Search Optimization Research Articles

A two-stage bidirectional coevolution algorithm with reverse search for constrained multiobjective optimization

Abstract Constrained multiobjective optimization problems (CMOPs) are widespread in reality. The presence of constraints complicates the feasible region of the original problem and increases the difficulty of problem solving. There are not only feasible regions, but also large areas of infeasible regions in the objective space of CMOPs. Inspired by this, this paper proposes a bidirectional coevolution method with reverse search (BCRS) combined with a two-stage approach. In the first stage of evolution, constraints are ignored and the population is pushed toward promising regions. In the second stage, evolution is divided into two parts, i.e., the main population evolves toward the constrained Pareto front (CPF) within the feasible region, while the reverse population approaches the CPF from the infeasible region. Then a solution exchange strategy similar to weak cooperation is used between the two populations. The experimental results on benchmark functions and real-world problems show that the proposed algorithm exhibits superior or at least competitive performance compared to other state-of-the-art algorithms. It demonstrates BCRS is an effective algorithm for addressing CMOPs. Graphical Abstract

Exploring the Human History: Cybernetic Modeling, Systemic Perspectives, and Applications in Archaeological Eras

Since the 1970s, cybernetic modeling of evolutionary processes has progressed, particularly with the development of the informatics-cybernetic model (ICM). This model conceptualizes humanity as a self-regulating hierarchical network system, continuously tracking energy-based target crite-ria through search optimization algorithms. The outcomes are recorded in the system memory of corresponding hierarchical subsystems. Within the ICM framework, the spatio-temporal charac-teristics of global evolution exhibit modifications reminiscent of the Zhirmunsky-Kuzmin number series, a geometric progression they identified in the exploration of critical levels in biosystem development. The study also showcases applications of mathematical-cybernetic modeling results in understanding historical processes examined by archaeologists and historians.

Task scheduling approach in fog and cloud computing using Jellyfish Search (JS) optimizer and Improved Harris Hawks optimization (IHHO) algorithm enhanced by deep learning

Task scheduling approach in fog and cloud computing using Jellyfish Search (JS) optimizer and Improved Harris Hawks optimization (IHHO) algorithm enhanced by deep learning

Enhancing CNN‐LSTM neural networks using jellyfish search algorithm for pandemic modeling

SummaryThis paper presents a comprehensive three‐step approach (CNN‐JSO‐LSTM) for predictive modeling using a pandemic such as COVID‐19 as a test case. Initially, a Convolutional Neural Network (CNN) is employed to extract crucial features pertinent to the pandemic. Subsequently, the Jellyfish Search Optimizer (JSO) algorithm is applied for feature selection, identifying the most relevant factors. These chosen features are then inputted into a Long Short‐Term Memory (LSTM) network, responsible for classifying samples into “healthy” and “diseased” categories. Our method enhances LSTM performance using the Jellyfish Search optimizer, resulting in exceptional prediction accuracy. Our experiments achieved remarkable metrics, with an accuracy of 95.32%, high sensitivity (94.87%), and precision (94.28%), surpassing alternative methods. In conclusion, our study presents a promising and highly accurate approach for pandemic prediction, harnessing deep learning and swarm intelligence techniques. These findings suggest a potential for more effective pandemic management and intervention strategies.

A novel on high voltage gain boost converter with cuckoo search optimization based MPPTController for solar PV system

Traditionally, isolated and non-isolated boost converters are used for solar photovoltaic systems (SPV). These converters have limitations such as low voltage gain, less voltage ripples, temperature dependence, high voltage stress across the switches, and being bulky in size. Besides, the solar PV system also has non-linear characteristics between I–V and P–V, and the energy yield potential is affected by partial shading phenomena. Therefore, maximum power point tracking (MPPT) is being added to the SPV system to get the maximum output power under steady and dynamic climate conditions. Although the conventional MPPT has drawbacks such as less accuracy in predicting the MPP under partial shading conditions, low tracking speed, and more ripples, Hence, the research proposes a stackable single switch boost converter (SSBC) with a Cuckoo search MPPT controller for the SPV system. The efficiency of the proposed circuit topology has been compared with conventional boost converters with various MPPTs. Subsequently, the accuracy of tracking true MPPT by CSO is compared with that of PSO and FPNA. The results show, that the CMPPT with CBC has produced more ripples, whereas the BMPPT with SSBC produces ripple-free power under steady conditions. It is also observed that SSBC with BMPPT produces more power than SSBC with TMPPT. The efficiency of SSBC with BMPPT is better than other combinations. Finally, a prototype model has been developed and verified.

