Levy Flight Research Articles

A Secure and Optimization Based Clustering for Vertical and Horizontal Fragmentation in Distributed Database Management System

Distributed database systems are increasingly important due to the massive data output, and their effectiveness is largely based on their design. Two key processes, fragmentation and allocation, are used to improve the efficiency and efficacy of these systems. Effective data fragmentation requires both horizontal and vertical categorization of tuples. Advanced optimization techniques are used for both fragmentations, such as the Enhanced Arithmetic Optimization (EAO) algorithm with Opposition-based Learning (OBL) and Levy Flight Distributer (LFD) for vertical fragmentation and the hybrid Aquila Optimizer (AO) with Artificial Rabbit Optimization (ARO) algorithm for horizontal fragmentation. The fragmented data is securely transmitted using the Fully Homomorphic Encryption (FHE) algorithm. The implementation is executed using the Python language, and the performance of the proposed algorithms is evaluated using different performance parameters. The execution time analysis shows that the proposed EAOA algorithm consumes 5.5 seconds for vertical fragmentation, while the hybrid AARO algorithm takes 5.9 seconds for horizontal fragmentation. The vertical fragmentation is found to be better than the horizontal one in DDBMS.

Improving Kinnow Fruit Classification with Feature Weighting using Modified Levy Flight Distribution-Inspired Sunflower Optimization Technique

In this paper, Feature weighting is used to create an intelligent and effective classification method for Kinnow fruits. Feature weighting approach is used because it improves classification performance more than feature selection methods. The modified sunflower optimization algorithm (SFO) is proposed to search the optimal feature weights and parametric values of k-Nearest Neighbour (kNN).The levy flight distribution operator has been utilised to enhance the convergence speed of the sunflower optimization algorithm by improving the local and global search ability of the optimization algorithm. Also, the algorithmic parameter of the SFO algorithm has been adaptively selected using the linear time varying adaption method. In addition, tanh normalization technique is used for the data pre-processing to reduce the influence of outliers and dominating features before the feature weighting method. The findings suggest that the proposed wrapper based approach feature weighting technique is more capable of achieving higher accuracy than the existing strategies.

Cuckoo Coupled Improved Grey Wolf Algorithm for PID Parameter Tuning

In today’s automation control systems, the PID controller, as a core technology, is widely used to maintain the system output near the set value. However, in some complex control environments, such as the application of ball screw-driven rotating motors, traditional PID parameter adjustment methods may not meet the requirements of high precision, high performance, and fast response time of the system, making it difficult to ensure the stability and production efficiency of the mechanical system. Therefore, this paper proposes a cuckoo search optimisation coupled with an improved grey wolf optimisation (CSO_IGWO) algorithm to tune PID controller parameters, aiming at resolving the problems of the traditional grey wolf optimisation (GWO) algorithm, such as slow optimisation speed, weak exploitation ability, and ease of falling into a locally optimal solution. First, the tent chaotic mapping method is used to initialise the population instead of using random initialization to enrich the diversity of individuals in the population. Second, the value of the control parameter is adjusted by the nonlinear decline method to balance the exploration and development capacity of the population. Finally, inspired by the cuckoo search optimisation (CSO) algorithm, the Levy flight strategy is introduced to update the position equation so that grey wolf individuals are enabled to make a big jump to expand the search area and not easily fall into local optimisation. To verify the effectiveness of the algorithm, this study first verifies the superiority of the improved algorithm with eight benchmark test functions. Then, comparing this method with the other two improved grey wolf algorithms, it can be seen that this method increases the average and standard deviation by an order of magnitude and effectively improves the global optimal search ability and convergence speed. Finally, in the experimental section, three parameter tuning methods were compared from four aspects: overshoot, steady-state time, rise time, and steady-state error, using the ball screw motor as the control object. In terms of overall dynamic performance, the method proposed in this article is superior to the other three parameter tuning methods.

Multi-Objective Reactive Power Optimization for Distribution Networks Based on the Modified Golden Eagle Algorithm

The Golden Eagle algorithm was proposed in 2020 by Abdolkarim et al. and has been applied in several fields. In this paper, we introduce the proposed algorithm to the reactive power optimization problem for distribution networks and develop a dual-objective reactive power optimization model with active network loss and node voltage bias. Logistic chaotic mapping and Levy flights are introduced to improve the original algorithm, which is prone to local optima and slow convergence. Finally, the IEEE30 node system is used for testing, which verifies the feasibility of the proposed algorithm in the reactive power optimization problem, and the improved algorithm has faster convergence and higher solution accuracy.

