Bio-inspired Algorithms Research Articles

A Novel Guided Box Filter Based on Hybrid Optimization for Medical Image Denoising

Medical image denoising is a crucial pre-processing task in the medical field to ensure accurate analysis of anomalies or sicknesses in the human body. Digital filters are popular for reducing undesired noise as they provide reliability, high accuracy, and reduced sensitivity to component tolerances compared to analog filters. However, conventional digital filter design approaches lack efficiency in achieving global optimization robustness. To overcome these incapabilities, this paper adopted bio-inspired optimization algorithms to offer viable digital filter designing tools because of their simple implementation and requirement of a few parameters to control their convergence. This research article explores a hybrid strategy that combines a novel guided decimation box filter (GDBF) with a hybrid cuckoo particle swarm optimization (HCPSO) algorithm to design a denoising filter for medical images. It is the first time a decimation box filter has been used for denoising, leading to novelty. The HCPSO algorithm is applied to obtain the filter parameters optimally. Medical images mostly suffer from four types of noises. The performance of the proposed filter is analyzed for these types of noise. To highlight the importance of parameter selection, the results of the proposed method are compared with other recently utilized bio-inspired genetic algorithms, such as PSO (particle swarm optimization), CS (cuckoo search), and FF (firefly). The superiority (potency) of the proposed method has been established by calculating the improvement in quality parameters such as the peak signal-to-noise ratio (PSNR), structure similarity index (SSIM), and feature similarity index (FSIM). The proposed filter achieved the highest PSNR (~35.7 dB), SSIM (~0.95), and FSIM (~0.92) and proved its numerical and visual quality efficacy over state-of-the-art models.

Short-term electricity demand forecasting using a hybrid ANFIS–ELM network optimised by an improved parasitism–predation algorithm

One of the most crucial steps in comprehensively planning the proper and efficient use of energy (optimisation of consumption) and appropriate management of resources to fulfil the power demand is accurately forecasting the energy demand (optimisation of production). This study presents the modelling of an ideal technique for short-term power demand prediction as a novel hybrid approach comprising two distinct methods, namely the Elman neural network (ELM) and adaptive network–basedfuzzy inference system (ANFIS). The hybrid approach outperforms the conventional individual methods because it can eliminate the drawbacks of the individual methods while retaining their advantages, particularly considering that ELM and ANFIS can handle non-linear data. The weight coefficients of the procedures in the proposed hybrid approach were determined using a novel, enhanced bioinspired algorithm, called the improved parasitism–predation algorithm, to achieve better accuracy. The simulation results demonstrated the superiority of the proposed approach over other state-of-the-art approaches including the independent ELM and ANFIS.

Optimization of Aquaponic Lettuce Evapotranspiration Based on Artificial Photosynthetic Light Properties Using Hybrid Genetic Programming and Moth Flame Optimizer

Land and water resources, climate change, and disaster risks significantly affect the agricultural sector. An effective solution for growing crops to improve productivity and optimize the use of resources is through controlled-environment agriculture (CEA). Evapotranspiration (ET) is an important greenhouse crop attribute that can be optimized for optimum plant growth. Light intensity and radiation are significant for controlling ET. To address this challenge, this study successfully determined the properties of optimum artificial light for minimum evapotranspiration rate of head development-stage and harvest-stage lettuce under light-period and dark-period using genetic programming and bio-inspired algorithms namely, grey wolf optimization (GWO), whale optimization algorithm (WOA), dragonfly algorithm (DA), and moth flame optimization (MFO). MFO provided the optimized global solution for the configured models. Results showed that head development-stage lettuce requires higher light intensity with lower visible to infrared radiation ratio (Vis/IR) than harvest-stage lettuce when exposed to light. On the other hand, harvest-stage lettuce requires higher light intensity with lower Vis/IR than head development-stage under dark-period respiration reaction. Findings of this study can be utilized in growing and improving yield crops in controlled-environment agriculture.

