Lifeng Xi

Image Information Hiding Encryption Using Chaotic Sequence

In this paper, we propose a new image watermark algorithm of information hiding scheme based on chaotic encryption. Chaotic sequence is regarded as a noise-like spread sequence, and the secret signal to be transmitted is modulated and hidden in the carrier image as white noise to implement secure communication. The encryption principle of new algorithm is firstly presented in this paper, and the merits of new scheme are quantitatively analyzed by defining integrality and imperceptibility of image information. The results of computer simulation are described in the end.

Transient Air-Fuel Ratio Estimation in Spark Ignition Engine Using Recurrent Neural Networks

Neural networks is very useful in modeling processes for which mathematical modeling is difficult or impossible. In the present work recurrent neural network (RNN) is used for air-fuel ratio (AFR) estimation in Spark Ignition (SI) Engine. AFR estimation is difficult due to the nonlinearity and dynamic behavior in SI engines. Additionally, delays in engine dynamics limit the performance of engine controller. Estimating AFR a few steps in advance can help engine controller to take care of these. RNN is trained using data from engine simulations in MATLAB/SIMULINK environment. Uncorrelated signals were generated for training and validation. It has been shown that recurrent neural network can predict engine simulations with reasonably good accuracy.

Fault Detecting Technology Based on BP Neural Network Algorithm

This paper describes an automatic online detecting system. In the system, digital image processing technology is used to preprocess X-ray images of the products, and neural network algorithm is applied to diagnose faults. The fault recognition model adopts an improved back-propagating neural network, which is trained by a series of standard X-ray images of correctly assembled products. The detecting system combines digital radiography technology with digital image processing, and applies the back-propagating neural network algorithm in the fault recognition process. The system improves the speed and reliability of fault detection and has application in the field of industrial nondestructive detection.

Distributed Web Service Mechanism Based on Peer to Peer and Chord Protocol

Although Web Service already can be implemented by decentralized control, its publication and discovery with Universal Description, Discovery and Integration for Web Service is still based on a centralized structure. In this paper, we propose a new mechanism for decentralized Web Service by employing the efficient dynamics performance of Semantic Web and the efficient online explore capabilities of Peer to Peer networks. We furnish enriched semantic Web annotation with domain ontology, which indexes are contained in a distributed hash table based on classified service for efficient publication and discovery for Web Service. Moreover, we have proposed the decentralized Web Service framework mechanism by using classified ontology to coordinate definite requirement.

Application of Business Intelligence in the Information Development of Construction Enterprise

Due to the great ability in data analysis and mining, BI (Business Intelligence) can provide the data base information for the enterprise leaders to analyze and make the decisions. In this article, we described the BI system of China Overseas Holdings Limited. It shows the great strategic significance of BI in the building field.

Improvement of an Image Encryption Algorithm Based on Combined Multidimensional Chaotic Systems

In this paper, we propose a chaotic image encryption algorithm, which adopts the mechanism of shuffling the positions and changing the grey values of image pixels. Firstly, the discrete Kolmogorov flow is used to shuffle the positions of the image pixels in the spatial-domain. The second, the Liu chaotic system is adopted to generate integer key for the image encryption, and the shuffled image is encrypted by the integer key. The third, we show that the advantages of large key space due to its improved security and the maturity of the technology using chaotic image encryption algorithm.

Investigation on Fitting Graph Based on Fractal Dimension's Pretreatment

In this paper, we investigate an algorithm, which integrates the Box dimensions pretreatment with self-affine fractal interpolation function (AFIF). As a result of our experiments, we conclude that the algorithm allows us to fit graphs of various complexities.

Application of Genetic Algorithm to Hausdorff Measure Estimation of Sierpinski Carpet

In this paper, we discuss the realization of the genetic algorithm on calculating the Hausdorff measure of the Sierpinski gasket with compression ratio 1/2 in detail, mainly including the encoding and decoding method, generation of the initial population, and fitness computation. The experimental results prove that the genetic algorithm is an effective and universal method to calculate Hausdorff measure.

Fractal Interpolation Fitness Based on BOX Dimension’s Pretreatment

For graphs of various local complex degrees, this paper will investigate their fitting approach and conduct experiments by using the mixture processing method which is a combination of the Box dimension’s pretreatment with self-affine fractal interpolation function (AFIF).