Hua Chu

An approach for reversely generating hierarchical UML statechart diagrams

One of the most crucial and complex steps of object-oriented system design lies in the transition needed to go from system behavior (defined by means of scenario models) to component behavior (described by means of communicating hierarchical state machine models).This paper presents a re-verse approach for generating hierarchical UML statechart diagrams. Firstly, we put forward a generation algorithm for a flat statechart diagram based on the BK-algorithm, which is validated useful in our reverse engineering tool XDRE by generating UML statechart diagrams from a set of UML sequence diagrams. Secondly, according to UML composite state, an automatic approach of introducing hierarchy to the generated flat statechart diagrams is proposed and implemented. Finally, systematic experiment is conducted in the paper in order to verify the validity of this approach.

Event-based Evolution Mechanism in Dynamic Environment for Multi-Agent System

As Agent-based software development methods get more and more attention and Agent-based software system has been used in a variety of occasions, the features and advantages of Agent have been recognized by scholars. However, the runtime environment of Agent is dynamic, open and changeable; runtime in this kind of environment is a big challenge to ensure that the software system can satisfy the users requirements and is proper in continuous running. An event-based evolution mechanism in dynamic environment for multi-agent system was proposed. Taking advantage of the Agents characteristics such as autonomy and intelligence, the evolution mechanism can satisfy the requirements of users and support software upgrade in dynamic environment by means of software evolution. By the proposed mechanism, the Agent could autonomously cooperate with others to complete the task. Finally, an experiment of the mechanism was presented to verify its effectiveness.

Method for Knowledge Acquisition and Decision-Making Process Analysis in Clinical Decision Support System

The traditional clinical decision support system (CDSS) is based on the rule engine and knowledge base which are arranged and imported into the system by the relevant personnel before the system running. Therefore once the system is put into use, the knowledge and rules will be rarely revised and updated dynamically according to the actual clinical environment. In addition, conventional systems has failed to take full advantage of the data stored in Hospital Information System (HIS) to excavate implicit knowledge of the diagnosis and treatment. Furthermore, the lack of logging mechanism during the diagnosis and treatment decisions link results in the imperfection of the learning ability for the CDSS. To solve the above problems above, this paper proposes to introduce the knowledge mining technology into the CDSS to use the data in the HIS for knowledge mining activities. And the use of the excavated knowledge and rules makes the knowledge systems dynamically updated and expanded. With using the clinical log to store the information of the decision-making process, it will be easy to study, analysis, assessment the implicit knowledge in order to find the problems and make targeted to improve them to achieve the purpose of improve the decision-making accuracy.

Knowledge Reasoning Model to Support Clinical Decision Making

According to the characteristics of clinical decision-making and the actual work of clinical diagnosis, this paper presents to introduce the knowledge reasoning model about the clinical diagnosis and treatment into the clinical decision support systems (CDSS) to enhance the decision-making ability. Furthermore, a kind of structure of the reasoning model and a comprehensive method of the clinical decision making based on event-driven is also proposed in this paper. This method can dynamically adjust to new medical behavioral events, support the complex medical decision-making behavior, make the CDSS to better support the real-time clinical diagnosis and treatment decisions, so as to effectively assist clinicians in clinical diagnosis and treatment work, and improve normalization and accuracy in medical work.

An improved decision tree algorithm using rough set theory in clinical decision support system

In the Clinical Decision Support System (CDSS), over-fitting phenomenon may appear when decision tree algorithm was used. For this problem, this paper will make use of the Rough Set theory to the training set for attribute reduction, the decision tree built by using the decision tree algorithm was used to predict the test data. In this paper, 46 copies of coronary heart disease clinical data were used to test the improved algorithm. Comparing the accuracy of the algorithm and the improved algorithm, we can know that, the improved algorithm has a better recognition rate for the diagnosis of coronary heart disease, and effectively solves the over-fitting phenomenon in the Decision Tree Algorithm.

DCISL: dynamic control integration script language

This paper studies a script language DCISL for the dynamic control integration of the MAS (Multi-Agent System), which is used to describe the integration rules based on service flow. With the analysis of MAS-related language elements and combination of formalized description method and structure tool, this paper provides the definition of DCISL and realization of DCISL interpreter. DCISL uses the way of unifying the logistic definition and separating the physical realization to describe the MAS integration rules. Through the script interpreter, the integration rules between service agents which are described in DCISL are mapped into behavior logic between service agents, and by using the interpreting mechanism of the script interpreter, the dynamic script switch is realized. Through the interpreter within the service agents, the integration rules within the agents which are described in DCISL are mapped into the behavior logic between function agents, and according to the contract net protocol, the service agents interact with CMB (Common Message Blackboard) to realize the dynamic bid inviting. Ultimately, the experiment shows that the agents can run independently according to the integration logic based on the integration rules which are described in DCISL and eventually realizes the cooperation between agents and the dynamic integration control of agents system by using of the script switch and bid inviting mechanism.

Multi-agent Organization for Hiberarchy Dynamic Evolution

With increasingly dynamic operating environment and user requirements, software adopts a unified strategy to achieve the different levels of evolution, a fact which reduces the flexibility and efficiency. So, in this paper, a method with agent technology is proposed to support the hiberarchy evolution of both the function and service levels. Precisely, a multi-agent organization is proposed to separate the calculation and collaboration logics of software which are corresponding to the different levels of evolution. To achieve the function-level evolution, an adaptive agent model with knowledge reasoning provides the software an ability to dynamically modify the calculation logics. With the adjustment of the collaboration logics, the multi-agent organization can make it convenient for the software to deal with the service-level evolution. Finally, a case study of air defense simulation system and some test metrics indicates that the proposed multi-agent organization can effectively support the hierarchy evolution.

Adaptive mechanism based on shared learning in Multi-Agent System

In view of the deployment environment of the adaptive system is complex, dynamic, unpredictable, focusing on the construction of dynamic, uncertain environment adaptive system, and this paper combines the reinforcement learning technology and software agent technology to propose an adaptive mechanism based on shared learning in multiple agent system. Based on this, framework for constructing adaptive systems and shared learning algorithm of agent are given. Finally, by conducting a comparative experiment and result analysis to verify the feasibility of the theory put forward by this article.

An Intelligent Knowledge Retrieval Framework for Clinical Diagnosis and Treatment in CDSS

In the field of Clinical Decision Support System (CDSS), the clinical pathway has been widely used and promoted in the hospitals.Tthe traditional way to manage and organize the clinical pathway has already not adapt to the needs of the present. In order to adapt to the current application requirements of the clinical pathway and improve the way to manage, organize and search the clinical pathway, this paper proposes to build a clinical pathway database to manage and store the clinical pathway. Based on the structure characteristics of the clinical pathway, a new Lucene-based method and a framework are proposed in this paper. The Lucene-based method can index the clinical pathway according the structure of the article of the clinical pathway.