Control of Mutual Coupling in Microstrip Antenna Design Based on Bio-inspired Algorithms

Control of Mutual Coupling in Microstrip Antenna Design Based on Bio-inspired Algorithms

A Bionic Dynamic Path Planning Algorithm of the Micro UAV Based on the Fusion of Deep Neural Network Optimization/Filtering and Hawk-Eye Vision

A micro unmanned aerial vehicle (UAV) only equipped with a monocular camera is hard to accomplish a flying task with obstacles avoidance and target tracking simultaneously. In this article, a bionic dynamic path planning algorithm was developed for cooperation of obstacles avoidance and target tracking. An improved bat algorithm (BA) optimized transfer learning convolutional neural network (CNN) and bio-inspired optical flow balance algorithm was combined for obstacles avoidance. The Hawk-eye algorithm with line of sight (LOS) tracking rules is aimed at UAV dynamic tracking with obstacles avoidance. All of perception information, including avoidance and tracking were fused in UAV motion decision phase. The experiments include “obstacles avoidance” and “obstacles avoidance <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$+$</tex-math> </inline-formula> target tracking” parts. Comparing with manual control and other algorithms, the bionic dynamic path planning algorithm in this article showed certain advantages in success rate, less obstacles collisions, and less major accidents.

Prognostics of aerospace electromechanical actuators: comparison between model-based metaheuristic methods

Electro-Mechanical Actuators (EMAs) deployment as aircraft flight control actuators is an imperative step towards more electric concepts, which propose an increased electrification in aircraft subsystems at the expense of the hydraulic system. Despite the strong benefits linked to EMAs adoption, their deployment is slowed down due to the lack of statistical data and analyses concerning their often-critical failure modes. Prognostics and Health Management (PHM) techniques can support their adoption in safety critical domains. A very promising approach involves the development of model-driven prognostics methodologies based on metaheuristic bio-inspired algorithms. Evolutionary (Differential Evolution (DE)) and swarm intelligence (particle swarm (PSO), grey wolf (GWO)) methods are approached for PMSM based EMAs. Furthermore, two models were developed: a reference, high fidelity model and a monitoring, low fidelity counterpart. Several failure modes have implemented: dry friction, backlash, short circuit, eccentricity and proportional gain. The results show that these algorithms could be employed in pre-flight checks or during the flight at specific time intervals. Therefore, EMA actual state can be assessed and PHM strategies can provide technicians with the right information to monitor the system and to plan and act accordingly (e.g. estimating components Remaining Useful Life (RUL)), thus enhancing the system availability, reliability and safety.

A Comprehensive Review -Application of Bio-inspired Algorithms for Cyber Threat Intelligence Framework

In most of the modern-day computing systems, security enhancements are a part of security design. The majority of the effort in providing robust security to a system is involved in the identification of cyber threats and how to recover from such cyberattacks. Many researchers have proposed sub-optimal strategies which has been the motivation of this research. This study summarises the research gaps and proposes research direction for mitigating the challenges concerned in that direction. This work reviews the current methodologies to provide a framework which can auto identify cyber threats and to determine how the bio-inspired algorithms can be applied to minimize the effort involved in identification and recovery from cyberattacks. Cyber threat intelligence frameworks serve as crucial elements in providing secure operating environment for the cyber practitioners. The design and development of cyber threat intelligence framework is challenging not only for the cost and effort involved in it but also due to intrinsic dependent entities of cyber security. This study proposes novel principles for bridging the identified research gaps through feature engineering, trust computing base, and bio-inspired based time optimization. There is a lot of research potential in this direction and this study is a sincere and ideal attempt towards the same goal.

A new bio-inspired metaheuristic algorithm for solving optimization problems based on walruses behavior

This paper introduces a new bio-inspired metaheuristic algorithm called Walrus Optimization Algorithm (WaOA), which mimics walrus behaviors in nature. The fundamental inspirations employed in WaOA design are the process of feeding, migrating, escaping, and fighting predators. The WaOA implementation steps are mathematically modeled in three phases exploration, migration, and exploitation. Sixty-eight standard benchmark functions consisting of unimodal, high-dimensional multimodal, fixed-dimensional multimodal, CEC 2015 test suite, and CEC 2017 test suite are employed to evaluate WaOA performance in optimization applications. The optimization results of unimodal functions indicate the exploitation ability of WaOA, the optimization results of multimodal functions indicate the exploration ability of WaOA, and the optimization results of CEC 2015 and CEC 2017 test suites indicate the high ability of WaOA in balancing exploration and exploitation during the search process. The performance of WaOA is compared with the results of ten well-known metaheuristic algorithms. The results of the simulations demonstrate that WaOA, due to its excellent ability to balance exploration and exploitation, and its capacity to deliver superior results for most of the benchmark functions, has exhibited a remarkably competitive and superior performance in contrast to other comparable algorithms. In addition, the use of WaOA in addressing four design engineering issues and twenty-two real-world optimization problems from the CEC 2011 test suite demonstrates the apparent effectiveness of WaOA in real-world applications. The MATLAB codes of WaOA are available in https://uk.mathworks.com/matlabcentral/profile/authors/13903104.

