An efficient multi-level thresholding method for breast thermograms analysis based on an improved BWO algorithm

Multilevel thresholding is an effective and indispensable technology for image segmentation that has attracted extensive attention in recent years. However, the multilevel thresholding method has some disadvantages, such as a large computational complexity and low segmentation accuracy. Therefore, this paper proposes a whale optimization algorithm (WOA) based on Kapur's entropy method to solve the image segmentation problem. The WOA can effectively balance exploration and exploitation to avoid falling into premature convergence and obtain the global optimal solution. To verify the segmentation performance of the WOA, a series of experiments on underwater images from the experimental pool of Harbin Engineering University are conducted, and the segmentation results are compared with those of the BA, the FPA, MFO, the MSA, PSO and WWO by maximizing the fitness value of Kapur's entropy method. The fitness value, peak signal-to-noise ratio (PSNR), structure similarity index (SSIM), execution time and Wilcoxon's rank-sum test are used to evaluate the overall performance of each algorithm. The experimental results reveal that the WOA is superior to the other comparison algorithms and has a higher segmentation accuracy, better segmentation effect and stronger robustness. In addition, the feasibility and efficiency of the WOA are verified.

An efficient hybrid sine-cosine Harris hawks optimization for low and high-dimensional feature selection

In this paper, a new hybrid whale optimization algorithm (WOA) called WOA-DE is proposed to better balance the exploitation and exploration phases of optimization. Differential evolution (DE) is adopted as a local search strategy with the purpose of enhancing exploitation capability. The WOA-DE algorithm is then utilized to solve the problem of multilevel color image segmentation that can be considered as a challenging optimization task. Kapur’s entropy is used to obtain an efficient image segmentation method. In order to evaluate the performance of proposed algorithm, different images are selected for experiments, including natural images, satellite images and magnetic resonance (MR) images. The experimental results are compared with state-of-the-art meta-heuristic algorithms as well as conventional approaches. Several performance measures have been used such as average fitness values, standard deviation (STD), peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), Wilcoxon’s rank sum test, and Friedman test. The experimental results indicate that the WOA-DE algorithm is superior to the other meta-heuristic algorithms. In addition, to show the effectiveness of the proposed technique, the Otsu method is used for comparison.

A novel dynamic Nelder-based Electric Eel Foraging algorithm for global optimization and pathological colorectal cancer image segmentation.

Many challenges are involved in solving mechanical design optimization problems related to the real-world, such as conflicting objectives, assorted design variables, discrete search space, intuitive flaws, and many locally optimal solutions. A comparison of algorithms on a given set of problems can provide us with insights into their performance, finding the best one to use, and potential improvements needed in their mechanisms to ensure maximum performance. This motivated our attempts to comprehensively compare eight recent meta-heuristics on 15 mechanical engineering design problems. Algorithms considered are water wave optimizer (WWO), butterfly optimization algorithm (BOA), Henry gas solubility optimizer (HGSO), Harris Hawks optimizer (HHO), ant lion optimizer (ALO), whale optimization algorithm (WOA), sine–cosine algorithm (SCA) and dragonfly algorithm (DA). Comparative performance analysis is based on the solution trait obtained from statistical tests and convergence plots. The results demonstrate the wide range of adaptability of considered algorithms for future applications.