An IoT‐based multiple teaching quality evaluation method for English translation with improved deep learning

AbstractTo enhance the teaching quality (TQ) of English translation (ET) courses, multivariate evaluation methods have garnered significant attention for their ability to identify deficiencies in the teaching process and subsequently improve instructional standards. Traditional evaluation techniques have shown limited effectiveness. Therefore, this paper proposes an ET in multiple teaching quality (MTQ) evaluation method with improved deep learning in internet of things (IoT). First, the paper establishes evaluation indicators for ET in MTQ, which mainly encompass ET teaching effectiveness, pedagogic competency in ET, teaching methods, content, as well as attitudes towards ET teaching. It then utilizes IoT technology to preliminarily collect data on these indicators, and using clustering algorithm based on weighted attributes and density (CABWAD) algorithm to mine data on English teaching MTQ evaluation indicators for ET. The extracted evaluation indicator data is then denoised using a probabilistic undirected graph model. Ultimately, the multilayer perceptron in deep learning is improved through Wolfe line search optimization, and this enhanced multilayer perceptron is employed to construct an ET in MTQ evaluation model. The denoised indicator data is inputted into the model, which then outputs precise MTQ evaluation results. The results show that the absolute value of the average Pearson correlation coefficient of this method is the highest, the Spearman correlation coefficient is the lowest, the mean average precision value is 0.965, and the positive category imbalance degree and the negative category imbalance degree are the lowest, indicating that the proposed method has outstanding performance in all aspects, and has certain application value in the field of TQ evaluation.

Slope stability prediction based on GSOEM-SV: A mobile application practicably deploy in engineering verification

Slope stability evaluation is a complex and uncertain system problem, and carrying out slope stability prediction is the prerequisite and foundation for slope disaster prevention. In order to achieve fast and accurate prediction of slope stability, this paper considers height, total slope angle, unit weight, cohesion, internal friction angle, and pore water pressure ratio as input features and proposes an intelligent slope stability prediction method based on grid search optimization ensemble learning model by soft voting (GSOEM-SV). First, 390 sets of on-site data were collected to form a dataset, and analyses including correlation coefficients, density estimates, and box lines were carried out. Then, the grid search optimization algorithm is used to optimize the hyperparameters of five algorithms—Gradient Boosting Decision Trees, Light Gradient Boosting Machine, Categorical Boosting, Support Vector Machine, and Random Forest, and integrates them through soft voting. Furthermore, this paper optimizes the hyperparameters of the above five algorithms based on grid search, particle swarm and simulated annealing algorithms, builds 15 improved models and 2 ensemble models and conducts comparison. The results reveal that the GSOEM-SV has the highest slope stability prediction accuracy, up to 91 %, the area under the curve (AUC) is 0.950, and its F1 score 0.917, which are better than the 15 improved and 2 integrated models. In addition, a set of slope stability prediction app based on uni-app is developed in the paper. It provides a technical foundation and an open and shareable information service platform for slope hazard prediction in geotechnical engineering.

Enhancing forest optimization algorithm with gravitational search for nonlinear continuous optimization

Meta-heuristic algorithms have great role in solving problems related to optimization. Meta-heuristic method cannot solve problems related to optimization due to No Free Lunch theory. Hence different optimization methods are proposed by various researchers each year in order to solve optimization problems. Forest Optimization Algorithm (FOA) is an evolutionary optimization algorithm that is appropriate for continuous nonlinear optimization problems. The algorithm drawbacks include entrapment in local optimum and failure in achieving global optimum. The paper proposes hybrid algorithm called FOAGSA, in which the Gravitational Search Algorithm (GSA) is employed to improve the FOA performance in order to solve nonlinear continuous problems. The FOAGSA was evaluated through 39 benchmark optimization functions and two engineering problems. The experimental results proved that the FOAGSA exhibited acceptable results compared to state-of-art and well-known Meta-heuristic algorithms. Friedman ranking algorithm was utilized to compare FOAGSA with existing methods. The FOAGSA was ranked first on that basis.

