Abstract:
This paper compares conventional and deep machine learning in self-organizing network anomaly detection. Deep learning has gained popularity, especially in applications where large amounts of data can be collected and processed, but conventional methods may still offer strong statistical alternatives, especially when using proper learning representations.
Support vector machines can be used with one-class learning and data augmentation to improve binary classification applications.
For the first time, on a publicly available dataset, conventional machine learning outperforms deep learning by 15% on average across four application scenarios. Our results show that conventional machine learning is a robust alternative for 5G self-organizing networks, especially when execution and detection times are critical.
Keywords: Anomaly Detection, Support Vector Machines, Self-Organizing Networks, Machine Learning, Deep Learning, 5g Mobile Communication, Wireless Sensor Networks, Learning (Artificial Intelligence), Pattern Classification, Support Vector Machines
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
