Hybrid Multilayer Perceptron Research Articles

Intelligent computer vision system for Sprague-Dawley rat sperm classification using gray-level microscopic images

This paper presents a development of intelligent computer vision system for Sprague-Dawley rat sperm classification. The system is developed to help pathologists and improve the current conventional detection methods and classification of Sprague-Dawley rat sperm. The conventional method tends to result in errors and is also time consuming. Thus, the new computer vision system is developed to overcome these problems and, consequently, produce more accurate results. The system is capable of classifying rat sperm into two groups, namely, normal and abnormal, based on the morphological characteristics of the sperm head. Furthermore, the system has the ability to classify the shapes of abnormal sperms which are banana and hookless shapes. The new system consists of four stages. In the first stage, sperms are segmented using the adaptive fuzzy moving K-means (AFMKM) clustering algorithm. In the second stage, a new automatic cropping algorithm was used to isolate the sperm head and to exclude other details. In the third stage, the feature extraction process was performed, wherein five features namely curvature angle, two flattened angles, curvature depth and number of curvatures are proposed to classify the sperm head of the rat. In the fourth (final) stage, the sperm head is classified using hybrid multilayered perceptron (HMLP) neural network trained with modified recursive prediction error (MRPE) algorithm. The developed system achieved an accuracy rate of 98.7%. Key words: Sprague-Dawley rat sperm, adaptive fuzzy moving K-means clustering algorithm, hybrid multilayered perceptron network, modified recursive prediction error algorithm.

Intelligent classification of cervical pre-cancerous cells based on the FTIR spectra

Inspired from the great potential of the Fourier-transform infrared (FTIR) spectroscopy as a screening tool for cervical cancer, this paper proposes an intelligent classification of cervical pre-cancerous cells based on the FTIR spectra. It consists of two parts: the extraction of FTIR characteristics and the intelligent classification of the pre-cancerous cells. Peak-corrected area-based features’ extraction (PCABFE) is introduced as a tool for the first part, while the Hybrid Multilayered Perceptron (HMLP) network is employed to classify the cervical pre-cancerous cells according to the Bethesda classification. Correlation test proves the capability of the proposed PCABFE to be as effective as the manual extraction by human experts, while the HMLP network produces a good classification performance with 97.4% of accuracy.

Predictability and forecasting automotive price based on a hybrid train algorithm of MLP neural network

In this paper, using the Hurst exponent value H, we first show that the automotive price in Iran Khodro Company (IRAN) is predictable and therefore a good forecasting can be done using neural networks. We then introduce a new global and fast hybrid multilayer perceptron neural network (MLP-NN) in order to forecast the automotive price. In our new framework, we hybridize the genetic algorithm (GA) and least square (LS) method in order to train the connected weights of the network, which leads us to have a global and fast network. To do so, the connected weights between input and hidden layers are trained by GA and the connected weights between the hidden and output layers are trained by LS method. We finally apply our new MLP-NN to forecast the automotive price in Iran Khodro Company, which is the biggest automotive manufacturing in IRAN. The results are well promising compared with the cases when we apply the GA and LS individually. We also compare the results with the case when we employ the gradient-based optimization techniques such as Levenberg–Marquardt method as well as some heuristic algorithms such as extended tabu search algorithm instead of LS method and hybridization of MLP-LM with GA.

Sprague Dawley rat sperm classification using hybrid multilayered Perceptron network

As of now, the analysis of sperm such as counting and detection processes are still operated manually which tends to produce errors. False detection in sperm analysis must be minimized as possible. Therefore, the current study focuses on developing a Sprague Dawley rat sperm classification system to assist the detection process by pathologist. The system has the ability to classify the Sprague Dawley rat sperm into two classes namely normal and abnormal based on the morphological characteristic of sperm's head. The proposed system employs the Hybrid Multilayered Perceptron (HMLP) neural network trained with the Modified Recursive Prediction Error (MRPE) algorithm as the intelligent classifier tool. This study will also investigate three significant morphological characteristics of rat sperm's head namely opened degree, width of the curve and template matching percentage as the input data for the HMLP network. Furthermore, this study further classifies the abnormal sperm into hookless and banana shape. Promising result with 100% and 94.62% of accuracy has been achieved for two classes and three classes classification of rat sperm respectively.