Autism Spectrum Disorder Prediction by Bio-inspired Algorithm with Blockchain based Database

Autism Spectrum Disorder Prediction by Bio-inspired Algorithm with Blockchain based Database

A comparative evaluation of a set of bio-inspired optimization algorithms for design of two-DOF robust FO-PID controller for magnetic levitation plant

A comparative evaluation of a set of bio-inspired optimization algorithms for design of two-DOF robust FO-PID controller for magnetic levitation plant

Guiding the optimization of membraneless microfluidic fuel cells via explainable artificial intelligence: Comparative analyses of multiple machine learning models and investigation of key operating parameters

Membraneless microfluidic fuel cells (MMFCs) offer great potential for clean energy production, but their expense and tedious optimization process have limited their wider use. Machine learning (ML) algorithms have shown promise in improving the optimization of MMFCs, but the “black box” nature of these models has caused uncertainty and limited their adoption. To address this, we conducted the first study that implements the explainable artificial intelligence (XAI) approach to gain in-depth insights into multiple ML optimization models' predictions and the impacts of operating parameters on MMFCs' performance. Among 27 investigated models that are generated based on nine ML and three bio-inspired evolutionary algorithms, the combination of a decision tree and the particle swarm optimization algorithm is the most effective model that satisfied all criteria of high time efficiency (execution time = 3.194 s), accuracy (squared correlation coefficient = 0.999), and optimum power density identification (0.278 mWcm−2). The ML-optimized power density is 239.024% increased, which is 3.4 times higher than the average power density obtained without optimization. We further utilized the XAI model to comprehensively examine the impacts of operating parameters, providing valuable decision aids for the researchers, technicians, and engineers in manufacturing optimal power MMFCs at a significantly lower cost and faster rate.

GWO-Based Multi-Stage Algorithm for PMDC Motor Parameter Estimation.

During the design of a wheeled mobile robot, the problem of the proper selection of the parameters of its motor controllers was encountered. Knowing the parameters of the robot's Permanent Magnet Direct Current (PMDC) motors, precise tuning of the controllers can be performed, which then results in improved robot dynamics. Among many methods of parametric model identification, optimization-based techniques, particularly genetic algorithms, have gained more and more interest recently. The articles on this topic present the results of parameter identification, but they do not refer to the search ranges for individual parameters. With too wide a range, genetic algorithms do not find solutions or are time-inefficient. This article introduces a method for determining the parameters of a PMDC motor. The proposed method performs an initial estimation of the range of searched parameters to shorten the estimation time of the bioinspired optimization algorithm.

Parameter Extraction of Solar Photovoltaic Modules Using a Novel Bio-Inspired Swarm Intelligence Optimisation Algorithm

For extracting the equivalent circuit parameters of solar photovoltaic (PV) panels, a unique bio-inspired swarm intelligence optimisation algorithm (OA) called the dandelion optimisation algorithm (DOA) is proposed in this study. The suggested approach has been used to analyse well-known single-diode (SD) and double-diode (DD) PV models for several PV module types, including monocrystalline SF430M, polycrystalline SG350P, and thin-film Shell ST40. The DOA is adopted by minimizing the sum of the squares of the errors at three locations (short-circuit, open-circuit, and maximum power points). Different runs are conducted to analyse the nature of the extracted parameters and the V–I characteristics of the PV panels under consideration. Obtained results show that for Mono SF430M, the error in the SD model is 2.5118e-19, and the error in the DD model is 2.0463e-22; for Poly SG350P, the error in the SD model is 9.4824e-21, and the error in the DD model is 2.1134e-20; for thin-film Shell ST40, the error in the SD model is 1.7621e-20, and the error in DD model is 7.9361e-22. The parameters produced from the suggested method yield the least amount of error across several executions, which suggests its better implementation in the current situation. Furthermore, statistical analysis of the SD and DD models using DOA is also carried out and compared with two hybrid OAs in the literature. Statistical results show that the standard deviation, sum, mean, and variance of various PV panels using DOA are lower compared to those of the other two hybrid OAs.

