Gases Brownian Motion Optimization Research Articles

Active hybrid energy storage management in a wind-dominated standalone system with robust fractional-order controller optimized by Gases Brownian Motion Optimization Algorithm

Accessibility to sustainable and reliable electrical energy for remote area power supply (RAPS) systems under high penetration levels of wind energy requires adopting appropriate technologies and controllers. In recent years, energy storage has gained significant attention for smoothing inherent voltage and power fluctuations of standalone systems. This paper presents a filtration-based fractional-order PI (FOPI) controller optimized by Gases Brownian Motion Optimization (GBMO) algorithm to manage an active battery-supercapacitor hybrid energy storage system (HESS) in a wind-dominated RAPS system. The GBMO algorithm has a high accuracy and convergence rate among optimization algorithms introduced in recent years. Moreover, a fuzzy logic controller (FLC) guarantees the wind turbine generator's maximum power point tracking (MPPT) at any wind condition while mitigating its fluctuating torque. The proposed RAPS system uses the advantages of the FOPI controller, the GBMO optimization algorithm, the FLC-based MPPT algorithm, and a high-pass filter to manage precise coordination between different components of the RAPS system. The high-pass filter decouples high and low-frequency voltage oscillations to modify the HESS performance and relieve battery stress, thereby extending its lifespan. The proposed controller's performance and robustness are verified in comparison with an optimal PI controller based on GBMO under turbulent wind speed and load step changes in a detailed model of the system. The results demonstrate the superiority of the optimal FOPI controller over the optimal PI controller.

Modified Parallel Tunicate Swarm Algorithm and Application in 3D WSNs Coverage Optimization

<p>As the application of Wireless Sensor Networks (WSNs) in today’s society becomes more and more extensive, and the status is getting higher and higher, the node layout of sensors has also begun to attract social attention. In reality, the coverage of WSNs in 3D space is particularly important. Therefore, it is worth investigating an efficient way to find out the maximum coverage of WSNs. In this paper, a Modified Parallel Tunicate Swarm Algorithm (MPTSA) is proposed based on modified parallelism, which can improve the convergence of the algorithm and optimal global solution. Next, the proposed MPTSA is implemented and tested on 23 benchmark functions to verify the algorithm performance. Finally, a WSNs network layout scheme based on MPTSA is proposed to improve the coverage of the whole network. Experimental results show that, compared with the traditional PSO (Particle Swarm Optimization), improved PSO (PPSO and APSO), GBMO (Gases Brownian Motion Optimization) and traditional TSA, MPTSA family algorithms show better performance in WSNs network layout.</p> <p> </p>

Optimal fractional-order PID control design for time-delayed multi-input multi-output seismic-excited structural system

The application of the fractional-order PID (FOPID) controller is recently becoming a topic of research interest for vibration control of structures. Some researchers have successfully implemented the FOPID controller in a single-input single-output (SISO) control structural system subjected to earthquake excitations. However, there is a lack of research that focuses on its application in multi-input multi-output (MIMO) control systems to implement it in seismic-excited structures. In this case, the cross-coupling of the process channels in the MIMO control structural system may result in a complex design process of controllers so that each loop is independently designed. From an operational point of view, the time delay and saturation limit of the actuators are other challenges that significantly affect the performance and robustness of the controller so that ignoring them in the design process may lead to unrealistic results. According to the challenges, the present study proposed an optimal fractional-order PID control design approach for structural control systems subjected to earthquake excitation. Gases Brownian motion optimization (GBMO) algorithm is utilized for optimal tuning of the controller parameters. Considering six real earthquakes and seven performance indices, the performance of the proposed controller, implemented on a ten-story building equipped with an active tendon system (ATS), is compared with those provided by the classical PID controller. Simulation results indicate that the proposed FOPID controller is more efficient than the PID in both terms of seismic performance and robustness against time-delay effects. The proposed FOPID controller can maintain suitable seismic performance in small time delays, while a significant performance loss is observed for the PID controller.

