Figure 1 - uploaded by Sankalap Arora
Content may be subject to copyright.
Source publication
Grey Wolf Optimizer (GWO) is a new meta-heuristic search algorithm inspired by the social behavior of leadership and the hunting mechanism of grey wolves. GWO algorithm is prominent in terms of finding the optimal solution without getting trapped in premature convergence. In the original GWO, half of the iterations are dedicated to exploration and...
Contexts in source publication
Context 1
... that belong to Canidae family which simulates the behavior of leadership quality and the social hunting mechanism of grey wolves in three steps as tracking, encircling and attacking [44]. There are particularly four types of grey wolves namely alpha (α), beta (β), delta (δ) and omega (ω) having a strict social dominant hierarchy as shown in Fig. ...
Context 2
... The centroid of those anchor nodes is calculated which are present within the transmission range of target node using Eq. (13). ...
Context 3
... during trial runs are averaged. Besides having a random deployment in each iteration, the number of nodes that are localized is different, leading to change in computation time [57]. The results of node localization, i.e., the target nodes, anchor nodes and the position of the localized node with different meta-heuristic algorithms are shown in Fig. 10. The number of anchor nodes and target nodes is kept constant for all the algorithms viz. PSO, FA, GWO and proposed EGWO algorithm. Results of range based node localization using different meta- heuristic optimization algorithms in 3 trials are summarized in Table 5. Table 5 The results obtained from these metaheuristic algorithms in ...
Context 4
... algorithms in solving the localization problem with different noise conditions are presented in Table 6. The effect of noise added to the measured distance is clearly noticed from the results. If the noise is more, the computed localization error is more and vice-versa, which indicates that a localization error is dependent on noise as shown in Fig. 11. If the noise is more, the accuracy of localizing the target nodes reduces with the decrease in a number of localized nodes. From Fig. 11, it is noted that the localization error for localizing the unknown target nodes is less using proposed EGWO algorithm than other standard stochastic optimization algorithm. From the results in ...
Context 5
... the noise is more, the accuracy of localizing the target nodes reduces with the decrease in a number of localized nodes. From Fig. 11, it is noted that the localization error for localizing the unknown target nodes is less using proposed EGWO algorithm than other standard stochastic optimization algorithm. From the results in Tables 5 and 6, it is clear that location estimation of un-localized nodes, i.e., target nodes from proposed algorithm is more accurate as compared to nodes localized by PSO, FA and GWO as the proposed EGWO algorithm out searches the search space and then exploit the solu- tion in order to find the position of localized nodes with the minimum localization error. ...
Context 6
... performance evaluation of a parameter transmission range is kept 15. Post that, the transmission range for determining the performance of applied optimization algorithms on parameter anchor node density is fixed to 30 units. The number of iterations for carrying out the performance evaluation for node localization is taken 100. It is depicted in Fig. 12 that increase in the number of it- erations decreases the localization error. The localization error determined from the proposed EGWO algorithm is minimal as compared to error determined from other algorithms. Proposed EGWO al- gorithm extensively searches the search space and later finds the best solution by not getting trapped in ...
Context 7
... is observed that keeping the number of anchor nodes limited does not promote the localization of target nodes. With the increase in the anchor node density, the location estimation of un-localized nodes is preeminent and an immense count of target nodes gets localized as shown in Fig. 13. An insufficient number of anchor nodes around the target node (M ≥ 3) edge to failure in localization of maximum number of ...
Similar publications
The conventional sine cosine algorithm (SCA) does not appropriately balance exploration and exploitation, causing premature convergence, especially for complex optimization problems, such as the complex shifted or shifted rotated problems. To address this issue, this paper proposes an enhanced brain storm SCA (EBSSCA), where an enhanced brain storm...
The original brain storm optimization (BSO) method does not rationally compromise global exploration and local exploitation capability, which results in the premature convergence when solving complicated optimization problems like the shifted or shifted rotated functions. To address this problem, the paper develops a vector grouping learning BSO (V...
Citations
... Unlike conventional approaches that need the human configuration of hyperparameters, G-GWO takes inspiration from grey wolves' social structure and hunting tactics [26][27][28][29]. Throughout its development, GWO has undergone several changes focused on improving convergence speed and minimizing the risk of being stuck in local optima [30][31][32]. ...
