Fault Prediction Using Statistical and Machine Learning Methods for Improving Software Quality

Ruchika Malhotra,Ankita Jain 한국정보처리학회 2012 Journal of information processing systems Vol.8 No.2

Achieving Location Privacy through CAST in Location Based Services

Ruchika Gupta,Udai Pratap Rao 한국통신학회 2017 Journal of communications and networks Vol.19 No.3

The widespread usage of location based services (LBS); where obtaining any informational service is entirely based upon the user's current location, have raised a significant concern about location privacy of the user. For the queries like `where is my closest ATM?', `where is my nearest hospital', or any route assistance in general, it is essential to submit the user's actual location to avail the demanded services. Similar communication holds true for a location based vehicular transportation system. Cloaking and obfuscation are the two generalized approaches to deal with location privacy preservation in LBS. These approaches are mainly based on a trusted third party (TTP) and exploits the well established ${\mathcal{K}}$- anonymity principle in order to make the query issuer indistinguishable with other ${\mathcal{K}}-1$ more users. In such approaches all the data (mainly location coordinates and queries) becomes available at the central server, thus complete knowledge of the query (including user id) exists at central node. This is the major limitation of TTP based architecture and makes such frameworks susceptible to different privacy attacks. This paper is a research attempt to extend the realm of collaborative communication among peers belonging to a mobile user group in a decentralized or trusted third party free architecture. We propose a collaborative P2P communication model; called CAST, that employs the series of trust among peers and peers use their cached mobile data to collaborate with each other in order to get the results locally.~The scheme provides results locally with low latency and works efficiently when the peers share common inclinations (or data value). The proposed algorithm preserves user's privacy and performs effectively under pull-based sporadic query scenario.

Analyzing Machine Learning Techniques for Fault Prediction Using Web Applications

Ruchika Malhotra,Anjali Sharma 한국정보처리학회 2018 Journal of information processing systems Vol.14 No.3

Web applications are indispensable in the software industry and continuously evolve either meeting a newercriteria and/or including new functionalities. However, despite assuring quality via testing, what hinders astraightforward development is the presence of defects. Several factors contribute to defects and are oftenminimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases ofsoftware development is important. Therefore, a fault prediction model for identifying fault-prone classes in aweb application is highly desired. In this work, we compare 14 machine learning techniques to analyse therelationship between object oriented metrics and fault prediction in web applications. The study is carried outusing various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, theinput basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statisticalanalysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of thesemetrics in the defect prediction of web applications. The overall predictive ability of different fault predictionmodels is first ranked using Friedman technique and then statistically compared using Nemenyi post-hocanalysis. The results not only upholds the predictive capability of machine learning models for faulty classesusing web applications, but also finds that ensemble algorithms are most appropriate for defect prediction inApache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique andthe statistical analysis of the datasets.

Faculty Recruitment in Engineering Organization Through Fuzzy Multi-Criteria Group Decision Making Methods

Ruchika Banerjee,Dipendra Nath Ghosh 보안공학연구지원센터(IJUNESST) 2013 International Journal of u- and e- Service, Scienc Vol.6 No.4

A Regression Test Selection and Prioritization Technique

Ruchika Malhotra,Arvinder Kaur,Yogesh Singh 한국정보처리학회 2010 Journal of information processing systems Vol.6 No.2

An Adequacy Based Test Data Generation Technique Using Genetic Algorithms

Ruchika Malhotra,Mohit Garg 한국정보처리학회 2011 Journal of information processing systems Vol.7 No.2

Prediction & Assessment of Change Prone Classes Using Statistical & Machine Learning Techniques

( Ruchika Malhotra ),( Ravi Jangra ) 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.4

Software today has become an inseparable part of our life. In order to achieve the ever demanding needs of customers, it has to rapidly evolve and include a number of changes. In this paper, our aim is to study the relationship of object oriented metrics with change proneness attribute of a class. Prediction models based on this study can help us in identifying change prone classes of a software. We can then focus our efforts on these change prone classes during testing to yield a better quality software. Previously, researchers have used statistical methods for predicting change prone classes. But machine learning methods are rarely used for identification of change prone classes. In our study, we evaluate and compare the performances of ten machine learning methods with the statistical method. This evaluation is based on two open source software systems developed in Java language. We also validated the developed prediction models using other software data set in the same domain (3D modelling). The performance of the predicted models was evaluated using receiver operating characteristic analysis. The results indicate that the machine learning methods are at par with the statistical method for prediction of change prone classes. Another analysis showed that the models constructed for a software can also be used to predict change prone nature of classes of another software in the same domain. This study would help developers in performing effective regression testing at low cost and effort. It will also help the developers to design an effective model that results in less change prone classes, hence better maintenance.

Epitaxial growth of highly transparent and conducting Sc-doped ZnO films on c-plane sapphire by sol.gel process without buffer

Ruchika Sharma,Kiran Sehrawat,R.M. Mehra 한국물리학회 2010 Current Applied Physics Vol.10 No.1

Highly transparent and conductive scandium doped zinc oxide (ZnO:Sc) films were deposited on c-plane sapphire substrates by sol.gel technique using zinc acetate dihydrate [Zn(CH3COO)2·2H2O] as precursor,2-methoxyethanol as solvent and monoethanolamine as a stabilizer. The doping with scandium is achieved by adding 0.5 wt% of scandium nitrate hexahydrate [(ScNO3·6H2O)] in the solution. The influence of annealing temperature (300-550 ℃) on the structural, optical and electrical properties was investigated. X-ray Diffraction study revealed that highly c-axis oriented films with full-width half maximum of 0.16˚ are obtained at an annealing temperature of 400 ℃. The surface morphology of the films was judged by SEM and AFM images which indicated formation of grains. The average transmittance was found to be above 92% in the visible region. ZnO:Sc film, annealed at 400 ℃ exhibited minimum resistivity of 1.91 × 10-4 Ω cm. Room-temperature photoluminescence measurements of the ZnO:Sc films annealed at 400 ℃ showed ultraviolet peak at ~3.31eV with a FWHM of 11.2 meV, which are comparable to those found in high-quality ZnO films. Reflection high-energy electron diffraction pattern confirmed the epitaxial nature of the films even without introducing any buffer layer.

Analyzing Machine Learning Techniques for Fault Prediction Using Web Applications

Malhotra, Ruchika,Sharma, Anjali Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.3

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

Prediction & Assessment of Change Prone Classes Using Statistical & Machine Learning Techniques

Malhotra, Ruchika,Jangra, Ravi Korea Information Processing Society 2017 Journal of information processing systems Vol.13 No.4

Software today has become an inseparable part of our life. In order to achieve the ever demanding needs of customers, it has to rapidly evolve and include a number of changes. In this paper, our aim is to study the relationship of object oriented metrics with change proneness attribute of a class. Prediction models based on this study can help us in identifying change prone classes of a software. We can then focus our efforts on these change prone classes during testing to yield a better quality software. Previously, researchers have used statistical methods for predicting change prone classes. But machine learning methods are rarely used for identification of change prone classes. In our study, we evaluate and compare the performances of ten machine learning methods with the statistical method. This evaluation is based on two open source software systems developed in Java language. We also validated the developed prediction models using other software data set in the same domain (3D modelling). The performance of the predicted models was evaluated using receiver operating characteristic analysis. The results indicate that the machine learning methods are at par with the statistical method for prediction of change prone classes. Another analysis showed that the models constructed for a software can also be used to predict change prone nature of classes of another software in the same domain. This study would help developers in performing effective regression testing at low cost and effort. It will also help the developers to design an effective model that results in less change prone classes, hence better maintenance.