Bio-inspired Computational Intelligence Research Articles

A bio-inspired computational classifier system for the evaluation of children’s theatrical anxiety at school

Theatrical performance constitutes a complicated way for students to express and to communicate with each other, since it targets both various artistic and educational goals. Even though it constitutes a top moment of students’ expression, several students do not feel comfortable when participating in such cultural activities, as performance anxiety, a negative emotional experience stemming from the public audience exposure, affects them. The aim of this research is to apply and evaluate a student segmentation technique with the help of bio-inspired computational intelligence, for identifying high levels of performance anxiety at schoolchildren. A Mayfly-based clustering optimization algorithm is applied on a dataset with 774 instances of students to classify them according to their levels of emotions and performance anxiety that are developed during the event. A comparison with a genetic algorithm as well as particle swarm optimization shows that the proposed method is distinguished by superior categorization capabilities. The findings demonstrate the effective dissimilar student groups formation, with the members of each being distinguished by similar characteristics in terms of emotions and performance anxiety, highlighting the ones with unmanageable emotional experiences. Therefore, the drama educator is able to effortlessly detect, manage students and develop coping practices in those at risk, by acknowledging each group’s characteristics.

Virtual Modeling and Immersive Holographic Imaging Technologies, Cloud-based Digital Twin Manufacturing and Visual Perceptive Systems, and Bio-inspired Computational Intelligence and Context Awareness Algorithms in the Industrial Metaverse

Virtual Modeling and Immersive Holographic Imaging Technologies, Cloud-based Digital Twin Manufacturing and Visual Perceptive Systems, and Bio-inspired Computational Intelligence and Context Awareness Algorithms in the Industrial Metaverse

Bio-inspired Computational Intelligence and Deep Learning Algorithms, 3D Modeling and Cognitive Neuro-Engineering Technologies, and Immersive Visualization and Internet of Things-based Decision Support Systems in the Virtual Environment of the Metaverse

Bio-inspired Computational Intelligence and Deep Learning Algorithms, 3D Modeling and Cognitive Neuro-Engineering Technologies, and Immersive Visualization and Internet of Things-based Decision Support Systems in the Virtual Environment of the Metaverse

Multi-Modal Synthetic Data Fusion and Analysis, Virtual Immersive and Cognitive Neuro-Engineering Technologies, and Bio-inspired Computational Intelligence and Deep Learning Algorithms in the Industrial Metaverse

Multi-Modal Synthetic Data Fusion and Analysis, Virtual Immersive and Cognitive Neuro-Engineering Technologies, and Bio-inspired Computational Intelligence and Deep Learning Algorithms in the Industrial Metaverse

Energy optimized hybrid PSO and wolf search based LEACH

In wireless sensor networks (WSN), computational challenges exist in determining a global energy optimized communication routing in large spaced network. WSN challenges can be handled by applying heuristic bio-inspired computational intelligence optimization methods. In WSN, Low Energy Adaptive Clustering Hierarchy (LEACH) algorithm is most frequently used hierarchical routing algorithm in spite of certain limitations. The proposed work is addressed in this direction, to improve issues of LEACH, such as identification of reliable CH, selection of energy efficient inter and intra route communication using relay nodes, so as to extend the network lifespan. The proposed work applies Particle Swarm Optimization (PSO) and Wolf Search optimization methods to improve the performance of LEACH algorithm. PSO is castoff for cluster formation and Wolf search for identification of two relay nodes: intra and inter relay node. The Spyder-py3 tool is used to simulate the proposed algorithm: LEACH PSO Wolf search based Optimization (LEACH-PWO). The proposed work compared with original LEACH, power-efficient gathering in sensor information systems, Ant Cuckoo optimized using energy-efficient data aggregation, and Genetic Algorithm data Aggregation LEACH protocols indicate prolonged lifetime of network and increased throughput.

