Engineering Papers⌕ Search

Engineering topics

Bryan, Jonathan

Publications and source records attributed to Bryan, Jonathan.

Graph-based machine learning improves just-in-time defect prediction

The increasing complexity of today’s software requires the contribution of thousands of developers. This complex collaboration structure makes developers more likely to introduce defect-prone changes that lead to software faults. Determining when these defect-prone changes are introduced has proven challenging, and using traditional machine learning (ML) methods to make these determinations seems to have reached a plateau. In this work, we build contribution graphs consisting of developers and source files to capture the nuanced complexity of changes required to build software. By leveraging these contribution graphs, our research shows the potential of using graph-based ML to improve Just-In-Time (JIT) defect prediction. We hypothesize that features extracted from the contribution graphs may be better predictors of defect-prone changes than intrinsic features derived from software characteristics. We corroborate our hypothesis using graph-based ML for classifying edges that represent defect-prone changes. This new framing of the JIT defect prediction problem leads to remarkably better results. We test our approach on 14 open-source projects and show that our best model can predict whether or not a code change will lead to a defect with an F1 score as high as 77.55% and a Matthews correlation coefficient (MCC) as high as 53.16%. This represents a 152% higher F1 score and a 3% higher MCC over the state-of-the-art JIT defect prediction. We describe limitations, open challenges, and how this method can be used for operational JIT defect prediction.

59 BASIC BIOLOGICAL SCIENCES↗

Systematic Operating Temperature Differences Between Al-BSF, PERC, and PERT-With-Optimized-Rear-Reflector Solar Mini-Modules Due to Rear Reflectance

Reflecting sub-bandgap light from photovoltaic modules has the potential to improve lifetime energy generation of fielded systems by reducing operating temperature. In this article, the temperature of fielded aluminum back-surface field (Al-BSF) and passivated emitter and rear contact (PERC) mini-modules was monitored every 5 minutes for 75 days along with corresponding meteorological data. Additionally, passivated emitter rear totally diffused (PERT) mini-modules with high-performance sub-bandgap rear reflectors were tested and compared to the state-of-the-art industrial modules. These reflectors consisted of a >300-nm-thick silicon dioxide nanoparticle film with a low refractive index. The impact of reflectance on measured operating temperature was isolated with a previously developed thermal model and quantified as the reflectance-induced median temperature difference between each tested module at representative outdoor conditions (1000 W m -2 , 25 degrees C ambient temperature, and 1.43 m s -1 wind speed). We found that, because of their reflectance differences, PERC modules ran systematically cooler than Al-BSF modules by 1.0 degrees C, whereas the PERT-with-optimized-rear-reflector systematically operated 1.4 degrees C cooler than the Al-BSF module and 0.4 degrees C than the PERC module. We also found that the rear reflector provided the greatest temperature benefit during periods of highest irradiance.

14 SOLAR ENERGY↗