COOPERATIVE SOURCE DETECTION USING AN OPTIMIZED DISTRIBUTED LEVY FLIGHT ALGORITHM

Source signal detection plays important roles in many real-world target searching problems. Source detection is necessary before a full search process utilizing the detected signal can be performed where minimizing the detection time and maximizing the search space exploration or coverage are the main problems. In this paper, an optimized Levy Flight algorithm known as a Distributed Levy Flight (DLF) for swarm agents is proposed. The DLF algorithm is optimized by means of repulsive artificial potential force to disperse the agents in order to optimize the search space coverage and detection time. Additionally, to integrate cooperative behavior, an artificial attractive force is used to maintain communication among the agents. The results showed that the proposed DLF algorithm successfully improve detection time (113.1s) and area coverage (78.3%) compared to the existing algorithms: Brownian Walk (325.5s, 31.7%), Correlated Random Walk (356.2s, 35.1%), Levy Flight (201.3s, 56.6%), Levy Flight with Artificial Potential Fields (151.9s, 70.2%).

A meta-heuristic assisted method for the deployment of the multi-BWBUG cooperative system

Blended-wing-body underwater gliders (BWBUGs) are characterized by low noise and high endurance, and they are well suited for deployment in offshore missions. However, the deployment of the multi-BWBUG cooperative system faces great difficulties due to the complex ocean environment and the difficulty of accurately establishing the deployment model. Thus, a novel meta-heuristic assisted method is proposed for the deployment of the multi-BWBUG cooperative system in this study. First, the deployment optimization model of the multi-BWBUG cooperative system is established by combining the detection coverage ratio and the all-terminal reliability. In addition, Levy flight with visual expansion (LVE) is put forward to effectively enhance the search capability of the search unit. Then, an LVE-enhanced whale optimizer (LVEWO) is proposed for improving the quality of the initial population and the search strategy. The embedding of LVE and the well-designed competition mechanism can improve the convergence speed of LVEWO. Simulation experiments and statistical analysis results convincingly demonstrate the effectiveness of the proposed deployment model and the competency of LVEWO to deploy the multi-BWBUG cooperative system. The comprehensive performance of LVEWO is better than those of the FA, EABC, and WO algorithms.

Secure Clustering and Routing using Adaptive Decision and Levy Flight based Artificial Hummingbird Algorithm for Wireless Sensor Networks

Wireless Sensor Network (WSN) receives huge attention from various remote monitoring applications because of its self configuration, ease of maintenance and scalability features. But, the sensors of the WSNs vulnerable to malicious attackers due to the energy constraint, open deployment and lack of centralized administration. Therefore, the secure routing is established for achieving the secure and reliable data broadcasting in the WSN. In this paper, an Adaptive Decision and Levy Flight based Artificial Hummingbird Algorithm (ADLFAHA) is proposed for performing an effective secure routing under the blackhole and Denial of Service (DoS) attacks. The ADLFAHA is developed to perform Secure Cluster Head (SCH) selection and secure path identification according to the trust, energy, load and communication cost. An adaptive decision strategy and levy flight incorporated in the ADLFAHA is used to enhance exploration and achieves global optimization capacity that helps to enhance the searching process. Moreover, the developed ADLFAHA helps to avoid the congestion among the nodes by balancing the load in network. The ADLFAHA is analyzed using End to End Delay (EED), throughput, Packet Delivery Ratio (PDR) and overhead. The existing researches such as Firebug Optimized Modified Bee Colony (FOMBC) and Lightweight Secure Routing (LSR) are used to compare the ADLFAHA. The PDR of the ADLFAHA for the simulation time of 100 s is 98.21 that is high than the FOMBC and LSR.

The Situation Assessment of UAVs Based on an Improved Whale Optimization Bayesian Network Parameter-Learning Algorithm

To realize unmanned aerial vehicle (UAV) situation assessment, a Bayesian network (BN) for situation assessment is established. Aimed at the problem that the parameters of the BN are difficult to obtain, an improved whale optimization algorithm based on prior parameter intervals (IWOA-PPI) for parameter learning is proposed. Firstly, according to the dependencies between the situation and its related factors, the structure of the BN is established. Secondly, in order to fully mine the prior knowledge of parameters, the parameter constraints are transformed into parameter prior intervals using Monte Carlo sampling and interval transformation formulas. Thirdly, a variable encircling factor and a nonlinear convergence factor are proposed. The former and the latter enhance the local and global search capabilities of the whale optimization algorithm (WOA), respectively. Finally, a simulated annealing strategy incorporating Levy flight is introduced to enable the WOA to jump out of the local optimum. In the experiment for the standard BNs, five parameter-learning algorithms are applied, and the results prove that the IWOA-PPI is not only effective but also the most accurate. In the experiment for the situation BN, the situations of the assumed mission scenario are evaluated, and the results show that the situation assessment method proposed in this article is correct and feasible.