Analysis of Binary and Discrete Grey Wolf Optimization Algorithms Applied for Enhancing Performance of Energy Efficient Low Energy Adaptive Clustering Hierarchy

Wireless sensor networks (WSN) are a yield of advancement in information technology and the requirement of large-scale communication infrastructures. Routing of data via selected paths is a critical task in WSN as process need to be carried on under resource constraint situations. This route identification problem can be better handled by employing appropriate heuristic bio-inspired computational intelligence optimization method. The most frequently applied routing is hierarchical routing algorithm is Low Energy Adaptive Clustering Hierarchy (LEACH) algorithm which has limitations in identifying energy efficient inter and intra route communication, identification of number of cluster head (CH), an eminent node to communicate to CH and Base Station (BS), selection of CH, and computing residual energy level, etc. Hence, researchers are focusing on boosting the capability of LEACH clustering algorithm by applying heuristic bio-inspired computational intelligence optimization methods. The proposed work is an attempt in this direction through applying heuristic bio-inspired Grey Wolf Optimization algorithm (GWO) for improving the performance of LEACH algorithm. In this paper, focus is given to increase the overall network time by adapting two modifications to conventional algorithms (i) selection of vice cluster head (VCH) in addition to CH (VCH node will replace the CH when CH when CH node goes down due to unexpected reasons as sensor node work under critical and uninterruptable environments and (ii) selection of intra and inter relay nodes (intra relay node will enhance the life span during CH data gathering and inter relay node will further enhance the life span of CH by acting as a mediator between CH an BS). The Spyder-py3 tool is used to simulate the proposed algorithms, LEACH Binary Grey Wolf search based Optimization (LEACH-BGWO) and LEACH Discrete Grey Wolf search based Optimization (LEACH-DGWO) protocols. The proposed work is compared with cluster based LEACH algorithm, chain based power-efficient gathering in sensor information systems (PEGASIS) algorithm, bio-inspired GWO and Genetic Algorithm data Aggregation (GADA) LEACH protocols. The results prove that both proposed algorithms outperformed other conventional algorithms in terms of prolonged network lifespan and increased throughput. Among proposed algorithms LEACH-BGWO outperformed LEACH-DGWO

Numerical solution of doubly singular nonlinear systems using neural networks-based integrated intelligent computing

In this paper, a bio-inspired computational intelligence technique is presented for solving nonlinear doubly singular system using artificial neural networks (ANNs), genetic algorithms (GAs), sequential quadratic programming (SQP) and their hybrid GA–SQP. The power of ANN models is utilized to develop a fitness function for a doubly singular nonlinear system based on approximation theory in the mean square sense. Global search for the parameters of networks is performed with the competency of GAs and later on fine-tuning is conducted through efficient local search by SQP algorithm. The design methodology is evaluated on number of variants for two point doubly singular systems. Comparative studies with standard results validate the correctness of proposed schemes. The consistent correctness of the proposed technique is proven through statistics using different performance indices.

Bio-inspired computational heuristics to study the boundary layer flow of the Falkner-Scan system with mass transfer and wall stretching

In the present study, a bio-inspired computational intelligence technique is developed for finding the solutions of the celebrated Falkner-Skan equation arising in fluid mechanics problems using feed-forward Artificial Neural Networks (ANNs), Genetic Algorithms (GA), the Active-Set (AS) method and their combination namely a GA-AS approach. The differential equations based ANNs modeling of the Falkner-Skan system is constructed by defining an unsupervised error function. The training of the design parameters of ANNs is carried out with the help of viable global search through GAs and fine tuning of the results is achieved with an efficient local search using the AS method. The proposed scheme is applied to a number of scenarios for the Falkner-Skan system based on boundary layer flow over a moving wall with mass transfer in the presence of a free stream with power-law velocity distributions. The dynamics of the system are investigated for different cases of mass transfer and wall stretching. The proposed results are compared with analytical and numerical solutions to verify the correctness of the approach. The accuracy and convergence of the proposed solver are validated through sufficient large numbers of independent runs in terms of different performance indices based on mean absolute error, Thail’s inequality coefficient and Nash-Suitcliff efficiency. These solutions greatly enrich possible approaches for stochastic numerical solution of the celebrated Falkner-Skan system.

