Chihiro Ikuta

Chaos glial network connected to Multi-Layer Perceptron for Solving Two-Spiral Problem

Some methods using artificial neural network were proposed for solving to the Two-Spiral Problem (TSP). TSP is a problem which classifies two spirals drawn on the plane, and it is famous as the high nonlinear problem. In this paper, we propose a chaos glial network which connected to Multi-Layer Perceptron (MLP). The chaos glial network is inspired by astrocyte which is glial cell in the brain. By computer simulations for solving TSP, we confirmed that the proposed chaos glial network connected to MLP gains better performance than the conventional MLP.

Multi-Layer Perceptron with positive and negative pulse glial chain for solving two-spirals problem

A glia is a nervous cell existing in a brain. The brain is composed of the relationship with glias and neurons. By an ion concentration, the glia transmits signal to neurons and neighboring glias. In this study, we propose the MLP with positive and negative pulse glial chain which is inspired from features of the biological glia.We add the MLP to the positive and negative pulse glial chain. In the positive and negative pulse glial chain, the glias are connected to the neurons one by one. The glia generates pulse when the glia is excited by the connected neurons output. If the connected neuron has large amount of output, the glia generates positive pulse. Moreover, if the connected neuron has small amount of output, the glia generates the negative pulse. The positive and negative pulse are propagated to the connected neuron and neighboring glias. We consider that the positive and negative pulse glial chain give the relationships of position of neurons in a same layer. By solving a Two-Spirals Problem (TSP), we confirm that the proposed MLP has better a learning performance and a generalization capability than the conventional MLP.

A novel optimization design approach for Contourlet directional filter banks

A Contourlet transform, an expansion of a wavelet transform, is a double filter bank structure composed of Laplacian Pyramid and directional filter banks. Several wavelet filters of preferable performance have been developed for wavelet transforms, e.g. CDF (Cohen, Daubechies and Feauveau) 9/7 filter. However, there is still only a limited number of wavelet filters applicable for Contourlet transforms. Therefore, it has become an urgent issue to find effective contourlet filters and design methods in the field of multiscale geometric analysis. In order to design a new directional filter bank for Contourlet transforms, this paper uses parametric modeling to obtain a novel PKVA (See-May Phoong, Chai W. Kim, P. P. Vaidyanathan, and Rashid Ansari) filter, by first implementing Chebyshev best uniform approximation, and then reaching the optimal solution by means of Parks-McClellan algorithm. Using Brodatz standard texture image database for test images, and using image denoising treated with hidden Markov tree (HMT) models in the Contourlet domain, the optimal PKVA filter was obtained on the basis of the peak signal to noise ratio (PSNR) maximum criterion with human visual properties considered. Experiment results show that the image denoising performance of our filter is better than that of Po and Do’s. The PSNR obtained from the experiment is 1.011449 higher than that of Po and Do’s in average. Therefore, Contourlet transforms using the proposed PKVA filter as DFB can ensure that the local error in images is of a uniform minimum value, and that good overall visual effect can be achieved.

Multi-Layer Perceptron including glial pulse and switching between learning and non-learning

A glia is a nervous cell which is existing in a brain. This cell changes a Ca2+ concentration. This ion affects a neuron membrane potential and it is propagated to the neighboring glia. Moreover, the Ca2; directly affects the human memory by increasing of a D-serine. From these functions, we propose a Multi-Layer Perceptron (MLP) including glial pulse and switching between a learning and non-learning. In this method, the neurons in the hidden-layer received the pulse from connected glias. The pulse is generated depending on the neuron outputs and it is propagated to the neighboring glias and neurons. Moreover, the neurons are separated to some groups. Each group periodically switches a learning term and a non-learning term. Each group starts the learning term having a small lag each other. We consider that a performance of the MLP improves by two different methods influencing each other. By two simulations, we confirm that the MLP obtains the high solving ability by using our methods.

Investigation of Multi-Layer Perceptron with Pulse Glial Chain Based on Individual Inactivity Period

In this study, we propose a Multi-Layer Perceptron (MLP) with pulse glial chain based on individual inactivity period which is inspired from biological characteristics of a glia. In this method, we one-by-one connect a glia with neurons in the hidden-layer. The connected glia is excited by the connecting neuron output. Then, the glia generates the pulse. This pulse is input to the connecting neuron threshold. Moreover, this pulse is propagated into the glia network. Thus, the glia has a position density each other. In this network, a period of inactivity of the glia is dynamically changed according to pulse generation time. In the previous method, we fix the period of inactivity, thus the pulse generation pattern is often fixed. It is similar to the local minimum. By varied the period of inactivity, the pulse generation pattern obtains the diversity. We consider that this diversity of the pulse generation pattern is efficiency to the MLP performance. By the simulation, we confirm that the proposed MLP improves the MLP performance than the conventional MLP.