In response to the growing number of diabetes cases worldwide, Our study addresses the escalating issue of diabetic eye disease (DED), a significant contributor to vision loss globally, through a pioneering approach. We propose a novel integration of a Genetic Grey Wolf Optimization (G-GWO) algorithm with a Fully Convolutional Encoder-Decoder Network (FCEDN), further enhanced by a Kernel Extreme Learning Machine (KELM) for refined image segmentation and disease classification. This innovative combination leverages the genetic algorithm and grey wolf optimization to boost the FCEDN’s efficiency, enabling precise detection of DED stages and differentiation among disease types. Tested across diverse datasets, including IDRiD, DR-HAGIS, and ODIR, our model showcased superior performance, achieving classification accuracies between 98.5% to 98.8%, surpassing existing methods. This advancement sets a new standard in DED detection and offers significant potential for automating fundus image analysis, reducing reliance on manual examination, and improving patient care efficiency. Our findings are crucial to enhancing diagnostic accuracy and patient outcomes in DED management.
... The proposed model is inspired by the hunting process of the grey wolf. Joshi and Arora [40] proposed an enhanced GWO. EGWO emphasizes striking the right balance between exploration and exploitation. ...
A one-dimensional Co finite element model (FEM) based on cubic-order beam theory in conjunction with the artificial neural network–genetic algorithm (ANN–GA) and artificial neural network–grey wolf optimization (ANN–GWO) metamodels has been adopted for the bending analysis of the pervious composite beam. The axial displacement field is a third-order equation and a function of the variation of the thickness of the beam. The parabolic variation of the shear stress is assumed; therefore, the shear stress value is zero at the extreme surface of the beam. The validation of the presented model has been done with the published research work and found suitable for further analysis. The Monte Carlo simulation–finite element method (MCS–FEM) has been developed and coded in the FORTRAN environment. The dataset obtained from MCS–FEM is used for the training and testing of the machine learning model. The ANN–GA and ANN–GWO metamodels are coded in the MATLAB environment. The various statistical parameters, regression analysis, and rank analysis have been done to find out the accuracy and efficiency of the proposed soft computation metamodels.
... In [33], the authors presented an improved version of Gray Wolf Optimization (GWO) to improve the connectivity in the wireless network. ...
A wireless data collection network (DCN) is the key constituent of the IoT. It is used in many applications such as transport, logistics, security and monitoring. Despite the continuous development of DCN, communication between nodes in such network presents several challenges. The major issue is the deployment of connected objects and, more precisely, how numerous nodes are appropriately positioned to attain full coverage. The current work presents a hybrid technique, named DTABC, combining a geometric deployment method, called Delaunay Triangulation diagram DT, and an optimization algorithm named the Artificial Bee Colony (ABC) algorithm. In the centralized approach, this hybrid method is executed on a single node while, in a distributed approach, it is executed in parallel on different nodes deployed in a wireless data collection network. This study aims at enhancing the coverage rate in data collection networks utilizing less sensor nodes. The Delaunay Triangulation diagram is utilized to produce solutions showing the first locations of the IoT objects. Then, the Artificial Bee Colony algorithm is used to improve the node deployment coverage rate. The developed DTABC approach performance is assessed experimentally by prototyping M5StickC nodes on a real testbed. The obtained results reveal that the coverage rate, the number of the objects’ neighbors, the RSSI and the lifetime of the distributed approach are better than those of the algorithms introduced in previous research works.
... According to the literature, to overcome the afore-mentioned limitations and enhance the application of hybrid ML paradigms, this research suggests a high-performance ML solution for predicting the CS of cement containing MK. To this end, enhanced GWO (EGWO), proposed by Joshi et al. [27], was employed to optimize the weights and biases of ELM. EGWO is an augmented form of the classic GWO. ...
... However, this approach ignored the importance of striking the appropriate balance between the two activities in order to arrive at a close approximation of the global optimum. Thus, to solve the problem, Joshi and Arora [27] proposed EGWO, in which the a was set to be random between [0, 1], and hence, the a search agents were modified. According to the study of Joshi and Arora [27], the hunting mechanism is given by: ...
