Feature Selection based Neural Networks for Software Defect Prediction

Srinivas, M. Satya; Pradeepini, G.

doi:10.21742/ijstsd.2014.1.1.02

Cited by 3 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, students cannot understand easily the difference between the natural language level algorithm and the implemented real program. In the software textbook, problemsolving processes for the examples are expressed finally into algorithms with natural language codes [1][2][3][4][5].…”

Section: Hierarchical Block Coding Algorithms Via Input Device Connecmentioning

confidence: 99%

“…Naturally, most jobs require computing thinking. As a result of these changes, computational literacy, which is the ability to utilize computational thinking, has begun to be emphasized as a core competence required to live in the future, and to secure professional personnel with an understanding of software principles will soon lead to national competitiveness [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

“…Second, the input, processing, and output processes of digital and analog sensors included in Arduino are different from the conventional programming learning, in that programming error detection (debugging) is physically transmitted through the learner's manipulative activities, It is possible to correct the programming error quickly and improve the learning interest and satisfaction of the learners. Third, it provides a process of designing creative prototypes to solve real-life problems, and it can positively influence problem-solving ability by supporting the generation of learner's ideas [5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Block Coding Algorithm Training Examples using Arduino Board for Elementary and Secondary School Students

Hur¹,

Sohn²,

Kwon³

2018

IJAST

View full text Add to dashboard Cite

show abstract

Section: Hierarchical Block Coding Algorithms Via Input Device Connecmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Block Coding Algorithm Training Examples using Arduino Board for Elementary and Secondary School Students

Hur¹,

Sohn²,

Kwon³

2018

IJAST

View full text Add to dashboard Cite

show abstract

“…The main theme of the paper [6] was to assist the developers to improvise the quality of the software by predicting the software defects using the software metrics and using classification techniques. In the work [7] the authors proposed principal component analysis based feature selection and prediction of defects using the neural networks with the reduced feature set. They use AR1 dataset available in PROMISE repository and they showed in their result that the neural networks with and without feature selection performance.…”

Section: Related Workmentioning

confidence: 99%

An optimized feature selection using fuzzy mutual information based ant colony optimization for software defect prediction

Manivasagam¹,

Gunasundari²

2017

IJET

View full text Add to dashboard Cite

In recent years, there is a significant notification focused towards the prediction of software defect in the field of software engineering. The prediction of software defects assist in reducing the cost of testing effort, improving the process of software testing and to concentrate only on the fault-prone software modules. Recently, software defect prediction is an important research topic in the software engineering field. One of the important factors which effect the software defect detection is the presence of noisy features in the dataset. The objective of this proposed work is to contribute an optimization technique for the selection of potential features to improve the prediction capability of software defects more accurately. The Fuzzy Mutual Information Ant Colony Optimization is used for searching the optimal feature set with the ability of Meta heuristic search. This proposed feature selection efficiency is evaluated using the datasets from NASA metric data repository. Simulation results have indicated that the proposed method makes an impressive enhancement in the prediction of routine for three different classifiers used in this work.

show abstract

“…Firstly, students understand the SW-making steps using a CT model to solve a problem. Secondly, students understand that in software development, it is necessary for students to have a high level of CT thinking ability to store and use data to mathematical operations [10][11][12][13]. Thirdly, the software should be developed to process the given data to produce useful information [7][8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Scoring Program Development Course for Software Education Using Computational Thinking Model

Hur¹,

Sohn²,

Kwon³

2019

IJAST

View full text Add to dashboard Cite

In the age of the fourth industrial revolution, major social needs for indispensable SW (software) education are the CT (computational thinking) training. However, there is a lack of sympathetic software projects in the CT training for nonmajor students, when using a block coding tool like the scratch 3.0. Effective CT training examples should include the use of abstraction, decomposition, pattern recognition, and algorithmic thinking techniques, along with adequate structures for data storage. In this paper, we focused on how to make a model of CT processes to achieve the goals of SW education. Then, we proposed a CT model and its educational use-case in the project of developing an OX-type scoring program. The proposed OX-type scoring program was systematically developed in accordance with predefined problem-solving steps in the CT model. This proposal can be applied to various SW education subjects to educate the problem-solving steps using software and to enhance the understanding of CT processes.

show abstract

Feature Selection based Neural Networks for Software Defect Prediction

Abstract: Abstract

Cited by 3 publications

References 5 publications

Block Coding Algorithm Training Examples using Arduino Board for Elementary and Secondary School Students

Block Coding Algorithm Training Examples using Arduino Board for Elementary and Secondary School Students

An optimized feature selection using fuzzy mutual information based ant colony optimization for software defect prediction

Scoring Program Development Course for Software Education Using Computational Thinking Model

Contact Info

Product

Resources

About