学生のPhan Viet AnhさんがKSE 2016においてbest student paper awardを受賞

 学生のPhan Viet Anhさん(博士後期課程2年、知能ロボティクス領域グェン研究室)がKSE 2016においてbest student paper awardを受賞しました。

The KSE conference is an open international forum for presentation, discussion and exchange of the latest advances and challenges in research of Knowledge and Systems Engineering. The eighth edition of the conference, KSE 2016, was held in Hanoi, the capital of Vietnam, during October 6-8, 2016, and organized by the Le Quy Don Technical University. KSE 2016 presentations include contributions dealing with any aspects of Knowledge and Systems Engineering such as machine learning, data mining, knowledge management, and so on.


 Exploiting Tree Structures for Classifying Programs by Functionalities

Analyzing source code to solve software engineering problems such as fault prediction, cost, and effort estimation always receives much attention of researchers as well as companies. The traditional approaches are based on machine learning, and software metrics obtained by computing standard measures of software projects. However, these methods have faced many challenges due to limitations of using software metrics which were not enough to capture the complexity of programs.

The aim of this paper is to apply several natural language processing techniques, which deal with software engineering problems by exploring information of programs' abstract syntax trees (ASTs) instead of software metrics. To speed up computational time, we propose a pruning tree technique to eliminate redundant branches of ASTs. In addition, the k-Nearest Neighbor (kNN) algorithm was adopted to compare with other methods whereby the distance between programs is measured by using the tree edit distance (TED) and the Levenshtein distance. These algorithms are evaluated based on the performance of solving 104-label program classification problem. The experiments show that due to the use of appropriate data structures although kNN is a simple machine learning algorithm, the classifiers achieve the promising results.

Our group is in Prof. Le-Minh Nguyen laboratory. We are very honored and thankful for the award. We would like to thank Prof. Le-Minh Nguyen for his guidance and deep discussions about the approaches. We also would like to thank other members of our lab for their constructive comments on the first versions of the paper. We are also really thankful to JAIST for providing us a great environment for doing research. This award encourages us doing researches better to obtain higher achievements.