Investigation of recall image by Partitioned Hopfield Neural Network

In this study, we propose Partitioned Hopfield Neural Network (PHNN) to realize the memory mechanism of the human brain. The PHNN is realized by arranging cell which has a small HNN in the whole image regularly without overlap. By computer simulations, we confirm that the PHNN recalls the whole image from the partial characteristic of the stored images.

Multi-layer perceptron with pulse glial chain having oscillatory excitation threshold

A brain has neuron and glial cells. In the brain, these cells correlate each other and make a higher brain function. In this study, we propose a Multi-Layer Perceptron (MLP) with pulse glial chain having oscillatory excitation threshold. We connect artificial glia units with the neurons in a hidden-layer. When the connecting neuron output is larger than an excitation threshold of the connected glia, the glia excites and generates the pulse. This pulse transmits to the neighboring glias and the connecting neuron. The pulse increases a threshold of the connecting neuron, thus the glia gives energy for solving tasks. In this model, the excitation threshold is oscillating within a defined value. Even if the connecting neuron output does not change, the pulse generation occurs by the oscillation of the excitation threshold. The oscillation of the excitation threshold gives more energy to the network and improves a learning performance of the MLP. By computer simulation, we confirm that the oscillation of the excitation threshold improves a learning performance.

Improvement of learning performance of multi-layer perceptron by two different pulse glial networks

A glia is the most number of nervous cells in a brain. The glia is investigated in a medical field, because the glia correlates to neuron works and composes a human cerebration. We consider that the glia function can be applied to an artificial neural network. In this study, we propose the Multi-Layer Perceptron (MLP) with the two different pulse glial networks. The proposed MLP has the glial network which is inspired from biological functions of the glia. One neuron is connected with two glias. Two glias generate the pulse depending on the output neurons. One glia connects the neuron for increasing the output of neuron. On the other hand, the glia connects the neuron for decreasing the output of neuron. Both glias composes the glial networks. These effects are propagated into the networks. The glial effects become complexity and affects the MLP learning performance. By the computer simulation, we confirm that the learning performance of the proposed MLP is better than the conventional MLP.

A novel image fusion algorithm using an NSCT and a PCNN with digital filtering

ABSTRACT Image fusion is an important task in both image processing and computer vision research that use multisensor processing and multiscale analysis. This paper proposed a novel image fusion algorithm using a nonsubsampled contourlet transform (NSCT) and a pulse-coupled neural network (PCNN) with digital filtering. First, we decomposed two original images into a low-frequency and a series of high-frequency subband coefficients based on the NSCT and repeated that step for the next low-frequency subband. Second, each low-frequency subband coefficient in different levels in the frequency domain for both images was duplicated, and then these low-frequency subband coefficients of different levels from two different images were processed through a Laplacian filter and an average filter. The Laplacian filter can improve the performance of both edge and texture representation; the average filter can implement image smoothing for creating a superior reconstruction of an image via the low-frequency subband coefficients of the frequency domain in image processing. Moreover, the coupling coefficients from different images were fused by using the PCNN. Finally, reconstructed a fused image based on low- and high-frequency subband coefficients in different scales and directions using the inverse NSCT. Experimental results show that the proposed algorithm is superior to state-of-the-art conventional image fusion algorithms.

Investigation of four-layer multi-layer perceptron with glia connections of hidden-layer neurons

A glia is a nervous cell existing in a brain. This cell transmits signals by various ion concentrations. By the ion concentration, the glia correlates the neuron by ions. Thus, the glia composes the network different to the neural network. We proposed a four-layer Multi-Layer Perceptron (MLP) with glia connections of hidden-layer neurons which is inspired from characteristics of the biological glia. The proposed MLP has two hidden-layer. In this network, we connect the glia to the neurons in two hidden-layer. The glia receives the output of connecting neuron and the outputs are summed. When the summed value is over the glia excitation threshold, this glia is excited. The excited glia generates a pulse. This pulse input to the thresholds of connecting glias. We consider that the glia gives the energy to the MLP and the glia give the position relationship of neurons in the different layers. By the simulation, we confirm that the proposed MLP obtains a high solving ability. Moreover, we investigate the characteristics of the proposed MLP.