Taylor Shepherd Golden Optimization-Enabled ResUNet for Forest Change Detection Using Satellite Images

The pivotal task of remote sensing image (RSI) processing change detection (CD) highly aims to accurately detect changes in land cover based on multi-temporal images. With the advent of deep learning, technology has delivered remarkable results in the last years in the detection of variations in forest land cover data. Some of the conventional CD techniques are weak and are highly susceptible to errors and can result even in inaccurate outcomes. Thus, certain techniques are not desirable for real-time CD applications. To abridge this gap, this research introduces an innovative work for forest CD utilizing the proposed Taylor Shepherd Golden Optimization_ResUNet (TSGO_ResUNet) and Fuzzy Neural network (Fuzzy NN) for segment mapping. Here, the segmentation process is accomplished using ResUNet to determine the exact boundary or shape of each object for every pixel in the image. Furthermore, TSGO is achieved by consolidating Taylor Shuffled Shepherd Optimization (TSSO) with Golden Search Optimization (GSO). In addition, the devised TSGO_ResUNet + Fuzzy NN has gained maximum accuracy and kappa coefficient of 0.952 and 0.785, and minimum error rate of 0.051.

Cascaded Fractional-Order Controller-Based Load Frequency Regulation for Diverse Multigeneration Sources Incorporated with Nuclear Power Plant

To sustain a system frequency within acceptable limits, it is widely conceded that retaining a power balance between generation and demand is necessary. In order to regulate the frequency of power systems (PSs) this article proposes a novel cascaded based fractional-order controller termed as fractional-order integer- (FOI-) fractional-order proportional integral with double derivative (FOPIDD2). In addition to redox flow batteries and capacitive energy storage, the recommended control strategy has been validated with gas, thermal reheat, hydro, and nuclear power systems. Additionally, a newly designed algorithm known as squid game optimizer (SGO) optimizes the gains of the new FOI-FOPIDD2 controller. The squid game optimizer technique is inspired by the fundamental principles of a conventional Korean sport. It employs a population of candidate solutions and iteratively adjusts the control parameters to discover the optimal set that reduces frequency abnormalities and improves system stability. A comparison is also made between the controller’s performance and benchmarks, including the jellyfish search algorithm, the firefly algorithm, the grey wolf optimizer, and the particle swarm algorithm. The proposed algorithms reduced peak overshoot as compared to grey wolf optimizer algorithm by 35.34%, 46.78%, and 76.89%; jellyfish search optimization algorithm by 34.76%, 77.22%, and 82.56%; and firefly algorithm by 82.67%, 89.23%, and 29.67% for frequency variations in area 1, area 2 and tie line power, respectively. Furthermore, SGO-FOI-FOPIDD2 controllers under different loading circumstances and conditions were evaluated and endorsed for their ability to withstand uncertainties in power system parameters.

Using the Cuckoo Optimization to Initialize the Harmony Memory in Harmony Search Algorithm to Find New Hybrid (CSHS) Algorithm

The current paper seeks to present a hybrid harmony search algorithm, using CS and HS. The proposed algorithm takes advantage of using a method to initialize the harmony memory (HM) with the help of the cuckoo search optimization algorithm. The HS algorithm is inspired by the method used by musicians to create and enhance harmony in music. It follows 3 main principles of pitch adjustment (PA), HM consideration (HMC), and random selection (RS). The performance of HS can be affected by its poor accuracy in optimization and speed of convergence, 2 main issues with it. However, to improve the HS algorithm, Cuckoo search can be used as it can do a local search using one parameter only, other than the size of the population, making it work more efficiently. This current method has been tested for its validity and efficiency in performance by being implemented on many international standard optimization problems. The results confirm the fact that the performance of the currently proposed algorithm is better and more efficient in finding solutions compared to HS and other algorithms.

