Generalized Neuron Research Articles

Damping Magnetorheological Systems Based on Optimal Neural Networks Preview Control Integrated with New Hybrid Fuzzy Controller to Improve Ride Comfort

<div>Adaptive neural networks (ANNs) have become famous for modeling and controlling dynamic systems. However, because of their failure to precisely reflect the intricate dynamics of the system, these have limited use in practical applications and perform poorly during training and testing. This research explores novel approaches to this issue, including modifying the simple neuron unit and developing a generalized neuron (GN). The revised version of the neuron unit helps to develop the system controller, which is responsible for providing the desired control signal based on the inputs received from the dynamic responses of the vehicle suspension system. The controller is then tested and evaluated based on the performance of the magnetorheological (MR) damper for the main suspension system. These results of the tests show that the optimal preview controller designed using the GN both ∑-Π-ANN and Π-∑-ANN can accurately capture the complex dynamics of the MR damper and improve their damping characteristics compared with other methods. The seat and main suspension systems work together to provide more support and comfort for the driver and passengers. The short stroke of the MR damper is used in seat suspension as it allows for more precise control over the suspension and can provide a smoother ride. The new hybrid fuzzy type-2 (T-2) control is designed to accurately estimate the desired damping force for the seat MR damper. This system also allows for the damping force to be adjusted to meet the desired requirements of the seat MR damper. This integration of damping systems allows better control and stability of the vehicle and provides a smoother ride for drivers and passengers. Furthermore, integrating the damping systems increases the overall performance of the vehicle, making it better able to handle various road conditions.</div>

A Generalized Neuron Model (GNM) Based Human Age Estimation

In real-world application, the identification characteristic of face images has been widely explored, ranging from National ID card, International passport, driving license amongst others. In spite of the numerous investigation of person identification from face images, there exists only a limited amount of research on detecting and estimating the demographic information contained in face images such as age, gender, and ethnicity. This research aim at detecting the age/age range of individual based on the facial image. In this research, a generalized neuron (GN), which is a modification of the simple neuron, is used, to overcome some of the problems of artificial neural network (ANN) and improve its training and testing performance. The GN is trained with discrete wavelet transform (DWT) features obtained after the application of Canny edge detection algorithm on the face Image. Validating the technique on FGNET face images reveals that the frequency domain features obtained using the DWT captures the wrinkles on the face region, which represents a distinguishing factor on the face as humans grow older. The empirical results demonstrates that the GN outperforms the simple neuron, with detection rate of 93.5%, training time of 96.30secs, matching time of 14secs and root mean square error of 0.0523. The experimental results suggest that the GN model performs comparably and could be adopted for detecting human ages. Keywords: Estimation, Detection, Generalized Neuron Model (GNM), Human Age & Frequency Aims Research Journal Reference Format: Babatunde, R.S. & Yakubu, I.A. (2017): A Generalized Neuron Model (GNM) Based Human Age Estimation. Advances in Multidisciplinary & Scientific Research Journal. Vol. 3. No.3, Pp 65-72. dx.doi.org/10.22624/AIMS/V3N3P9

Generalized neuron: Feedforward and recurrent architectures

Feedforward neural networks such as multilayer perceptrons (MLP) and recurrent neural networks are widely used for pattern classification, nonlinear function approximation, density estimation and time series prediction. A large number of neurons are usually required to perform these tasks accurately, which makes the MLPs less attractive for computational implementations on resource constrained hardware platforms. This paper highlights the benefits of feedforward and recurrent forms of a compact neural architecture called generalized neuron (GN). This paper demonstrates that GN and recurrent GN (RGN) can perform good classification, nonlinear function approximation, density estimation and chaotic time series prediction. Due to two aggregation functions and two activation functions, GN exhibits resilience to the nonlinearities of complex problems. Particle swarm optimization (PSO) is proposed as the training algorithm for GN and RGN. Due to a small number of trainable parameters, GN and RGN require less memory and computational resources. Thus, these structures are attractive choices for fast implementations on resource constrained hardware platforms.

