CSO Algorithm Research Articles

Power quality improvement of PWM AC Chopper fed capacitor run induction motor using BFO, PSO and CSO Algorithm

This paper exhibits performance enhancement of PWM AC chopper fed capacitor run induction motor by using optimization algorithm. The PWM AC chopper utilizes enhanced asymmetrical pulse width modulation technique by incorporating four pulses in quarter cycle. The switching instants are obtained optimally by bacteria foraging optimization, particle swarm optimization and cuckoo search optimization algorithm. The power quality parameters considered in this paper are total harmonic distortion of current, total harmonic distortion of voltage, power factor and efficiency. The simulation result shows that proposed algorithm shows better performance compared to other optimization techniques.

Pulling color from a colored image for coloring gray images using CSO algorithm

Pulling color from a colored image for coloring gray images using CSO algorithm

Nearly-zero carbon optimal operation model of hybrid renewable power stations comprising multiple energy storage systems using the improved CSO algorithm

In light of the abundant renewable energy resources in Northwestern China, this study introduces a novel hybrid power plant structure known as the (Renewable energy-concentrating solar power-combined heat and power) RCC system. The RCC system integrates various energy sources, including the photovoltaic, the wind power plant, the concentrating solar power (CSP) plant, and the combined heat and power (CHP) plant. It also incorporates power-to-gas (P2G) technology to convert wind and solar power surpluses into methane. Moreover, carbon capture and storage (CCS) technology is applied to capture carbon dioxide emissions from the CHP plants, which serves as a raw material for the P2G process. To address the energy trilemma, we develop a nearly-zero carbon emission optimization model for the RCC system, considering different renewable energy source (RES) endowments. The fuzzy membership function method is employed to identify the optimum satisfaction target across multiple attributes. An enhanced CSO algorithm is introduced and validated using a simulation study on a CSP plant in Dunhuang. The results show that compared with traditional power stations, the proposed RCC system can reduce the investment cost by 34.45 %, increase the operating income by 17.7 %, and reduce carbon emission by 3.2 %. At the same time, the methane stock in the system increased by 53.7 % compared with the traditional power station containing P2G equipment, which helps the hybrid power station to participate in the methane market and obtain more profits. In addition, the direct energy supply ratio of RES decreased by 83.16 %, reducing the risk of the system caused by the uncertainty of RES. To sum up, the proposed RCC system has a good development prospect.

Hyper-parameter tuning for support vector machine using an improved cat swarm optimization algorithm

Support vector machine (SVM) is a supervised machine learning algorithm for classification and regression problems. SVM performs better when combined with other classifiers or optimized with an optimization algorithm. The SVM parameters such as kernel and penalty have good performance on the classification accuracy. Recently, a lot of evolutionary optimization algorithms were used for optimizing the SVM. In this paper, an Improved Cat Swarm Optimization (ICSO) was proposed for optimizing the parameters of SVM with the aim of enhancing its performance. CSOs have the problem of a low convergence rate and are easily trapped in local optima. To address this problem, a new parameter was added to the velocity for the tracing mode and the Opposition-Based Learning (OBL) technique was used to modify the CSO algorithm (ICSO-SVM). A new parameter was introduced to guide the cats’ positions to the local and global best positions in the velocity tracing mode of the CSO algorithm. The proposed algorithm was verified using 15 datasets from the University of California Irvine (UCI) data repository and also six different performance metrics were used. The experimental results clearly indicate that the proposed method performs better than the other state-of-the-art methods.

A Compact Snake Optimization Algorithm in the Application of WKNN Fingerprint Localization.

Indoor localization has broad application prospects, but accurately obtaining the location of test points (TPs) in narrow indoor spaces is a challenge. The weighted K-nearest neighbor algorithm (WKNN) is a powerful localization algorithm that can improve the localization accuracy of TPs. In recent years, with the rapid development of metaheuristic algorithms, it has shown efficiency in solving complex optimization problems. The main research purpose of this article is to study how to use metaheuristic algorithms to improve indoor positioning accuracy and verify the effectiveness of heuristic algorithms in indoor positioning. This paper presents a new algorithm called compact snake optimization (cSO). The novel algorithm introduces a compact strategy to the snake optimization (SO) algorithm, which ensures optimal performance in situations with limited computing and memory resources. The performance of cSO is evaluated on 28 test functions of CEC2013 and compared with several intelligent computing algorithms. The results demonstrate that cSO outperforms these algorithms. Furthermore, we combine the cSO algorithm with WKNN fingerprint positioning and RSSI positioning. The simulation experiments demonstrate that the cSO algorithm can effectively reduce positioning errors.