The sand cat swarm optimization (SCSO) is a new heuristic optimization algorithm that simulates the behavior of sand cat groups in the desert using hearing to hunt. To address the shortcomings of low accuracy of SCSO solution, slow convergence in late iterations and easy convergence stagnation, a sand cat swarm optimization based on stochastic variation and elite collaboration (SE-SCSO) is proposed. SE-SCSO first introduces a nonlinear periodic adjustment mechanism to balance the exploration and local exploitation ability of the algorithm and accelerate the convergence of the algorithm.Secondly, the pseudo-opposition and pseudo-reflection learning mechanisms are used to speed up the optimization-seeking efficiency of the SCSO algorithm and improve the global convergence capability. Designing elite collaborative strategies with random variation to enable the algorithm to jump away from the local extrema, further improving the algorithm’s optimization-seeking accuracy and convergence speed. In the simulation experiments, SE-SCSO is compared with Sand Cat Swarm Optimization (SCSO), Sine Cosine Algorithm (CSA), Circle Search Algorithm (SCA), Salp Swarm Algorithm (SSA), Harris Hawks Optimization (HHO), Whale Optimization Algorithm (WOA), and Golden Jackal Optimization (GJO) are tested for comparison. The experimental results validate the effectiveness of the proposed improvement strategies. Finally, SE-SCSO is applied to three engineering optimization problems. The results show that the improved strategy can effectively improve the performance performance of the algorithm, which gives SE-SCSO the advantages of high convergence accuracy, fast convergence, and the ability to jump out of local optimal solutions.

In this article, an enhanced arithmetic optimization algorithm (EAOA) is utilized to resolve the optimal reactive power dispatch problem (ORPD) of power plants, which is a non‐linear, non‐smooth, complex optimization problem. Typically, it is formulated as a constrained optimal power flow problem. This paper utilizes the gamma distribution to generate initial random solutions, which improves the accuracy of the arithmetic optimization algorithm (AOA). The original mode of deviation of math optimizer accelerated (MOA) is replaced with the improved pattern of change in the prey's energy in Harris Hawk Optimization (HHO), which creates a superior balance between the exploration and exploitation of AOA. This paper implements logarithmic and exponential operators in place of division and multiplication operators, which improves the exploration ability of AOA and also utilizes the gamma distribution in the generation of random numbers, which are essential for the selection of operators in both search phase which enlarges the search area and improves the global optimum solution. A parametric analysis is performed on 10 benchmark functions for nine possible values before selecting the algorithm's initial parameters. A comparative statistical analysis along with Friedman's test is carried out on 23 benchmark functions to test the overall performance as compared to Sine‐Cosine Algorithm (SCA), Swarm‐Salp Algorithm, Grey Wolf Optimization (GWO), and basic Arithmetic Optimization Algorithm (AOA). EAOA is applied to the IEEE 57 bus system for optimal reactive power control. EAOA reports a significant reduction in a power loss of 23.2 MW, which is 18.596% smaller than the system's base case power loss of 28.5 MW as compared to Artificial Bee Colony (ABC), Firefly Algorithm (FA), Bat‐inspired Algorithm (BAT), Cuckoo Search Algorithm (CSA), and Modified Ant Lion Algorithm (MALO) which reports a reduction in a power loss of 14.73%, 15.43%, 15.43%, 16.14%, and 16.14% respectively. EAOA reduces the TVD to 0.76 pu, compared to ABC, FA, BAT, CSA, and MALO, which minimizes the TVD to 0.84, 0.82, 0.88, 0.82, and 0.79, respectively. This proves that EAOA performs better in resolving ORCP problems regarding the quality of solutions and convergence. A detailed comparative statistical analysis of EAOA with CSA, BAT, and WOA (Whale Optimization Algorithm) is conducted in terms of Probability Distribution Functions (PDF) and Cumulative Distribution Functions (CDF), along with the Wilcoxson sign rank test, which proves that EAOA gives the solution with a higher degree of precision.