Hybrid Crow Search and Particle Swarm Algorithmic optimization based CH Selection method to extend Wireless Sensor Network operation

In ad hoc wireless sensor networks, the mobile nodes are deployed to gather data from source and transferring them to base station for reactive decision making. This process of data forwarding attributed by the sensor nodes incurs huge loss of energy which has the possibility of minimizing the network lifetime. In this context, cluster-based topology is determined to be optimal for reducing energy loss of nodes in WSNs. The selection of CH using hybrid metaheuristic algorithms is identified to be significant to mitigate the quick exhaustion of energy in entire network. This paper explores the concept of hybrid Crow Search and Particle Swarm Optimization Algorithm-based CH Selection (HCSPSO-CHS) mechanism is proposed with the merits of Flower Pollination Algorithm (FPA) and integrated Crow Search Algorithm (CSA) for efficient CH selection. It further adopted an improved PSO for achieving sink node mobility to improve delivery of packets to sink nodes. This HCSPSO-CHS approach assessed the influential factors like residual energy, inter and intra-cluster distances, network proximity and network grade during efficient CH selection. It facilitated better search process and converged towards the best global solution, such that frequent CH selection is avoided to maximum level. The outcomes of the suggested simulation HCSPSO-CHS confirm better performance depending on the maximum number of active nodes by 23.18%, prevent death of sensor nodes by 23.41% with augmented network lifetime of 33.58% independent of the number of nodes and rounds of data transmission.

Study of the Geometry of an Oscillating Water Column Device with Five Chambers Coupled under Regular Waves through the Constructal Design Method

This research conducts a numerical study of a wave energy converter (WEC) device with five coupled hydropneumatic chambers, operating based on the principle of an oscillating water column (OWC). A turbine was not included, only considering the tube without it. The computational domain was defined by a wave channel housing an OWC device subjected to regular incident waves. The central objective was to assess the impact of chamber geometry on maximizing the total hydropneumatic power in energy conversion. The numerical simulations consider the pressure, mass flow rate, and total hydropneumatic power, with the latter being the performance indicator. To determine the geometries to be analyzed, the Constructal Design method was employed in conjunction with the exhaustive search optimization method to maximize the performance indicator. The degrees of freedom defined were the ratios between the height (Hn) and the length (Ln) of the hydropneumatic chambers (Hn/Ln, where n varies from one to five). Based on the results of the mass flow rate and pressure, their influence on power was evaluated. It was observed that the influence of the degrees of freedom on the pressure difference, mass flow rate, and hydrodynamic power was quite similar, displaying an increase for low ratios of Hn/Ln up to a maximum magnitude and followed by a decrease in magnitude. The best performance was achieved for the geometric configuration with Hn/Ln = 0.2613 (Hn = 5.0625 m and Ln = 15.8219 m), representing an improvement of 98.6% compared to the worst case analyzed.

Filtered Ofdm System Model for Papr Reduction in the Growth Of 5g

A proposed waveform for fifth generation (5G) communications is the filtered orthogonal frequency division multiplexing (F-OFDM) system. Filtering-based waveform frameworks distinguish themselves by suppressing out-of-band emission and asynchronous transmission. Meanwhile, the high Peak-To-Average Power Ratio (PAPR) remains a barrier to new waveform possibilities. Partials transmit sequence (PTS) is a successful strategy for reducing high PAPR in multicarrier networks. This work presents a multicarrier in OFDM and UFMC based on the Filter Bank Multicarrier (FBMC) waveform for communication systems. Furthermore, FBMC waveforms have limited orthogonality between subcarriers, which can mitigate Doppler and multipath effects. This FBMC approach uses the cosine law to filter the traffic signal, and the Welch algorithm is offered for segmentation, which lowers noise in estimated power spectra. As a result, a hybrid Selective Mapping (SLM) with Cuckoo Search and Ant Lion Optimization (CS-ALO) algorithms is suggested using the FBMC framework to reduce PAPR in the OFDM system. The proposed work is implemented, and detailed experimental research is carried out to show the increased performance in 5G networks. Based on a fair comparison, the F-OFDM scheme outperforms previous approaches in terms of BER and multicarrier system capacity. Simulation results show that the proposed waveform design and processing method outperform standard OFDM and F-OFDM methods in PAPR reduction and communication integrated systems.

