Nature-inspired Optimization Technique Research Articles

An improved multi-strategy Golden Jackal algorithm for real world engineering problems

The Golden Jackal Optimization (GJO) algorithm is a novel, nature-inspired optimization technique that has gained recognition as a highly promising metaheuristic due to its notable efficiency and adaptability. However, the GJO algorithm possesses several shortcomings, including inadequate exploitation ability, vulnerability to local optima, and imbalanced exploration-exploitation. Therefore, this paper presents an enhanced version of the named mGJO, tailored explicitly for addressing real-world engineering and feature selection problems. The mGJO incorporates four improvements to the standard GJO. To begin with, Chaos-OBL (COBL) based population initialization is proposed to increase diversity in population. Secondly, a nonlinear control parameter is proposed to regulate the exploration-exploitation transition. Thirdly, the original updating rule of GJO is combined with the ESQ mechanism to prevent the leader solutions from influencing the local optimal solutions. Finally, a new adaptive mutation strategy is presented to alter individuals and improve positions based on their fitness. To evaluate the efficiency of the suggested mGJO is assessed using CEC2005, CEC2017, CEC2020 and CEC2022 benchmark functions. The proposed mGJO is also applied to five common real-world engineering problems and is also applied to the feature selection problems to assess its performance. Furthermore, the proposed mGJO is compared with various advanced algorithms to evaluate its performance. Statistical analyses, including the Friedman rank test and Wilcoxon test, are applied to the experimental data to validate the superiority of the extracted results. The experimental results and the statistical analysis indicate the superiority of mGJO in terms of convergence rate, solution quality, and optimization accuracy.

Deep convolutional neural network framework with multi-modal fusion for Alzheimer’s detection

The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools. The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients. In this study, we integrated a lightweight custom convolutional neural network (CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology, which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by 2-5%. In conclusion, a customized lightweight CNN model and nature-inspired optimization techniques can significantly enhance progress detection, leading to better biomedical research and patient care.

An Optimum Load Forecasting Strategy (OLFS) for Smart Grids Based on Artificial Intelligence

Recently, the application of Artificial Intelligence (AI) in many areas of life has allowed raising the efficiency of systems and converting them into smart ones, especially in the field of energy. Integrating AI with power systems allows electrical grids to be smart enough to predict the future load, which is known as Intelligent Load Forecasting (ILF). Hence, suitable decisions for power system planning and operation procedures can be taken accordingly. Moreover, ILF can play a vital role in electrical demand response, which guarantees a reliable transitioning of power systems. This paper introduces an Optimum Load Forecasting Strategy (OLFS) for predicting future load in smart electrical grids based on AI techniques. The proposed OLFS consists of two sequential phases, which are: Data Preprocessing Phase (DPP) and Load Forecasting Phase (LFP). In the former phase, an input electrical load dataset is prepared before the actual forecasting takes place through two essential tasks, namely feature selection and outlier rejection. Feature selection is carried out using Advanced Leopard Seal Optimization (ALSO) as a new nature-inspired optimization technique, while outlier rejection is accomplished through the Interquartile Range (IQR) as a measure of statistical dispersion. On the other hand, actual load forecasting takes place in LFP using a new predictor called the Weighted K-Nearest Neighbor (WKNN) algorithm. The proposed OLFS has been tested through extensive experiments. Results have shown that OLFS outperforms recent load forecasting techniques as it introduces the maximum prediction accuracy with the minimum root mean square error.

Optimal management strategies of renewable energy systems with hyperexponential service provisioning: an economic investigation

The current research proposes optimal management strategies for queueing modeling-based renewable energy systems with hyper-exponentially distributed maintenance/repair under the assumption of an admission control policy. Using the concept and steps of the matrix-analytical method, the steady-state probability distribution associated with energy systems is explicitly presented. A relatively straightforward computation that can help with modeling wind energy generation, investigating wind farm performance, optimizing energy based on system storage, reliability inspection, service maintenance planning, and numerous other purposes can be employed to mathematically derive several system performance indicators. The investigation findings are validated via quantitative outcomes, illustrative possesses, and a step-by-step recursive methodology for efficient management of the renewable energy system. Additionally, considering multiple governing parameter values, the nature-inspired optimization technique, Cuckoo Search (CS), is employed to demonstrate the optimum anticipated cost of renewable energy system. A comparison with other metaheuristics and semi-classical approaches is also presented to establish the best convergence results. In order to help system designers, policymakers, engineers, and researchers, several numerical examples are also provided to construct more practical strategies based on the production of energy, storage, and system management. The economic, parametric, and performance investigation findings are highlighted, and the opportunities and recommendations for further research are provided. In a nutshell, the outcomes of the present analysis can be adopted to formulate the most effective economic strategies and regulate decision-making processes in the energy sectors.

