This article presents a novel optimization algorithm inspired by camel traveling behavior that called Camel algorithm (CA). Camel is one of the extraordinary animals with many distinguish characters that allow it to withstand the severer desert environment. The Camel algorithm used to find the optimal solution for several different benchmark test functions. The results of CA and the results of GA and PSO algorithms are experimentally compared. The results indicate that the promising search ability of camel algorithm is useful, produce good results and outperform the others for different test functions.
This paper presents a new optimization algorithm called corrosion diffusion optimization algorithm (CDOA). The proposed algorithm is based on the diffusion behavior of the pitting corrosion on the metal surface. CDOA utilizes the oxidation and reduction electrochemical reductions as well as the mathematical model of Gibbs free energy in its searching for the optimal solution of a certain problem. Unlike other algorithms, CDOA has the advantage of dispensing any parameter that need to be set for improving the convergence toward the optimal solution. The superiority of the proposed algorithm over the others is highlighted by applying them on some unimodal and multimodal benchmark functions. The results show that CDOA has better performance than the other algorithms in solving the unimodal equations regardless the dimension of the variable. On the other hand, CDOA provides the best multimodal optimization solution for dimensions less than or equal to (5, 10, 15, up to 20) but it fails in solving this type of equations for variable dimensions larger than 20. Moreover, the algorithm is also applied on two engineering application problems, namely the PID controller and the cantilever beam to accentuate its high performance in solving the engineering problems. The proposed algorithm results in minimized values for the settling time, rise time, and overshoot for the PID controller. Where the rise time, settling time, and maximum overshoot are reduced in the second order system to 0.0099, 0.0175 and 0.005 sec., in the fourth order system to 0.0129, 0.0129 and 0 sec, in the fifth order system to 0.2339, 0.7756 and 0, in the fourth system which contains time delays to 1.5683, 2.7102 and 1.80 E-4 sec., and in the simple mass-damper system to 0.403, 0.628 and 0 sec., respectively. In addition, it provides the best fitness function for the cantilever beam problem compared with some other well-known algorithms.
License plate recognition is an essential part of contemporary surveillance systems since it is helpful in many applications, including parking management, vehicle access control, traffic control, and law enforcement. This project aims to provide a robust and dependable method for detecting license plates that will outperform existing approaches in accuracy and dependability. This observation method uses contemporary technology to address challenging troubles related to license plate recognition. Our methodology is primarily based on the Faster R-CNN structure, an established model for picture item detection. The novel thing, even though, is how Gray Wolf Optimization—which draws notion from the searching conduct of gray wolves—is mixed with the Faster R-CNN network. The accuracy is greatly improved by this synergistic combination, which also improves detection abilities. Moreover, an improved ResNet-50 model is blanketed to improve the classification system similarly, ensuring accurate license plate detection in several situations. The extensively utilized ”car license plate detection” dataset is used to assess the recommended technology very well, confirming its efficacy in practical settings. The empirical outcomes show exceptional performance, with a median precision of 98.21%, demonstrating how nicely the hybrid method works to attain the very best stage of license plate detecting accuracy. This painting establishes a new benchmark in license plate identity using cutting-edge technology and innovative techniques, starting the door for enhanced safety and surveillance.
The traditional economic dispatch (ED) inattention to the fossil fuels emission of thermal power plants no longer satisfies the environmental needs. As a result of the non-convex, non-smooth fuel cost functions in addition to the nonlinearity of the emission modelling. These make the combined economic and emission dispatch (CEED) a highly nonlinear optimization problem. Furthermore, different operation process constraints should be taken into account, such as loss in electrical networks and power balance of unit operation. These constraints increase the difficulty of obtaining the global optimal solution based on traditional methods. Recently, meta-heuristic population-based algorithms have successfully become a beneficial technique for solving nonlinear optimization problems. The major contribution in this work is presenting a recent meta-heuristic approach known as Mayfly algorithm (MA) for solving nonlinear and complex CEED problem. The numerical results are compared with results obtained from modern meta-heuristic algorithms like Jellyfish Search (JS) optimizer, Dwarf mongoose optimization (DMO), Tunicate swarm algorithm (TSA), Red deer algorithm (RDA), Tuna Swarm Optimization (TSO), Golden Eagle Optimizer (GEO) and Bald eagle search Optimization algorithm (BES). The standard IEEE 30-bus test system is used in this article. The simulation results are done using MATLAB environment. The results approve the reliability, stability, and consistency of the proposed approach. The proposed technique gives reliable, robust, and high-quality solution with faster computational time. Moreover, MA is more suitable for solving nonlinear CCED problem because it has a considerable convergence feature.
In this paper, fuzzy Petri Net controller is used for Quadrotor system. The fuzzy Petrinet controller is arranged in the velocity PID form. The optimal values for the fuzzy Petri Net controller parameters have been achieved by using particle swarm optimization algorithm. In this paper, the reference trajectory is obtained from a reference model that can be designed to have the ideal required response of the Quadrotor, also using the quadrotor equations to find decoupling controller is first designed to reduce the effect of coupling between different inputs and outputs of quadrotor. The system performance has been measured by MATLAB. Simulation results showed that the FPN controller has a reasonable robustness against disturbances and good dynamic performance.