Machine-Learning-Based UAV-Assisted Agricultural Information Security Architecture and Intrusion Detection

In recent years, Unmanned Aerial Vehicle (UAV) remote sensing has developed rapidly in the field of farmland information monitoring. Real-time and accurate access to farmland information and crop growth dynamics is a prerequisite for the implementation of precision agriculture. Machine Learning identifies existing knowledge to acquire new knowledge, promotes the development of Artificial Intelligence, and brings a large number of data training sets for Machine Learning. The present work aims to ensure the safe operation of agricultural information systems and guarantee the data security of intelligent agriculture. The Machine Learning method explores the wireless network deployment of the UAV system. The geographical location deployment of agricultural information security can effectively carry out rapid security detection of agricultural information security. Firstly, the UAV-assisted information acquisition system was studied. Besides, a Double Deep Q-network (DDQN) algorithm for location deployment based on Geography Position Information (GPI) was proposed to quickly optimize the deployment location of UAVs. GPI can avoid the complicated calculation process of channel state information. The DDQN algorithm was introduced to obtain the functional relationship between GPI and the optimal UAV deployment position, forming a new GPI-Learning strategy. In addition, the Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are integrated as the CNN-LSTM algorithm to build the intrusion detection system for agricultural IoT for agricultural. In the integrated network structure of the system, LSTM is responsible for data transmission, and CNN is capable of network model building. Combined with the influence of various parameters on the performance of the UAV deployment location algorithm, the simulation experiment set the population size as 36, the discovery probability as 0.25, the step scaling factor as 0.8, and the Levy flight index as 1.25. The network throughput performance of the GPI-Learning algorithm combined with Cuckoo Search was better than other algorithms under different numbers of UAVs. On the KDD-CUP99 data set, the accuracy and detection rate of the agricultural IoT intrusion detection system based on the CNN+LSTM algorithm reached 93.5% and 94.4%, respectively. In general, the agricultural IoT intrusion detection system reported here has crucial practical reference value for the safe operation of agricultural information systems.

Dynamic Reactive Power Compensation Optimization Strategy for Distribution Networks with Distributed Generators and Energy Storage Systems

To balance the output and load dynamic changes of distributed power generators (DG) and energy storage systems (ESS), a demand-side response-based dynamic reactive power optimization (RPO) strategy for distribution networks (DN) is proposed. This strategy adopts a phased optimization method to coordinate and optimize different types of reactive variables within the same period. By adjusting the states of parallel capacitor banks (SCBs) on load voltage transformers (OLTC), DGs, and ESS inverters, the RPO of the DN is carried out. Based on the characteristics of the model, an improved particle swarm optimization algorithm (IPSO) is used to solve different types of variables, and an IPSO based on tent chaotic mapping and levy flight strategy is proposed to improve the efficiency of collaborative solving. The simulation results show that the proposed strategy, considering the change of new energy output and demand side response, can reduce the solution scale while obtaining high satisfaction RPO results.

Impact of DGs on the Reactive Power-Supported Optimal EDN for Profit Maximisation

Significant issues such as high-Power Loss (PLoss) and drop in node voltages in Electric Distribution Networks (EDNs) can be well mitigated using renowned techniques such as Alteration of Electric Distribution Network Switches (AEDNS), Optimal Capacitor Support (OCS), and Integration of Dispersed Generation (IDG), which are identified as the most economical and efficient approaches. This study presents the optimisation of AEDNS with and without OCS considering four different scenarios to maximise the profit through reduction in PLoss, which is regarded as the first-step process. To further increase profit, IDG was integrated into the EDNs after the combined optimisation of OCS and AEDNS. In this work, Levy Flight Mechanism (LFM) was incorporated into the Seagull Optimisation Algorithm (SOA) and applied to solve the objective function based on economics. The effectiveness of the presented methodology was evaluated and confirmed using a real 59-bus in Cairo, Egypt, EDN, as well as a conventional 33-bus test system. For each scenario, the PLoss reductions and net profit of the proposed methodology were contrasted with those obtained from previously reported approaches. The collected findings show that by optimising AEDNS, OCS, and IDG, the established methodology effectively yields more economic gain for all scenarios.

