Classifying a Strength of Dependency between classes by using Software Metrics and Machine Learning in Object-Oriented System

BACKGROUND: Fault data is vital to predicting the fault-proneness in large systems. Predicting faulty classes helps in allocating the appropriate testing resources for future releases. However, current fault data face challenges such as unlabeled instances and data imbalance. These challenges degrade the performance of the prediction models. Data imbalance happens because the majority of classes are labeled as not faulty whereas the minority of classes are labeled as faulty. AIM: The research proposes to improve fault prediction using software metrics in combination with threshold values. Statistical techniques are proposed to improve the quality of the datasets and therefore the quality of the fault prediction. METHOD: Threshold values of object-oriented metrics are used to label classes as faulty to improve the fault prediction models The resulting datasets are used to build prediction models using five machine learning techniques. The use of threshold values is validated on ten large object-oriented systems. RESULTS: The models are built for the datasets with and without the use of thresholds. The combination of thresholds with machine learning has improved the fault prediction models significantly for the five classifiers. CONCLUSION: Threshold values can be used to label software classes as fault-prone and can be used to improve machine learners in predicting the fault-prone classes.

Download Full-text

Application of machine learning algorithms for code smell prediction using object-oriented software metrics

Journal of Statistics and Management Systems ◽

10.1080/09720510.2020.1799576 ◽

2020 ◽

Vol 23 (7) ◽

pp. 1159-1171

Author(s):

Mansi Agnihotri ◽

Anuradha Chug

Keyword(s):

Machine Learning ◽

Software Metrics ◽

Learning Algorithms ◽

Object Oriented ◽

Machine Learning Algorithms ◽

Code Smell

Download Full-text

PLHIM: Proposing an Inheritance based Object-Oriented Metric

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.i1101.0789s419 ◽

2019 ◽

Vol 8 (9S4) ◽

pp. 1-4

Keyword(s):

Cost Estimation ◽

Software Metrics ◽

Research Work ◽

Main Idea ◽

Object Oriented ◽

Stage Of Development ◽

Abstraction Levels ◽

Different Levels ◽

Oriented System

Software metrics has been utilized to evaluate inheritance as well as to assist the designer in order to focus on product quality as well as cost estimation in all the lifecycle stage of development of the final product. To pertain measurement through the diverse level of class hierarchy, a person can evaluate inheritance with reuse, to acquire the best computation of abstraction levels of a object oriented system. In our paper, a new metric of hierarchical inheritance is proposed that measures the quality of the program through different levels of Object-Orientedness, and we named it PLHIM: Per Level of Hierarchical Inheritance Metric. The main idea behind proposed metrics and research work was to make use of measurement as a criterion for improvement in software development at different levels to minimize risk and this has been done by taking the problems of C++ and Java.

Download Full-text

DESIGN OPTIMIZATION METRICS FOR UML BASED OBJECT-ORIENTED SYSTEMS

International Journal of Software Engineering and Knowledge Engineering ◽

10.1142/s0218194007003252 ◽

2007 ◽

Vol 17 (03) ◽

pp. 423-448 ◽

Cited By ~ 3

Author(s):

E. RAMARAJ ◽

S. DURAISAMY

Keyword(s):

Software Metrics ◽

Quality Evaluation ◽

Unified Modeling Language ◽

Object Oriented ◽

Evaluation Process ◽

Quality Model ◽

Design Quality ◽

Object Oriented Systems ◽

Oriented System

Design plays a key role in the development of software. The quality of design is crucial and is a fundamental decision element in assessing the software product. The early availability of design quality evaluation provides a better way to decide the quality of the final product. This avoids presumption in the quality evaluation process. Hence Software Metrics provide a valuable and objective insight of enhancing each of the software quality characteristics. This paper proposes a quality model to assess the design phase of any object-oriented system based on the works of Chidamber, Kemrer and Basili and suggests two new metrics. The research focuses on analyzing a set of metrics, which has direct influence on the quality of the software and creating a metrics tool based on Java that can be used to validate the object-oriented projects against these metrics. The analysis is carried out on a set of real world projects designed using Unified Modeling Language, which are used as test cases. These metrics and models are proposed to add more quality information in refining any object-oriented system during the early stages of design itself.

Download Full-text

A Literature Review Study of Software Defect Prediction using Machine Learning Techniques

International Journal of Emerging Research in Management and Technology ◽

10.23956/ijermt.v6i6.286 ◽

2018 ◽

Vol 6 (6) ◽

pp. 300 ◽

Cited By ~ 3

Author(s):

Feidu Akmel ◽

Ermiyas Birihanu ◽

Bahir Siraj

Keyword(s):

Machine Learning ◽

Software Metrics ◽

Quality Standard ◽

Machine Learning Techniques ◽

Software Systems ◽

Health Care Insurance ◽

Software Defect ◽

Learning Techniques ◽

Software Product

Software systems are any software product or applications that support business domains such as Manufacturing,Aviation, Health care, insurance and so on.Software quality is a means of measuring how software is designed and how well the software conforms to that design. Some of the variables that we are looking for software quality are Correctness, Product quality, Scalability, Completeness and Absence of bugs, However the quality standard that was used from one organization is different from other for this reason it is better to apply the software metrics to measure the quality of software. Attributes that we gathered from source code through software metrics can be an input for software defect predictor. Software defect are an error that are introduced by software developer and stakeholders. Finally, in this study we discovered the application of machine learning on software defect that we gathered from the previous research works.

Download Full-text