Adam golden search optimization enabled DCNN for classification of breast cancer using histopathological image

Breast Cancer (BC) is a killing disorder, every year it kills millions of human beings. Early diagnosis is the only way to mitigate the mortality rate. Among all kinds of screening methods, medical imaging is an essential method for screening BC. Existing medical imaging alters the tissue structure and cell morphology. To overcome these limitations, histopathology image is used because it can support the decision of pathologists about the closeness or the non-appearance of a disease, as well as it can help in infection development estimation. Hence, this research develops an efficient method for BC classification using the proposed Adam Golden Search Optimization-based Deep Convolutional Neural Network (AGSO-DCNN). Initially, Gaussian filter-enabled pre-processing is utilized for mitigating the noises composed in the input images. Afterwards, k-means clustering is used to feed the input images into the segmentation phase to reduce the complexity of the image. Then, to extract features like shape features, statistical features, Local Vector Patterns (LVP), and Pyramid Histogram of Oriented Gradients (PHOG) feature extraction is performed. Thereafter, the obtained features are forwarded to the multi-grade BC classification stage, where DCNN is employed for classifying the image into six categories, such as apoptosis, tubule, mitosis, non-tubule, tumour nuclei, and non-tumor nuclei. DCNN is trained by the formulated AGSO mechanism, which is obtained by incorporating the Adam Optimizer and Golden Search Optimization (GSO) algorithm. Moreover, the AGSO-based DCNN technique achieved better accuracy, TPR and TNR with the values of 97.90%, 98.00%, and 98.30%, respectively.

Fabric surface defect classification and systematic analysis using a cuckoo search optimized deep residual network

Fabric defects can significantly impact the quality of a textile product. By analyzing the types and frequencies of defects, manufacturers can identify process inefficiencies, equipment malfunctions, or operator errors. Although deep learning networks are accurate in classification applications, some defects may be subtle and difficult to detect, while others may have complex patterns or occlusions. CNNs may struggle to capture a wide range of defect variations and generalize well to unseen defects. Discriminating between genuine defects and benign variations requires sophisticated feature extraction and modeling techniques. This paper proposes a residual network-based CNN model to enhance the classification of fabric defects. A pretrained residual network, ResNet50, is fine-tuned to classify fabric defects into four categories: holes, objects, oil spots, and thread errors on the fabric surface. The fine-tuned network is further optimized via cuckoo search optimization using classification error as a fitness function. The network is systematically analyzed at different layers, and the investigation of classification results are reported using a confusion matrix and classification accuracy for each class. The experimental results confirm that the proposed model achieved superior performance with 95.36% accuracy and a 95.35% F1 score for multiclass classification. In addition, the proposed model achieved higher accuracy with similar or fewer trainable parameters than traditional deep CNN networks.

Multi‐mode non‐linear inversion of Rayleigh wave dispersion curves with grey wolf optimization and cuckoo search algorithm

AbstractDispersion curve inversion is one of the core contents of Rayleigh wave data processing. However, the dispersion curve inversion has the characteristics of multi‐parameter, multi‐extremum as well as nonlinearity. In the face of Rayleigh wave data processing under complex seismic‐geological conditions, it is difficult to reconstruct an underground structure quickly and accurately apply a single global‐searching non‐linear inversion algorithm. For this reason, we proposed a strategy to invert multi‐order mode Rayleigh wave dispersion curves by combining with grey wolf optimization (GWO) and cuckoo search (CS) algorithms. On the basis of introducing the mechanism of iterative chaotic map with infinite collapses (ICMIC) and the strategy of dimension learning–based hunting (DLH), an improved GWO was developed that was called IDGWO (ICMIC and DLH GWO). After searching the near‐optimal region through IDGWO, the CS with a variable step‐size Lévy flight search mechanism was switched adaptively to complete the final inversion. The correctness of our method was verified by the multi‐order mode dispersion curve inversion of a six‐layer high‐velocity interlayer model. Then it was further applied to the processing of real seismic datasets. The research results show that our method fully utilizes the advantages of each of the two global‐searching non‐linear algorithms after integrating IDGWO and CS, while effectively balancing the ability between global search and local exploitation, further improving the convergence speed and inversion accuracy and having good anti‐noise performance.

