm considering multi-criteria decision making

With the development of science and technology and the need for multi-criteria decision making (MCDM), the optimization problem to be solved becomes extremely complex. The theoretically accurate and optimal solutions are often difficult to obtain. Therefore, meta-heuristic algorithms based on multi-point search have received extensive attention. The flower pollination algorithm (FPA) is a new swarm intelligence meta-heuristic algorithm, which can effectively control the balance between global search and local search through a handover probability, and gradually attracts the attention of researchers. However, the algorithm still has problems that are common to optimization algorithms. For example, the global search operation guided by the optimal solution is easy to lead the algorithm into local optimum, and the vector-guided search process is not suitable for solving some problems in discrete space. Moreover, the algorithm does not consider dynamic multi-criteria decision problems well. Aiming at these problems, the design strategy of hybrid flower pollination algorithm for virtual network embedding problem is discussed. Combining the advantages of the genetic algorithm and FPA, the algorithm is optimized for the characteristics of discrete optimization problems. The cross-operation is used to replace the cross-pollination operation to complete the global search and replace the mutation operation with self-pollination operation to enhance the ability of local search. Moreover, a life cycle mechanism is introduced as a complement to the traditional fitness-based selection strategy to avoid premature convergence. A chaos optimization strategy is introduced to replace the random sequence-guided crossover process to strengthen the global search capability and reduce the probability of producing invalid individuals. In addition, a two-layer BP neural network is introduced to replace the traditional objective function to strengthen the dynamic MCDM ability. Simulation results show that the proposed method has good performance in link load balancing, revenue???cost ratio, VN requests acceptance ratio, mapping average quotation, average time delay, average packet loss rate, and the average running time of the algorithm.

DNA Cryptography: A Novel Approach for Data Security Using Flower Pollination Algorithm

The number of threats is increasing with the growth of technologies and due to extensive internet usage, it has become more difficult to provide security to important data. To overcome these issue, data encryption is necessary before sending information through transmission channel. To overcome these issues, a new technique is proposed based on the DNA cryptography along with the nature-inspired FPA algorithm. The idea behind to convert plain text to DNA strand because of its uncrackable characteristic and The FPA is considered as best and able to find effective optimized result as compared to other algorithms. In this paper, we proposed a new hybrid flower pollination algorithm with DNA cryptography. Flower pollination algorithm is a nature-inspired algorithm that helps to find the optimal solution whereas DNA cryptography helps to encrypt a large number of data in few grams of DNA. In this paper, the original form of flower pollination algorithm is presented with DNA cryptography in order to achieve optimized technique to enhance cloud security.

An improved hybrid flower pollination algorithm for assembly sequence optimization

PurposeAssembly sequence optimization is a difficult combinatorial optimization problem having to simultaneously satisfy various feasibility constraints and optimization criteria. Applications of evolutionary algorithms have shown a lot of promise in terms of lower computational cost and time. But there remain challenges like achieving global optimum in least number of iterations with fast convergence speed, robustness/consistency in finding global optimum, etc. With the above challenges in mind, this study aims to propose an improved flower pollination algorithm (FPA) and hybrid genetic algorithm (GA)-FPA.Design/methodology/approachIn view of slower convergence rate and more computational time required by the previous discrete FPA, this paper presents an improved hybrid FPA with different representation scheme, initial population generation strategy and modifications in local and global pollination rules. Different optimization objectives are considered like direction changes, tool changes, assembly stability, base component location and feasibility. The parameter settings of hybrid GA-FPA are also discussed.FindingsThe results, when compared with previous discrete FPA and GA, memetic algorithm (MA), harmony search and improved FPA (IFPA), the proposed hybrid GA-FPA gives promising results with respect to higher global best fitness and higher average fitness, faster convergence (especially from the previously developed variant of FPA) and most importantly improved robustness/consistency in generating global optimum solutions.Practical implicationsIt is anticipated that using the proposed approach, assembly sequence planning can be accomplished efficiently and consistently with reduced lead time for process planning, making it cost-effective for industrial applications.Originality/valueDifferent representation schemes, initial population generation strategy and modifications in local and global pollination rules are introduced in the IFPA. Moreover, hybridization with GA is proposed to improve convergence speed and robustness/consistency in finding globally optimal solutions.

Dynamic Economic Dispatch Incorporating Photovoltaic and Wind Generation using Hybrid FPA with SQP

ABSTRACTThis paper presents a hybrid approach to explore the effect of wind and photovoltaic energy on conventional power network using dynamic economic dispatch. This model deals with stochastic and unpredictable character of wind and solar power output while considering the gaps between the real and predicted output power. A hybrid flower pollination algorithm with sequential quadratic programming is applied to reduce the overall operating costs of generators, while allocating generation to the committed units. The proposed technique is applied on power system having 13 solar units and a wind plant connected with 3, 5, and 10 generating units, respectively. The results of algorithm simulations performed in MATLAB 2014b confirm the competence of the suggested method.