Effective Routing Using Multi-Objective Levy flight- Artificial Rabbit Optimization Algorithm for Wireless Mesh Networks

Effective Routing Using Multi-Objective Levy flight- Artificial Rabbit Optimization Algorithm for Wireless Mesh Networks

Modified reptile search algorithm for optimal integration of renewable energy sources in distribution networks

AbstractThis paper introduces a Modified Reptile Search Algorithm (MRSA) designed to optimize the operation of distribution networks (DNs) considering the growing integration of renewable energy sources (RESs). The integration of RESs‐based Distributed Generation (DG) systems, such as wind turbines (WTs) and photovoltaics (PVs), presents a complex challenge due to its significant impact on DN operations and planning, particularly considering uncertainties related to solar irradiance, temperature, wind speed, consumption, and energy prices. The primary objective is cost reduction, encompassing electricity acquisition, PV and WTs unit costs, and annual energy losses. The proposed MRSA incorporates two strategies: the fitness‐distance balance method and Levy flight motion, enhancing its searching capabilities beyond standard Reptile Search Algorithm and mitigating local optima issues. The uncertainties in load demand, energy prices, and renewable energy generation are represented through probability density functions and simulated using Monte Carlo methods. Evaluation involves typical bentchmark functions and a real 112‐bus Algerian DN, comparing MRSA's efficacy with other optimization techniques. Results indicate that the proposed DN optimization program with WTs and PVs integration reduces annual costs by 21.43%, from 6.2715E + 06 to 4.9270E + 06 USD, reduce voltage deviations by 21.67%, from 77.1022 to 60.4007 USD, and enhance system stability by 2.59%, from 2.3699E + 03 to 2.4314E + 03 USD, compared with the base case.

Application of Modified Adaptive Bats Sonar Algorithm with Doppler Effect and Levy Flight (MABSA-DELF) to Optimize Mechanical Engineering Problems

This paper describes the application of the Modified Adaptive Bats Sonar Algorithm with Doppler Effect and Levy Flight (MABSA-DELF) to mechanical engineering design optimization issues. MABSA-DELF is a new algorithm that employs Doppler Effect and Levy Flight theory to improve the position of the transmitted bats’ beam. This project served as a showcase for the superior performance of MABSA-DELF. It was created using the MATLAB software’s computer simulation method. MABSA-DELF demonstrated a superior ability to solve engineering design problems in the fields of business, mechanical/manufacturing engineering, and electrical engineering. MABSA-DELF’s result are compared to those of other established algorithms.

Hybrid grey wolf optimizer for solving permutation flow shop scheduling problem

SummaryThe permutation flow shop scheduling problem, as a classical problem in the scheduling field, is an NP‐hard problem. However, most of the reported algorithms are difficult to achieve good accuracy and efficiency. To address this problem, a hybrid grey wolf optimizer (HGWO) is proposed in this paper. First, one cooperative initialization strategy is proposed to improve the quality of the initial solution based on the improved Nawaz‐Enscore‐Ham (NEH) method and the tent chaotic map method. Second, a levy flight strategy is introduced to balance the exploitation and exploration of the algorithm for the problem's characteristics. Third, the crossover and mutation strategy, and the critical block exchange based on critical path strategy are proposed to avoid falling into the local optimum. In addition, for the best individual, the variable neighborhood descent strategy is proposed to enhance the convergence accuracy of the algorithm. To verify the performance of the proposed algorithm, three different types of instances are selected for comparison experiments with other existing methods, and the experimental results show that the proposed HGWO outperforms other comparison algorithms in solving the problem.

Artificial Intelligence-Driven Eye Disease Classification Model

Eye diseases can result in various challenges and visual impairments. These diseases can affect an individual’s quality of life and general health and well-being. The symptoms of eye diseases vary widely depending on the nature and severity of the disease. Early diagnosis can protect individuals from visual impairment. Artificial intelligence (AI)-based eye disease classification (EDC) assists physicians in providing effective patient services. However, the complexities of the fundus image affect the classifier’s performance. There is a demand for a practical EDC for identifying eye diseases in the earlier stages. Thus, the author intends to build an EDC model using the deep learning (DL) technique. Denoising autoencoders are used to remove the noises and artifacts from the fundus images. The single-shot detection (SSD) approach generates the key features. The whale optimization algorithm (WOA) with Levy Flight and Wavelet search strategy is followed for selecting the features. In addition, the Adam optimizer (AO) is applied to fine-tune the ShuffleNet V2 model to classify the fundus images. Two benchmark datasets, ocular disease intelligent recognition (ODIR) and EDC datasets, are utilized for performance evaluation. The proposed EDC model achieved accuracy and Kappa values of 99.1 and 96.4, and 99.4 and 96.5, in the ODIR and EDC datasets, respectively. It outperformed the recent EDC models. The findings highlight the significance of the proposed EDC model in classifying eye diseases using complex fundus images. Healthcare centers can implement the proposed model to improve their standards and serve a more significant number of patients. In the future, the proposed model can be extended to identify a comprehensive range of eye diseases.

