Complex-valued Neural Network Model Research Articles

IMAGE CLASSIFICATION OF VINE LEAF DISEASES USING COMPLEX-VALUED NEURAL NETWORK

Leaf diseases are a serious challenge in the agricultural industry affecting crop quality and yield especially in grapevines. Early recognition and classification of grape leaf diseases is crucial to enable farmers to take appropriate preventive measures in maintaining the health of their crops. The research utilized an innovative approach based on Complex-Valued Neural Network (CVNN) to address the problem. Using Complex-Valued Neural Network (CVNN) this research seeks to identify and classify grape leaf diseases through a series of experiments. A total of 100 images divided into 4 classes namely Black Rot, ESCA, Leaf Blight, and Healthy were collected to train the model. The results show that the trained CVNN model successfully achieved a training accuracy of 100% and a testing accuracy of 97%, demonstrating excellent performance in classifying grape leaf diseases. This states that the proposed approach has great potential to be an effective tool in helping growers manage their vineyards more efficiently and effectively. The developed image processing method is expected to be applied in designing a system to perform image classification of diseases on grape leaves.

Periodic oscillation for a complex-valued neural network model with discrete and distributed delays

In this paper, a complex-valued neural network model with discrete and distributed delays is investigated under the assumption that the activation function can be separated into its real and imaginary parts. Based on the mathematical analysis method, some sufficient conditions to guarantee the existence of periodic oscillatory solutions are established. Computer simulation is given to illustrate the validity of the theoretical results.

Neural Cryptography Based on Complex-Valued Neural Network.

Neural cryptography is a public key exchange algorithm based on the principle of neural network synchronization. By using the learning algorithm of a neural network, the two neural networks update their own weight through exchanging output from each other. Once the synchronization is completed, the weights of the two neural networks are the same. The weights of the neural network can be used for the secret key. However, all the existing works are based on the real-valued neural network model. There are seldom works studying the neural cryptography based on a complex-valued neural network model. In this technical note, a neural cryptography based on the complex-valued tree parity machine network (CVTPM) is proposed. The input, output, and weights of CVTPM are a complex value, which can be considered as an extension of TPM. There are two advantages of the CVTPM: 1) the security of CVTPM is higher than that of TPM with the same hidden units, input neurons, and synaptic depths and 2) the two parties with the CVTPM can exchange two group keys in one neural synchronization process. A series of numerical simulation experiments is provided to verify our results.

Hopf bifurcation analysis of a complex-valued neural network model with discrete and distributed delays

In this paper, a class of complex-valued neural network model with discrete and distributed delays is proposed. Regarding the discrete time delay as the bifurcating parameter, the problem of Hopf bifurcation in the newly-proposed complex-valued neural network model is investigated under the assumption that the activation function can be separated into its real and imaginary parts. Based on the normal form theory and center manifold theorem, some sufficient conditions which determine the direction of the Hopf bifurcation and the stability of the bifurcating periodic solutions are established. Finally, a numerical example is given to illustrate the validity of the theoretical results.

Small-time Scale Network Traffic Prediction Based on Complex-valued Neural Network

Accurate models play an important role in capturing the significant characteristics of the network traffic, analyzing the network dynamic, and improving the forecasting accuracy for system dynamics. In this study, complex-valued neural network (CVNN) model is proposed to further improve the accuracy of small-time scale network traffic forecasting. Artificial bee colony (ABC) algorithm is proposed to optimize the complex-valued and real-valued parameters of CVNN model. Small-scale traffic measurements data namely the TCP traffic data is used to test the performance of CVNN model. Experimental results reveal that CVNN model forecasts the small-time scale network traffic measurement data very accurately

Novel Complex-Valued Neural Network for Dynamic Complex-Valued Matrix Inversion

Static matrix inverse solving has been studied for many years. In this paper, we aim at solving a dynamic complex-valued matrix inverse. Specifically, based on the artful combination of a conventional gradient neural network and the recently-proposed Zhang neural network, a novel complex-valued neural network model is presented and investigated for computing the dynamic complex-valued matrix inverse in real time. A hardware implementation structure is also offered. Moreover, both theoretical analysis and simulation results substantiate the effectiveness and advantages of the proposed recurrent neural network model for dynamic complex-valued matrix inversion.

Synchronization of complex-valued neural network with sliding mode control

In this paper, the synchronization and module-phase synchronization of complex-valued neural network are studied with sliding mode controllers. Both inner synchronization in the same complex-valued neural network and outer synchronization of two complex-valued networks are considered. By separating the real part and imaginary part, a new complex-valued neural network model is provided and module-phase synchronization is defined. With an equivalent linear controller, sliding mode controllers are designed to get the synchronization and module-phase synchronization theorems. Finally, some numerical simulations are presented to show the robustness and effectiveness of our study.

Efficient RSOA modelling using polar complex-valued neural networks

This work presents an effective solution to reduce the computational complexity order of behavioral model generation for reflective semiconductor optical amplifier (RSOA). The proposed model is based on a complex valued (CV) neural network (CVNN) structure, using polar CV basis functions architecture. The CV model parameters are extracted by means of nonlinear complex-domain Levenberg–Marquardt algorithm, from recorded experimental 20Msymbol/s 64-quadrature amplitude modulation (QAM) input–output data. The evaluation results of polar CVNN model prove to be more adequate to accurately describe the nonlinear dynamic magnitude and phase distortions of RSOA, compared to double-input double-output real-valued neural network (RVNN) rectangular structure. Additionally, significant reduction of the computational cost is achieved in comparison to the RVNN approach.

Complex-Valued Neural Network in Signal Processing: A Study on the Effectiveness of Complex Valued Generalized Mean Neuron Model

A complex valued neural network is a neural network which consists of complex valued input and/or weights and/or thresh- olds and/or activation functions. Complex-valued neural networks have been widening the scope of applications not only in electronics and informatics, but also in social systems. One of the most important applications of the complex valued neural network is in signal processing. In Neural networks, generalized mean neuron model (GMN) is often discussed and studied. The GMN includes a new aggregation function based on the concept of generalized mean of all the inputs to the neuron. This paper aims to present exhaustive results of using Generalized Mean Neuron model in a complex-valued neural network model that uses the back-propagation algorithm (called 'Complex-BP') for learning. Our experiments results demonstrate the effectiveness of a Generalized Mean Neuron Model in a complex plane for signal processing over a real valued neural network. We have studied and stated various observations like effect of learning rates, ranges of the initial weights randomly selected, error functions used and number of iterations for the convergence of error required on a Generalized Mean neural network model. Some inherent properties of this complex back propagation algorithm are also studied and discussed.