Portrayal of Positive Psychological Capital in Quran

The present study aims at exploring positive psychological capital in the verses of Qur’an. Positive psychology is the latest advancement in the field of psychology which focuses on improving the well-being of society. Positive psychological capital refers to the combination of overall qualities of positive psychology that contributes to the well-being and mental health. The present study is based on the content analysis of the verses of Qur’an. Content analysis comprises of three steps including identifying the categories or themes, dividing the information into units or parts and finally rating all the themes in all units. In the first step the researchers identified 41 themes from Qur’an by using committee approach and reading the verses between the lines. All these categories were identified by keeping in view the underlying themes of positive psychology. In the second step 30 units were devised from Qur’an by considering each Part as a single unit. The categories included behavior modification, belief in divine help, brotherhood, bravery, contentment, civility, credibility, encouragement of virtue, emotional regulation, excellence, forgiveness, generosity, gratitude, honesty, hopefulness, humility, justice, knowledge, lawful spending, learning, meaningfulness, mindfulness, moderation, obedience, patience, peace, determination, positivity, prosperity, repentance, resilience, reward, self-actualization, self-awareness, self-control, sincerity, social leadership, truthfulness, trust, and wisdom. Results suggest that the most prominent category in Qur’an is the reward. Validity of the study was maintained through the selection of the themes with the help of committee approach. Reliability of the scoring system was maintained through partial inter-rater reliability. Overall the present research has many implications in the positive psychology of religion.    

Softwaredefect Prediction Model Using Multi-Layer Feed Forwardneural Networks

Software defect prediction techniques are being focused by many researchers due to its effectiveness for cost reduction in testing process. Most of the software defect dataset contains uncleaned, noisy, high dimensional and imbalance data. These problems reduce the prediction accuracy of a classifier. In this paper, a framework is proposed which combines approaches to deal with all these problems. This framework comprises of four stages 1) data preprocessing 2) feature selection (FS) 3) class balancing, and 4) classification through ensemble learning. Normalization is performed on cleaned datasets. Multilayer perceptron (MLP) is used as subset evaluator in FS process with six search methods Best first (BF), Greedy Stepwise (GS), Genetic Search (GA), Particle swam Optimization Search (PSO), Rank Search (RS) and Linear forward selection (LFS). Resample and SMOTE algorithm are used for class balancing. In classification stacking ensemble model is applied to build model on 80% of the input data. Here meta classifier is set to MLP and base classifiers include decision tree (J48), Random forest (RF), Support vector machine (SVM), K nearest neighbor (kNN) and Bayes Net (BN). Parameter tuning of meta and base classifier is also performed. Performance is evaluated on NASA MDP using precision, recall, F-measure, MCC, ROC and accuracy. Results have shown that the proposed method showed significant improvement is defect prediction compared to base classifiers.