Yang Bing-ru

A SVM regression based approach to filling in missing values

In KDD procedure, to fill in missing data typically requires a very large investment of time and energy – often 80% to 90% of a data analysis project is spent in making the data reliable enough so that the results can be trustful. In this paper, we propose a SVM regression based algorithm for filling in missing data, i.e. set the decision attribute (output attribute) as the condition attribute (input attribute) and the condition attribute as the decision attribute, then use SVM regression to predict the condition attribute values. SARS data set experimental results show that SVM regression method has the highest precision. The method with which the value of the example that has the minimum distance to the example with missing value will be taken to fill in the missing values takes the second place, and the mean and median methods have lower precision.

KAAPRO: An approach of protein secondary structure prediction based on KDD* in the compound pyramid prediction model

The problem of protein secondary structure prediction is one of the most important problems in Bioinformatics. After the study of this problem for 30 years and more, there have been some breakthroughs. Especially, the introduction of ensemble prediction model and hybrid prediction model makes the accuracy of prediction better, but there is a long distance to induce the tertiary structures from the secondary ones. As one of the extension researches of KDTICM [Bingru, Yang (2004). Knowledge discovery based on theory of inner cognition mechanism and application. Beijing: Electronic Industry Press] theory, this paper proposed a method KAAPRO, which is based on Maradbcm algorithm which is induced by KDD* model and combined with CBA, for protein secondary structure prediction. And a gradually enhanced, multilayer systematic prediction model, compound pyramid model, is proposed. The kernel of this model is KAAPRO. Domain knowledge is used through the whole model, and the physical–chemical attributes are chosen by causal cellular automata. In the experiment, the test proteins used in reference Muggleton et al. (Muggleton, S. H., King, R., Sternberg, M. (1992). Protein secondary structure prediction using logicbased machine learning. Protein Engineering, 5(7), 647–657) are predicted. The structures of amino acids, whose structural traits are obscure, are predicted well by KAAPRO. Hence, the result of this model is satisfying too. Crown Copyright 2008 Published by Elsevier Ltd. All rights reserved.

Research on Short Text Classification Algorithm Based on Statistics and Rules

In this paper, we introduced the overview of short text research and the short text classification firstly. On the foundation of several common used classic text classification algorithms, mainly according to the major feature extraction methods, the short text classification based on statistics and rules is proposed. Experiments show that this algorithm has better performance than other algorithms. In order to improve the recall rate of short text classification, two-steps classification method is put forward.

A New Model for Multiple Time Series Based on Data Mining

Time series are the important type of data in the world, and time series data mining is one of the most important subfields of data mining. In this paper we propose a model of temporal pattern discovery from multiple time series based on temporal logic. Firstly, multiple time series are transform to multiple event sequences, and then they are synthesized into one event sequence. Secondly, we generate the observation sequence to mining the temporal pattern and the rules based on the interval temporal logic. The algorithm is proposed to mining online frequent episodes and mining change of patterns on mass event sequences. Finally, efficiency of the model and the algorithm is proved through experiments.

New construction for expert system based on innovative knowledge discovery technology

Knowledge acquisition is the bottleneck of expert system. To solve this problem, KD (D&K), which is a comprehensive knowledge discovery process model cooperating both database and knowledge base, and related technology are proposed. Then based on KD (D&K) and related technology, the new construction of Expert System based on Knowledge Discovery (ESKD) is proposed. As the key knowledge acquisition component of ESKD, KD (D&K) is composed of KDD* and KDK*. KDD*—the new process model based on double bases cooperating mechanism; KDK*—the new process model based on double-basis fusion mechanism are introduced, respectively. The overall framework of ESKD is proposed. Some sub-systems and dynamic knowledge base system are discussed. Finally, the effectiveness and advantages of ESKD are tested in a real-world agriculture database. We hope that ESKD may be useful for the new generation of expert systems.

State-of-the-art in distributed privacy preserving data mining

Privacy preserving data mining has become an important research problem. The chief research is how to mine the potential knowledge and not to reveal the sensitive data. In reality, large amounts of data are stored in distributed sites, so the DPPDM (Distributed Privacy Preserving Data Mining) is very important. This paper gave a survey on the DPPDM. Based on different underlying technologies, there are three kinds of techniques: perturbation, secure multi-party computation and restricted query. It provides a detailed description of the research in this area, compares the advantages and disadvantages of each method, foucs on the hot topic in this field, points out the future research directions.

Research on Domain Ontology Construction in Military Intelligence

This paper is started from addressing the common automatic method of ontology construction. Then, from viewpoint of the military intelligent processing, the two-level domain ontology architecture is designed. One level is the keyword ontology. The other level is the instance ontology. Different level has different ontology architecture. At last, the domain ontology is constructed by reusing the existing ontology together with extracting ontology from text information and extending it. According to the results of the first application cases, it took good effects.

FIA and CASE based on fuzzy language field

This paper, for the first time, brings up a new conception of fuzzy language field and a new method of fuzzy integrated algorithm (FIA) in the background of the product device hazard level rating and they are put to verify effectively in the applications of many chemical industry instances. It opens up a path for the integration of fuzzy system method, fuzzy analysis and design, and computer-assisted safe evaluation (CASE) in the general discrete-state space. ~; 1998 Elsevier Science B.V.This paper, for the first time, brings up a new conception of fuzzy language field and a new method of fuzzy integrated algorithm (FIA) in the background of the product device hazard level rating and they are put to verify effectively in the applications of many chemical industry instances. It opens up a path for the integration of fuzzy system method, fuzzy analysis and design, and computer-assisted safe evaluation (CASE) in the general discrete-state space.

An improved CBA prediction algorithm in compound pyramid model

As one of KDTICM[8] theory researches, this paper propose an improved algorithm -- CBA, which is based on KDD* model and combined with KAAPRO method, for protein secondary structure prediction problem. Further, multi-layer systematic prediction model--Compound Pyramid Model, is proposed. The kernel of this model is CBA which is a classic association rules analysis algorithm. Domain knowledge is used through the model, and the phy-chemical attributes is chosen by Causal Cellular Automation. In experiment, the proteins bias alpha/beta structure are precisely predicted. The structures of amino acids, whose structure are obscure, are predicted well by the improved CBA. Finally, the result of this model is satisfied.

Causal association rule mining methods based on fuzzy state description

Abstract Aiming at the research that using more new knowledge to develope knowledge system with dynamic accordance, and under the background of using Fuzzy language field and Fuzzy language values structure as description framework, the generalized cell Automation that can synthetically process fuzzy indeterminacy and random indeterminacy and generalized inductive logic causal model is brought forward. On this basis, a kind of the new method that can discover causal association rules is provded. According to the causal information of standard sample space and commonly sample space, through constructing its state (abnormality) relation matrix, causal association rules can be gained by using inductive reasoning mechanism. The estimate of this algorithm complexity is given, and its validity is proved through case.