Nonsteroidal anti-inflammatory drug solubility optimization through green chemistry solvent: Artificial intelligence technique

This research paper presents a comprehensive thermodynamic and heat transfer study on predicting the ternary solubility of Nystatin in SC-CO2-Ethanol (supercritical CO2 and ethanol). The employed process is a thermal-based green processing for preparation of solid nanoparticles. The data collection, consisting of temperature and pressure as input features and ternary solubility as the target variable, was used to train and evaluate four different machine learning algorithms: Random Forest (RF), Extra Trees (ET), NU-SVR, and EPSILON-SVR. The hyper-parameter tuning process employed the Bat Optimization Algorithm (BA), a nature-inspired optimization technique to fine-tune the models and enhance their predictive capabilities. The ET model had a notable R2 score of 0.98526, RMSE of 2.48774E-02, and MAE of 2.13417E-02. The RF model also yielded strong performance, achieving an R2 score of 0.98436, RMSE of 2.55130E-02, and MAE of 2.06314E-02. However, the NU-SVR model exhibited superior performance compared to other models, as evidenced by its remarkable R2 score of 0.99943, thereby showcasing its exceptional precision. The RMSE and MAE for NU-SVR were 4.92372E-03 and 3.94943E-03, respectively, underscoring its precision in predicting ternary solubility. The EPSILON-SVR model, while still respectable, obtained a score of 0.93574 in terms of R2, RMSE of 4.37434E-02, and MAE of 3.79800E-02.

Application of Bat Algorithm for Data Anonymization

The rapid proliferation of digital data has raised significant concerns regarding privacy and data security, necessitating the development of effective data anonymization techniques. This research presents a novel application of the Bat Algorithm (BA) for data anonymization, a nature-inspired optimization algorithm that mimics the echolocation behavior of Bats. The proposed approach leverages the BA's unique search capabilities to achieve a delicate balance between data utility and privacy preservation, a critical aspect in today's data-driven world. By treating data attributes as potential solutions and employing the BA's search process, the algorithm iteratively identifies and modifies sensitive attributes while minimizing information loss. This research contributes to the developing field of research on data anonymization by introducing a nature-inspired optimization technique that offers a promising alternative to traditional anonymization methods. Experimental results on various real-world datasets demonstrate the effectiveness of the proposed approach in achieving robust privacy protection while maintaining data quality, outperforming existing anonymization methods in terms of utility and computational efficiency. Furthermore, the proposed BA-based data anonymization approach exhibits versatility, scalability, and adaptability, making it suitable for diverse application domains, from healthcare and finance to social media and beyond. In summary, this study highlights the potential of the Bat Algorithm as a valuable tool in the field of data anonymization, offering a promising avenue for addressing the privacy challenges associated with the ever-expanding digital data landscape.

Improved Teaching Learning Algorithm with Laplacian operator for solving nonlinear engineering optimization problems

Teaching Learning Algorithm (TLA) is a recently developed nature-inspired optimization technique applicable to complex optimization problems. This paper proposes an improved TLA version using the Laplacian operator of the Genetic Algorithm (GA), named LX-TLA. The proposed algorithm is tested on benchmark optimization problems, including unimodal and multimodal problems. The numerical results are obtained in the form of objective function values, and a t-test is applied to compare the performance of LX-TLA and basic TLA. Convergence plots are given to provide insight into the convergence behavior of LX-TLA. The results reveal that proposed algorithm provides effective and efficient performance in solving benchmark test functions. The proposed algorithm is also applied to engineering design problems, such as Tuned Mass Damper (TMD), truss structure, welded beam, tension string, and pressure vessel. The results obtained using LX-TLA are compared with other nature-inspired optimization algorithms. The results demonstrate that the proposed algorithm is a robust and effective tool for solving complex optimization problems.

