Utilization of Random Vector Functional Link integrated with Marine Predators Algorithm for tensile behavior prediction of dissimilar friction stir welded aluminum alloy joints

Elaziz, Mohamed Abd; Shehabeldeen, Taher A.; Elsheikh, Ammar H.; Zhou, Jianxin; Ewees, Ahmed A.; Al-qaness, Mohammed A. A.

doi:10.1016/j.jmrt.2020.08.022

Cited by 73 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…algorithms for the MLT approach for image segmentation by proposing a hybrid approach MPAMFO that combines MPA with MFO. In [69] [109] combined (MPA) with Random Vector Functional Link (RVFL) network to improve the prediction accuracy of tensile elongation (T.E.) and ultimate tensile strength (UTS).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Combine metaheuristic algorithms with K-NN [51] GA-ANN for FS approaches [52] hybrid approach with GA [53] PSO [54] PSO with C4.5 [55] PSO with a multiple inertia weight strategy (CBPSO-MIWS) [8] binary WOA [26] binary variants of the WOA [57] GWO [24] HHO-SVM and HHO-kNN [58] Salp swarm Algorithm ISSAFD [59] SSA-RWN [62] GA-PSO [56] GWO -PSO [60] BBA-PSO [66] ANFIS-MPA [67] CNN-MPA [68] MFO-MPA [69] RVFL-MPA [64] ANFIS-MPA [63] a multiple SI algorithms [70] ANFIS-MPA…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Marine Predators Algorithm for Feature Selection

et al. 2021

View full text Add to dashboard Cite

Feature Selection (F.S.) reduces the number of features by removing unnecessary, redundant, and noisy information while keeping a relatively decent classification accuracy. F.S. can be considered an optimization problem. As the problem is challenging and there are many local solutions, stochastic optimization algorithms may be beneficial .This paper proposes a novel approach to dimension reduction in feature selection. As a seminal attempt, this work uses binary variants of the recent Marine Predators Algorithm (MPA) to select the optimal feature subset to improve classification accuracy. MPA is a new and novel nature-inspired metaheuristic. This research proposes an algorithm that is a hybridization between MPA and k-Nearest Neighbors (k-NN) called MPA-KNN. k-Nearest Neighbors (k-NN) is used to evaluate the selected features on medical datasets with feature sizes ranging from tiny to massive. The proposed methods are evaluated on 18 well-known UCI medical dataset benchmarks and compared with eight well-regarded metaheuristic wrapper-based approaches. The core exploratory and exploitative processes are adapted in MPA to select the optimal and meaningful features for achieving the most accurate classification. The results show that the proposed MPA-KNN approach had a remarkable capability to select the optimal and significant features. It performed better than the well-established metaheuristic algorithms we tested. The algorithms we used for comparison are Grey Wolf Optimizer (GWO), MothFlame Optimization Algorithm (MFO), Sine Cosine Algorithm (SCA), Whale Optimization Algorithm (WOA), Slap Swarm Algorithm (SSA), Butterfly Optimization Algorithm (BFO), and Harris Hawks Optimization (HHO). This paper is the first work that implements MPA for Feature Selection problems. The results ensure that the proposed MPA-KNN approach has a remarkable capability to select the optimal and significant features and performed better than several metaheuristic algorithms. MPA-KNN achieves the best averages accuracy, Sensitivity, and Specificity rates of all datasets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

An Efficient Marine Predators Algorithm for Feature Selection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As a conclusion, GF could be used to enhance the mechanical properties of PP, and rubber powder could be used to enhance the elongation of the developed composite with fewer side effects on the ultimate tensile strength. Moreover, it is recommended to apply advanced machine learning techniques, such as the artificial neural network (Elsheikh et al, 2020a(Elsheikh et al, , 2019bKhoshaim et al, 2021a), support vector machine (El-Said et al, 2021), long short-term memory network (Elsheikh et al, 2021;Saba and Elsheikh, 2020), adaptive neuro-fuzzy inference system (Elaziz et al, 2019;Shehabeldeen et al, 2019), and random vector functional link (Abd Elaziz et al, 2020;Shehabeldeen et al, 2020), to predict the mechanical properties of the developed composite.…”

Section: Tensile Testmentioning

confidence: 99%

The effect of rubber powder additives on mechanical properties of polypropylene glass-fiber-reinforced composite

et al. 2021

Self Cite

View full text Add to dashboard Cite

Abstract. Reinforced thermoplastic composites offer considerable advantages in structural and industrial applications in terms of high specific strength, excellent corrosion resistance, high impact toughness, high specific stiffness, recyclability, cost effectiveness, and design flexibility. Glass fibers (GFs) are the reinforcement material used in polypropylene (PP) composites to enhance PP properties with reasonable cost. To obtain better mechanical properties and decrease the overall cost, recycled rubber powder was used as a low-cost additive to PP/GF composites. The PP and GF, with different weight fractions, were mixed mechanically; then, the mixture was fed into injection molding machine. The PP/GF composites with the highest mechanical properties were selected for further improvements using rubber powder. The obtained samples were tested using tension, impact, and wear tests. The results show that tensile strength of PP/GF composite was improved by 17.8 % by adding 15 wt % GF, and there was a huge drop in impact strength by 80 % for the same GF weight fraction (15 wt %) compared to that of pure PP because of existence of GF. Wear properties and impact strength were improved by adding rubber powder to the composite, with a low weight fraction of 5 wt %, due to the shock-absorbing properties of rubber powder. Micrographs of the fractured sample surfaces revealed the good adhesion between the GF, PP, and the rubber particles.

show abstract

“…The input layer's fundamental weight values provided to the hidden layer can be randomly created in the appropriate domain and retained during the learning process to avoid becoming stuck in a local minimum. RVFL applications are used to optimize many scientific areas applications, including performance predictions of solar photovoltaic thermal collectors [9], crude-oil price forecasting [10], and tensile behavior prediction of dissimilar friction stirwelded aluminum alloy joints [11].…”

Section: Introductionmentioning

confidence: 99%

Android malware classification based on random vector functional link and artificial Jellyfish Search optimizer

2021

View full text Add to dashboard Cite

Smartphone usage is nearly ubiquitous worldwide, and Android provides the leading open-source operating system, retaining the most significant market share and active user population of all open-source operating systems. Hence, malicious actors target the Android operating system to capitalize on this consumer reliance and vulnerabilities present in the system. Hackers often use confidential user data to exploit users for advertising, extortion, and theft. Notably, most Android malware detection tools depend on conventional machine-learning algorithms; hence, they lose the benefits of metaheuristic optimization. Here, we introduce a novel detection system based on optimizing the random vector functional link (RVFL) using the artificial Jellyfish Search (JS) optimizer following dimensional reduction of Android application features. JS is used to determine the optimal configurations of RVFL to improve classification performance. RVFL+JS minimizes the runtime of the execution of the optimized models with the best performance metrics, based on a dataset consisting of 11,598 multi-class applications and 471 static and dynamic features.

show abstract

Utilization of Random Vector Functional Link integrated with Marine Predators Algorithm for tensile behavior prediction of dissimilar friction stir welded aluminum alloy joints

Cited by 73 publications

References 40 publications

An Efficient Marine Predators Algorithm for Feature Selection

An Efficient Marine Predators Algorithm for Feature Selection

The effect of rubber powder additives on mechanical properties of polypropylene glass-fiber-reinforced composite

Android malware classification based on random vector functional link and artificial Jellyfish Search optimizer

Contact Info

Product

Resources

About