Name
Title | ||
|---|---|---|
A Cloud-Based Architecture For Automated Grading Of Computer-Aided Design Student Work Using Deep Learning |
Abstract | ||
|---|---|---|
The practical benefits of deep convolutional networks are increasingly proven by successful implementations of deep learning models in various image processing applications. A model is proposed to evaluate the realize the benefits of deep convolutional neural networks to grade computer aided student drawings. Such model would assist in full automating the educators task or serving as a decision support system. Given the shared fundamental skills at least for fundamental drawing skills, the model has the potential to be used as Cloud service to be utilized by various distributed users. This would only serve to support and improve the model's performance given the additional training it could provide.A cloud software as a service (SaaS) architecture is introduced. The neural network model for the image recognition problem is introduced and evaluated. Experimental results using student drawings prove the model's capability to automatically generate accurate grades for the computer aided designs. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/CCECE47787.2020.9255825 | 2020 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE) |
Keywords | DocType | ISSN |
Deep learning, Cloud services, Scalability | Conference | 0840-7789 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Maysa Faroun Khaleel | 1 | 0 | 0.34 |
| Mohamed Abu Sharkh | 2 | 88 | 6.62 |
| Mohamad Kalil | 3 | 45 | 5.21 |