Workflow Scheduling Scheme for Optimized Reliability and End-to-End Delay Control in Cloud Computing Using AI-Based Modeling

In the context of cloud systems, the effectiveness of placing modules for optimal reliability and end-to-end delay (EED) is directly linked to the success of scheduling distributed scientific workflows. However, the measures used to evaluate these aspects (reliability and EED) are in conflict with each other, making it impossible to optimize both simultaneously. Thus, we introduce a scheduling algorithm for distributed scientific workflows that focuses on enhancing reliability while maintaining specific EED limits. This is particularly important given the inevitable failures of processing servers and communication links. To achieve our objective, we first develop an artificial intelligence-based model that merges an improved version of the wild horse optimization technique with a levy flight approach. This hybrid approach enhances the ability to explore new possibilities effectively. Additionally, we establish a viable strategy for sharing mapping decisions and stored information among processing servers, promoting scalability and robustness—essential qualities for large-scale distributed systems. This strategy not only boosts local search capabilities but also prevents premature convergence of the algorithm. The primary goal of this study is to pinpoint resource placements that strike a balance between global exploration and local exploitation. This entails effectively harnessing the search space and minimizing the inclination toward resources with a high likelihood of failures. Through experimentation in various system configurations, our proposed method consistently outperformed competing workflow scheduling algorithms. It achieved notably higher levels of reliability while adhering to the same EED constraints.

WSN node localization algorithm of sparrow search based on elite opposition-based learning and Levy flight

WSN node localization algorithm of sparrow search based on elite opposition-based learning and Levy flight

MSXFGP: combining improved sparrow search algorithm with XGBoost for enhanced genomic prediction

BackgroundWith the significant reduction in the cost of high-throughput sequencing technology, genomic selection technology has been rapidly developed in the field of plant breeding. Although numerous genomic selection methods have been proposed by researchers, the existing genomic selection methods still face the problem of poor prediction accuracy in practical applications.ResultsThis paper proposes a genome prediction method MSXFGP based on a multi-strategy improved sparrow search algorithm (SSA) to optimize XGBoost parameters and feature selection. Firstly, logistic chaos mapping, elite learning, adaptive parameter adjustment, Levy flight, and an early stop strategy are incorporated into the SSA. This integration serves to enhance the global and local search capabilities of the algorithm, thereby improving its convergence accuracy and stability. Subsequently, the improved SSA is utilized to concurrently optimize XGBoost parameters and feature selection, leading to the establishment of a new genomic selection method, MSXFGP. Utilizing both the coefficient of determination R2 and the Pearson correlation coefficient as evaluation metrics, MSXFGP was evaluated against six existing genomic selection models across six datasets. The findings reveal that MSXFGP prediction accuracy is comparable or better than existing widely used genomic selection methods, and it exhibits better accuracy when R2 is utilized as an assessment metric. Additionally, this research provides a user-friendly Python utility designed to aid breeders in the effective application of this innovative method. MSXFGP is accessible at https://github.com/DIBreeding/MSXFGP.ConclusionsThe experimental results show that the prediction accuracy of MSXFGP is comparable or better than existing genome selection methods, providing a new approach for plant genome selection.

An efficient Covid-19 detection and severity analysis using optimized mask region-based convolution neural network

Coronavirus 2019 (COVID-19) is a severe disease in respiratory syndrome. Early identification and efficient treatment of COVID-19 are not presented which provides ineffective treatment. This research develops an efficient system for early detection and segmentation of COVID-19 severity with the consideration of CT images. To overcome the abovementioned drawbacks, we develop the optimized Mask R-CNN method to train and test the dataset to classify and segment the COVID-19 disease. The proposed technique contains three phases which are, pre-processing, segmentation, and severity analysis. Initially, the patient’s CT images are collected from a different clinic. Then, the noise present in the images is detached with a Gaussian filter. Then, the pre-processed images are given to the optimized mask region-based convolution neural network (OMRCNN) classifier to detect, classify and segment the image. After segmentation, the severity of the disease is examined. To enhance the performance of the mask RCNN classifier, the parameter is efficiently chosen by using the adaptive red deer algorithm. In the adaptive red deer algorithm, the levy flight is utilized to enhance the updating process. The performance of the proposed technique is analyzed based on various metrics.