Hybrid Flower Pollination Algorithm and Support Vector Machine for Breast Cancer Classification

Microarray technology is a system that enable experts to examine gene profile at molecular level for early disease detection. Machine learning algorithms such as classification are used in detection of dieses from data generated by microarray. It increases the potentials of classification and diagnosis of many diseases such as cancer at gene expression level. Though, numerous difficulties may affect the performance of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data preprocessing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper proposed a new technique for feature selection and classification of breast cancer based on Flower Pollination algorithm (FPA) and Support Vector machine (SVM) using microarray data. The result for this research reveals that FPA-SVM is promising by outperforming the state of the earth Particle Swam Optimization algorithm with 80.11% accuracy.

Review of modified and hybrid flower pollination algorithms for solving optimization problems

Flower pollination algorithm (FPA) is a nature-inspired meta-heuristics to handle a large scale optimization process. This paper reviews the previous studies on the application of FPA, modified FPA and hybrid FPA for solving optimization problems. The effectiveness of FPA for solving the optimization problems are highlighted and discussed. The improvement aspects include local and global search strategies and the quality of the solutions. The measured enhancements in FPA are based on various research domains. The results of review indicate the capability of the enhanced and hybrid FPA for solving optimization problems in variety of applications and outperformed the results of other established optimization techniques.

Optimal design of fractional-order digital integrators:An evolutionary approach

This paper presents an optimal approach to design Fractional-Order Digital Integrators (FODIs) using a metaheuristic technique, called Hybrid Flower Pollination Algorithm (HFPA). HFPA is a hybrid approach which combines the exploitation and exploration capabilities of two di erent evolutionary optimization algorithms, namely, Particle Swarm Optimization (PSO) and Flower Pollination Algorithm (FPA). The proposed HFPA based designs are compared with the designs based on Real Coded Genetic Algorithm (RGA), PSO, Di erential Evolution (DE), and FPA. Simulation results demonstrate that HFPA based FODIs of all the di erent orders consistently achieve the best magnitude responses. The proposed technique yields FODIs which surpass all the designs based on both classical and evolutionary optimization approaches reported in recent literature.

Optimal design of wideband digital integrators and differentiators using hybrid flower pollination algorithm

In this paper, a recently proposed metaheuristic optimization technique called hybrid flower pollination algorithm (HFPA) is applied to design wideband infinite impulse response digital differentiators (DDs) and digital integrators (DIs). In recent years, benchmark nature-inspired optimization algorithms such as particle swarm optimization (PSO), simulated annealing, and genetic algorithm have been employed for the design of wideband DDs and DIs. However, individually, these algorithms show major drawbacks such as premature convergence, thus leading to a sub-optimal solution. HFPA, however, is a hybrid approach which combines the efficient exploitation and exploration capabilities of two different metaheuristics, namely PSO and flower pollination algorithm (FPA), respectively. The HFPA-based designs have been compared with real-coded genetic algorithm, PSO, differential evolution, success-history-based adaptive differential evolution with linear population size reduction (L-SHADE), self-adaptive differential evolution (jDE), and FPA-based designs with respect to the solution quality, robustness, convergence, and optimization time. Simulation results demonstrate that among all the algorithms, the HFPA-based designs consistently achieve superior performances in the least number of function evaluations. Exhaustive experimentations are conducted to determine the best values of the control parameters of HFPA for the optimal design of DDs and DIs. The proposed designs also outperform the recently reported designs based on non-optimal, classical, and nature-inspired optimization approaches in terms of magnitude response. The lower orders of the proposed designs render them suitable for real-time applications.

Parameter estimation for chaotic systems via a hybrid flower pollination algorithm

Parameter estimation is a fundamental research issue which has attracted great concern in the control and synchronization of chaotic systems. This problem can be mathematically described as a multi-dimensional continuous optimization problem through constructing an appropriate fitness function, and then solved via meta-heuristic algorithms. A hybrid flower pollination algorithm is proposed in this paper for solving this problem more efficiently. The proposed algorithm well combines the good global exploration ability of the original flower pollination algorithm and the powerful local exploitation ability of the Nelder–Mead simplex method together by integrating these two methods in a very simple way. The experimental results tested on three typical chaotic system parameter estimation problems with three unknown system parameters, including the Lorenz system, the Rossler system, and the Lorenz system under the noise condition, demonstrate that the algorithm can estimate the unknown parameters efficiently and accurately. The comparisons with the basic flower pollination algorithm and some other four reported methods including the quantum particle swarm optimization, the hybrid adaptive cuckoo search optimization algorithm, the oppositional backtracking search optimization algorithm, and the hybrid algorithm combining differential evolution with artificial bee colony suggest that the proposed algorithm is energy efficient and superior. The proposed algorithm can be used as a new and effective choice for parameter estimation of chaotic systems.