W44. OXTR DNA METHYLATION DIFFERENTIATES MEN ON THE OBESITY SPECTRUM WITH AND WITHOUT AN EATING DISORDER

The facts show that multi-instance multi-label (MIML) learning plays a pivotal role in Artificial Intelligence studies. Evidently, the MIML learning introduces a framework in which data is described by a bag of instances associated with a set of labels. In this framework, the modeling of the connection is the challenging problem for MIML. The RBF neural network can explain the complex relations between the instances and labels in the MIMLRBF. The parameters estimation of the RBF network is a difficult task. In this paper, the computational convergence and the modeling accuracy of the RBF network has been improved. The present study aimed to investigate the impact of a novel hybrid algorithm consisting of Gases Brownian Motion optimization (GBMO) algorithm and the gradient based fast converging parameter estimation method on multi-instance multi-label learning. In the current study, a hybrid algorithm was developed to estimate the RBF neural network parameters (the weights, widths and centers of the hidden units) simultaneously. The algorithm uses the robustness of the GBMO to search the parameter space and the efficiency of the gradient. For this purpose, two real-world MIML tasks and a Corel dataset were utilized within a two-step experimental design. In the first step, the GBMO algorithm was used to determine the widths and centers of the network nodes. In the second step, for each molecule with fixed inputs and number of hidden nodes, the parameters were optimized by a structured nonlinear parameter optimization method (SNPOM). The findings demonstrated the superior performance of the hybrid algorithmic method. Additionally, the results for training and testing the dataset revealed that the hybrid method enhances RBF network learning more efficiently in comparison with other conventional RBF approaches. The results obtain better modeling accuracy than some other algorithms.

Investigation of butterfly optimization and gases Brownian motion optimization algorithms for optimal multilevel image thresholding

Image processing is one of the major research regions in the most recent decades, in which, image segmentation has gained more popularity due to its enormous applications. Before segmenting an image, it has to be pre-processed using thresholding techniques. A properly thresholded image would give better segmentation results. Many researchers have contributed significant algorithms based on Otsu and Kapur based methods and reported outstanding results. These methods are suitable for bi-level as well as multilevel thresholding cases, however, the process of selecting the optimal thresholds in the case of multilevel thresholding is difficult and time consuming. To avoid this problem, this paper investigates the ability of two different algorithms namely: BOA (Butterfly Optimization Algorithm) and GBMO (Gases Brownian Motion Optimization) to determine the optimal threshold levels for image segmentation. The BOA is inspired from natural behaviour of butterflies which have special style of information propagation based on intensity of fragrance; whereas, GBMO is based on law of motion of gases which have greater ability to trade-off between exploration and exploitation. The candidate solutions were created using image histogram based on selected algorithms, and then they were updated according to the characteristics of each algorithm. The solutions are estimated using Otsu’s between class variance as fitness function during the process of optimization. The performance of the proposed algorithms has been evaluated using various benchmark images and has been compared with seven different algorithms such as MFO (Moth Flame Optimization), WOA (Whale Optimization Algorithm), SSO (Social Spider Optimization), FASSO (Firefly Assisted Social Spider Optimization), FA (Firefly Algorithm), SCA (Sine Cosine Algorithm), and HS (Harmony Search). The outcomes have been analysed based on various metrics like fitness value, PSNR and SSIM, as well as time complexity and the Wilcoxon statistical test. The experimental results showed that the proposed methods outperformed the other algorithms. Among BOA and GBMO, BOA yields better results than GBMO for all images at all threshold levels.

Optimal design of zero-phase digital Riesz FIR fractional-order differentiator

This article introduces an optimal design of finite impulse response-type Riesz fractional-order digital differentiator (FODD) of orders p = 0.3, 0.5, and 0.75. A very little study on Riesz-based differentiator has been reported so far. Moreover, none of the published Riesz FODD-based literature has studied the optimal design of Riesz FODD, which is explored in this article. In the reported literature, the Riesz FODD is realized by adopting conventional mathematical approaches, which are not efficient for the Riesz FODD-type design problem where the nature of the search landscape is multidimensional, multimodal, non-uniform, and nonlinear. To solve this problem, the design parameters of the proposed Riesz FODDs are estimated by using three independent metaheuristic optimization algorithms called salp swarm algorithm (SSA), gases Brownian motion optimization (GBMO), and gravitational search algorithm (GSA). In SSA, the adaptive variation of the iteration-dependent parameters helps the search agents not only to avoid the suboptimal solutions, but also ensures the faster convergence to reach the near-global optimal solution compared to GSA- and GBMO-based design approaches. The maximum phase error (MPE) and maximum absolute magnitude error (MAME) of the proposed SSA-based Riesz FODD are as low as 3.7119E−014 degree and − 9.6824 dB, respectively, for p = 0.3; 3.1523E−014 degree and − 15.6443 dB, respectively, for p = 0.5; and 3.5780E−014 degree and − 18.7525 dB, respectively, for p = 0.75. In terms of MPE and MAME, the proposed SSA-based Riesz FODD significantly outperforms the GSA- and GBMO-based Riesz FODD designs. The proposed SSA-based Riesz FODD of order p = 0.5 is also implemented on the TMS320C6713 digital signal processor, and its precise zero-phase performance is tested on real electrocardiogram (ECG) signal. Moreover, the proposed Riesz FODD is utilized in the ECG QRS complex identification system to demonstrate its real-time application.