Computational intelligence methodology for the analysis of RC circuit modelled with nonlinear differential order system

In this study, we solve nonlinear initial value problems arising in circuit analysis by applying bio-inspired computational intelligence technique using feed-forward artificial neural networks (ANNs) optimized with genetic algorithms (GAs), sequential quadratic programming (SQP), and their combined scheme. The system of resister–capacitor (RC) circuit having nonlinear capacitance is mathematically modelled with unsupervised ANNs by defining an energy function in mean-square error (MSE) sense. The objectives are to minimize the MSE for which the parameters of the networks are estimated initially with GA-based global search and in steady state with SQP algorithm for efficient local search. We consider a set of scenarios to evaluate the performance of the proposed scheme for different resistance and capacitance values along with current variations in the nonlinear RC circuit system. The results are compared with well-established fully explicit Runge–Kutta numerical solver in order to verify the accuracy of the applied bio-inspired heuristics. To prove the worth of the scheme, a comprehensive statistical analysis is provided for the performance metrics based on root MSE, mean absolute error, Theil’s inequality coefficient, Nash–Sutcliffe efficiency, variance account for, and the coefficient of determination (R 2).

An intelligent computing technique to analyze the vibrational dynamics of rotating electrical machine

In this study, bio-inspired computational intelligence is exploited to analyze the nonlinear vibrational dynamics of rotating electrical machine (VD-REM) model by applying artificial neural networks (ANNs), genetic algorithms (GAs) and active-set methods (ASMs). The superintended mathematical relation of VD-REM is modeled with ANNs by employing an unsupervised error function. Design parameters of the networks are trained with meta-heuristic approach based on GAs, used as a tool for effective global search method, hybrid with ASM for efficient local search. The design scheme is evaluated for VD-REM models by taking different values of shaft stiffness along with an amplitude of force and parametric excitations. The performance of the proposed scheme is validated through the comparison of results from Adam numerical method with the help of different measures based on mean absolute derivation, root mean square error, and Nash-Sutcliffe efficiency.

Detecting invasive species with a bio-inspired semi-supervised neurocomputing approach: the case of Lagocephalus sceleratus

The need to protect the environment and biodiversity and to safeguard public health require the development of timely and reliable methods for the identification of particularly dangerous invasive species, before they become regulators of ecosystems. These species appear to be morphologically similar, despite their strong biological differences, something that complicates their identification process. Additionally, the localization of the broader space of dispersion and the development of invasive species are considered to be of critical importance in the effort to take proper management measures. The aim of this research is to create an advanced computational intelligence system for the automatic recognition, of invasive or another unknown species. The identification is performed based on the analysis of environmental DNA by employing machine learning methods. More specifically, this research effort proposes a hybrid bio-inspired computational intelligence detection approach. It employs extreme learning machines combined with an evolving Izhikevich spiking neuron model for the automated identification of the invasive fish species “Lagocephalus sceleratus” extremely dangerous for human health.

Bio-inspired optimal site selection of LPG stations for gas-driven cars in an urban region

Siting new liquefied petroleum gas (LPG) stations in a metropolitan region to support the initiative of air pollution control is intimately tied to where these LPG stations are located for filling up those vehicles. Unlike traditional siting and routing problems, the LPG stations must be sited to serve the consumers with the highest mobility instead of meeting the regular consumers’ demand. To optimize the spatial allocation of LPG stations in an intelligent transportation network with consideration of the economies of scale, this study presents a bio-inspired computational intelligence algorithm based on the gravity model to express the behavior of drivers in search of a set of neighboring LPG stations. The practical implementation of the proposed method was evaluated using a real-world case study, in which the planning objective is to minimize the expected distance for fueling vehicles. A Monte Carlo simulation is performed to determine the effect of the uncertainty that is caused by the mobility of LPG cars and parameters in the gravity model on the optimal results. The results reveal that the optimal number of LGP stations in the case study is approximately 15, and the minimized expected distance for fueling is 2500 m. The proposed method is useful when the behavior of customers cannot be ignored in siting problems.