The students’ performance prediction (SPP) problem is a challenging problem that managers face at any institution. Collecting educational quantitative and qualitative data from many resources such as exam centers, virtual courses, e-learning educational systems, and other resources is not a simple task. Even after collecting data, we might face imbalanced data, missing data, biased data, and different data types such as strings, numbers, and letters. One of the most common challenges in this area is the large number of attributes (features). Determining the highly valuable features is needed to improve the overall students’ performance. This paper proposes an evolutionary-based SPP model utilizing an enhanced form of the Whale Optimization Algorithm (EWOA) as a wrapper feature selection to keep the most informative features and enhance the prediction quality. The proposed EWOA combines the Whale Optimization Algorithm (WOA) with Sine Cosine Algorithm (SCA) and Logistic Chaotic Map (LCM) to improve the overall performance of WOA. The SCA will empower the exploitation process inside WOA and minimize the probability of being stuck in local optima. The main idea is to enhance the worst half of the population in WOA using SCA. Besides, LCM strategy is employed to control the population diversity and improve the exploration process. As such, we handled the imbalanced data using the Adaptive Synthetic (ADASYN) sampling technique and converting WOA to binary variant employing transfer functions (TFs) that belong to different families (S-shaped and V-shaped). Two real educational datasets are used, and five different classifiers are employed: the Decision Trees (DT), k-Nearest Neighbors (k-NN), Naive Bayes (NB), Linear Discriminant Analysis (LDA), and LogitBoost (LB). The obtained results show that the LDA classifier is the most reliable classifier with both datasets. In addition, the proposed EWOA outperforms other methods in the literature as wrapper feature selection with selected transfer functions.

Image enhancement is an important step in image processing to improve contrast and information quality. Intelligent enhancement algorithms are gaining popularity due to the limitations of traditional methods. This paper utilizes a transformation function to enhance the global and local information of grayscale images, but the parameters of this function can produce significant changes in the processed images. To address this, the whale optimization algorithm (WOA) is employed for parameter optimization. New equations are incorporated into WOA to improve its global optimization capability, and exemplars and advanced spiral updates improve the convergence of the algorithm. Its performance is validated on four different types of images. The algorithm not only outperforms comparison algorithms in the objective function but also excels in other image enhancement metrics, including peak signal-to-noise ratio (PSNR), feature similarity index (FSIM), structural similarity index (SSIM), and patch-based contrast quality index (PCQI). It is superior to the comparison algorithms in 11, 6, 11, 13, and 7 images in these metrics, respectively. The results demonstrate that the algorithm is suitable for image enhancement both subjectively and statistically.

Segmentation of brain MRI using an altruistic Harris Hawks’ Optimization algorithm

Wide variety of medical images are degraded by different types of noise such as Impulse noise, Gaussian noise, Poisson or a mixed of all. These noise disruptions typically result from sensor malfunctions, transmission issues, or environmental factors [1]. They provide an essential basis for clinical diagnosis and treatment. Unlike natural photographs, medical images often contain significant signal-related noise during their creation, resulting in lower contrast and more visible noise [3].No single method or procedure is effective for noise removal hence care should be taken before cleaning noisy area of image. Factors such as type of image (CT scan, Ultrasound, MRI etc) and type of noise such as (Gaussian, the impulsive and speckle noise etc) should be identified and based on the type of input, an appropriate method should be selected. For accurate segmentation of medical images through the automatic means,it is necessary to remove the noise from the images. There are many methods such as learning based (traditional methods) and non-learning based methods(using various types neural networks).To measure the denoising accuracy, parameters like Signal-to-Noise Ratio (SNR), Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) are used. This paper discusses the results obtained through the various methods and their comparison in terms of PSNR,SSIM. Removing noise is crucial for accurate segmentation of medical images. These noise-less images are to be treated as pre-processed images for the segmentation task.

This chapter presents a comparison of the performance of integral (I) and proportional-integral-derivative (PID) controllers in frequency stabilization or load frequency control (LFC) of two-area interconnected power system considering generation rate constraints (GRCs) with Doubly fed induction generator (DFIG)-based wind energy. Two mathematically models are identified for investigations. Power system model 1 is two-area interconnected power system which contains two identical non-reheat thermal plants without DFIG participation. Whereas, power system model 2 contains two identical non-reheat thermal plants with dynamic participation of DFIG at both areas. Moreover, Harris Hawks Optimizer (HHO), Salp Swarm Algorithm (SSA), and Sine Cosine Algorithm (SCA) are applied to find the optimal values of the controller settings mentioned above. The effectiveness of the proposed controllers, which are optimally designed by several optimization techniques (i.e., HHO, SSA, and SCA) is tested and verified through an interconnected power system comprises two identical non-reheat thermal power plants with/without DFIG participation. Time-domain simulation results of the studied power system with all mentioned optimization techniques are carried out using Matlab/Simulink® software to validate the robustness of the proposed controllers.

