Electronic Implementation of a Fuzzy Neuron Model With a Gupta Integrator

Abstract

In this paper the electronic circuit implementation of a fuzzy neuron model with a fuzzy Gupta integrator is presented.This neuron model simulates the performance and the fuzzy response of a fast-spiking biological neuron. The fuzzyneuron response is analyzed for two classical (non-fuzzy) input signals, the results are spike trains with relative andabsolute refractory period and an axonal delay. A comparison between the response of the proposed fuzzy neuronmodel and the intracellular registers of biological fast-spiking cortical interneurons is made, as well as the transientspresented at the beginning of each spike train. Also the results obtained from the electronic circuit of the fuzzy neuronmodel with the Matlab™ simulation of the mathematical model are compared.

PID Control Algorithm Based on Particle Swarm Optimization for Quadrotor UAV with Tip Defect

“…According to the paper [8], ρf is defined as the ratio between the thrust generated by the propeller after the propeller tip defect fault and the original thrust: ρ θ k /3 θ k /4 λk /2 / θ /3 θ /4 λ/2 (13) [8] Where θ0 represents the zero incidence Angle of the blade, θtw represents the torsional incidence Angle, λ represents the ratio of the incoming flow velocity to the tip velocity, and k represents the ratio between the blade radius after the defect and the initial blade radius. In this paper, the blade parameters of the four-rotor UAV in paper [6] will be taken as an example. The parameters are specifically set as θ0= 0.67rad, θtw= 0.29rad, λ=0.05, and the k value is assigned as 0.7…”

A New Spike Membership Function for the Recognition and Processing of Spatiotemporal Spike Patterns: Syllable-Based Speech Recognition Application

“…The problem of voice recognition using solfeggio syllables in Spanish is solved by comparing the methods of FAN-activation function step-type (STEPAF)-SPKAF, the Augmented Spiking Neuron Model, and Augmented FAN-STEPAF-SPKAF. This article is divided into the following sections: Section 2 presents the methods, a description of the FAN model with a Gupta Integrator [7][8][9], and the new SPKAF model for fuzzy neurons from Ramírez-Mendoza et al [5,10,11,29,[32][33][34][35]. Section 3 describes the models and algorithms of fuzzy systems based on ANFIS and FAN-SPKAF for the processing of spike-time-encoded information and pattern recognition.…”

“…Biological-inspired models of neurons have been proposed, including the models by McCulloch and Pitts, Hodgkin and Huxley [1,2], Gerstner and Kistler, Izhikevich, and Ramírez-Mendoza [3][4][5]. The theory of fuzzy logic such as that by Zadeh [6] has been very successful for decades, and models of fuzzy neurons, such as that from Gupta [7][8][9], have emerged, some of them with a spike response such as those by Ramírez-Mendoza et al and Zhang [10][11][12].…”

A Novel Fuzzy System With Adaptive Neurons for Earthquake Modeling

“…From (26) and (33) we know is the function of ( ) and * Φ[ ( )] . The "INPUT" and the "STATE" correspond to both terms of (35).…”

“…If the fuzzy system (2) could match the nonlinear plant (1) exactly ( ( ) = 0), i.e., we could find the best membership function and * such that the nonlinear system could be written as ( ) = * Φ[ ], the thee same learning law makes the identified error ‖E( )‖ asymptotically stable lim → ‖E( )‖ = 0 (36) Remark 3. The normalization of the learning rates in (26) and (27), are time-varying in order to insure the stability of identification error. The learning rates are easier to be reached than [10,11], where they select = 1.…”