Search

Despite intense investigation in the area of software defect prediction, there are some critical regions that still need attention. Heterogeneity of data is one of these areas that seek attention. Local models have gained focus in resolving the problem of heterogeneity. Limited studies have proven local models to be better than global models, so there is contradiction among researcher. Various researchers also considered feature selection as a method to mitigate the affect of heterogeneity. Our study presents a hybrid feature selection strategy with global and local (GL) models of software defect prediction (SDP). The proposed Hybrid Feature Selection Strategy (HFSS) has additionally improved the predicting power of GL models. Empirical results showcase that local models have preferential results than global models. Our study compared proposed approach with baselines techniques from literature on three PROMISE projects and traditional global models. Our proposed approach achieved better results in terms of accuracy, precision, recall and f-measure.

Background: The rapid growth and increasing complexity of software applications are causing challenges in maintaining software quality within constraints of time and resources. This challenge led to the emergence of a new field of study known as Software Defect Prediction (SDP), which focuses on predicting future defect in advance, thereby reducing costs and improving productivity in software industry. Objective: This study aimed to address data distribution disparities when applying transfer learning in multi-project scenarios, and to mitigate performance issues resulting from data scarcity in SDP. Methods: The proposed approach, namely Transfer Learning based Low Shot Classifier (TLLSC), combined transfer learning and low shot learning approaches to create an SDP model. This model was designed for application in both new projects and those with minimal historical defect data. Results: Experiments were conducted using standard datasets from projects within the National Aeronautics and Space Administration (NASA) and Software Research Laboratory (SOFTLAB) repository. TLLSC showed an average increase in F1-Measure of 31.22%, 27.66%, and 27.54% for project AR3, AR4, and AR5, respectively. These results surpassed those from Transfer Component Analysis (TCA+), Canonical Correlation Analysis (CCA+), and Kernel Canonical Correlation Analysis plus (KCCA+). Conclusion: The results of the comparison between TLLSC and state-of-the-art algorithms, namely TCA+, CCA+, and KCCA+ from the existing literature consistently showed that TLLSC performed better in terms of F1-Measure. Keywords: Just-in-time, Defect Prediction, Deep Learning, Transfer Learning, Low Shot Learning

Background: The purpose of this study is to investigate the electroosmotic flow of a hybrid nanofluid (Al2O3-Cu/Blood) with gyrotactic microorganisms through a bifurcated artery with mild stenosis in both parent and daughter arteries. The flow is subjected to a uniform magnetic field, viscous dissipation, and a heat source. Methods: The governing equations undergo the non-dimensional transformation and coordinate conversion to regularize irregular boundaries, then solve the resulting system using the Crank-Nicolson method. Results: In both sections of the bifurcated artery (parent and daughter artery), the wall shear stress (WSS) profile decreases with increasing stenotic depth. Nusselt profile increases with an increase in the heat source parameter. Conclusions: The present endeavour can be beneficial for designing better biomedical devices and gaining insight into the hemodynamic flow for therapeutic applications in the biomedical sciences.

Introduction: Management of chyluria with initial conservative approach and then using endoscopic sclerotherapy is a mainstay approach. However, a wide range of sclerosants are available with differential success rates and complication rates. This study evaluated the safety and efficacy of a single-dose instillation of 1% povidone iodine for the treatment of chyluria. Materials and Methods: This was a prospective, observational study conducted on patients with chyluria who did not respond to conservative management with dietary restriction and diethylcarbamazine. The site of chyle efflux was identified by cystoscopy. A 6 Fr ureteral stent was inserted into effluxing side, diluted contrast was injected to delineate the pelvicalyceal system and the pyelolymphatic connection (arborization of the pelvicalyceal system), and a single-dose of 1% povidone iodine was instilled. Patients were observed for loin pain, fever, and disappearance of milky urine postinstillation and followed up at intervals of 3 months for a total duration of 1 year. Results: Of a total 50 patients included, 35 were men and 15 were women, with a mean age of 37 years. Pyelolymphatic connections were noted in 48% of the patients. All patients showed an immediate disappearance of milky urine. During 1-year follow-up, 92% of the patients were symptom-free till the last follow-up while only 8% of the patients experienced recurrence of chyluria which were treated with other treatment modalities. The mean duration of recurrence was 8 weeks. Conclusion: Single dose of 1% povidone iodine was effective in immediate clearance of milky urine and well tolerated in patients with chyluria during 1-year follow-up.

A novel analysis of the electromagnetohydrodynamic (EMHD) non-Newtonian nanofluid blood flow incorporating CuO and Al2O3 nanoparticles through a permeable walled diseased artery having irregular stenosis and an aneurysm is analyzed in this paper. The non-Newtonian behavior of blood flow is addressed by the Casson fluid model. The effective viscosity and thermal conductivity of nanofluids are calculated using the Koo-Kleinstreuer-Li model, which takes into account the Brownian motion of nanoparticles. The mild stenosis approximation is employed to reduce the bi-directional flow of blood to uni-directional. The blood flow is influenced by an electric field along with a magnetic field perpendicular to the blood flow. The governing mathematical equations are solved using Crank-Nicolson finite difference approach. The model has been developed and validated by comparing the current results to previously published benchmarks that are peculiar to this study. The results are utilized to investigate the impact of physical factors on momentum diffusion and heat transfer. The Nusselt number escalates with increasing CuO nanoparticle diameter and diminishing the diameter of Al2O3 nanoparticles. The relative % variation in Nusselt number enhances with Magnetic number, whereas a declining trend is obtained for the electric field parameter. The present study’s findings may be helpful in the diagnosis of hemodynamic abnormalities and the fields of nano-hemodynamics, nano-pharmacology, drug delivery, tissue regeneration, wound healing, and blood purification systems.

This article examines the effects of entropy generation, heat transmission, and mass transfer on the flow of Jeffrey fluid under the influence of solar radiation in the presence of copper nanoparticles and gyrotactic microorganisms, with polyvinyl alcohol–water serving as the base fluid. The impact of source terms such as Joule heating, viscous dissipation, and the exponential heat source is analyzed via a nonlinear elongating surface of nonuniform thickness. The development of an efficient numerical model describing the flow and thermal characteristics of a parabolic trough solar collector (PTSC) installed on a solar plate is underway as the use of solar plates in various devices continues to increase. Governing PDEs are first converted into ODEs using a suitable similarity transformation. The resulting higher-order coupled ODEs are converted into a system of first-order ODEs and then solved using the RK 4th-order method with shooting technique. The remarkable impacts of pertinent parameters such as Deborah number, magnetic field parameter, electric field parameter, Grashof number, solutal Grashof number, Prandtl number, Eckert number, exponential heat source parameter, Lewis number, chemical reaction parameter, bioconvection Lewis number, and Peclet number associated with the flow properties are discussed graphically. The increase in the radiation parameter and volume fraction of the nanoparticles enhances the temperature profile. The Bejan number and entropy generation rate increase with the rise in diffusion parameter and bioconvection diffusion parameter. The novelty of the present work is analyzing the entropy generation and solar radiation effects in the presence of motile gyrotactic microorganisms and copper nanoparticles with polyvinyl alcohol–water as the base fluid under the influence of the source terms, such as viscous dissipation, Ohmic heating, exponential heat source, and chemical reaction of the electromagnetohydrodynamic (EMHD) Jeffrey fluid flow. The non-Newtonian nanofluids have proven their great potential for heat transfer processes, which have various applications in cooling microchips, solar energy systems, and thermal energy technologies.