Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
An Enhanced Cloud-Native Deep Learning Pipeline for the Classification of Network Traffic
In a rapidly changing world, the way of solving real-world problems has changed to leverage the power of the advancements in multiple fields. Cloud-native computing approaches can be utilized with deep learning techniques to provide solutions in several important areas. For instance, with the emerge...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | In a rapidly changing world, the way of solving real-world problems has changed to leverage the power of the advancements in multiple fields. Cloud-native computing approaches can be utilized with deep learning techniques to provide solutions in several important areas. For instance, with the emergence of the pandemic, much dependence on modern technologies came out as a replacement for face-to-face interaction. Deep learning can reach a high level of accuracy, which makes it very effective in the support of modern services and technologies. However, there are some challenging issues because deep learning requires many large-scale experiments, which demand a lot of time and computational resources. Also, it needs lots of labeled data. In this research, we propose an improved cloud-native deep learning pipeline to alleviate these issues. We use the classification of network traffic as a realworld use case, which has multiple vital applications that empower modern services and technologies. We offer a serverless cloud-native approach for data preprocessing, model building (hyperparameter tuning), and model serving. Also, our approach supports the scenarios of partially and fully labeled data. We were able to attain speedup and scalability values, which are near to the theoretically calculated ones. In addition, our approach reached better accuracy within a limited time budget in comparison with existing work. We begin by defining the problem. Then, we survey the background and studies that attempt to use different approaches. After that, we present the proposed methodology. Finally, we describe the experiments and show the results. |
|---|