Machine Learning For Network Traffic and Video Quality Analysis: Develop and Deploy Applications Using JavaScript

Table of Contents
About the Authors
About the Technical Reviewer
Chapter 1: Introduction
	1.1 Overview of Network Traffic Monitoring and Analysis
		1.1.1 Importance of NTMA
		1.1.2 Key Objectives of NTMA
		1.1.3 Network Traffic Components
		1.1.4 NTMA Techniques and Methodologies
		1.1.5 Challenges of NTMA
		1.1.6 Use Cases of NTMA
		1.1.7 Emerging Trends in NTMA
		1.1.8 Bridging the Gap between NTMA and User Experience
	1.2 Overview of Video Quality Assessment
		1.2.1 Significance of VQA
		1.2.2 Factors Affecting Video Quality
		1.2.3 Evolution of VQA Approaches
		1.2.4 Real-World Applications of VQA
		1.2.5 Challenges in VQA
		1.2.6 Emerging Trends in VQA
	1.3 Machine Learning in JavaScript
		1.3.1 Introduction to Machine Learning
		1.3.2 Coupling JavaScript with Machine Learning
		1.3.3 Data Preparation and Preprocessing in JavaScript
		1.3.4 Supervised Learning with JavaScript
		1.3.5 Unsupervised Learning with JavaScript
		1.3.6 Deep Learning in JavaScript
		1.3.7 Deploying Machine Learning Models in Web Applications
	1.4 Node.js and Networking
	1.5 Book Overview
	1.6 References – Chapter 1
Chapter 2: Network Traffic Monitoring and Analysis
	2.1 NTMA Fundamentals
		2.1.1 Data Sources and Collection
		2.1.2 Key Metrics
		2.1.3 Data Preprocessing and Cleaning
		2.1.4 Network Topology and Architecture
		2.1.5 Data-Driven Analytics
		2.1.6 Supervised Learning for Traffic Classification
		2.1.7 Unsupervised Learning for Anomaly Detection
		2.1.8 Predictive Analytics
		2.1.9 Real-time AI-Based Decision Support
	2.2 Existing NTMA Applications
		2.2.1 SolarWinds NetFlow Traffic Analyzer
		2.2.2 Paessler PRTG Network Monitor
		2.2.3 Wireshark
		2.2.4 ManageEngine NetFlow Analyzer
		2.2.5 Site24x7 Network Monitoring
		2.2.6 Prometheus
		2.2.7 Commercial vs. Open-Source Solutions
		2.2.8 Challenges and Considerations
	2.3 State-of-the-Art Review of NTMA
		2.3.1 Background of NTMA
		2.3.2 The Rise of Machine Learning
		2.3.3 Machine Learning Algorithms to Classify Network Traffic
		2.3.4 Machine Learning Algorithms to Predict Network Traffic
	2.4 Summary
	2.5 References – Chapter 2
Chapter 3: Video Quality Assessment
	3.1 VQA Fundamentals
		3.1.1 Video Quality Metrics
		3.1.2 Human Perception in Video Quality
		3.1.3 Video Quality Attributes
		3.1.4 The Optimal VQA Strategy
		3.1.5 Quality of Experience (QoE) Metrics
		3.1.6 Quality of Service (QoS) Metrics
		3.1.7 Quality of Performance (QoP) Metrics
		3.1.8 Subjective VQA
		3.1.9 Objective VQA
		3.1.10 Quality Metrics for Network, Video, and Streaming
		3.1.11 Video Quality Databases and Benchmarking
		3.1.12 Temporal and Spatial Considerations in VQA
		3.1.13 VQA for Evolving Video Content
	3.2 Existing VQA Applications
		3.2.1 Sentry by Telestream
		3.2.2 Real-Time Media Assessment (RTMA) by ThinkTel
		3.2.3 Witbe
		3.2.4 ViCue Soft
		3.2.5 AccepTV Video Quality Monitor
		3.2.6 VQEG Image Quality Evaluation Tool (VIQET)
	3.3 State-of-the-Art Review of VQA
		3.3.1 Background of VQA
		3.3.2 Machine Learning in VQA
		3.3.3 Machine Learning Algorithms to Analyze Video Quality in Multimedia Communications
	3.4 Summary
	3.5 References – Chapter 3
Chapter 4: Machine Learning Techniques for NTMA and VQA
	4.1 Classification Model for NTMA
		4.1.1 Data Collection for Classification
		4.1.2 K-Nearest Neighbor (KNN) Algorithm
		4.1.3 Data Preparation for Classification
		4.1.4 Shorthand Example for KNN
	4.2 Prediction Model for NTMA
		4.2.1 Multilayer Perceptron (MLP) Algorithm
		4.2.2 Hyperparameters
		4.2.3 Data Preparation for Time-Series Prediction
		4.2.4 Sliding Window Concept