A considerable number of intermittent renewable resources like photovoltaic generation and wind energy when integrated into the conventional grid technology causes serious issues in the power systems like frequency instability. So an intelligent controller is desired for steady and reliable operation of the electric grid. This paper deals with the frequency control of hybrid power system (HPS) employing a sine cosine adopted Harris' hawks optimization (SCaHHO) technique. The proposed technique aims at improving the performance of the original Harris' hawks optimization (HHO) algorithm by incorporating a sine and cosine function in the calculation of escaping energy and chances of escaping of prey respectively to emphasize the exploitation process of hawks. The effectiveness of the SCaHHO technique is validated with the novel HHO technique as well as moth flame optimization, sine cosine algorithm, grey wolf optimization, salp swarm algorithm and gravitational search algorithm using 23 standard test functions. A non-parametric statistical investigation is also carried out to verify the effectiveness of the suggested technique. Later the SCaHHO technique is utilized to tune a newly proposed adaptive fuzzy proportional integral derivative controller (AFPID) for frequency control of HPS. The suggested SCaHHO-tuned AFPID controller achieves an improved control action by moderating the frequency fluctuations as compared to the PID controller. Hardware-in-loop validation of the proposed load frequency control scheme is also carried out using OPAL-RT to measure its fidelity with the numerical simulation results.

When it comes to improving the performance of a wireless mesh network, the positioning of routers is critical. In order to provide the greatest network accessibility, it is essential that mesh routers be installed in appropriate locations. One way to improve the network’s performance is to increase the coverage while utilizing an optimum number of routers. The network coverage may be optimised using a number of different techniques that have been developed over time in the scientific literature. An algorithm called Harris Hawk’s Optimization (HHO) is being used in this study to optimally locate mesh routers in a mesh network in order to optimise coverage and reduce network congestion. The HHO identifies the best positions to place the routers in order to have the best possible network topology by removing the overlapping routers to minimize the number of routers while keeping the coverage maximized. In this research, 60, and 100 mesh routers are deployed in two different network topologies. The simulation results are analysed and compared with Sine Cosine Algorithm (SCA), Gray Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) algorithm. With regard to network coverage and congestion reduction, simulation results show that HHO surpasses the benchmark algorithms by having 98% coverage and 34% reduction in the network size.

In this study, we propose a CNN-GAN-based real-time processing technique for filtering images of underwater cables used in power systems. This addresses the excessive interference impurities that are frequently observed in images captured by remotely operated vehicles (ROVs). The process begins with the input of the original image into the convolutional neural network (CNN). Subsequently, the training outcomes, which serve as input parameters for the generative adversarial network (GAN), facilitate the filtering process. The system also calculates both the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR), performing model updates via backward propagation. This technique utilizes deep learning technologies to achieve rapid, real-time filtering of underwater cable images. The experimental results reveal that the loss function of the CNN reaches 0.16 with an accuracy of 97.5%, while the loss function of the adversarial GAN network approaches 0.05. Compared with traditional methods such as DDN, JORDOR, RESCAN, and PRENet, the proposed CNN-GAN algorithm exhibits superior performance, as evidenced by the higher PSNR and SSIM values. Specifically, for clear water images, the PSNR reaches 29.86 dB and the SSIM is 0.9045. For severely polluted images, the PSNR is 28.67 dB and the SSIM is 0.8965, while for unevenly illuminated images, the PSNR and SSIM values are 24.37 dB and 0.88, respectively. These enhancements significantly benefit the monitoring and maintenance of power systems.