Parallel genetic algorithms for optimization of Modular Neural Networks in pattern recognition

In this paper a Particle Swarm Algorithm (PSO) is applied for the optimization of modular neural networks. This method is used for optimizing modular neural network in medical image recognition (Echocardiograms). As echocardiograms, these images help to diagnose heart diseases by the specialists and so can reduce the number of deaths by disease. Simulation results show that the scaled conjugate gradient (trainscg method) offers much higher performance with an average 81.4% recognition rate and with the gradient descent with adaptive learning (traingda method) an average of 76.3% recognition rate.

We describe in this paper the architecture of a modular neural network (MNN) for pattern recognition. More recently, the study of modular neural network techniques theory has been receiving significant attention. The design of a recognition system also requires careful attention. The paper aims to use the Ant Colony paradigm to optimize the architecture of this Modular Neural Network for pattern recognition in order to obtain a good percentage of image identification and in the shortest time possible.

We describe in this paper the evolution of modular neural networks using hierarchical genetic algorithms for pattern recognition. Modular neural networks (MNN) have shown significant learning improvement over single neural networks (NN). For this reason, the use of MNN for pattern recognition is well justified. However, network topology design of MNN is at least an order of magnitude more difficult than for classical NNs. We describe in this paper the use of a hierarchical genetic algorithm (HGA) for optimizing the topology of each of the neural network modules of the MNN. The HGA is clearly needed due to the fact that topology optimization requires that we are able to manage both the layer and node information for each of the MNN modules. Simulation results prove the feasibility and advantages of the proposed approach.

Bio-Inspired Hybrid Intelligent Systems for Image Analysis and Pattern Recognition comprises papers on diverse aspects of bio-inspired models, soft computing and hybrid intelligent systems. The articles are divided into four main parts. The first one consists of papers that propose new fuzzy and bio-inspired models to solve general problems. The second part deals with the main theme of modular neural networks in pattern recognition, which are basically papers using bio-inspired techniques. The third part contains papers that apply hybrid intelligent systems to the problem of time series analysis and prediction, while the fourth one shows papers dealing with bio-inspired models in optimization and robotics applications. An edited book in which both theoretical and application aspects are covered.

Designing and Learning Algorithm of Neural Networks for Pattern Recognition

In this chapter we describe the application of a full model of PSO as an optimization method for modular neural networks with the LVQ algorithm in order to find the optimal parameters of a modular architecture for the classification of arrhythmias. Simulation results show that this modular model optimized with PSO achieves acceptable classification rates for the MIT-BIH arrhythmia database with 15 classes.

To solve the challenge of efficient signal processing consider the complex scenarios, this paper proposes the novel classification algorithm of English accent signal based on multi-parameter neural network. In the existing traditional research, most of the processing methods regard the time-varying signal as short-term stationary and linear, and the focus is on the information contained in the time domain and frequency domain, so as to perform signal classification without reference. In this paper, the advantages of neural network in pattern recognition are used, and the relevant parameters are optimized through the theoretical analysis of the “optimal” classification rules. In the designed neural model, the graph features are considered to better extract the features, and then the bagging algorithm is applied to classify the models. Through the experiment compared with the C-4.5, CNNs, PSO and BP, it is evident that the proposed algorithm performs better in classification accuracy aspect.

In view that the efficiency of computer forensics technology is insufficient and some other problems at present, a computer dynamic forensics method has been proposed based on BP neural network. This method has combined the advantages of artificial neural network in pattern recognition which can timely and accurately identify the network attack behaviors. On this basis, a prototype system with dynamic forensics has been designed. And the experiment has showed that this system has high detection rate for the network bad behaviors and the detection performance is superior to other pattern recognition methods.

The article is devoted to the formation of the initial data set for training neural networks. A proven method for creating synthetic data based on a graphics processor using a graphics pipeline is presented. A distinctive feature of this method is its modular architecture, which makes it easy to modify, delete or add individual stages to the synthetic image generation pipeline. A one-stage automatic detector based on a convolutional neural network of the Yolo type has been trained, the quality of the trained model and the operation of the recognition algorithm were also evaluated. Conclusions are drawn regarding the possibility of using this approach when creating representative samples of a large volume and their further use for training neural networks in pattern recognition.

Neural Networks in Pattern Recognition and their Applications

A novel method for early diagnosis of Alzheimer’s disease based on pseudo Zernike moment from structural MRI

The complexity of problems has led to a shift toward the use of modular neural networks in place of traditional neural networks. The number of inputs to neural networks must be kept within manageable limits to escape from the curse of dimensionality. Attribute division is a novel concept to reduce the problem dimensionality without losing information. In this paper, the authors use Genetic Algorithms to determine the optimal distribution of the parameters to the various modules of the modular neural network. The attribute set is divided into the various modules. Each module computes the output using its own list of attributes. The individual results are then integrated by an integrator. This framework is used for the diagnosis of breast cancer. Experimental results show that optimal distribution strategy exceeds the well-known methods for the diagnosis of the disease.

The bio-inspired concept of Spike-Timing-Dependent Plasticity (STDP) derived from neurobiology is increasingly used in Spiking Neural Networks (SNNs) nowadays. Mostly found in unsupervised learning, though recent work has shown its usefulness in supervised or reinforced paradigms too, STDP is a key element to understanding SNN architectures’ learning process. This review introduces a categorisation of its several variants and discusses their specificities and applications, from a pattern recognition perspective. It gathers a variety of definitions used in machine learning for pattern recognition. It provides relevant information for research communities of various backgrounds looking for an overview of this field.

Floorplanning is an important problem in very large-scale integrated-circuit (VLSI) design automation as it determines the performance, size, yield and reliability of VLSI chips. From the computational point of view, floorplan area minimization is an NP-hard problem. This paper presents a parallel genetic algorithm (GA) for floorplan area optimization. The parallel GA is based an island model with an asynchronous migration mechanism, and is implemented using Web services and multithreading technologies. The parallel GA is compared with a sequential GA that the parallel GA is based on. Experimental results show that the parallel GA can produce better results than the sequential GA when they use the same amount of computing resources. In addition, since the number of islands and migration interval are two important parameters that directly affect the performance of island-based parallel GAs, the impact of the two parameters on the performance of the parallel GA are empirically studied in this paper.

We consider different parallel architectures and methods for self-organization and minimization of complexity for heterogeneous polynomial neural networks (PNN) in problems of pattern recognition and in diagnostics of states. Constructive estimates for the heterogeneity index and parallelism in the process of autonomous classifying decision making with the use of PNNs of different kinds are obtained. It is shown that the parallelism, self-organization, and robustness of heterogeneous PNNs can significantly increase in group (multiagent) solutions of difficult problems in pattern recognition, image analysis, large-scale (vector) diagnostics of states, and adaptive routing of data flows.