Neurofuzzy Power System Stabilizer

An adaptive fuzzy logic power system stabilizer (AFPSS) consisting of a generalized neuron (GN)-based predictor and a fuzzy logic controller (FLC) is described. The inference mechanism of the FLC is represented by a rule-base and a database. Two parameters, decided on the basis of the GN-predictor output and the current system conditions, are used to tune the AFPSS. This mechanism of tuning makes the fuzzy logic-based power system stabilizer adaptive to changes in the operating conditions. Therefore, variation in the system response, under a wide range of operating conditions, is less compared to the system response with a fixed-parameter conventional PSS. The performance of the AFPSS has been tested by simulation and experimental studies.

Experimental Studies of a Generalized Neuron Based Adaptive Power System Stabilizer

Artificial neural networks trained as intelligent controllers can easily accommodate the non-linearities and time dependencies of non-linear, dynamic systems. However, they require large training time and large number of neurons to deal with complex problems. Taking benefit of the characteristics of a generalized neuron (GN), that requires much smaller training data and shorter training time, a generalized neuron based adaptive power system stabilizer (GNAPSS) is proposed. It consists of a GN as an predictor, that predicts the plant dynamics, and a GN as a controller to damp low frequency oscillations. Results show that the proposed GNAPSS can provide a consistently good dynamic performance of the system over a wide range of operating conditions.

Generalized Neuron-Based Adaptive PSS for Multimachine Environment

Artificial neural networks can be used as intelligent controllers to control nonlinear, dynamic systems through learning, which can easily accommodate the nonlinearities and time dependencies. Taking advantage of the characteristics of a generalized neuron (GN), that requires much smaller training data and shorter training time, a GN-based adaptive power system stabilizer (GNAPSS) is proposed. It consists of a GN as an identifier, which predicts the plant dynamics one step ahead, and a GN as a controller to damp low frequency oscillations. Results of studies with a GN-based PSS on a five-machine power system show that it can provide good damping of both local and inter-area modes of oscillations over a wide operating range and significantly improve the dynamic performance of the system.

Performance of a Generalized Neuron-Based PSS in a Multimachine Power System

An artificial neural network can work as an intelligent controller for nonlinear dynamic systems through learning, as it can easily accommodate the nonlinearities and time dependencies. In dealing with complex problems, most common neural networks have some drawbacks of large training time, large number of neurons and hidden layers. These drawbacks can be overcome by a nonlinear controller based on a generalized neuron (GN) which retains the quick response of neural net. Results of studies with a GN-based power system stabilizer on a five-machine power system show that it can provide good damping over a wide operating range and significantly improve the dynamic performance of the system.

Generalized Neuron Based Power System Stabilizer

Artificial neural networks can be an intelligent controller to control non-linear, dynamic system through learning, which can easily accommodate the non-linearities and time dependencies. Most common neural networks have drawbacks such as large training time, large number of neurons and hidden layers required to deal with complex problems. To overcome these drawbacks and to develop a non-linear controller for a power system a generalized neuron (GN) has been developed. Combining the advantages of self-optimizing adaptive control strategy and the quick response of the GN, a new power system stabilizer is proposed. Results show that the proposed GN-based power system stabilizer (PSS) can provide good damping of the power system over a wide operating range and significantly improve the dynamic performance of the system.

Experimental Studies With a Generalized Neuron-Based Power System Stabilizer

Artificial neural networks (ANNs) can be used as intelligent controllers to control nonlinear, dynamic systems through learning, which can easily accommodate the nonlinearities and time dependencies. However, they require large training time and large number of neurons to deal with complex problems. To overcome these drawbacks, a generalized neuron (GN) has been developed that requires much smaller training data and shorter training time. Taking benefit of these characteristics of the GN, a new power system stabilizer (PSS) is proposed. Results show that the proposed GN-based PSS can provide a consistently good dynamic performance of the system over a wide range of operating conditions.

Comparison of Generalized Neuron Based PSS and Adaptive PSS

Artificial neural networks (ANN) can be used as intelligent controllers to control non-linear, dynamic systems through learning, which can easily accommodate the nonlinearities and time dependencies. However, they require large training time and large number of neurons to deal with complex problems, Taking benefit of the characteristics of a Generalized Neuron (GN), that requires much smaller training data and shorter training time, a generalized neuron based PSS (GNPSS) and adaptive PSS (GNAPSS) are developed and compared.