Cooperative coevolutionary competition swarm optimizer with perturbation for high-dimensional multi-objective optimization

In the realm of high-dimensional problem spaces, particle swarm optimizers have been found to exhibit unnecessary roaming behavior. In response, this paper proposes a cooperative coevolutionary competition swarm optimizer with perturbation (CPCSO) that reduces computational resource consumption. The CPCSO is both simple and effective. Specifically, this optimizer divides the swarm into two sub-swarms, denoted NP1 and NP2. A modified CSO algorithm is used in NP1 to facilitate search space exploration while ensuring that the swarm is well diversified. In NP2, perturbation is introduced to each loser particle to guide it along a smooth granular trajectory, thereby avoiding unnecessary oscillations and improving its capacity to exploit the search space. The two sub-swarms exchange information to balance convergence and distribution, with excellent particles shared between them. Finally, we demonstrate the efficacy of the proposed CPCSO algorithm and several state-of-the-art high-dimensional multi-objective optimizers on the high-dimensional benchmark set LSMOP. Our experimental results indicate that the proposed CPCSO outperforms other algorithms regarding solution quality, convergence speed, and computational cost. Notably, the proposed optimizer demonstrates robust performance across various landscape problems.

English

Phishing is a type of online fraud which enables attackers to trick individuals into giving away confidential data like login credentials or financial data. A phishing website utilizes a URL that is comparable to a reasonable website to trick users into thinking it is legitimate, or it may comprise suspicious links or forms which has been developed for collecting sensitive data from users. Machine learning (ML) can be utilized to categorise websites as phishing or legitimate to protect users from falling victim to these attacks. There are several approaches to using machine learning for phishing website classification. This article focuses on the design of Chicken Swarm Optimization with Improved Random Forest for Phishing Website Classification (CSOIRF-PWC) technique. The CSOIRF-PWC technique aims to discriminate the legitimate and phishing websites accurately. To execute this, the presented CSOIRF-PWC approach initially performs the data normalization process. Next, the classification of phishing websites takes place using the IRF classifier. For improving the classification performance of the RF classifier, the parameter tuning process is performed through the CSO algorithm, which supports attaining improved classification performance. The simulation values of the CSOIRF-PWC methodology are investigated on two datasets, and the outputs are investigated under diverse measures. The comprehensive comparative outcomes emphasized the enhanced performance of the CSOIRF-PWC system over other methodologies in terms of several measures.

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

Accurate soil prediction is a vital parameter involved to decide appropriate crop, which is commonly carried out by the farmers. Designing an automated soil prediction tool helps to considerably improve the efficacy of the farmers. At the same time, fuzzy logic (FL) approaches can be used for the design of predictive models, particularly, Fuzzy Cognitive Maps (FCMs) have involved the concept of uncertainty representation and cognitive mapping. In other words, the FCM is an integration of the recurrent neural network (RNN) and FL involved in the knowledge engineering phase. In this aspect, this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classification (FCMCSO-ASC) technique. The goal of the FCMCSO-ASC technique is to identify and categorize seven different types of soil. To accomplish this, the FCMCSO-ASC technique incorporates local diagonal extrema pattern (LDEP) as a feature extractor for producing a collection of feature vectors. In addition, the FCMCSO model is applied for soil classification and the weight values of the FCM model are optimally adjusted by the use of CSO algorithm. For examining the enhanced soil classification outcomes of the FCMCSO-ASC technique, a series of simulations were carried out on benchmark dataset and the experimental outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.

Optimal estimation of proton exchange membrane fuel cell model parameters based on an improved chicken swarm optimization algorithm

ABSTRACT Proton exchange membrane fuel cell (PEMFC) has been gradually applied in new energy vehicles, aviation and other industries, attracting widespread attention. Accurately identifying unknown parameters in the mathematical model of PEMFC is beneficial to the simulation, control and prediction of its output Current-Voltage curve. In order to identify the optimal unknown parameters, based on basic Chicken Swarm Optimization, this paper introduces positive/negative learning strategies for roosters and positive learning strategies for hens and chicks. An Improved Chicken Swarm Optimization algorithm is proposed. Compared with Particle Swarm Optimization, Salp Swarm Algorithm, Whale Optimization Algorithm and basic CSO algorithm, the proposed algorithm shows better convergence and accuracy. The five algorithms are applied to three common stacks (250W PEMFC, NedStack PS6 PEMFC, Ballard Mark V) and PEMFC monomer for model unknown parameter identification and optimization. The results show that, the ICSO algorithm obtains the minimum integral of absolute error of the actual stack voltage and the simulated stack voltage in the three test stacks and a PEMFC monomer, which are 2.288, 5.857, 2.407 and 0.408, the ICSO algorithm has a maximum increase of 8.63%, 4.52%, 6.20% and 64.83% in accuracy, respectively. The simulation data agrees well with the experimental data. These indicating that the mathematical model of PEMFC based on ICSO algorithm can accurately simulate the polarization curve at different temperatures and partial pressures, and it can be obtained that with the increase of temperature and partial pressure, the output performance of the PEMFC is also getting better.