Bio-Inspired Multi-UAV Path Planning Heuristics: A Review

Despite the rapid advances in autonomous guidance and navigation techniques for unmanned aerial vehicle (UAV) systems, there are still many challenges in finding an optimal path planning algorithm that allows outlining a collision-free navigation route from the vehicle’s current position to a goal point. The challenges grow as the number of UAVs involved in the mission increases. Therefore, this work provides a comprehensive systematic review of the literature on the path planning algorithms for multi-UAV systems. In particular, the review focuses on biologically inspired (bio-inspired) algorithms due to their potential in overcoming the challenges associated with multi-UAV path planning problems. It presents a taxonomy for classifying existing algorithms and describes their evolution in the literature. The work offers a structured and accessible presentation of bio-inspired path planning algorithms for researchers in this subject, especially as no previous review exists with a similar scope. This classification is significant as it facilitates studying bio-inspired multi-UAV path planning algorithms under one framework, shows the main design features of the algorithms clearly to assist in a detailed comparison between them, understanding current research trends, and anticipating future directions. Our review showed that bio-inspired algorithms have a high potential to approach the multi-UAV path planning problem and identified challenges and future research directions that could help improve this dynamic research area.

Deep learning based source identification of environmental audio signals using optimized convolutional neural networks

The research in the field of environmental sounds is a growing area due to its enormous potential and its applications. One of the major factors that affect the model performance is the noisy, redundant, or irrelevant features. Deep learning models have shown promise in this area, but the extraction of optimal features from audio signals and classification efficiency of the model are still challenging issues in this field. To address the challenges faced by existing methods, this research proposes a unique deep learning framework-based model that employs an enhanced bio-inspired algorithm for feature extraction and environmental sound classification. The quality and relevance of the training features are essential for the model’s accuracy, and a novel algorithm is introduced to select optimal features for improved performance. The algorithm is further improved for weight optimization to address overfitting and accuracy issues. Additionally, a modified version of the Discrete Fourier Transform is introduced to reduce computational complexity, which makes the model more suitable for real-time applications or resource-limited devices. This research emphasizes the necessity for improved algorithms for feature selection and weight optimization. The proposed model exhibits excellent accuracy and efficiency, making it suitable for real-time applications.

Optimal Load Frequency Control of a Hybrid Electric Shipboard Microgrid Using Jellyfish Search Optimization Algorithm

This paper examines the critical topic of load frequency control (LFC) in shipboard microgrids (SMGs), which face challenges due to low system inertia and the intermittent power injection of renewable energy sources. To maintain a constant frequency (even under system uncertainties), a robust and well-tuned controller is required. In this paper, a study was conducted first by examining the performance of three different controller architectures, in order to determine which is the most-appropriate for the multi-energy SMG system. The time delays that occur due to communication links between the sensors and the controller were also considered in the analysis. The controllers were tuned using a very recent bio-inspired optimization algorithm called the jellyfish search optimizer (JSO), which has not been used until recently in LFC problems. To assess the tuning efficiency of the proposed optimization algorithm, the SMG’s frequency response results were comprehensively compared to the results obtained with other bio-inspired optimization algorithms. The results showed that the controllers with gains provided by the JSO outperformed those tuned with other bio-inspired optimization counterparts, with improvements in performance ranging from 19.13% to 93.49%. Furthermore, the robustness of the selected controller was evaluated under various SMG operational scenarios. The obtained results clearly demonstrated that the controller’s gains established in normal conditions do not require retuning when critical system parameters undergo a significant variation.