Identification of vulnerable selfish peer in P2P network using nature-inspired optimization techniques

Microservice is considered a distributed cloud native approach where a standalone application is composed of multiple loosely coupled and free-spirited deployable components in the form of peers. These peers are heterogeneous and autonomous by nature and behave according to their good interests. In a distributed environment, some peers subsidize others and could behave vulnerably or selfishly. These selfish peers severely affect the performance of the distributed P2P network if not addressed adequately. In distributed microservices applications, these selfish peers are addressed in two ways, i.e. Identification and Mitigation of the selfish peers. This study presents the AI-based approach towards identifying selfish peers in P2P microservices distributed networks with nature-inspired algorithms for feature selection. Efforts are also made to generate a real dataset SAMPARK followed by the standard procedure for the distributed P2P network. The developed hybrid feature selection (FS) technique composed of Grey-Wolf-Optimization (GWO) and Particle-Swarm-Optimization (PSO) is used for selecting the important feature subset. The feature selection technique combines AI-enabled techniques to develop six hybrid models for the identification of selfish peers in microservice networks. In experimentation, the effectiveness of all the proposed algorithms and models is found satisfactory, with an achieved maximum accuracy of 99.60% and outperforming other proposed approaches.

Multi-objective optimization in electrochemical micro-drilling of Ti6Al4V using nature-inspired techniques

ABSTRACT Current study investigates the efficacy of electrochemical micro-drilling (ECMD) process during micro-hole fabrication on a Ti6Al4V alloy sheet of 1.2 mm thickness using a cylindrical-shaped micro-tool. Ethylene glycol-based electrolyte was selected to overcome excessive passivation. Experiments were conducted by altering voltage, feed rate (FR), and electrolyte concentration (EC) using a central-composite-design to observe their effects on the output parameters. The desired response parameters, such as radial overcut (ROC), and taper were examined while fabricating dimensionally accurate micro-holes including the volume removal rate (VRR) that occurred during the process. ANOVA results established voltage as the major significant input parameter that affects all the responses, followed by FR. In addition, different nature-inspired optimization techniques, namely Multi-Objective Grey-Wolf Optimizer (MOGWO), Multi-Objective Bonobo Optimizer (MOBO), and Multi-Objective Particle Swarm Optimization (MOPSO), were employed. MOBO reported the best Pareto-surface in terms of uniformity and spread measures and suggested a FR of 0.3 μm/s for optimal micro-drilling operations.

Mathematical modeling, parameter identification, and electrical performance of a DSSC based on nature-inspired optimization techniques

The aim of this research is to achieve the highest efficiency for a dye-sensitized solar cell (DSSC) before the fabrication process. For DSSC efficiency improvement, six different optimization algorithms are used for the DSSC parameter extraction. The algorithms used are the genetic algorithm, grey wolf algorithm, dragonfly algorithm, moth flame algorithm, ant-lion algorithm, and whale algorithm, developed based on MATLAB coding. The physical parameters for the DSSC are the electron lifetime, electrode thickness, ideality factor, absorption coefficient, and diffusion coefficient. A comparative study is carried out among the six algorithms based on the highest efficiency and computational speed. Finally, a sensitivity analysis of environmental conditions (solar irradiance and temperature) and physical parameters is implemented and analyzed to simulate the DSSC performance for different values of these parameters. The DSSC parameters studied are short-circuit current density, open-circuit voltage, fill factor, and efficiency. The optimal electron lifetime is 100 ms, and the optimal thickness of the photoanode layer is 1 μm, reaching maximum efficiency equal to 11.79%.

Modified Firefly Optimization Algorithm-Based IDS for Nature-Inspired Cybersecurity

The new paradigm of nature-inspired cybersecurity can establish a robust defense by utilizing well-established nature-inspired computing algorithms to analyze networks and act quickly. The existing research focuses primarily on the efficient selection of features for quick and optimized detection rates using firefly and other nature-inspired optimization techniques. However, selecting the most appropriate features may be specific to the network, and a different set of features may work better than the selected one. Therefore, there is a need for a generalized pre-processing step based on the standard network monitoring parameters for the early detection of suspicious nodes before applying feature-based or any other type of monitoring. This paper proposes a modified version of the firefly optimization algorithm to effectively monitor the network by introducing a novel health function for the early detection of suspicious nodes. We implement event management schemes based on the proposed algorithm and optimize the observation priority list based on a genetic evolution algorithm for real-time events in the network. The obtained simulation results demonstrate the effectiveness of the proposed algorithm under various attack scenarios. In addition, the results indicate that the proposed method reduces approximately 60–80% of the number of suspicious nodes while increasing the turnaround time by only approximately 1–2%. The proposed method also focuses specifically on accurate network health monitoring to protect the network proactively.