The main objective of this paper project was to create a state-of-the-art face identification technique that can handle the various difficulties caused by changes in illumination, occlusions, and facial emotions. Face detection is a cornerstone of computer vision, facilitating diverse applications ranging from surveillance systems to human-computer interaction. Throughout this paper, the comprehensive exploration of advancing face detection methodologies has been undertaken, culminating in developing and evaluating a novel approach. The challenges posed by variations in facial expressions, lighting conditions, and occlusions necessitated a multifaceted solution. Our proposed method, which consists of interconnected steps, works quite well to overcome these challenges. Using deep learning architectures to increase feature extraction and discrimination was beneficial in the initial stage of fine-tuning Residual Networks (ResNet-50) to serve as the Region-based Convolutional Neural Network (Faster R-CNN) framework classifier. The process of gradually optimizing thresholds, such as batch size, learning rate, and detection threshold, involved using the Gray Wolf optimization technique (GWO). The conversion process was accelerated and improved overall detection process efficiency and accuracy using a clever fusion of machine learning and metaheuristic optimization techniques. A key component of our methodology is the careful data processing, which was necessary to ensure. The suggested method was carefully examined on a particular dataset, and the 94% training accuracy that was attained together with an identical test dataset accuracy highlights the method’s resilience. These findings support the effectiveness of our approach in reducing false positives and negatives, resulting in unmatched recall and precision in the detection system. The discovery has significant significance as it can potentially improve face detection systems’ performance and reliability in various real-world applications, such as human-computer interaction and surveillance. Convolutional neural networks, deep learning architectures, and metaheuristic optimization approaches were synergized to produce a new and reliable solution
Chaotic Sine-Cosine Algorithms (CSCAs) are new metaheuristic optimization algorithms. However, Chaotic Sine-Cosine Algorithm (CSCAs) are able to manipulate the problems in the standard Sine-Cosine Algorithm (SCA) like, slow convergence rate and falling into local solutions. This manipulation is done by changing the random parameters in the standard Sine-Cosine Algorithm (SCA) with the chaotic sequences. To verify the ability of the Chaotic Sine-Cosine Algorithms (CSCAs) for solving problems with large scale problems. The behaviors of the Chaotic Sine-Cosine Algorithms (CSCAs) were studied under different dimensions 10, 30, 100, and 200. The results show the high quality solutions and the superiority of all Chaotic Sine-Cosine Algorithms (CSCAs) on the standard SCA algorithm for all selecting dimensions. Additionally, different initial values of the chaotic maps are used to study the sensitivity of Chaotic Sine-Cosine Algorithms (CSCAs). The sensitivity test reveals that the initial value 0.7 is the best option for all Chaotic Sine-Cosine Algorithms (CSCAs).
Load Frequency Control (LFC) is a basic control strategy for proper operation of the power system. It ensures the ability of each generator in regulating its output power in such way to maintain system frequency and tie-line power of the interconnected system at prescribed levels. This article introduces comprehensive comparative study between Chaos Optimization Algorithm (COA) and optimal control approaches, such as Linear Quadratic Regulator (LQR), and Optimal Pole Shifting (OPS) regarding the tuning of LFC controller. The comparison is extended to the control approaches that result in zero steady-state frequency error such as Proportional Integral (PI) and Proportional Integral Derivative (PID) controllers. Ziegler-Nicholas method is widely adopted for tuning such controllers. The article then compares between PI and PID controllers tuned via Ziegler-Nicholas and COA. The optimal control approaches as LQR and OPS have the characteristic of steady-state error. Moreover, they require the access for full state variables. This limits their applicability. Whereas, Ziegler-Nicholas PI and PID controllers have relatively long settling time and high overshoot. The controllers tuned via COA remedy the defects of optimal and zero steady-state controllers. The performance adequacy of the proposed controllers is assessed for different operating scenarios. Matlab and its dynamic platform, Simulink, are used for stimulating the system under concern and the investigated control techniques. The simulation results revealed that COA results in the smallest settling time and overshoot compared with traditional controllers and zero steady-state error controllers. In the overshoot, COA produces around 80% less than LQR and 98.5% less than OPS, while in the settling time, COA produces around 81% less than LQR and 95% less than OPS. Moreover, COA produces the lowest steady-state frequency error. For Ziegler-Nicholas controllers, COA produces around 53% less in the overshoot and 42% less in the settling time.
