Sökning: "defect prediction"
Visar resultat 1 - 5 av 14 uppsatser innehållade orden defect prediction.
1. Perception and implementation of Zero Defect Manufacturing approach in foundries
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : Foundry is an industry that is both very old and very forward-looking. It is an essential base for several industrial sectors in today’s world. However, the metal casting industry faces a lot of challenges, including quality. LÄS MER
2. Defect intention : the specific challenges faced by women in open source that may predict (or influence) their intention to leave an open source software project/community
Magister-uppsats, Blekinge Tekniska Högskola/Institutionen för industriell ekonomiSammanfattning : Background Open source is largely accepted as an important innovation driver in the technology industry. Even though inclusion and diversity is beneficial for the success of technology projects (including open source software projects), many statistics are pointing out that diversity in open source is even worse than in the technology sector in general. LÄS MER
3. Life and fracture in very high cycle fatigue of a high strength steel
Master-uppsats, Karlstads universitet/Institutionen för ingenjörsvetenskap och fysik (from 2013)Sammanfattning : Classical fatigue models teach that there is an intrinsic fatigue limit for steels, representing a level of stress that is too low for regular crack growth where every cyclic load propagates a fatigue crack through the material. Modern application with extreme lifetimes has shown that fatigue will still take place in steels with stress levels well below the expected fatigue limit. LÄS MER
4. Evaluation of Attention Mechanisms for Just-In-Time Software Defect Prediction
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Just-In-Time Software Defect Prediction (JIT-DP) focuses on predicting errors in software at change-level with the objective of helping developers identify defects while the development process is still ongoing, and improving the quality of software applications. This work studies deep learning techniques by applying attention mechanisms that have been successful in, among others, Natural Language Processing (NLP) tasks. LÄS MER
5. Introducing automatic software fault localization in a continuous integration environment
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In this thesis we investigate the usefulness of neural networks to infer the relationship between co-changes of software modules and test verdicts with the goal of localizing software faults. Data for this purpose was collected from a continuous integration (CI) environment at the telecommunications company Ericsson. LÄS MER