Multiple Information Fusion Research Articles

A Feature Extraction Strategy Based on Multiple Color Information

In this paper, a feature extraction strategy based on multiple color information fusion was proposed. Firstly this method started with analyzing the transform formula of color space, which transform was mainly thinking about RGB color space to other color spaces. Secondly by analyzing the characteristic of every color space in describing the actual color information, the advantages and disadvantages of every color space were showed. Thirdly through above conclusion, the algorithm which extracted the target feature only using single color information was defective, and then the strategy based on multiple color information fusion was proposed. Lastly the detail fusion strategy was given, which fused the probability distributed information of multiple color into the last probability distributed information as the target feature. The feature extraction strategy in this paper is verified by the camshift algorithm. The results show that the multiple color information fusion can improve the tracking performance of moving target.

Research on Neural Network Model Based on Subtraction Clustering and Its Applications

This paper takes advantage of the integration of subtraction clustering and fuzzy c-means clustering algorithm to obtain precise number of clusters and the degree of membership, and establishes the neural network model based on the multiple criterion information fusion and the fuzzy technology. Collecting a variety of data in actual underground mining process and integrating them as a whole, the simulations are performed. Experimental results indicate that the proposed method is valid.

GeMiBi: A general multiple sources information Bayesian fusion for performance evaluation and an application to HPC cluster

Efficient and accurate performance evaluation is a challenge for many application areas. Information fusion is a widely used technology for this issue. Most existing information fusion methods have the requirement of taking a large sample into consideration. However, only small-scale experiments can be carried out for performance evaluation due to relatively severe resource constraints. To address this challenge, we delve into multiple sources information fusion method based on Bayesian inference for small samples case. In this paper, we propose GeMiBi: a general multiple sources information Bayesian inference method based on the minimum Jensen–Shannon Divergence (JSD). We exploit JSD to measure the similarity of different prior information and formulate a multiple constraints optimization problem to model the relation between different prior information and small samples observation data. In order to eliminate the massive numerical calculation when using the complex fused prior, we propose a novel and general information Bayesian inference method based on minimum JSD weights. Extensive experiments based on high performance cluster disk data are carried out to demonstrate the efficacy and effectiveness of the proposed method. Results show that the mean error of our method is 0.56% in the illustrating application, and it is greatly reduced compared with previous methods.

A Framework for Multiple and Heterogeneous Earthquake Disaster Information Fusion

To realize the fusion of multiple and heterogeneous earthquake disaster information and get effective disaster information, situation and characteristics are addressed on different earthquake disaster information acquiring methods, in which some new earthquake disaster information acquiring methods are described. A fusion architecture of multiple and heterogeneous disaster information is put forward, including data level, fusion level and application level. And function principle of each level is described. Finally key technologies and realization methods in the fusion architecture are expounded, which are transformation and match of multiple disaster information and coding of the information.

Study on intelligent syndrome differentiation in Traditional Chinese Medicine based on multiple information fusion methods

Numerous researchers have taken the solid step forward towards the objectification research of Traditional Chinese Medicine (TCM) four diagnostic methods. However, it is deficient in studies on information fusion of the four diagnostic methods. We establish four-diagnosis syndrome differentiation model of TCM based on information fusion technology. The objective detection instruments of four-diagnostic method are applied to collect four-diagnosis objective information of 506 cases of clinical heart-system patients. Then multiple information fusion methods are adopted to establish recognition model of syndromes. The results of our experiments show that recognition rates of the six syndromes using multi-label learning is better than OCON artificial neural network and multiple support vector machine.

Nonlinear Estimation and Multiple Sensor Fusion Using Unscented Information Filtering

This letter represents a new unscented information filtering algorithm for nonlinear estimation and multiple sensor information fusion. The proposed information fusion algorithm is derived by embedding the unscented transformation method used in the sigma point filter into the extended information filtering architecture. The new information filter achieves not only the accuracy and robustness of the sigma point filter but also the flexibility of the information filter for multiple sensor estimation. Performance comparison of the proposed filter with the extended information filter is demonstrated through a target-tracking simulation study.

Multiple information fusion and quality classification of aluminum alloy resistance spot welding

Resistance spot welding quality real-time monitoring of aluminum alloy is realized by distributed multiple-sensor synchronous collection system and the related data processing software is also developed by using LABVIEW graphical language.The results show that the endo-expulsion in spot welding is related to the notching curve of voltage and electrode displacement signal.Moreover,there is a correlation between the high frequency impulse amplitude and duration of the electrode pressure signal and the expulsion strength index,and three characteristics simultaneously or separately occur according to the expulsion strength index in spot welding. Resistance spot welding quality can be reflected by nine characteristics of high signal-to-noise ratio,and they become the base of on-line quality classification of aluminum alloy spot welding in future.Furthermore,using principal component analysis may implement the information fusion and data compression.The percentage of spot welding quality classification accuracy can reach 98%.

Multiple behavior information fusion based quantitative threat evaluation

How to evaluate network security threat quantitatively is one of key issues in the field of network security, which is vital for administrators to make decision on the security of computer networks. A novel model of security threat evaluation with a series of quantitative indices is proposed on the analysis of prevalent network intrusions. This model is based on multiple behavior information fusion and two indices of privilege validity and service availability that are proposed to evaluate the impact of prevalent network intrusions on system security, so as to provide security evolution over time, i.e., monitor security changes with respect to modification of security factors. The Markov model and the algorithm of D-S evidence reasoning are proposed to measure these two indices, respectively. Compared with other methods, this method mitigates the impact of unsuccessful intrusions on threat evaluation. It evaluates the impact of important intrusions on system security comprehensively and helps administrators to insight into intrusion steps, determine security state and identify dangerous intrusion traces. Testing in a real network environment shows that this method is reasonable and feasible in alleviating the tremendous task of data analysis and facilitating the understanding of the security evolution of the system for its administrators.