Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of exis...
详细信息
This research investigates the transformative potential of deep learning in revolutionizing home interior design through the development of a web application with three core functionalities: object replacement within ...
详细信息
To facilitate efforts to transform the domain-specific business vendor to be customer-centered, results-oriented, and market-based cyber-organization or e-organization, with the advances of Advanced Computing Technolo...
详细信息
Civil engineering is one of the disciplines with close combination of theory and practice. Theory teaching is the main form of imparting knowledge. Mechanics course is abstract and boring, and focuses on theory and fo...
详细信息
Spontaneous thermal runaway has become a significant issue for thermal management and control systems during the operation of lithium-ion batteries recently. Therefore, we discussed the heat distribution of lithium-io...
详细信息
Data has become a crucial element powering the fourth industrial revolution, making it more important than ever for employees at various organizations to be able to work with data. The value of data literacy is rapidl...
详细信息
Remote sensing is a detection technology that has gained increasing prominence due to the global climate change and the degradation of ecosystems. In an effort to examine the current state of research and key areas of...
详细信息
The objective of this study is to establish the relevance of employability skills that engineers lack, the educational system of higher education institutions, and the key characteristics of graduates from the perspec...
详细信息
Modern cyber-physical applications, such as those adopting the Digital Twin paradigm, typically connect simulators with data-rich components and domain knowledge, both often formalized as knowledge graphs. engineering...
详细信息
ISBN:
(数字)9781713852889
ISBN:
(纸本)9781713852889
Modern cyber-physical applications, such as those adopting the Digital Twin paradigm, typically connect simulators with data-rich components and domain knowledge, both often formalized as knowledge graphs. engineering such applications poses challenges to developers. This paper presents a language-based integration of knowledge graphs and simulators for object-oriented languages. We use Functional Mock-Up Objects (FMOs) as a programming layer to encapsulate simulators compliant with the FMI standard into OO structures and integrate FMOs into the class and type systems. We show how FMOs can be integrated into knowledge graphs by means of semantical lifting, and used to ensure structural properties of cyber-physical applications. We provide a prototype implementation of the proposed integration and discuss how it can be realized in other languages. Finally, the use of FMOs in practice is illustrated by two case studies.
Deep learning-based automated program repair (DL-APR) can automatically fix software bugs and has received significant attention in the industry because of its potential to significantly reduce software development an...
详细信息
ISBN:
(纸本)9781450394130
Deep learning-based automated program repair (DL-APR) can automatically fix software bugs and has received significant attention in the industry because of its potential to significantly reduce software development and maintenance costs. The Samsung mobile experience (MX) team is currently switching from Java to Kotlin projects. This study reviews the application of DL-APR, which automatically fixes defects that arise during this switching process;however, the shortage of Kotlin defect-fixing datasets in Samsung MX team precludes us from fully utilizing the power of deep learning. Therefore, strategies are needed to effectively reuse the pretrained DL-APR model. This demand can be met using the Kotlin defect-fixing datasets constructed from industrial and open-source repositories, and transfer learning. This study aims to validate the performance of the pretrained DL-APR model in fixing defects in the Samsung Kotlin projects, then improve its performance by applying transfer learning. We show that transfer learning with open source and industrial Kotlin defect-fixing datasets can improve the defect-fixing performance of the existing DL-APR by 307%. Furthermore, we confirmed that the performance was improved by 532% compared with the baseline DL-APR model as a result of transferring the knowledge of an industrial (non-defect) bug-fixing dataset. We also discovered that the embedded vectors and overlapping code tokens of the code-change pairs are valuable features for selecting useful knowledge transfer instances by improving the performance of APR models by up to 696%. Our study demonstrates the possibility of applying transfer learning to practitioners who review the application of DL-APR to industrial software.
暂无评论