INNOSAT ATTITUDE CONTROL SYSTEM BASED ON ADAPTIVE NEURO-CONTROLLER

The current research focuses on the designing of an intelligent controller for the Attitude Control System (ACS) of the Innovative Satellite (InnoSAT). The InnoSAT mission is to demonstrate local innovative space technology amongst the institutions of higher learning in the space sector. In this study, an Adaptive Neuro-controller (ANC) based on the Hybrid Multi Layered Perceptron (HMLP) network has been developed. The Model Reference Adaptive Control (MRAC) system is used as a control scheme to control a time varying systems where the performance specifications are given in terms of a reference model. The Weighted Recursive Least Square (WRLS) algorithm will adjust the controller parameters to minimize error between the plant output and the model reference output. The objective of this paper is to analyse the time response and the tracking performance of the ANC based on the HMLP network and the ANC based on the standard MLP network for controlling an InnoSAT attitude. These controllers have been tested using an InnoSAT model with some variations in operating conditions such as varying gain, measurement noise and disturbance torques. The simulation results indicated that the the ANC based on the HMLP network is adequate to control satellite attitude and give better results than the ANC based on the MLP network.

Clustered-Hybrid Multilayer Perceptron network for pattern recognition application

This paper introduces a modified version of the Hybrid Multilayer Perceptron (HMLP) network to improve the performance of the conventional HMLP network. We adopted the Clustering Algorithm from the Radial Basis Function (RBF) network architecture and incorporated it into the conventional HMLP network architecture. The modified model is called Clustered-Hybrid Multilayer Perceptron (Clustered-HMLP) network. The proposed Clustered-HMLP network architecture is trained using modified training algorithm called Clustered-Modified Recursive Prediction Error (Clustered-MRPE). The capability of the Clustered-HMLP network with Clustered-MRPE training algorithm is demonstrated using seven benchmark datasets from the University of California at Irvine (UCI) machine learning repository (i.e. Iris, Ionosphere, Pima Indian Diabetes, Wine, Lung Cancer, Hayes-Roth and Glass) and compared with the performance of other twelve classifiers reported in literature. Further, the new network is implemented to model a Transformer Fault Diagnosis System and Aggregate Shape Identification System. The results indicate that the proposed Clustered-HMLP network outperforms other eleven classifiers and provides a significant improvement to the conventional HMLP network for pattern recognition application.

Modified Recursive Least Squares algorithm to train the Hybrid Multilayered Perceptron (HMLP) network

In this paper, a new learning algorithm, called the Modified Recursive Least Square (MRLS), is introduced for the Hybrid Multilayered Perceptron (HMLP) network. Adopting the Recursive Least Square (RLS) algorithm as its basis, the MRLS algorithm differs from RLS in the way that the weight of the linear connections for the HMLP network is estimated. The convergence rate of the MRLS algorithm is further improved by varying the forgetting factor, optimizing the way the momentum and learning rate are assigned. To investigate its applicability, the MRLS algorithm is demonstrated on the HMLP network using six benchmark data sets obtained from the UCI repository. The classification performance of the HMLP network trained with the MRLS algorithm is compared with those of the HMLP network trained with the Modified Recursive Prediction Error (MRPE) algorithm and the MLP trained with the standard RLS algorithm as well as with other commonly adopted machine learning classifiers. The comparison results indicated that the proposed MRLS trained HMLP network provides significant improvement over RLS trained MLP network, MRPE trained HMLP network, and other machine learning classifiers in terms of accuracy, convergence rate and mean square error (MSE).

Predicting strengths of concrete-type specimens using hybrid multilayer perceptrons with center-unified particle swarm optimization

This study explores the effectiveness of results obtained by using proposed hybrid multilayer perceptron (HMLP) networks to predict strength in concrete cylinders, reinforced-concrete deep beams, and reinforced-concrete squat walls. Such HMLP networks were designed to incorporate one linear and three high-order layer connections. Of the latter, one, employed only in the first layer connection, was derived from drawings referenced in the literature and two were developed by the author for this study. To calculate appropriate network coefficients, this study designed a center-unified particle swarm optimization (CUPSO) approach, composed of a center particle and global and local variants, which is quite effective for optimization tasks. This study gathered 103, 62, and 62 datasets, respectively, from drawings in three cases reported in the literature. Results, which showed that certain high order HMLP models perform better than their traditional counterpart, evidence the efficacy of proposed HMLP families. Each family, comprising high-order models and a linear counterpart, achieved results that were superior to those attained using traditional MLP networks only.