Microgrids Imitate Nature for Improved Performance—Use of Nature-Inspired Optimization Techniques in Future Power Systems

There is a constant push towards increasing use of renewable energy-based distributed generators around the globe. While they provide a clean and sustainable source of energy, they employ technologies that are unknown to traditional power systems. These generators are interfaced via inverters that lack the inertia of large synchronous machines. This manifests itself as a more volatile frequency profile that is susceptible to disturbances. This phenomenon is more amplified in stand-alone microgrids which are utilized as a popular electrification alternative in isolated or underserved communities. One solution approach takes its inspiration from nature, e.g., behavior of bees, butterflies, or ants. When employed in a suitable way, animals’ natural behavior helps optimize interaction between different renewable-energy based generators and create a more stable microgrid. There are different approaches to stabilizing such systems with novel optimization approaches. Some of them optimize the ratio between generators that utilize rotating machines and inverters. Penetration of renewable energy generation is about increasing the share of inverter-interfaced generators in the system without causing stability issues. Since renewable energy resources are intermittent and not dispatchable, it is important to create a diverse portfolio where the overall system achieves some stability. For instance, if a local grid is fed by PV panels, wind generation and a small-scale hydroelectric power plant, the varying nature of these resources may complement each other. On a sunny day, PV output might be very high, and wind may not be so significant. On the other hand, on a rainy day, clouds may reduce PV output while precipitation may feed the local hydro power plant. Similarly, wind generation might complement others on a windy day. While the idea is easy to comprehend qualitatively, finding the correct ratio is not trivial. Furthermore, there are many factors at play that are independently changing and impacting the outcome. For different sites, the available renewable energy resources, their profiles as well as the local load conditions would be different. Therefore, a systematic approach is required to optimize these systems at planning, operation and control levels. Nature-inspired optimization algorithms seem to have an edge in doing just that.

A Novel Light Weight CNN Framework Integrated with Marine Predator Optimization for the Assessment of Tear Film-Lipid Layer Patterns

Tear film, the outermost layer of the eye, is a complex and dynamic structure responsible for tear production. The tear film lipid layer is a vital component of the tear film that provides a smooth optical surface for the cornea and wetting the ocular surface. Dry eye syndrome (DES) is a symptomatic disease caused by reduced tear production, poor tear quality, or excessive evaporation. Its diagnosis is a difficult task due to its multifactorial etiology. Out of several clinical tests available, the evaluation of the interference patterns of the tear film lipid layer forms a potential tool for DES diagnosis. An instrument known as Tearscope Plus allows the rapid assessment of the lipid layer. A grading scale composed of five categories is used to classify lipid layer patterns. The reported work proposes the design of an automatic system employing light weight convolutional neural networks (CNN) and nature inspired optimization techniques to assess the tear film lipid layer patterns by interpreting the images acquired with the Tearscope Plus. The designed framework achieves promising results compared with the existing state-of-the-art techniques.

Eagle perching optimizer for the online solution of constrained optimization

The paper proposes a novel nature-inspired optimization technique called Eagle Perching Optimizer (EPO). It is an addition to the family of swarm-based meta-heuristic algorithms. It mimics eagles’ perching nature to find prey (food). The EPO is based on the exploration and exploitation of an eagle when it descends from the height such that it formulates its trajectory in a way to get to the optimal solution (prey). The algorithm takes bigger chunks of search space and looks for the optimal solution. The optimal solution in that chunk becomes the search space for the next iteration, and this process is continuous until EPO converges to the optimal global solution. We performed the theoretical analysis of EPO, which shows that it converges to the optimal solution. The simulation includes three sets of problems, i.e., uni-model, multi-model, and constrained real-world problems. We employed EPO on the benchmark problems and compared the results with state-of-the-art meta-heuristic algorithms. For the real-world problems, we used a cantilever beam, three-bar truss, and gear train problems to test the robustness of EPO and later made the comparison. The comparison shows that EPO is comparable with other known meta-heuristic algorithms.

System Reliability-Redundancy optimization with High-Level of subsystems

High systems’ reliability is crucial in competitive industrial plants. System Reliability-Redundancy Allocation (RRA) is an essential design consideration for maximizing the overall systems’ reliability under various systems’ constraints. This paper addresses the system RRAP problem by investigating two effective nature-inspired optimization techniques, namely Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO), implemented with penalty functions. Their capability in solving the RRA problem is evaluated regarding a system consisting of fifteen subsystems connected in series. Results show that the PSO is a better approach to solving this problem than the GWO.