Clustering is a fundamental data analysis task that presents challenges. Choosing proper initialization centroid techniques is critical to the success of clustering algorithms, such as k-means. The current work investigates six established methods (random, Forgy, k-means++, PCA, hierarchical clustering, and naive sharding) and three innovative swarm intelligence-based approaches—Spider Monkey Optimization (SMO), Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO)—for k-means clustering (SMOKM, WOAKM, and GWOKM). The results on ten well-known datasets strongly favor swarm intelligence-based techniques, with SMOKM consistently outperforming WOAKM and GWOKM. This finding provides critical insights into selecting and evaluating centroid techniques in k-means clustering. The current work is valuable because it provides guidance for those seeking optimal solutions for clustering diverse datasets. Swarm intelligence, especially SMOKM, effectively generates distinct and well-separated clusters, which is valuable in resource-constrained settings. The research also sheds light on the performance of traditional methods such as hierarchical clustering, PCA, and k-means++, which, while promising for specific datasets, consistently underperform swarm intelligence-based alternatives. In conclusion, the current work contributes essential insights into selecting and evaluating initialization centroid techniques for k-means clustering. It highlights the superiority of swarm intelligence, particularly SMOKM, and provides actionable guidance for addressing various clustering challenges.
The performance of power distribution systems (PDS) has improved greatly in recent times ever since the distributed generation (DG) unit was incorporated in PDS. DG integration effectively cuts down the line power losses (PL) and strengthens the bus voltages (BV) provided the size and place are optimized. Accordingly, in the present work, a hybrid optimization technique is implemented for incorporating a single DG unit into radial PDS. The proposed hybrid method is formed by integrating the active power loss sensitivity (APLS) index and whale optimization meta-heuristic algorithm. The ideal place and size for DG are optimized to minimize total real power losses (TLP) and enhance bus voltages (BV). The applicability of the proposed hybrid technique is analyzed for Type I and Type III DG installation in a balanced IEEE 33-bus and 69-bus radial PDS. Optimal inclusion of type I and III DG in a 33-bus radial test system cut down TLP by 51.85% and 70.02% respectively. Likewise, optimal placement of type I and III DG reduced TLP by 65.18%, and 90.40%, respectively for 69-bus radial PDS. The impact of DG installation on the performance of radial PDS has been analyzed and a comparative study is also presented to examine the sovereignty of the proposed hybrid method. The comparative study report outlined that the proposed hybrid method can be a better choice for solving DG optimization in radial PDS.
PID controller is the most popular controller in many applications because of many advantages such as its high efficiency, low cost, and simple structure. But the main challenge is how the user can find the optimal values for its parameters. There are many intelligent methods are proposed to find the optimal values for the PID parameters, like neural networks, genetic algorithm, Ant colony and so on. In this work, the PID controllers are used in three different layers for generating suitable control signals for controlling the position of the UAV (x,y and z), the orientation of UAV (θ, Ø and ψ) and for the motors of the quadrotor to make it more stable and efficient for doing its mission. The particle swarm optimization (PSO) algorithm is proposed in this work. The PSO algorithm is applied to tune the parameters of proposed PID controllers for the three layers to optimize the performances of the controlled system with and without existences of disturbance to show how the designed controller will be robust. The proposed controllers are used to control UAV, and the MATLAB 2018b is used to simulate the controlled system. The simulation results show that, the proposed controllers structure for the quadrotor improve the performance of the UAV and enhance its stability.
At recent days, the robot performs many tasks on behalf of humans or in support of humans. Among the most prominent benefits of robots for humans are removing the risk factor from humans, completing routine tasks for humans, saving a lot of time and effort, and mastering work. This paper presents a model of an eight-legged robot equipped with an intelligent controller that was simulated using MATLAB. The designed structure contains 24 controllers, three for each leg, to provide flexibility in movement and rotation. Proportional Integral Derivative (PID) controller has been used in this work , each leg contains three PIDs. A particle swarm optimization algorithm (PSO) was used to adjust the parameters of the PID controller (Kp , Ki and Kd). The structure of eight legs robot with controller is implemented using Simscape Multibody in the MATLAB program, where the movement of the eight-legged robot is visualized and analyzed without the need for complex analysis associated with a mathematical model. The simulation results were conducted in a three-dimensional environment and were presented in two scenarios . The first was implementing and simulating the robot without using a controller, which leads to the robot falling at the starting point. The second was when a PID controllers are used with the system, where better movement was obtained. Finally, the robustness of the controller was verified by changing the load that the robot bears.
It can be said that the system of sensing the tilt angle and speed of a multi-rotor copter come in the first rank among all the other sensors on the multi-rotor copters and all other planes due to its important roles for stabilization. The MPU6050 sensor is one of the most popular sensors in this field. It has an embedded 3-axis accelerometer and a 3-axis gyroscope. It is a simple sensor in dealing with it and extracting accurate data. Everything changes when this sensor is placed on the plane. It becomes very complicated to deal with it due to vibration of the motors on the multirotor copter. In this study, two main problems were diagnosed was solved that appear in most sensors when they are applied to a high-frequency vibrating environment. The first problem is how to get a precise angle of the sensor despite the presence of vibration. The second problem is how to overcome the errors that appear when the multirotor copter revolves around its vertical axis during the tilting in either direction x or y or both. The first problem was solved in two steps. The first step involves mixing data of the gyroscope sensor with the data of auxetometer sensor by a mathematical equation based on optimized complementary filter using gray wolf optimization algorithm GWO. The second step involves designing a suitable FIR filter for data. The second problem was solved by finding a non-linear mathematical relationship between the angles of the copter in both X and Y directions, and the rotation around the vertical axis of multirotor copter frame.