A novel aggregate classification technique using moment invariants and cascaded multilayered perceptron network

Occupying more than 70% of the concrete's volume, aggregates play a vital role as the raw feed for construction materials; particularly in the production of concrete and concrete products. Often, the characteristics such as shape, size and surface texture of aggregates significantly affect the quality of the construction materials produced. This article discusses a novel method for automatic classification of aggregate shapes using moment invariants and artificial neural networks. In the processing stage, Hu, Zernike and Affine moments are used to extract features from binary boundary and area images. In the feature selection stage, discriminant analysis is employed to select the optimum features for the aggregate shape classification. In the classification stage, a cascaded multilayered perceptron (c-MLP) network is proposed to categorize the aggregate into six shapes. The c-MLP network consists of three MLPs which are arranged in a serial combination and trained with the same learning algorithm. The proposed method has been tested and compared with twelve machine learning algorithms namely Levenberg–Marquardt (LM), Broyden–Fletcher–Goldfarb–Shanno quasi-newton (BFG), Resilient back propagation (RP), Scaled conjugate gradient (SCG), Conjugate gradient with Powell–Beale restarts (CGB), Conjugate gradient with Fletcher–Reeves updates (CGF), Conjugate gradient with Polak–Ribiere updates (CGP), One step secant (OSS), Bayesian regularization (BR), Gradient descent (GD), Gradient descent with momentum and adaptive learning rate (GDX) and Gradient descent with momentum (GDM) algorithms. Also, the classification performance of the c-MLP network is compared with those of the hybrid multilayered perceptron (HMLP), the radial basis function (RBF) as well as discriminant analysis classifiers. Concerning the cascaded MLP, 3 stage c-MLP gives the best accuracy compared to the 2 stage c-MLP and the standard MLP. Compared to other learning algorithms, LM algorithm achieved the best result. As far as the overall conclusion is concerned, c-MLP gives better classification performance than that of the HMLP, RBF and discriminant analysis.

An automated cervical pre-cancerous diagnostic system

This paper proposes to develop an automated diagnostic system for cervical pre-cancerous. METHODS AND DATA SAMPLES: The proposed automated diagnostic system consists of two parts; an automatic feature extraction and an intelligent diagnostic. In the automatic feature extraction, the system automatically extracts four cervical cells features (i.e. nucleus size, nucleus grey level, cytoplasm size and cytoplasm grey level). A new features extraction algorithm called region-growing-based features extraction (RGBFE) is proposed to extract the cervical cells features. The extracted features will then be fed as input data to the intelligent diagnostic part. A new artificial neural network (ANN) architecture called hierarchical hybrid multilayered perceptron (H(2)MLP) network is proposed to predict the cervical pre-cancerous stage into three classes, namely normal, low grade intra-epithelial squamous lesion (LSIL) and high grade intra-epithelial squamous lesion (HSIL). We empirically assess the capability of the proposed diagnostic system using 550 reported cases (211 normal cases, 143 LSIL cases and 196 HSIL cases). For evaluation of the automatic feature extraction performance, correlation test approach was used to determine the capability of the RGBFE algorithm as compared to manual extraction by cytotechnologist. The manual extraction of size was recorded in micrometer while the automatic extraction of size was recorded in number of pixels. Region color was recorded in mean of grey level value for both manual and automatic extraction. The results show that the estimated size and mean of grey level have strong linear relationship (correlation test more than 0.8) with those extracted manually by cytotechnologist. Hence, the size of nucleus, size of cytoplasm and grey level of cytoplasm created very strong linear relationship with correlation test more than 0.95 (approaching one). For the intelligent diagnostic, the performance of the H(2)MLP network was compared with three standard ANNs (i.e. multilayered perceptron (MLP), radial basis function (RBF) and hybrid multilayered perceptron (HMLP)). The performance was done based on accuracy, sensitivity, specificity, false negative and false positive. The H(2)MLP network performed the best diagnostic performance as compared to other ANNs. It was able to achieve 97.50% accuracy, 100% specificity and 96.67% sensitivity. The false negative and false positive were 1.33% and 3.00%, respectively. This project has successfully developed an automatic diagnostic system for cervical pre-cancerous. This study has also successfully proposed one image processing technique namely the RGBFE algorithm for automatic feature extraction process and a new ANN architecture namely the H(2)MLP network for better diagnostic performance.

