Software defect prediction using learning to rank approach.

Software defect prediction (SDP) plays a significant role in detecting the most likely defective software modules and optimizing the allocation of testing resources. In practice, though, project managers must not only identify defective modules, but also rank them in a specific order to optimize the resource allocation and minimize testing costs, especially for projects with limited budgets. This vital task can be accomplished using Learning to Rank (LTR) algorithm. This algorithm is a type of machine learning methodology that pursues two important tasks: prediction and learning. Although this algorithm is commonly used in information retrieval, it also presents high efficiency for other problems, like SDP. The LTR approach is mainly used in defect prediction to predict and rank the most likely buggy modules based on their bug count or bug density. This research paper conducts a comprehensive comparison study on the behavior of eight selected LTR models using two target variables: bug count and bug density. It also studies the effect of using imbalance learning and feature selection on the employed LTR models. The models are empirically evaluated using Fault Percentile Average. Our results show that using bug count as ranking criteria produces higher scores and more stable results across multiple experiment settings. Moreover, using imbalance learning has a positive impact for bug density, but on the other hand it leads to a negative impact for bug count. Lastly, using the feature selection does not show significant improvement for bug density, while there is no impact when bug count is used. Therefore, we conclude that using feature selection and imbalance learning with LTR does not come up with superior or significant results.

Medical Students' Perception and Perceived Value of Peer Learning in Undergraduate Clinical Skill Development and Assessment: Mixed Methods Study.

BACKGROUND: The effectiveness of peer learning in clinical skill development is well recognized and researched, given the many benefits gained such as enhanced learning, alleviation of the burden on faculty, and early development of teaching skills for future doctors. However, little is known in terms of its effectiveness as an assessment tool and the extent to which peer assessment can be relied upon in the absence of faculty support. OBJECTIVE: This study was conducted to assess medical students' perception toward peer learning, which is based on self-regulated learning as a tool of assessment, and to compare peer evaluation with faculty evaluation of clinical skill performance. METHODS: A cohort of 36 third-year medical students were exposed to peer learning (same-level) in clinical skills education for 3 months. A convergent mixed methods approach was adapted to collect data from 3 sources, namely, students' perception of peer learning, performance scores, and reflective observational analysis. A 5-point Likert-type scale was used to assess students' (n=28) perception on the value of peer learning. The students were asked to assess their peers by using a preset checklist on clinical skill performance, and scores were compared to faculty assessment scores. Reflective observational data were collected from observing video recordings of some of the peer learning sessions. The findings from all 3 sources were integrated using joint display analysis. RESULTS: Out of 28 students, 25 students completed the survey and 20 students perceived peer learning as valuable in clinical skills education. The mean score of peer assessment was higher than that of faculty assessment. There was a significant difference in student performance between supervised teaching and peer learning groups (P=.003). Most students focused on the mastery of skill with little attention to the technique's quality. Further, students were unable to appreciate the relevance of the potential clinical findings of physical examination. CONCLUSIONS: Peer learning in clinical skills education, based on self-regulated learning, empowers students to develop a more responsible approach toward their education. However, peer assessment is insufficient to evaluate clinical skill performance in the absence of faculty support. Therefore, we recommend that peer learning activities be preceded by supervised faculty-taught sessions.

Survey on awareness and attitudes of secondary school students regarding plastic pollution: implications for environmental education and public health in Sharjah city, UAE.

Since the industrial revolution in the 1800s, plastic pollution is becoming a global reality. This study aims to assess knowledge and attitude about plastic pollution among secondary school students in Sharjah city, United Arab Emirates. A cross-sectional study was conducted among 400 students in 6 different secondary schools in Sharjah city. Self-administered questionnaires were distributed through probability stratified random sampling method between February and April 2016. Majority of the population understands how harmful plastic wastes are to the environment (85.5%). However, the students' mean knowledge score was 53%, with females (P < 0.01), grades 11 and 12 (P = 0.024), and students whose mothers were more educated (P = 0.014) being more knowledgeable and inclined towards pro-environmental behavior. Yet, all students showed tendency to be involved in the fighting against this dilemma. Strategies which address deficiencies, provide incentives for change, and assure governmental support along with environmental education are needed to bridge the information gap and enhance opportunities to adopt pro-environmental behaviors.