Sleep Quality in relation with Perceived Stress and Physical Activity in the Students of Pakistani Medical Colleges

Background: Sleep is an essential function of our body. Many surveys have reported the prevalence of poor sleep in university students, especially in medical students.  Objectives: The objective of the study was to evaluate the effect of physical activity and stress on sleep quality among medical students in Pakistan. Materials & Methods: An observational cross-sectional study was conducted on medical students of private medical colleges in Lahore. A convenient sampling technique was used and 210 students were selected. The Pittsburgh Sleep Quality Index (PSQI), Godin Shephard Leisure Time Physical Activity Questionnaire (GSLTPAQ), and Perceived Stress Scale (PSS 10) were used for data collection. We used SPSS version 20 to analyze data and applied statistical tests: Chi-square test and Logistic Regression.  p-value < 0.05 was taken to establish significance. Results: Among the study participants 91(43.3%) were males and 119 (57.7%) were females. There was a significant effect of stress level on sleep quality (P=0.000*). The frequency of good sleepers was seen to increase by almost three times with increasing physical activity, however, this difference remained non-significant (p=0.07). The logistic regression test showed a significant relationship between poor sleep and stress (p=0. 008**) while no significant relationship was seen between sleep quality and physical activity. Conclusion: There was a significant association between poor sleep and high-stress levels and an increase in physical activity showed an increase in the frequency of good sleep, however, this difference was non-significant. It can be inferred that this positive effect of increasing physical activity on the quality of sleep could be indirectly due to its relieving effect on stress.  

Software Defect Prediction Via Machine Learning Classifiers

To improve software reliability, software should be developed without defects. SDP models can be employed to identify defective code sections at initial stage during the software development. When defects are ascertained early, it helps the practitioners to prioritize the efforts for testing and allocating more resources to defective modules. This results in improved software quality, reliability, and efficiency. Despite the fact that the numbers of approaches have been used in the past for SDP but most of them are not practically applicable. Manual feature selection is mostly performed by majority of feature selection methods. Core aim of this research is to propose iterative feature selection technique using Boruta (random forest) for SDP model. This research proposes Two?step preprocessing using SMOTE and BORUTA. Support Vector Machine (SVM), Neural Networks and XGboostclassifiers are used by MLC. Furthermore to confirm the accuracy, performance and capability of each classifier on PROMISE dataset evaluationmeasures AUC,recall, F1-measure, andaccuracy are used