Artificial Neural Networks (ANNs), as a nonlinear and adaptive information processing systems, play an important role in machine learning, artificial intelligence, and data mining. But the performance of ANNs is sensitive to the number of neurons, and chieving a better network performance and simplifying the network topology are two competing objectives. While Genetic Algorithms (GAs) is a kind of random search algorithm which simulates the nature selection and evolution, which has the advantages of good global search abilities and learning the approximate optimal solution without the gradient information of the error functions. This paper makes a brief survey on ANNs optimization with GAs. Firstly, the basic principles of ANNs and GAs are introduced, by analyzing the advantages and disadvantages of GAs and ANNs, the superiority of using GAs to optimize ANNs is expressed. Secondly, we make a brief survey on the basic theories and algorithms of optimizing the network weights, optimizing the network architecture and optimizing the learning rules, and make a discussion on the latest research progresses. At last, we make a prospect on the development trend of the theory.

Using Genetic Algorithms to Optimize Artificial Neural Networks.

CAPTCHA (Completely Automated Public Turing Test to tell Computers and Human Apart) is widely used than before, which becomes the common part of current website login system. However, the CAPTCHA implementation is tricky and risky without deliberate design. In this paper, we give a study case of the vulnerabilities in current login website using text-based CAPTCHA. Our target is a website of mainstream bank of china. We show that with some specialized methods, the CAPTCHA scheme in its website can be easily cracked. Finally, we give some advices for CAPTCHA designers to revise our CAPTCHA implementation security in the future.

A Case Study of Text-Based CAPTCHA Attacks

The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and particle swarm optimization algorithm is proposed to optimize the weight and threshold value of BP neural network. After network traffic prediction experiment, we can conclude that optimized BP network traffic prediction based on PSO-ABC has high prediction accuracy and has stable prediction performance.

Network Traffic Prediction based on Particle Swarm BP Neural Network

Research on the detection of fabric color difference based on T-S fuzzy neural network

Color is an indispensable indicator of product quality evaluation. To detect the color difference of fabrics, the Levenberg–Marquardt optimized back propagation (BP) algorithm is adopted to extract the color feature values of fabric images. First, RGB values are three inputs of BP neural network, and L*a*b* values measured by spectrophotometer are three outputs of the network. The trained network can obtain the corresponding L*a*b* values conveniently. Then the color difference can be calculated through color difference formula and the characteristic values obtained above. Finally, compared with the color difference calculated by the spectrophotometer, the most appropriate formula can be selected from the four formulas listed in the article (CIEDE2000, CMC, CIE94, and CIELAB) to acquire satisfying results. The experimental results reveal that the color difference of fabrics can be detected with a high accuracy and efficiency with this method. Plenty of duplication workloads and some complex conversion formulas can be avoided, making the acquirement of color difference more efficiently. © 2014 Wiley Periodicals, Inc. Col Res Appl, 40, 311–317, 2015

Application of improved back propagation algorithm in color difference detection of fabric

Back-Propagation (BP) neural network, as one of the most mature and most widespread algorithms, has the ability of large scale computing and has unique advantages when dealing with nonlinear high dimensional data. But when we manipulate high dimensional data with BP neural network, many feature variables provide enough information, but too many network inputs go against designing of the hidden-layer of the network and take up plenty of storage space as well as computing time, and in the process interfere the convergence of the training network, even influence the the accuracy of recognition finally. Factor analysis (FA) is a multivariate analysis method which transforms many feature variables into few synthetic variables. Aiming at the characteristics that the samples processed have more feature variables, combining with the structure feature of BP neural network, a FA-BP neural network algorithm is proposed. Firstly we reduce the dimensionality of the feature factor using FA, and then regard the features reduced as the input of the BP neural network, carry on network training and simulation with low dimensional data that we get. This algorithm here can simplify the network structure, improve the velocity of convergence, and save the running time. Then we apply the new algorithm in the field of pest prediction to emulate. The results show that under the prediction precision is not reduced, the error of the prediction value is reduced by using the new algorithm, and therefore the algorithm is effective.

Xiaoliang Liu

Papers

An Improved BP Neural Network Algorithm Based on Factor Analysis.