... Thus, to solve the problem, Joshi and Arora [27] proposed EGWO, in which the a was set to be random between [0, 1], and hence, the a search agents were modified. According to the study of Joshi and Arora [27], the hunting mechanism is given by: ...
This research proposes a highly effective soft computing paradigm for estimating the compressive strength (CS) of metakaolin-contained cemented materials. The proposed approach is a combination of an enhanced grey wolf optimizer (EGWO) and an extreme learning machine (ELM). EGWO is an augmented form of the classic grey wolf optimizer (GWO). Compared to standard GWO, EGWO has a better hunting mechanism and produces an optimal performance. The EGWO was used to optimize the ELM structure and a hybrid model, ELM-EGWO, was built. To train and validate the proposed ELM-EGWO model, a sum of 361 experimental results featuring five influencing factors was collected. Based on sensitivity analysis, three distinct cases of influencing parameters were considered to investigate the effect of influencing factors on predictive precision. Experimental consequences show that the constructed ELM-EGWO achieved the most accurate precision in both training (RMSE = 0.0959) and testing (RMSE = 0.0912) phases. The outcomes of the ELM-EGWO are significantly superior to those of deep neural networks (DNN), k-nearest neighbors (KNN), long short-term memory (LSTM), and other hybrid ELMs constructed with GWO, particle swarm optimization (PSO), harris hawks optimization (HHO), salp swarm algorithm (SSA), marine predators algorithm (MPA), and colony predation algorithm (CPA). The overall results demonstrate that the newly suggested ELM-EGWO has the potential to estimate the CS of metakaolin-contained cemented materials with a high degree of precision and robustness.
... There may have been a lack of evaluation of the algorithms' scalability [41] Cuckoo Search Algorithm (CSA) Node positions are accurately determined [42] Grey wolf optimizer (GWO) The algorithm is applied to address the node localization problem in real-world scenarios ...
... In the paper [42], a novel Enhanced Grey Wolf Optimization (EGWO) algorithm is introduced, featuring an improved hunting mechanism that aims to strike an equilibrium between exploitation and exploration. To evaluate the efficiency of the suggested EGWO algorithm, it is benchmarked against twenty-five benchmark functions with varying complexities. ...
Node localization is a non-deterministic polynomial time (NP-hard) problem in Wireless Sensor Networks (WSN). It involves determining the geographical position of each node in the network. For many applications in WSNs, such as environmental monitoring, security monitoring, health monitoring, and agriculture, precise location of nodes is crucial. As a result of this study, we propose a novel and efficient way to solve this problem without any regard to the environment, as well as without predetermined conditions. This proposed method is based on new proposed Nutcracker Optimization Algorithm (NOA). By utilizing this algorithm, it is possible to maximize coverage rates, decrease node numbers, and maintain connectivity. Several algorithms were used in this study, such as Grey Wolf Optimization (GWO), Kepler Optimization Algorithms (KOA), Harris Hawks Optimizer (HHO), Radient-Based Optimizer (GBO) and Gazelle Optimization Algorithm (GOA). The node localization was first tested in Istanbul, Turkey, where it was determined to be a suitable study area. As a result of the metaheuristic-based approach and distributed architecture, the study is scalable to large-scale networks. Among these metaheuristic algorithms, NOA, KOA, and GWO have achieved significant performance in terms of coverage rates (CR), achieving coverage rates of 96.15%, 87.76%, and 93.49%, respectively. In terms of their ability to solve sensor node localization problems, these algorithms have proven to be effective.
... The traditional GWO algorithm uses a hierarchical ranking system of alpha ( ), beta ( ), deltas ( ), and omega ( ) wolves to search for the global minimum of a given function [31]. However, the traditional GWO algorithm has limitations, such as premature convergence, lack of balance between exploration and exploitation, and low population diversity [32]. An enhanced version of GWO is proposed to address these issues, incorporating a dimension learning-based hunting strategy (DLHS) and multineighbor learning. ...
