Fractional Order Sliding Mode PID Controller/Observer for Continuous Nonlinear Switched Systems with PSO Parameter Tuning
In this article a fractional order sliding mode PID controller and observer for the stabilization of continuous nonlinear switched systems is proposed. The design of the controller and observer is done following the separation principle, this means that the observer and controller are designed in a separate fashion, so a hybrid controller is implemented by designing the sliding mode controller part using an integral sliding mode surface along with a PIλDμ controller part which is the fractional order PID controller that is implemented to stabilizes the system. For the observer part, an
FPGA-Based Memristor Emulator Circuit for Binary Convolutional Neural Networks
Binary convolutional neural networks (BCNN) have been proposed in the literature for resource-constrained IoTs nodes and mobile computing devices. Such computing platforms have strict constraints on the power budget, system performance, processing and memory capabilities. Nonetheless, the platforms are still required to efficiently perform classification and matching tasks needed in various applications. The memristor device has shown promising results when utilized for in-memory computing architectures, due to its ability to perform storage and computation using the same physical element
Transmission power adaptation for cognitive radios
In cognitive radio (CR) networks, determining the optimal transmission power for the secondary users (SU) is crucial to achieving the goal of maximizing the secondary throughput while protecting the primary users (PU) from service disruption and interference. In this paper, we propose an adaptive transmission power scheme for cognitive terminals opportunistically accessing a primary channel. The PU operates over the channel in an unslotted manner switching activity at random times. The secondary transmitter (STx) adapts its transmission power according to its belief regarding the PU's state of
AROMA: Automatic generation of radio maps for localization systems
Current methods for building radio maps for wireless localization systems require a tedious, manual and error-prone calibration of the area of interest. Each time the layout of the environment is changed or different hardware is used, the whole process of location fingerprinting and constructing the radio map has to be repeated. The process gets more complicated in the case of localizing multiple entities in a device-free scenario, since the radio map needs to take all possible combinations of the location of the entities into account. In this demo, we present a novel system (AROMA) that is

Chaotic system modelling using a neural network with optimized structure
In this work, the Artificial Neural Networks (ANN) are used to model a chaotic system. A method based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to determine the best parameters of a Multilayer Perceptron (MLP) artificial neural network. Using NSGA-II, the optimal connection weights between the input layer and the hidden layer are obtained. Using NSGA-II, the connection weights between the hidden layer and the output layer are also obtained. This ensures the necessary learning to the neural network. The optimized functions by NSGA-II are the number of neurons in the

Chaotic system modelling using a neural network with optimized structure
In this work, the Artificial Neural Networks (ANN) are used to model a chaotic system. A method based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to determine the best parameters of a Multilayer Perceptron (MLP) artificial neural network. Using NSGA-II, the optimal connection weights between the input layer and the hidden layer are obtained. Using NSGA-II, the connection weights between the hidden layer and the output layer are also obtained. This ensures the necessary learning to the neural network. The optimized functions by NSGA-II are the number of neurons in the

Chaotic gaining sharing knowledge-based optimization algorithm: an improved metaheuristic algorithm for feature selection
The gaining sharing knowledge based optimization algorithm (GSK) is recently developed metaheuristic algorithm, which is based on how humans acquire and share knowledge during their life-time. This paper investigates a modified version of the GSK algorithm to find the best feature subsets. Firstly, it represents a binary variant of GSK algorithm by employing a probability estimation operator (Bi-GSK) on the two main pillars of GSK algorithm. And then, the chaotic maps are used to enhance the performance of the proposed algorithm. Ten different types of chaotic maps are considered to adapt the

Optimization of fractional-order RLC filters
This paper introduces some generalized fundamentals for fractional-order RL β C α circuits as well as a gradient-based optimization technique in the frequency domain. One of the main advantages of the fractional-order design is that it increases the flexibility and degrees of freedom by means of the fractional parameters, which provide new fundamentals and can be used for better interpretation or best fit matching with experimental results. An analysis of the real and imaginary components, the magnitude and phase responses, and the sensitivity must be performed to obtain an optimal design
Chaotic properties of various types of hidden attractors in integer and fractional order domains
Nonlinear dynamical systems with chaotic attractors have many engineering applications such as dynamical models or pseudo-random number generators. Discovering systems with hidden attractors has recently received considerable attention because they can lead to unexpected responses to perturbations. In this chapter, several recent examples of hidden attractors, which are classified into several categories from two different viewpoints, are reviewed. From the viewpoint of the equilibrium type, they are classified into systems with no equilibria, with a line of equilibrium points, and with one
Controller Design and Optimization of Magnetic Levitation System (MAGLEV) using Particle Swarm optimization technique and Linear Quadratic Regulator (LQR)
Magnetic Levitation System is one of practical examples which faces some nonlinearities behavior. Such systems require special types of controller parameters consideration for accurate results. In this paper, the process of tuning is to determine the system poles and getting them away from the instability region using state feedback (SF) controller methodology. The resulted controllable system parameters are estimated using LQR controller. Since the desired goal is to minimize vital parameters in the system behavior like the steady state error, settling time, raising time of the system and
Pagination
- Previous page ‹‹
- Page 10
- Next page ››