Streaming Video Classification Using Machine Learning
Adnan Shaout and Brennan Crispin
The Electrical and Computer Engineering, the
University of Michigan-Dearborn, Michigan
Abstract: This
paper presents a method using neural networks and Markov Decision Process (MDP)
to identify the source and class of video streaming services. The paper presents
the design and implementation of an end-to-end pipeline for training and
classifying a machine learning system that can take in packets collected over a
network interface and classify the data stream as belonging to one of five
streaming video services: You Tube, You Tube TV, Netflix, Amazon Prime, or HBO.
Keywords:
Machine
Learning, Neural Networks, Deep Packet Inspection, MDP, Video Streaming, AI.
Received February 29, 2020;
accepted June 9, 2020