This paper presents a novel approach for fault location estimation in Distributed Generation (DG) based microgrid that combines a decomposition technique for feature extraction and a machine learning-based method for fault location computation. A hybrid meta-heuristic optimized-based KELM (HMOKELM) framework is implemented to improve the efficiency of the proposed scheme. Here, an energy-based strategy is used to extract the differential energy (DE) content of the three-phase signal through the ensemble averaging decomposition method. Then, a feature matrix is created using different features of the DE signal which is fed as input to the HMOKELM for fault location estimation. However, the proposed approach is tested in IEC-based standard microgrid model under MATLAB /SIMULINK environment. Further, different fault conditions, microgrid structures, and modes of operation are considered as a case study. Thereafter, the results are analyzed and extensively compared with other techniques to demonstrate the effectiveness and reliability of the proposed strategy.
... A comparison between the original DE and the Success-History-based Adaptive DE (SHADE), a stateof-the-art DE algorithm, illustrates the superiority of the proposed approach for most of the considered functions. Joshi and Arora (2017) introduced an Enhanced Grey Wolf Optimization (EGWO) algorithm, which incorporates an improved hunting mechanism compared to the original Grey Wolf Optimization (GWO). This enhancement effectively balances exploration and exploitation, optimizing the algorithm's performance and generating promising candidate solutions. ...
Real-world optimization problems are ubiquitous across scientific domains, and many engineering challenges can be reimagined as optimization problems with relative ease. Consequently, researchers have focused on developing optimizers to tackle these challenges. The Snake Optimizer (SO) is an effective tool for solving complex optimization problems, drawing inspiration from snake patterns. However, the original SO requires the specification of six specific parameters to operate efficiently. In response to this, enhanced snake optimizers, namely ESO1 and ESO2, were developed in this study. In contrast to the original SO, ESO1 and ESO2 rely on a single set of parameters determined through sensitivity analysis when solving mathematical functions. This streamlined approach simplifies the application of ESOs for users dealing with optimization problems. ESO1 employs a logistic map to initialize populations, while ESO2 further refines ESO1 by integrating a Lévy flight to simulate snake movements during food searches. These enhanced optimizers were compared against the standard SO and 12 other established optimization methods to assess their performance. ESO1 significantly outperforms other algorithms in 15, 16, 13, 15, 21, 16, 24, 16, 19, 18, 13, 15, and 22 out of 24 mathematical functions. Similarly, ESO2 outperforms them in 16, 17, 18, 22, 23, 23, 24, 20, 19, 20, 17, 22, and 23 functions. Moreover, ESO1 and ESO2 were applied to solve complex structural optimization problems, where they outperformed existing methods. Notably, ESO2 generated solutions that were, on average, 1.16%, 0.70%, 2.34%, 3.68%, and 6.71% lighter than those produced by SO, and 0.79%, 0.54%, 1.28%, 1.70%, and 1.60% lighter than those of ESO1 for respective problems. This study pioneers the mathematical evaluation of ESOs and their integration with the finite element method for structural weight design optimization, establishing ESO2 as an effective tool for solving engineering problems.
... GWO has developed as a potential way out to many optimization issues in recent years by simulating leadership hierarchy as well as group hunting behaviour in GW's [22][23][24][25]. Since the inception of GWO, several versions of methods for accelerating convergence while minimizing local optimums have been developed [26][27][28]. This paper suggested a novel form of GWO called G-GWO that uses GA to construct a significantly more suitable beginning population. ...
... The DME, DR, and GA image datasets IDRiD [29], DR-HAGIS [30], and ODIR [31] are utilized in this work to assess the model's successiveness. Extensive quantitative results performed on DED image datasets demonstrated the effectiveness of the G-GWO approach in terms of the Jaccard coefficient along with Jaccard loss, Sensitivity, accuracy, Specificity, and Precision when compared to the GA [32], PSO, GWO [21], Modified GWO (mGWO) [26], Enhanced [27] and incremental [28] GWO. We evaluate the segmentation performance of the hyperparameter-optimized FCEDN model based on G-GWO on the same dataset as other recently created segmentation networks, including Link-Net, U-Net, Seg-Net, as well as FCN. ...