Crystal Structure Optimization with Deep-Autoencoder-Based Intrusion Detection for Secure Internet of Drones Environment

Drone developments, especially small-sized drones, usher in novel trends and possibilities in various domains. Drones offer navigational inter-location services with the involvement of the Internet of Things (IoT). On the other hand, drone networks are highly prone to privacy and security risks owing to their strategy flaws. In order to achieve the desired efficiency, it is essential to create a secure network. The purpose of the current study is to have an overview of the privacy and security problems that recently impacted the Internet of Drones (IoD). An Intrusion Detection System (IDS) is an effective approach to determine the presence of intrusions in the IoD environment. The current study focuses on the design of Crystal Structure Optimization with Deep-Autoencoder-based Intrusion Detection (CSODAE-ID) for a secure IoD environment. The aim of the presented CSODAE-ID model is to identify the occurrences of intrusions in IoD environment. In the proposed CSODAE-ID model, a new Modified Deer Hunting Optimization-based Feature Selection (MDHO-FS) technique is applied to choose the feature subsets. At the same time, the Autoencoder (AE) method is employed for the classification of intrusions in the IoD environment. The CSO algorithm, inspired by the formation of crystal structures based on the lattice points, is employed at last for the hyperparameter-tuning process. To validate the enhanced performance of the proposed CSODAE-ID model, multiple simulation analyses were performed and the outcomes were assessed under distinct aspects. The comparative study outcomes demonstrate the superiority of the proposed CSODAE-ID model over the existing techniques.

Dietary assessment framework using improved K-means clustering and optimisation assisted CNN

ABSTRACT Dietary intakes portray what someone consumes throughout a day, which also offer important insight for carrying out the intercession programs to avoid several chronic diseases. Precise tools and techniques of assessing nutritional intakes are necessary for monitoring the dietary condition of patients for clinical and epidemiological research on the relationships between health and diet. Measuring the exact dietary intakes is regarded as an open issue in the health and nutrition fields. Thereby, this work develops a new dietary assessment model implemented with four main phases like ‘(1) pre-processing, (2) segmentation, (3) feature extraction and (4) classification’. The input image is first subjected to pre-processing, which includes median filtering to decrease noise. The pre-processed image is then used in segmentation, which is performed using modified K-means clustering. Then comes feature extraction, which involves extracting colour, shape and texture-based features. Following that, the collected features are classified using an optimised CNN. Furthermore, the weights of CNN are fine-tuned using Self-Adaptive Cat Swarm Optimisation (SA-CSO), which is an upgraded version of the CSO algorithm, to improve the accuracy of the created approach.

The simplified hybrid model based on BP to predict the reference crop evapotranspiration in Southwest China.

The accurate prediction of reference crop evapotranspiration is of great significance to climate research and regional agricultural water management. In order to realize the high-precision prediction of ETO in the absence of meteorological data, this study use XGBoost to select key influencing factors and BP algorithm to construct ETO prediction model of 12 meteorological stations in South West China in this study. ACO, CSO and CS algorithms are used to optimize the model and improve the adaptability of the model. The results show that Tmax, n and Ra can be used as the input combination of ETO model construction, and Tmax is the primary factor affecting ETO. ETO model constructed by BP algorithm has good goodness of fit with the ETO calculated by FAO-56 PM and ACO, CSO and CS have significant optimization effect on BP algorithm, among which CSO algorithm has the best optimization ability on BP, with RMSE, R2, MAE, NSE, GPI ranging 0.200-0.377, 0.932-0.984, 0.140-0.261, 0.920-0.984, 1.472-2.000, GPI ranking is 1-23. Therefore, the input combination (Tmax, n and Ra) and CSO-BP model are recommended as a simplified model for ETO prediction in Southwest China.

