http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
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.
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.
Dewan, Abhinav,Sharma, SK,Dewan, AK.,Srivastava, Himanshu,Rawat, Sheh,Kakria, Anjali,Mishra, Maninder,Suresh, T,Mehrotra, Krati Asian Pacific Journal of Cancer Prevention 2016 Asian Pacific journal of cancer prevention Vol.17 No.3
Objective of the study is to evaluate volumetric and dosimetric alterations taking place during radiotherapy for locally advanced head and neck cancer (LAHNC) and to assess benefit of replanning in them. Materials and Methods: Thirty patients with LAHNC fulfilling the inclusion and exclusion criteria were enrolled in a prospective study. Planning scans were acquired both pre-treatment and after 20 fractions (mid-course) of radiotherapy. Single plan (OPLAN) based on initial CT scan was generated and executed for entire treatment course. Beam configuration of OPLAN was applied to anatomy of interim scan and a hybrid plan (HPLAN30) was generated. Adaptive replanning (RPLAN30) for remaining fractions was done and dose distribution with and without replanning compared for remaining fractions. Results: Substantial shrinkage of target volume (TV) and parotids after 4 weeks of radiotherapy was reported (p<0.05). No significant difference between planned and delivered doses was seen for remaining fractions. Hybrid plans showed increase in delivered dose to spinal cord and parotids for remaining fractions. Interim replanning improved homogeneity of treatment plan and significantly reduced doses to cord (Dmax, D2% and D1%) and ipsilateral parotid (D33%, D50% and D66%) (p<0.05). Conclusions: Use of one or two mid-treatment CT scans and replanning provides greater normal tissue sparing along with improved TV coverage.
Lok Pratap Singh,Anjali Goel,Sriman Kumar Bhattachharyya,Saurabh Ahalawat,Usha Sharma,Geetika Mishra 한국콘크리트학회 2015 International Journal of Concrete Structures and M Vol.9 No.2
The influence of powdered and colloidal nano-silica (NS) on the mechanical properties of cement mortar has been investigated. Powdered-NS (~ 40 nm) was synthesized by employing the sol?gel method and compared with commercially available colloidal NS (~ 20 nm). SEM and XRD studies revealed that the powdered-NS is non-agglomerated and amorphous, while colloidal-NS is agglomerated in nature. Further, these nanoparticles were incorporated into cement mortar for evaluating compressive strength, gel/space ratio, portlandite quantification, C?S?H quantification and chloride diffusion. Approximately, 27 and 37 % enhancement in compressive strength was observed using colloidal and powdered-NS, respectively, whereas the same was up to 19 % only when silica fume was used. Gel/space ratio was also determined on the basis of degree of hydration of cement mortar and it increases linearly with the compressive strength. Furthermore, DTG results revealed that lime consumption capacity of powdered-NS is significantly higher than colloidal-NS, which results in the formation of additional calcium-silicate-hydrate (C?S?H). Chloride penetration studies revealed that the powdered-NS significantly reduces the ingress of chloride ion as the microstructure is considerably improved by incorporating into cement mortar.
Kaur, Prabhsharan,Shin, Mun-Sik,Joshi, Anjali,Kaur, Namarta,Sharma, Neha,Park, Jin-Soo,Sekhon, S. S. American Chemical Society 2013 The Journal of physical chemistry B Vol.117 No.11
<P>The interactions between multiwall carbon nanotubes (MWCNTs) and poly(diallyl dimethylammonium) chloride (PDDA) have been studied in the presence of different ionic and nonionic surfactants, such as sodium dodecyl sulfate (SDS), cetyltrimethylammonium bromide (CTAB), Tween 20, 40, 60, and 80, and Triton X-100. On the basis of scanning electron microscopy (SEM) results, the MWCNT/PDDA sample treated with Triton X-100 has been observed to show good dispersion of nanotubes. This is due to the π–π stacking between the benzene ring of Triton X-100 and the hexagonal carbon rings of nanotubes and better coating of PDDA on MWCNTs, as is confirmed by the Raman studies. Energy dispersive X-ray (EDX) spectroscopic data shows the presence of higher oxygen content in the MWCNTs/PDDA/Triton X-100 sample. The maximum upshift in the C1s peak position and down-shift in the N1s peak position for the MWCNTs/PDDA/Triton X-100 sample has been observed from X-ray photoelectron spectroscopy (XPS) results and is due to the intermolecular charge transfer from carbon in MWCNTs to nitrogen in PDDA. The presence and nature of a surfactant in the MWCNTs/PDDA system has been found to affect their interactions. The above results suggest that the MWCNTs/PDDA/Triton X-100 system is suitable as a metal-free electrocatalyst for the oxygen reduction reaction (ORR) in fuel cells.</P><P><B>Graphic Abstract</B> <IMG SRC='http://pubs.acs.org/appl/literatum/publisher/achs/journals/content/jpcbfk/2013/jpcbfk.2013.117.issue-11/jp3116534/production/images/medium/jp-2012-116534_0007.gif'></P>
Bajaj, Bharat,Joh, Han I.,Jo, Seong M.,Kaur, Gurpreet,Sharma, Anjali,Tomar, Monika,Gupta, Vinay,Lee, Sungho The Royal Society of Chemistry 2016 Journal of Materials Chemistry B Vol.4 No.2
<P>Electrospun carbon nanofibers (CNFs) decorated with copper oxide nanoparticles were successfully synthesized using a one step and modified hydroxyl ion assisted alcohol reduction method. The X-ray diffraction pattern reveals the presence of (−111), (111) and (−202) crystal planes of monoclinic copper oxide (CuO). The CuO coated CNF air annealed at 250 °C exhibited an electrical conductivity of 251 S m<SUP>−1</SUP>. The CuO coated CNFs were employed as a novel flexible matrix for a cholesterol biosensor. The biosensor exhibited a high sensitivity of 75 μA mM<SUP>−1</SUP> cm<SUP>−2</SUP> over the linear range (0.12 mM to 12.93 mM) of cholesterol. This coating method offers easy and inexpensive processing with a flexible and robust supporting structure for biosensing applications.</P>