... This study introduces a novel algorithm based on GWO [22], which simulates the social and hunting behaviour of GWs. Several GWO variants have been proposed, including MGWO [44], EGWO [27], RL-GWO [45], Ex-GWO, and Incremental Grey Wolf Optimizer [25]. ...
In the emerging field of image segmentation, Fully Convolutional Networks (FCNs) have recently become prominent. However, their effectiveness is intimately linked with the correct selection and fine-tuning of hyperparameters, which can often be a cumbersome manual task. The main aim of this study is to propose a more efficient, less labour-intensive approach to hyperparameter optimization in FCNs for segmenting fundus images. To this end, our research introduces a hyperparameter-optimized Fully Convolutional Encoder-Decoder Network (FCEDN). The optimization is handled by a novel Genetic Grey Wolf Optimization (G-GWO) algorithm. This algorithm employs the Genetic Algorithm (GA) to generate a diverse set of initial positions. It leverages Grey Wolf Optimization (GWO) to fine-tune these positions within the discrete search space. Testing on the Indian Diabetic Retinopathy Image Dataset (IDRiD), Diabetic Retinopathy, Hypertension, Age-related macular degeneration and Glacuoma ImageS (DR-HAGIS), and Ocular Disease Intelligent Recognition (ODIR) datasets showed that the G-GWO method outperformed four other variants of GWO, GA, and PSO-based hyperparameter optimization techniques. The proposed model achieved impressive segmentation results, with accuracy rates of 98.5% for IDRiD, 98.7% for DR-HAGIS, and 98.4%, 98.8%, and 98.5% for different sub-datasets within ODIR. These results suggest that the proposed hyperparameter-optimized FCEDN model, driven by the G-GWO algorithm, is more efficient than recent deep-learning models for image segmentation tasks. It thereby presents the potential for increased automation and accuracy in the segmentation of fundus images, mitigating the need for extensive manual hyperparameter adjustments.
... Joshi, H., Arora, S. [23] (2017) introduced a Grey Wolf Optimizer improvement modeled after how grey wolves hunt in nature. The proposed algorithm modifies the first three steps involved in the method of hunting existing GWO, namely tracking, pursuing, and a predator assault. ...
Human face expression Recognition is one of the most effective forms of social communication. Generally, facial expressions are a simple and obvious way for people to express their feelings and intentions. Typically, the goal of facial expression recognition is to categorize facial expressions into specific classes of expression labels. This paper presents a survey of facial emotion expression classification based on different machine learning and deep learning mechanisms and optimization algorithms. In order to evaluate the basic emotion of a person's face, a technology called facial expression recognition employs a computer as a helper with specific algorithms. Seven basic emotions were represented by facial expressions, including a smile, sadness, anger, disgust, surprise, fear, and a natural expression. In this paper, the focus is on using the Grey Wolf algorithm for selection of the optimal features from feature extraction from input image faces to recognize human facial emotions. In most studies, the FER system was applied to popular datasets such as the JAFEE database and the Cohn-Kanade database.
... Here, we compare the performance of NSCA with several other well-known swarm intelligence optimization algorithms. Specifically, we consider SCA [12], OBSCA [20], HISCA [26], ISCA [34], GWO [35], AGWO [36], EGWO [37], MFO [38], WOA [39], and OWOA [40]. These algorithms have been extensively studied and have shown good performance in solving complex numerical optimization problems in various engineering fields [41][42][43][44][45][46][47][48]. ...
The sine cosine algorithm (SCA) is a simple and efficient optimization algorithm that utilizes sine and cosine trigonometric functions to update solutions. The SCA may suffer from premature convergence to local optima due to its insufficient utilization of population information and lack of mechanism to escape from local optima. Therefore, this study proposes an improved version of the SCA called the novel sine cosine algorithm (NSCA). NSCA incorporates a new solution update equation, a greedy selection mechanism, and a disturbance mechanism to improve population diversity and prevent search stagnation. Experimental results on the Congress on Evolutionary Computation (CEC) 2017 benchmark function set and six point cloud registration problems demonstrate the effectiveness and robustness of NSCA compared to other algorithms.
