No abstract

In software testing, cause-effect graph assures coverage criteria of 100% functional requirements with minimum test case. The existing test case generation from causeeffect graph implements the algorithmic approach. It has disadvantages to modify the entire program if the input model is different. In contrast, model transformation approach can flexibly implement with even a different input models. In the future, we need to study the method of automatic generation of test cases from UML Diagram. It is possible to generate the test case when mapping between cause-effect graph and UML diagram. In this paper, as a first research step, we propose the method to generate test cases from cause-effect graph based on model transformation. To implement the proposed method, we write the rules of model transformation with ATLAS Transformation Language (ATL), and execute the rules in development environment of Eclipse. The implemented tool of the proposed method can be easily extended by rewriting with the mapping rule between cause-effect graph and UML diagram. We just define the relationship between each models to generate the test case.

No abstract

This paper proposes a intelligent approach on range decision of figure of merit. Unknown range of the underwater target and the non-fixed signal excess make the uncertainty for the tracking process. Using the input data of signal excess related to the range, we establish the rule of the fuzzy set and the original data acquired by sonar can be transformed to the fuzzified data set. To reduce the error arisen from the unexpected data, we use the new data transformed in fuzzy set. The piecewise relations of the min value, max one, and the mean one are calculated. The three values are used for the expected range of the underwater target. By analysing the fluctuation of the data, we can expect the target's position and the characteristics of the maneuvering. The examples are presented to show the performance and the effectiveness of the proposed method.

-This paper presents the smart interacting multiple model (SIMM) using the concept of predicted point and maximum noise level. Maximum noise level means the largest value of the mere noises. We utilize the positional difference between measured point and predicted point as acceleration. Comparing this acceleration with the maximum noise level, we extract the acceleration to recognize the characteristics of the target. To estimate the acceleration, we propose an optional algorithm utilizing the proposed method and the Kalman filter (KF) selectively. Also, for increasing the effect of estimation, the weight given at each sub-filter of the interacting multiple model (IMM) structure is varying according to the rate of noise scale. All the procedures of the proposed algorithm can be implemented by an on-line system. Finally, an example is provided to show the effectiveness of the proposed algorithm.