Cat Swarm Optimization-Based Computer-Aided Diagnosis Model for Lung Cancer Classification in Computed Tomography Images

Lung cancer is the most significant cancer that heavily contributes to cancer-related mortality rate, due to its violent nature and late diagnosis at advanced stages. Early identification of lung cancer is essential for improving the survival rate. Various imaging modalities, including X-rays and computed tomography (CT) scans, are employed to diagnose lung cancer. Computer-aided diagnosis (CAD) models are necessary for minimizing the burden upon radiologists and enhancing detection efficiency. Currently, computer vision (CV) and deep learning (DL) models are employed to detect and classify the lung cancer in a precise manner. In this background, the current study presents a cat swarm optimization-based computer-aided diagnosis model for lung cancer classification (CSO-CADLCC) model. The proposed CHO-CADLCC technique initially pre-process the data using the Gabor filtering-based noise removal technique. Furthermore, feature extraction of the pre-processed images is performed with the help of NASNetLarge model. This model is followed by the CSO algorithm with weighted extreme learning machine (WELM) model, which is exploited for lung nodule classification. Finally, the CSO algorithm is utilized for optimal parameter tuning of the WELM model, resulting in an improved classification performance. The experimental validation of the proposed CSO-CADLCC technique was conducted against a benchmark dataset, and the results were assessed under several aspects. The experimental outcomes established the promising performance of the CSO-CADLCC approach over recent approaches under different measures.

Stray capacitances calculation and harmonic measurement of capacitor voltage transformer

AbstractWhen the manufacturers produce capacitor voltage transformers (CVT), the function of harmonic measurement is not considered. Therefore, this paper explores methods to solve the problems of harmonic measurement from the perspective of manufacturers. Using the amplitude‐frequency characteristic curve of CVT under no‐load condition and standard environment as the benchmark, the estimation method of stray capacitance parameters in CVT based on CSO algorithm is proposed. Besides, in order to improve the accuracy of harmonic correction of CVT in different operating environments, this paper deeply studies the influence of oil temperature and industrial frequency on internal parameters and harmonic transfer characteristics of CVT. On this basis, this paper proposes a correction method of CVT harmonic transfer characteristic curves under different operating environments based on BP neural network algorithm. Finally, under the actual operating environment, calculating the amplitude‐frequency characteristic curve of CVT by utilizing the actual harmonic voltages at the secondary side of the CVT and RCVT, and comparing it with the amplitude‐frequency characteristic curve of CVT predicted by the BP neural network. The results show that the proposed methods are effective and feasible.

Parameter extraction of photovoltaic cell based on a multi-objective approach using nondominated sorting cuckoo search optimization

The extraction of PV cell and module parameters is vital for the accurate simulation of PV systems. PV cell exhibits non-linear nature of I–V and P–V curves. Hence, parameters estimated at the optimum value of the current error criterion, such as root mean square error (RMSE) of current, may not give accurate power estimation at maximum power point (MPP). In this work, the shortcomings of the single objective optimization (SOO) approach based parameter estimation methods are assessed using two different problem formulations: compound objective function and weighted sum. The results from the SOO approach indicate that weightage assigned to objectives such as RMSE and the percentage relative power Error at MPP (% RPE) has impacted the accuracy of parameter estimation. The selection of weightage for each objective is indeed a difficult choice to make. Moreover, the obtained cumulative value of RMSE and % RPE is high. In order to overcome these shortcomings of the SOO approach, a multi-objective optimization (MOO) approach based parameter estimation is formulated. Then formulated MOO problem is solved by using the proposed nondominated sorting cuckoo search optimization (NSCSO). Combining nondominated sorting, a crowded comparison technique, and Lévy flight characteristics, the NSCSO algorithm is proposed, which is inspired by both the NSGA-II and NSCS algorithms. Results indicate that the proposed parameter estimation method based on the MOO approach using NSCSO has given the optimum value for cumulative RMSE and % RPE in comparison with the SOO approach using the CSO algorithm. The proposed method is also validated on various PV models: PVM 752 (GaAs thin film) cell, STM6-40 (monocrystalline), and STP6-120/36 (polycrystalline) silicon modules.

Assessing and Improving Intelligent Physical Education Approaches Using Modified Cat Swarm Optimization Algorithm

In general, technological innovations have transformed sports training or physical education classrooms constructively. Physical education instructors can develop personalized and realistic expectations for their students using software, streaming videos, cameras, and trackers. However, the intelligent physical education models seek efficient assessment to improve its real-time acceptance. This paper proposes Enhanced Cat Swarm Optimization (ECSO) algorithm to create a physical education system assessment model and increase the evaluation impact of sports training methods. This research identifies and explains various factors to design a multi-functional physical education monitoring device based on visual sensing that meets the real needs of users. To find out how sensitive the parameters are, this study uses the local sensitivity analysis theory. It incorporates real-world needs to suggest an optimized CSO algorithm with modified searching and tracking modes. Subsequently, the proposed methodology implements a randomized experiment to assess the model’s success. The proposed ECSO algorithm employing modified searching and tracing modes gives the best assessment of 98.8%.