Bioprocess hybrid parametric/nonparametric modelling based on the concept of mixture of experts

This paper presents a novel method for bioprocess hybrid parametric/nonparametric modelling based on mixture of experts (ME) and the expectation maximisation (EM) algorithm. The bioreactor system is described by material balance equations whereas the cell population subsystem is described by an adjustable mixture of parametric/nonparametric sub-models inspired in the ME architecture. This idea was motivated by the fact that cellular metabolism has an inherent “modular” structure, organised in metabolic pathways, with complex interactions. This study was supported by simulations using models of different levels of complexity. The proposed method was compared with the conventional hybrid technique employing the multi-layer perceptron (MLP) and the radial basis function (RBF) networks. As main conclusions it can be stated that MEs trained with the EM algorithm are able to systematically detect metabolic shifts with the individual experts developing expertise in describing the individual pathways. The hybrid ME model with thin-plate spline RBF network as experts outperforms both the hybrid MLP model and the hybrid RBF model in its ability to describe metabolic switches.

Suitable features selection for the HMLP and MLP networks to identify the shape of aggregate

Aggregates are one of the main ingredients for producing concrete. In order to produce ‘high performance’ concrete, the properties of aggregates matter most. In particular, shape and surface texture of aggregates immensely influence the strength and structure of the resulting concrete. Often, low quality shape aggregates reduce the durability and strength of the concrete with much more requirement of sand, cement and water. Because the strength of concrete depends on the ratio of well-shaped aggregates to poor shape ones contained in the concrete mixture, the classification process for aggregates into well shaped and poor shaped is an essential step toward high quality concrete. Traditional technique requires aggregate to pass a stringent series of mechanical, chemical and physical test in order to demonstrate that they will perform satisfactorily, and meet or exceed specifications. Such stringent tests, often perform manually, tends to be slow, highly subjective and laborious. Therefore, an intelligent system that can separate the aggregates automatically could help to overcome these problems. This paper discusses an implementation of an intelligent classification system for the aggregate particles using neural network. The features obtained with image analysis, which are area, perimeter, Hu’s moments, Zernike’s moments of the aggregate’s area and perimeter were used as input data for the neural network. The hybrid multilayered perceptron network trained using modified recursive prediction error algorithm is employed to perform the classification. Performance analysis of the hybrid multilayered perceptron network is compared with the standard multilayered perceptron network trained using four different training algorithms, i.e. recursive prediction error, Bayesian Regulazation, Levenberg–Marquardt and scale conjugate gradient. The experimental results show that the performance for hybrid multilayered perceptron and multilayered perceptron networks are significantly better using the moments extracted based on object’s perimeter compared to object’s area. Model comparison confirms that the selected features combined with hybrid multilayered perceptron network attains the best performance in aggregates recognition.

Hybrid multilayered perceptron networks

This paper introduces a modified multilayered perception network (MLP) called the Hybrid Multilayered Perceptron (HMLP) network to improve the performance of a MLP network. The convergence rate of the proposed network is further improved by proposing a modified version of the recursive prediction error algorithm as the training algorithm. The capability of the proposed network architecture trained using the modified recursive prediction error algorithm was demonstrated using simulated and real data sets. The results indicated that the proposed network provides a significant improvement over a standard MLP network. These additional linear input connections do not significantly increase the complexity of the MLP network since the connections are linear. In fact, by using the linear input connections, the number of hidden nodes required by the standard MLP network model can be reduced, which will also reduce computational load. The performance of the HMLP network was also compared with Radial Basis Function (RBF) and Hybrid Radial Basis Function (HRBF) networks. It was found that the proposed HMLP network was much more efficient than both RBF and HRBF networks.