Automatic Path-Oriented Test Data Generation Using a Multi-population Genetic Algorithm

Chen, Yong; Zhong, Yong

doi:10.1109/icnc.2008.388

Cited by 28 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed technique is compared with path testing technique (discussed in [4]), for these programs. We have chosen path testing technique because path testing strategy can alone detect almost 65% of errors in the program [28].…”

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

“…The ten programs that are chosen are developed using C language and range from 35 to 200 lines of source code. In this work, we use the same fitness function as proposed in [4]. This is so because our aim is to compare the adequacy based test criteria with the reliability based criteria, where both the criteria are GA based only.…”

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

“…The fitness function concept that we use here is same as proposed in [4]. This concept is actually based on calculating the difference between values of program variables, such that the difference is minimized.…”

Section: Fitness Function Constructionmentioning

confidence: 99%

“…Our aim is to generate test case values that can minimize the value of fitness function. Table 3 represents the fitness function concept (as proposed in [4]) and is shown below: Adhering to the effectiveness of the fitness function concept proposed in [4], we have used the same here. We can use both min as well as max fitness function.…”

Section: Fitness Function Constructionmentioning

confidence: 99%

“…Reliability based testing criteria are used to show the correctness of the program in terms of achieving some coverage that may be either 'control flow coverage' or 'Data flow coverage'. Control flow coverage criteria include path testing [4], condition testing [5], branch testing [6,7], etc. Data flow coverage criteria include all-uses [8], all-du (definition use) paths [9,23,26,27] etc.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Adequacy Based Test Data Generation Technique Using Genetic Algorithms

Malhotra¹,

Garg²

2011

Journal of Information Processing Systems

View full text Add to dashboard Cite

Abstract-As the complexity of software is increasing, generating an effective test data has become a necessity. This necessity has increased the demand for techniques that can generate test data effectively. This paper proposes a test data generation technique based on adequacy based testing criteria. Adequacy based testing criteria uses the concept of mutation analysis to check the adequacy of test data. In general, mutation analysis is applied after the test data is generated. But, in this work, we propose a technique that applies mutation analysis at the time of test data generation only, rather than applying it after the test data has been generated. This saves significant amount of time (required to generate adequate test cases) as compared to the latter case as the total time in the latter case is the sum of the time to generate test data and the time to apply mutation analysis to the generated test data. We also use genetic algorithms that explore the complete domain of the program to provide near-global optimum solution. In this paper, we first define and explain the proposed technique. Then we validate the proposed technique using ten real time programs. The proposed technique is compared with path testing technique (that use reliability based testing criteria) for these ten programs. The results show that the adequacy based proposed technique is better than the reliability based path testing technique and there is a significant reduce in number of generated test cases and time taken to generate test cases.

show abstract

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

Section: Experimental Analysis and Resultsmentioning

confidence: 99%

Section: Fitness Function Constructionmentioning

confidence: 99%

Section: Fitness Function Constructionmentioning

confidence: 99%