Preface

The 2022 2nd International Conference on Power System and Energy Internet (PoSEI2022) was held online on August 5-7 in Nanjing, China. PoSEI 2022 brought together innovative academics and industrial experts in the field of Power systems and Energy Internet in a common forum, promoting research and developmental activities in these fields.In the conference, we were greatly honored to have both Prof. Rongbang An from Jinan University, China and Prof. Hzalie Bin Mokhlis from University of Malaya, Malaysia to serve as our Conference General Chairmen. 90 individuals around the world took part in the conference. Divided into three parts, the conference agenda included keynote speeches, oral presentations and online Q&A discussion. Firstly, the keynote speakers were each allocated 30-45 minutes to address their speeches. Then in the next part, oral presentations, the excellent papers we had selected were presented by their authors one by one.Five distinguished professors were invited to hold keynote speeches during the conference. Among them, Prof. Min Wang from Hohai University, China performed a thought-provoking speech on the Correlation Analysis and Its Typical Application in Power System. The concept of correlation, classification, characteristics and its typical application in power system were studied in this research. Especially, some typical applications of correlation analysis in the field of power system research were discussed, including multiscale dynamic correlation analysis of Wind-PV power station output based on TDIC, research on microgrid two-way auction mechanism based on fixed effect Spatial Lagged Model, and risk assessment of distribution network equipment based on the Marcos method. Moreover, Prof. Hzalie Bin Mokhlis from University of Malaya, Malaysia made a report on: The Role of Nature Inspired Optimization in Power System Research. The presentation discussed the application of nature-inspired optimization techniques in recent power system research, covering the current challenges to power systems. And some examples of research work on the use of nature-inspired optimizations were also presented. Their insightful speeches had triggered heated discussion. And every participant praised this conference for disseminating useful and insightful knowledge.List of Committee member is available in this pdf.

A secure data hiding approach based on least-significant-bit and nature-inspired optimization techniques

A secure data hiding approach based on least-significant-bit and nature-inspired optimization techniques

Power Systems Imitate Nature for Improved Performance Use of Nature-Inspired Optimization Techniques

Renewable energy transition creates unprecedented issues in power system control, operation and protection [...]

A nature-inspired optimal design for a ventilated brake disc

Brake discs are critical automobile components that provide the braking effect and ultimately ensure the safety of passengers. Because of intermittent braking operations, brake discs are subjected to fluctuating loads and are provided with ventilation to facilitate cooling. The present study utilized a combination of response surface methodology parametric analysis, finite element analysis, statistical analysis, predictive modeling, and design optimization. Based on the response surface methodology design of experimental runs, ventilated brake discs were modeled considering the critical design parameters, viz., radius of center hole, thickness of inboard and outboard plate, height of vanes, and offset. Using finite element analysis, the brake discs were simulated under actual braking conditions for fatigue life cycles. Thirty-two (32) trial finite element analysis trials were performed. The obtained results were interpreted using ANOVA and an effective predictive model was established. Parametric analysis was performed using plots of response surface methodology and contours to predict the optimal parameter settings. In addition, two nature-inspired optimization techniques, the genetic algorithm and particle swarm optimization, were implemented and the optimal design parameter settings were determined for maximum fatigue life. The genetic algorithm and particle swarm optimization produced 7.67% better results than the parametric analysis, clearly demonstrating that the proposed design techniques exhibited significant performance improvement compared to widely used classical techniques.

Detection of Congestive Heart Failure with Nature-Inspired Optimization and Classifiers Performance Amelioration from ECG Signals

This paper explores the earlier detection of CHF, and its allied Cardio Vascular Diseases (CVD) like Atrial Fibrillation (Afib) from nature-inspired optimization techniques using cardiac signals. The Beth Israel Deaconess Medical Centre (BIDMC) CHF, MIT-BIH-Afib, and Normal Sinus Rhythm (NSR) databases from the Physionet repository are utilized in this research. The Flower Pollination Algorithm (FPA), Binary Flower Pollination Algorithm (BFPA), and BFPA with Greedy Crossover approaches are applied to extract the features of CHF, Afib, and NSR cardiac classes ECG signals. Then extracted features are given into appropriate classifiers such as the SVM (Linear), SVM (Polynomial), SVM (RBF), WKNN, and NBC classifiers. The classifiers’ performance is assessed and compared by the standard performance benchmarks, such as Accuracy, F1 Score, Geometric Mean, Kappa Coefficient and Error Rate. The SVM (RBF) classifier with BFPA features achieved 97.71% overall average accuracy along with a 0.9540 kappa coefficient in {CHF} vs. {NSR} cardiac abnormality detection. The SVM (RBF) classifier with BFPA features reached 89.59% overall average accuracy along with a 0.7935 kappa coefficient in {Afib} vs. {NSR} cardiac class detection. As a result, the SVM (RBF) classifier with BFPA features outclasses all other classification techniques in detecting {CHF} vs. {NSR} cardiac abnormality classes.