Design of bio-inspired computational intelligence technique for solving steady thin film flow of Johnson–Segalman fluid on vertical cylinder for drainage problems

In the present study, bio-inspired computing technique is designed for solving governing mathematical relation for steady thin film flow of Johnson–Segalman fluid on vertical cylinder for drainage problems using Artificial Neural Networks (ANNs), genetic algorithms (GAs) and active-set algorithm (ASA). The strength of ANN modeling is exploited for the transformed equation of drainage problem which is derived from original partial differential equation using similarity transform. Training of design parameter of ANNs is carried out with evolutionary computing approach based on GAs hybrid with ASA for rapid local convergence. Design scheme is evaluated for number of cases of all four scenarios of drainage problem based on variations in Stokes number, Weissenberg number, ratio of viscosities, and slip parameters. Comparison of the results is made with Adams numerical method for each case in order to validate the accuracy of the proposed scheme. Results of statistical analysis in terms of performance measures based on mean, standard deviation, mean absolute deviation, root mean square error and Nash–Sutcliffe efficiency as well as their global variations further established the worth of the given scheme for each variant of drainage problem.

Diagnosis of the artificial intelligence-based predictions of flow regime in a constructed wetland for stormwater pollution control

Monitoring the velocity field and stage variations in heterogeneous aquatic environments, such as constructed wetlands, is critical for understanding hydrodynamic patterns, nutrient removal capacity, and hydrographic impact on the wetland ecosystem. Obtaining low velocity measurements representative of the entire wetland system may be challenging, expensive, and even infeasible in some cases. Data-driven modeling techniques in the computational intelligence regime may provide fast predictions of the velocity field based on a handful of local measurements. They can be a convenient tool to visualize the general spatial and temporal distribution of flow magnitude and direction with reasonable accurancy in case regular hydraulic models suffer from insufficient baseline information and longer run time. In this paper, a comparison between two types of bio-inspired computational intelligence models including genetic programming (GP) and artificial neural network (ANN) models was implemented to estimate the velocity field within a constructed wetland (i.e., the Stormwater Treatment Area in South Florida) in the Everglades, Florida. Two different ANN-based models, including back propagation algorithm and extreme learning machine, were used. Model calibration and validation were driven by data collected from a local sensor network of Acoustic Doppler Velocimeters (ADVs) and weather stations. In general, the two ANN-based models outperformed the GP model in terms of several indices. Findings may improve the design and operation strategies for similar wetland systems.

Particle Swarm Optimisation Aided MIMO Multiuser Transmission Designs

Bio-inspired computational methods have found wide-ranging applications in signal processing and other walks of engineering. The main attraction of adopting bio-inspired computational intelligence algorithms is that they may facilitate global or near global optimal designs with affordable computational costs. In this contribution, particle swarm optimisation (PSO) is invoked for designing optimal multiuser transmission (MUT) schemes for multiple-input multiple-output communication. Specifically, we consider the minimum bit-error-rate (MBER) linear MUT using PSO and we design a PSO aided MBER generalised vector precoding for nonlinear MUT. These PSO aided MUT techniques compare favourably with the state-of-the-art conventional schemes, in terms of performance and complexity.

Market segmentation of organ donors in Egypt: a bio-inspired computational intelligence approach

First performed in 1954, organ transplantation is a universally practiced clinical procedure. This study uses ant colony optimization (ACO), radial basis function neural network (RBFNN), Kohonen’s self-organizing maps (SOM), and support vector machines (SVMs) to examine the effect of various cognitive, psychographic, and attitudinal factors on organ donation. ACO, RBFNN, SOM, and SVMs are compared to a standard statistical method (linear discriminant analysis [LDA]). The variable sets considered are altruistic values, perceived risks/benefits, knowledge, attitudes toward organ donation, and intention to donate organs. The paper shows how it is possible to identify various dimensions of organ donation behavior by uncovering complex patterns in the dataset and also shows the classification and clustering abilities of machine-learning systems.