Search and hunt based-driving scene perception network for distance estimation and object detection

Visual tracking is generally utilized in numerous applications including surveillance and autonomous driving to provide a wide angle of vision. However, different types of alteration, including occlusion, pose, and illumination present in the video sequence act as one of the crucial troubles considered in visual tracking. Hence, this research developed a modified Deep learning (DL) approach useful for distance estimation, object detection, and pixel-wise semantic segmentation by shared convolutional architecture. The proposed object detection model employs a modified Driving Scene Perception network (DSP), which makes use of multi-task learning to enhance the efficacy of distance evaluation, semantic segmentation, and object detection. The prime significance of the research relies on the Search and Hunt optimization (SaHO) algorithm, which optimally selects the hyperparameter value of the DSP network. The experimental analysis substantiates that the proposed modified DSP network effectively estimates the distance between the moving object and the camera. The experimental analysis depicts the effectiveness of the DSP with SaHO model for both segmentation and object detection. For object detection, the DSP with SaHO model attained high rates of 0.98, 0.94, and 0.96 for accuracy, specificity, and sensitivity respectively utilizing the cityscape dataset. Additionally, the DSP with SaHO approach attained the lowest errors for segmentation and surpassed other existing techniques that revealed the efficiency of the DSP with the SaHO model.

Improvement of UAV thrust using the BSO algorithm-based ANFIS model

Abstract Unmanned aerial vehicles (UAVs), which are available in our lives in many areas today, bring with them new expectations and needs along with developing technology. In order to meet these expectations and needs, main subjects such as reducing energy consumption, increasing thrust and endurance, must be taken into account in UAV designs. In this study, Backtracking search optimisation (BSO) algorithm-based adaptive neuro-fuzzy inference system (ANFIS) model is proposed for the first time to improve UAV thrust. For this purpose, first, different batteries and propellers were tested on the thrust measuring device and a data set was obtained. Propeller diameter and pitch, current, voltage and the electronic speed controller (ESC) signal were selected as input, and UAV thrust was selected as output. ANFIS was used to relate input and output parameters that do not have a direct relationship between them. In order to determine the ANFIS parameters at the optimum value, ANFIS was trained with the obtained data set by using BSO algorithm. Then, the objective function based on the optimum ANFIS structure was integrated into BSO algorithm, and the input values that gave the optimum thrust were calculated using BSO algorithm. Simulation results, in which parameters such as engine, battery and propeller affecting the thrust are taken into account equally, emphasise that the proposed method can be used effectively in improving the UAV thrust. This hybrid method, consisting of ANFIS and BSO algorithm, can reduce the cost and time loss in UAV designs and allows many possibilities to be tested.

A grey wolf optimization algorithm for solving partial destructive disassembly line balancing problem consider feasibility evaluation and noise pollution

Partial destructive disassembly (PDD) is a crucial tool for enhancing efficiency and reducing disassembly costs when recycling complex end-of-life (EOL) products. Evaluating the feasibility of PDD is crucial for determining its implementation. However, the existing partial destructive disassembly line balancing (PDDLB) problem prioritizes profitability and randomly selects components for destructive, disregarding the feasibility of PDD and the noise pollution resulting from destructive operations. To address this concern, this paper introduces the integration of feasibility evaluation and noise considerations into the PDDLB problem for the first time. Subsequently, a mathematical model is established for the PDDLB problem, aiming to minimize disassembly costs, achieve smoothness balance, minimize the number of stations, and mitigate the adverse effects of noise. Then, an improved grey wolf optimization algorithm (IGWOA) considering feasibility evaluation and noise limitations is developed. It non-linearizes the convergence factor to enhance accuracy in the search for optimality, introduces a Lévy flight operation to further expand the search solution space, and incorporates an interference factor to prevent local optimality. In addition, the superiority of the proposed algorithm in solving different cases is verified by comparing five algorithms for the 25-task example and seven algorithms for the 52-task example in the latest literature. Finally, the proposed method is applied to a real engine case. The obtained results are compared with several classical Swarm Intelligence methods. The comparison results show that IGWOA has advantages due to other group intelligence methods in solving small, medium, and large-scale example. Moreover, the disassembly cost is comparatively low.