Optimal Planning of Wind -based DG Units in Uncertain Distribution Network

This paper presents the Zebra Optimization Algorithm (ZOA), a novel bio-inspired metaheuristic algorithm for optimizing the allocation of distributed generation (DG) units based on wind turbine (WT) technology in distribution networks (DN). The algorithm is based on the foraging and defense strategies of zebras in the wild. ZOA seeks to reduce total energy losses and improve the distribution network's daily voltage profile. The proposed method was applied to a typical IEEE 33-node distribution network, and the simulation results were compared to those obtained by other recently developed optimization algorithms. The comparison report affirmed the efficiency of the Zebra Optimization Algorithm method, demonstrating its ability to outperform existing optimization algorithms.

Optimal Planning of Photovoltaic-based DG Units in Uncertain Distribution Network

This paper introduces a novel bio-inspired metaheuristic algorithm called the Zebra Optimization Algorithm (ZOA) for optimizing the allocation of distributed generation (DG) units based on photovoltaic (PV) technology in distribution networks (DN). The algorithm is inspired by the foraging behavior and defense strategies of zebras in nature. ZOA aims to minimize total energy losses and improve the daily voltage profile in the distribution network. The proposed approach was applied to the typical IEEE 33 node distribution network, and the simulation results were compared with those obtained by other optimization algorithms developed in recent literature. The effectiveness of the Zebra Optimization Algorithm method was confirmed by the comparison report, demonstrating its ability to outperform existing optimization algorithms.

Prediction of Urinary Tract Infection in IoT-Fog Environment for Smart Toilets Using Modified Attention-Based ANN and Machine Learning Algorithms

UTI (Urinary Tract Infection) has become common with maximum error rates in diagnosis. With the current progress on DM (Data Mining) based algorithms, several research projects have tried such algorithms due to their ability in making optimal decisions and efficacy in resolving complex issues. However, conventional research has failed to attain accurate predictions due to improper feature selection. To resolve such existing pitfalls, this research intends to employ suitable ML (Machine Learning)-based algorithms for predicting UTI in IoT-Fog environments, which will be applicable to a smart toilet. Additionally, bio-inspired algorithms have gained significant attention in recent eras due to their capability in resolving complex optimization issues. Considering this, the current study proposes MFB-FA (Modified Flashing Behaviour-based Firefly Algorithm) for feature selection. This research initializes the FF (Firefly) population and interchanges the constant absorption coefficient value with the chaotic maps as the chaos possesses an innate ability to evade getting trapped in local optima with the improvement in determining global optimum. Further, GM (Gaussian Map) is taken into account for moving all the FFs to a global optimum in an individual iteration. Due to such nature, this algorithm possesses a better optimization ability than other swarm intelligence approaches. Finally, classification is undertaken by the proposed MANN-AM (Modified Artificial Neural Network with Attention Mechanism). The main intention for proposing this network involves its ability to focus on small and significant data. Moreover, ANNs possess the ability for learning and modelling complex and non-linear relationships, in which the present study considers it. The proposed method is compared internally by using Random Forest, Naive Bayes and K-Nearest Neighbour to show the efficacy of the proposed model. The overall performance of this study is assessed with regard to standard performance metrics for confirming its optimal performance in UTI prediction. The proposed model has attained optimal values such as accuracy as 0.99, recall as 0.99, sensitivity as 1, precision as 1, specificity as 0.99 and f1-score as 0.99.

Phase locking in voltage-controlled parametric oscillator

A recent experimental demonstration of a parametric magnetization oscillation excited by applying a microwave voltage to a ferromagnetic metal will be applicable not only to a new magnetization switching method but also to bio-inspired computing. It should be, however, noted that a phase of the parametric magnetization oscillation is not uniquely locked, related to the fact that a frequency of the microwave voltage is twice the value of the magnetization oscillation. There are two possible phases in the parametric oscillation state, and which of the two is realized depends on the initial condition of the magnetization. Here, we examine two approaches to lock the phase uniquely. One is to suppress the distribution of the initial state by enhancing the perpendicular magnetic anisotropy before applying microwave voltage, and the other is to use a sweeping frequency. Through numerical simulation of the Landau–Lifshitz–Gilbert equation and quantification of locked rate, we find that the sweeping frequency is more effective to lock the phase of the parametric magnetization oscillation.