A hybrid optimized learning‐based compressive performance of concrete prediction using GBMO‐ANFIS classifier and genetic algorithm reduction

AbstractHigh performance concrete (HPC) is a type of concrete that cannot be produced using conventional methods. The exact percentage of materials used in the production of this concrete is one of the challenges facing civil engineers so that if ingredients are not in proportion, the strength of concrete is undermined. In the present study, attempts have been made to find an intelligent model to predict the quality of HPC. As a result of regression analysis, the automatic recognition would be affected by inferential estimation. Hence, to increase classification accuracy, first extracted feature is rearranged based on expectation–maximization clustering algorithm and then feature vector size is reduced using genetic algorithm. The proposed classification is adaptive neuro‐fuzzy inference system, which is optimized by Gases Brownian Motion Optimization and able to predict outputs at an acceptable level in limited reiterations. The split ratio of data during learning and testing steps was 0.9 and 0.1, as measured by K‐fold cross‐validation method. Computation of criteria such as mean square error and mean absolute percentage error in the algorithm indicated the desirable performance of the proposed method.

An Efficient QRS Complex Detection Using Optimally Designed Digital Differentiator

Heart rate variability (HRV) analysis is considered as a preliminary diagnosis method to check the cardiac health of the human heart. The reliability of the HRV analysis system solely depends on the accuracy of the QRS complex detector. Hence, in this paper, an optimally designed digital differentiator (DD) for precise detection of QRS complex is proposed. The proposed DD is designed by using an efficient evolutionary optimization technique called gases Brownian motion optimization (GBMO) algorithm and is used in the preprocessing stage of the QRS detector. In GBMO algorithm, a balanced trade-off is maintained between both the exploration and the exploitation phases to find the global optimum solution. The electrocardiogram signal is preprocessed by using the proposed DD to generate the feature signals corresponding to the R-peaks only. The detection technique utilizes the principle of Hilbert transform and zeroes crossing detection. The proposed approach is verified against all the first channel records of MIT/BIH arrhythmia database by considering the standard QRS detection performance metrics and produces a sensitivity (Se) of 99.92%, positive predictivity (+P) of 99.92%, detection error rate (DER) of 0.1562%, QRS detection rate of 99.92%, accuracy (Acc) of 99.84%, and F score of 0.9992%. With respect to the standard performance metrics, the proposed QRS detector outperforms all the recently reported QRS detection techniques.

A GBMO-based PI λ D μ controller for vibration mitigation of seismic-excited structures

The advantages of fractional-order proportional–integral–derivative (FOPID) controllers in terms of flexibility, robustness against model uncertainties and good disturbance rejection, are good motivations to use them for vibration mitigation of seismic-excited structures. The application of the FOPID controller for adjusting the control force of an active tuned mass damper (ATMD) for seismic control a building is studied in this paper. Gases Brownian motion optimization (GBMO) algorithm is employed for optimal tuning of parameters of the FOPID and PID controllers. Evaluation of the frequency responses of the structure for uncontrolled and controlled cases shows that PID and FOPID controllers are very effective for the seismic control of structures. For further investigation, the performance of the FOPID controller in the reduction of seismic responses of the building in four well-known earthquake excitations is compared with those provided by the PID, linear–quadratic regulator (LQR) and fuzzy logic control (FLC). Simulation results show that the PID and LQR controllers provide the same performance in reducing the maximum top floor displacement of the structure. Moreover, the FLC and FOPID controllers demonstrate a superior performance in seismic control of the structure. The FLC is able to reduce the maximum displacements of all stories for all studied earthquakes. However, the proposed FOPID controller is able to provide a better performance in comparison with the FLC. In average, the FOPID controller mitigates the seismic responses of the structure as much as 29%, 27% and 15% better than the LQR, PID controller and FLC.

Design of a fractional order PID controller using GBMO algorithm for load–frequency control with governor saturation consideration

Load–frequency control is one of the most important issues in power system operation. In this paper, a Fractional Order PID (FOPID) controller based on Gases Brownian Motion Optimization (GBMO) is used in order to mitigate frequency and exchanged power deviation in two-area power system with considering governor saturation limit. In a FOPID controller derivative and integrator parts have non-integer orders which should be determined by designer. FOPID controller has more flexibility than PID controller. The GBMO algorithm is a recently introduced search method that has suitable accuracy and convergence rate. Thus, this paper uses the advantages of FOPID controller as well as GBMO algorithm to solve load–frequency control. However, computational load will higher than conventional controllers due to more complexity of design procedure. Also, a GBMO based fuzzy controller is designed and analyzed in detail. The performance of the proposed controller in time domain and its robustness are verified according to comparison with other controllers like GBMO based fuzzy controller and PI controller that used for load–frequency control system in confronting with model parameters variations.

