Defect Prediction Using Akaike and Bayesian Information Criterion

Analyzing the relationship between Internet attention and teaching research can provide a reference for extracting and identifying research hot spots in the discipline. Currently, many kinds of literature obtain social hot‐spot information based on a single platform, such as the Baidu Index, China National Knowledge Infrastructure (CNKI), and Web of Science. Still, they ignore the common information reflected between the Baidu Index platform and the professional academic platform and the lack of relationship demonstration between them. Therefore, based on the CNKI database and Baidu Index platform, the most critical data statistical analysis service platform in the Internet era, this article proposes a relationship modeling and prediction framework (RMPF). First, RMPF analyzes the relationship between public attention and teaching research from the perspective of “high school information technology” by word frequency analysis and Pearson. Second, RMPF constructs the relationship model between them using leave‐one‐out cross‐validation. Third, RMPF predicts the development of subject teaching and research using the autoregressive integrated moving average model and multiple regressions. The results show that the correlation coefficient between public attention and teaching research is more than 0.65 from the perspective of “high school information technology,” showing a strong positive correlation. In recent years, the focus of high school information technology discipline tends to be integrating multimedia technology, cloud classroom, artificial intelligence, and other technologies and disciplines. In addition, discipline literature volume growth will slow in the next 2 years, with an average annual publication of 350 articles. The overall number of literature decreased by about 120 compared with 2020. Based on the proposed RMPF, this study clarifies the relationship between subject attention and teaching research through experimental demonstration and provides an implementation framework reference for researchers of relevant literature.

show abstract

“…AIC and RMSE were selected in this study to check the model's goodness of fit 36 . Their calculation methods are, respectively:

\mathrm{AIC}=-2\ln (L)+2k,

$$ \mathrm{RMSE}=\sqrt{\frac{1}{m}\sum \limits_{i=1}^m{\left({y}_{\mathrm{predict}(i)}-{y}_{(i)}\right)}^2}.

…”

Section: Our Proposed Rmpf Frameworkmentioning

confidence: 99%

Relationship modeling and short‐term prediction analysis between public attention and teaching research

Zhao

Liu

et al. 2022

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…Software defect prediction is a helpful technology for detecting semantic defects. It often encodes the source code into several software features and applies the machine learning method to build defect prediction classifiers, which can estimate the software areas is clean or buggy [1][2][3][4][5]. However, in the modeling process of defect prediction, there are some common challenges: such as how to encode the program, how to extract features from the high dimensionality of defect datasets, how to select the suitable defect training models, and so on.…”

Section: Introductionmentioning

confidence: 99%

Compiler IR-Based Program Encoding Method for Software Defect Prediction

Chen¹,

Chen²,

He³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

With the continuous expansion of software applications, people's requirements for software quality are increasing. Software defect prediction is an important technology to improve software quality. It often encodes the software into several features and applies the machine learning method to build defect prediction classifiers, which can estimate the software areas is clean or buggy. However, the current encoding methods are mainly based on the traditional manual features or the AST of source code. Traditional manual features are difficult to reflect the deep semantics of programs, and there is a lot of noise information in AST, which affects the expression of semantic features. To overcome the above deficiencies, we combined with the Convolutional Neural Networks (CNN) and proposed a novel compiler Intermediate Representation (IR) based program encoding method for software defect prediction (CIR-CNN). Specifically, our program encoding method is based on the compiler IR, which can eliminate a large amount of noise information in the syntax structure of the source code and facilitate the acquisition of more accurate semantic information. Secondly, with the help of data flow analysis, a Data Dependency Graph (DDG) is constructed on the compiler IR, which helps to capture the deeper semantic information of the program. Finally, we use the widely used CNN model to build a software defect prediction model, which can increase the adaptive ability of the method. To evaluate the performance of the CIR-CNN, we use seven projects from PROMISE datasets to set up comparative experiments. The experiments results show that, in WPDP, with our CIR-CNN method, the prediction accuracy was improved by 12% for the AST-encoded CNN-based model and by 20.9% for the traditional features-based LR model, respectively. And in CPDP, the AST-encoded DBNbased model was improved by 9.1% and the traditional features-based TCA+ model by 19.2%, respectively.

show abstract