Competitive Swarm Optimization with Encryption Based Steganography for Digital Image Security

Digital image security is a fundamental and tedious process on shared communication channels. Several methods have been employed for accomplishing security on digital image transmission, such as encryption, steganography, and watermarking. Image stenography and encryption are commonly used models to achieve improved security. Besides, optimal pixel selection process (OPSP) acts as a vital role in the encryption process. With this motivation, this study designs a new competitive swarm optimization with encryption based stenographic technique for digital image security, named CSOES-DIS technique. The proposed CSOES-DIS model aims to encrypt the secret image prior to the embedding process. In addition, the CSOES-DIS model applies a double chaotic digital image encryption (DCDIE) technique to encrypt the secret image, and then embedding method was implemented. Also, the OPSP can be carried out by the design of CSO algorithm and thereby increases the secrecy level. In order to portray the enhanced outcomes of the CSOES-DIS model, a comparative examination with recent methods is performed and the results reported the betterment of the CSOES-DIS model based on different measures.

Optimization of CSO algorithm based on adaptive inertia weight coefficient

The traditional CSO algorithm is easy to fall into local extremum in optimization. In this paper, a CSO algorithm based on weight coefficient is proposed. In the CSO algorithm, the inertia weight coefficient is introduced into the hen position formula, and the learning factor influenced by the rooster is added to the chick position formula. Finally, using the idea of heredity, individuals with excellent fitness value are selected for crossover and mutation with a certain probability. Through the simulation comparison of five typical test functions, the simulation results show that the improved CSO algorithm can avoid local optimization, strengthen the global extreme value search ability, and improve the convergence speed and accuracy range of the algorithm.

RETRACTED: An Adaptive Fuzzy System based Insider Attacks detection with Group Key management for Wireless Ad-Hoc Network

Ad-hoc networking of wireless devices permits the establishment of contact links on the taking part hubs without pre-arranged infrastructure. In wireless ad hoc networks, participatorynodestypicallyengageingroupcommunicationssuchasbroadcast, multi-accessor relay functions. Protecting these communications is a challenging task, as internal attackers may secretly cause damage to the network, which is difficult to predict. Internal attackers can affect the sensors negatively and may disrupt the network by dropping sensitive packets or modifying packet information maliciously. Inside attackers are capable of causing many types of activities as well as passive attacks. Attackers located at a critical point in the network can significantly affect network performance. Insider attackers conceal themselves by marking themselves as legitimate nodes. Therefore, it becomes hard for the system to differentiate dishonest nodes from honest nodes. So as to make the communication among the network more secure, an adaptive fuzzy system that uses CSO algorithm for selecting optimal membership function has been proposed. In this approach, the group key is distributed by the cluster head to the cluster members. This makes sure that only the nodes with the same group key can speak with one another. Implementing appropriate group-key management in the system that focuses on internal attacks identifies the dishonest nodes which can be then eliminated through some other security measures. This ensures the absence of the dishonest nodes inside the network. The results have been simulated and the execution of the proposed approach has been contrasted with the tradition FS approach. The results have shown the presented approach has performed better than the traditional approach.

RETRACTED ARTICLE: Evaluation and improvement of sports training methods based on improved CSO algorithm

In order to improve the evaluation effect of sports training methods, this paper improves the traditional CSO algorithm to construct a sports training method evaluation model based on the improved CSO algorithm. Moreover, this paper combines actual needs to propose an improved chicken flock algorithm based on reverse learning and inertial weight reduction strategy, and uses the local sensitivity analysis theory to calculate the sensitivity of the parameters to be identified. Simultaneously, this paper divides the identification parameters into important identification parameters and secondary identification parameters, decouples the identification process, and identifies model parameters step by step to achieve the purpose of reducing the dimensions of the parameters to be identified and improving the accuracy of identification. In addition, this paper comprehensively considers and analyzes to meet the actual needs of users to build a multi-functional sports training system based on visual sensing. Finally, this paper designs a controlled experiment to evaluate the performance of the model constructed in this paper. The research results show that the model constructed in this paper has certain practical effects.