Hybrid Gases Brownian Motion and Gravitational Search Algorithm for Resource Scheduling

Grid computing provides efficient platform for users to access geographically distributed resources. To meet the quality requirements and timing efficiency constraints imposed by tasks running on Grid, the resources should be allocated efficiently. The plane of recent use is beyond distribution and sharing. The distributed shared resources are useful only if its resources are scheduled efficiently. Grid scheduling is mapping of incoming task to available heterogeneous resources. Here scheduling is NP-hard, henceforth a pile of effort to develop an efficient algorithm is vital to reduce makespan. Metaheuristic algorithms are simplest methods to solve efficiently complex problems. Hybridize metaheuristic algorithm is advanced; trend to improve quality of solution. In this paper Hybrid GSA-PSO (Gravitational Search Algorithm – Particle Swarm Optimization Algorithm); Hybrid GBMO-GSA (Gases Brownian Motion Optimization -Gravitational Search Algorithm) algorithms are amalgamated to provide optimal solution for task scheduling problem in computational grid. Hybrid algorithm implementation shows a significant result in minimizing makespan to meet user requirements comparatively.

Efficacy of utilizing a hybrid algorithmic method in enhancing the functionality of multi-instance multi-label radial basis function neural networks

The facts show that multi-instance multi-label (MIML) learning plays a pivotal role in Artificial Intelligence studies. Evidently, the MIML learning introduces a framework in which data is described by a bag of instances associated with a set of labels. In this framework, the modeling of the connection is the challenging problem for MIML. The RBF neural network can explain the complex relations between the instances and labels in the MIMLRBF. The parameters estimation of the RBF network is a difficult task. In this paper, the computational convergence and the modeling accuracy of the RBF network has been improved. The present study aimed to investigate the impact of a novel hybrid algorithm consisting of Gases Brownian Motion optimization (GBMO) algorithm and the gradient based fast converging parameter estimation method on multi-instance multi-label learning. In the current study, a hybrid algorithm was developed to estimate the RBF neural network parameters (the weights, widths and centers of the hidden units) simultaneously. The algorithm uses the robustness of the GBMO to search the parameter space and the efficiency of the gradient. For this purpose, two real-world MIML tasks and a Corel dataset were utilized within a two-step experimental design. In the first step, the GBMO algorithm was used to determine the widths and centers of the network nodes. In the second step, for each molecule with fixed inputs and number of hidden nodes, the parameters were optimized by a structured nonlinear parameter optimization method (SNPOM). The findings demonstrated the superior performance of the hybrid algorithmic method. Additionally, the results for training and testing the dataset revealed that the hybrid method enhances RBF network learning more efficiently in comparison with other conventional RBF approaches. The results obtain better modeling accuracy than some other algorithms.

Sensor deployment for fault diagnosis using a new discrete optimization algorithm

Optimal allocation of the sensor in a wireless sensor network (WSN) is required to have a satisfactory fault diagnosis within the system. In fact, the sensor nodes in the network should be located in an arrangement to maximize the failure diagnosis. In this paper, the sensor deployment optimization to diagnose the distributed failures in a wireless unmanned aerial vehicles (UAVs) network has been studied. In this way, a novel evolutionary optimization algorithm inspired by the gases Brownian and turbulent rotational motion is utilized which is called Discrete Gases Brownian Motion Optimization (DGBMO) algorithm. An integer linear programming (ILP) approach is used to formulate the sensor deployment. Then the sensor deployment optimization is solved by DGBMO as well as generic ILP solvers and Boolean satisfiability-based ILP solvers. The results show that DGBMO is suitable for sensor disposition optimization especially in large-sized UAV networks.

Gases Brownian Motion Optimization: an Algorithm for Optimization (GBMO)

In recent years, different optimization methods have been developed for optimization problem. Many of these methods are inspired by swarm behaviors in nature. In this paper, a new algorithm for optimization inspired by the gases brownian motion and turbulent rotational motion is introduced, which is called Gases Brownian Motion Optimization (GBMO). The proposed algorithm is created using the features of gas molecules. The proposed algorithm is an efficient approach to search and find an optimum solution in search space. The efficiency of the proposed method has been compared with some well-known heuristic search methods. The obtained results confirm the high performance of the proposed method in solving various functions.