An efficient feedback scheduling scheme based on the proposed Feed Forward Neural Network (FFNN) scheme is employed to improve the overall control performance while minimizing the overhead of feedback scheduling which exposed using the optimal solutions obtained offline by mathematical optimization methods. The previously described FFNN is employed to adapt online the sampling periods of concurrent control tasks with respect to changes in computing resource availability. The proposed intelligent scheduler will be examined with different optimization algorithms. An inverted pendulum cost function is used in these experiments. Then, simulation of three inverted pendulums as intelligent Real Time System (RTS) is described in details. Numerical simulation results demonstrates that the proposed scheme can reduce the computational overhead significantly while delivering almost the same overall control performance as compared to optimal feedback scheduling
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).
Growing interests in nature-inspired computing and bio-inspired optimization techniques have led to powerful tools for solving learning problems and analyzing large datasets. Several methods have been utilized to create superior performance-based optimization algorithms. However, certain applications, like nonlinear real-time, are difficult to explain using accurate mathematical models. Such large-scale combination and highly nonlinear modeling problems are solved by usage of soft computing techniques. So, in this paper, the researchers have tried to incorporate one of the most advanced plant algorithms known as Venus Flytrap Plant algorithm(VFO) along with soft-computing techniques and, to be specific, the ANFIS inverse model-Adaptive Neural Fuzzy Inference System for controlling the real-time temperature of a microwave cavity that heats oil. The MATLAB was integrated successfully with the LabVIEW platform. Wide ranges of input and output variables were experimented with. Problems were encountered due to heating system conditions like reflected power, variations in oil temperature, and oil inlet absorption and cavity temperatures affecting the oil temperature, besides the temperature’s effect on viscosity. The LabVIEW design followed and the results figure in the performance of the VFO- Inverse ANFIS controller.
Facial retouching, also referred to as digital retouching, is the process of modifying or enhancing facial characteristics in digital images or photographs. While it can be a valuable technique for fixing flaws or achieving a desired visual appeal, it also gives rise to ethical considerations. This study involves categorizing genuine and retouched facial images from the standard ND-IIITD retouched faces dataset using a transfer learning methodology. The impact of different primary optimization algorithms—specifically Adam, RMSprop, and Adadelta—utilized in conjunction with a fine-tuned ResNet50 model is examined to assess potential enhancements in classification effectiveness. Our proposed transfer learning ResNet50 model demonstrates superior performance compared to other existing approaches, particularly when the RMSprop and Adam optimizers are employed in the fine-tuning process. By training the transfer learning ResNet50 model on the ND-IIITD retouched faces dataset with the ”ImageNet” weight, we achieve a validation accuracy of 98.76%, a training accuracy of 98.32%, and an overall accuracy of 98.52% for classifying real and retouched faces in just 20 epochs. Comparative analysis indicates that the choice of optimizer during the fine-tuning of the transfer learning ResNet50 model can further enhance the classification accuracy.
Wind energy and its conversion is part of renewable energy resources as cheaper and cleaner energy today even though the initial cost varies from place to place. Most of the government sector always promotes renewable energy with a provision of subsidies as observed worldwide. Wind energy is an actual solution over costlier conventional energy sources. If it is not properly placed and the selection of turbine design is not up to the mark, then investments may require more time to acquire Net Profit Value called as NPV. This research work is focused on the development of mathematical models to optimize the turbine size and locations considering all constraints such as the distance between the turbines, hub height, and investment in internal road and substation cost. Particle-Swarm-Optimization is an intelligent tool to optimize turbine place and size. The database management system is selected as the appropriate data storage platform for before and after optimization simulation. Various plots and excel outputs of .net programming are addressed for the success of optimization algorithms for the purpose of wind turbine placement and WTG design is suggested to manage wind energy such that power system reliability has been improved and the same is monitored through the reliability indices.
The aim of this paper is to suggest a methodical smooth control method for improving the stability of two wheeled self-balancing robot under effect disturbance. To promote the stability of the robot, the design of linear quadratic regulator using particle swarm optimization (PSO) method and adaptive particle swarm optimization (APSO). The computation of optimal multivariable feedback control is traditionally by LQR approach by Riccati equation. Regrettably, the method as yet has a trial and error approach when selecting parameters, particularly tuning the Q and R elements of the weight matrices. Therefore, an intelligent numerical method to solve this problem is suggested by depending PSO and APSO algorithm. To appraise the effectiveness of the suggested method, The Simulation result displays that the numerical method makes the system stable and minimizes processing time.
The identification of system parameters plays an essential role in system modeling and control. This paper presents a parameter estimation for a permanent magnetic DC motor using the simulink design optimization method. The parameter estimation may be represented as an optimization problem. Firstly, the initial values of the DC motor parameters are extracted using the dynamic model through measuring the values of voltage, current, and speed of the motor. Then, these values are used as an initial value for simulink design optimization. The experimentally input- output data can be collected using a suggested microcontroller based circuit that will be used later for estimating the DC motor parameters by building a simulink model. Two optimization algorithms are used, the pattern search and the nonlinear least square. The results show that the nonlinear least square algorithm gives a more accurate result that almost approaches to the actual measured speed response of the motor. )