		4.2.5 MLP for Time-Series Network Traffic Prediction
		4.2.6 Short-hand Example for MLP
	4.3 SVM for VQA
		4.3.1 Blind Image Quality Assessment Using Distortion Aggravation
		4.3.2 Preliminary Steps
		4.3.3 Extraction of LBP Features
			Process and Equations
			Illustrations and Coding Procedure
		4.3.4 Distortion Aggravation
			JPEG Compression
			JPEG2000 Compression
			Gaussian Blur
			White Noise
		4.3.5 Similarity Index
		4.3.6 Scaling
		4.3.7 Using SVM for Prediction
	4.4 Summary
	4.5 References – Chapter 4
Chapter 5: NTMA Application with  JavaScript
	5.1 System Model for NTMA
		5.1.1 Components and Functionalities
		5.1.2 Prediction and Classification of Network Traffic
		5.1.3 NTMA Application Layout
		5.1.4 Client–Server Interaction
	5.2 Client Program Structure for NTMA
		5.2.1 Configuring Extension Settings and Permissions
		5.2.2 Configuring the Background Script
		5.2.3 Building the User Interface
			File Functionality
			Libraries and Required Resources
			Creating the Document Structure
			Adding the Document Details and References to External Resources
			Adding the Graph and Dashboard Components
			Styling the Components through Internal CSS
			Adding the User Interface to Google Chrome
			Visualizing the User Interface
		5.2.4 Building the Client Script
			File Functionality
			Creating the Script Structure
			Initializing and Configuring the Chart on Page Load
			Real-Time WebSocket Communication and Dynamic Graph Updates
			Real-Time Chart Update Mechanism
	5.3 Server Program Structure for NTMA
		5.3.1 Libraries and Required Resources
		5.3.2 Adding Libraries
		5.3.3 Declaring Global Variables
		5.3.4 Fetching Local Databases
		5.3.5 Creating a WebSocket Server
		5.3.6 Listening for a Client Connection Request
			Getting Messages from the Client
			Measuring Latency
			Measuring Network Traffic and Sending Real-Time Metrics to the Client
		5.3.7 Method for Time-Series Prediction with MLP Regression
		5.3.8 Method for Calculating the QoS Score
		5.3.9 Method for Classifying the Device Activity
	5.4 NTMA Application Testing and Deployment
	5.5 Summary
	5.6 References – Chapter 5
Chapter 6: Video Quality Assessment Application Development with JavaScript
	6.1 System Model for VQA
		6.1.1 Components and Functionalities
		6.1.2 Prediction of an MOS Score for Video Quality
		6.1.3 VQA Application Layout
		6.1.4 Client–Server–Servlet Interaction
	6.2 Client Program Structure for VQA
		6.2.1 Configuring Extension Settings and Permissions
		6.2.2 Configuring the Background Script
		6.2.3 Building the User Interface
			File Functionality
			Libraries and Required Resources
			Creating the Document Structure
			Adding the Document Details and References to External Resources
			Adding the Graph and Dashboard Components
			Styling the Components through Internal CSS
			Adding the User Interface to Google Chrome
			Visualizing the User Interface
		6.2.4 Building the Client Script
			File Functionality
			Creating the Script Structure
			Initializing and Configuring the Chart on Page Load
			Real-Time WebSocket Communication and Dynamic Graph Updates
			Real-Time Chart Update Mechanism
	6.3 Server Program Structure for VQA
		6.3.1 Libraries and Required Resources
		6.3.2 Adding Libraries
		6.3.3 Declaring Global Variables
		6.3.4 Emptying the Screenshot Folders
		6.3.5 Creating a WebSocket Server
		6.3.6 Listening for a Client Connection Request
			Receiving Metadata and Site Data
			Reconstructing and Cropping the Image
			Querying the Servlet and Handling the Response
	6.4 Servlet Program Structure for VQA
		6.4.1 Creating a Java Servlet in Eclipse
		6.4.2 Libraries and Required Resources
		6.4.3 Adding Libraries
		6.4.4 Adding Imports
		6.4.5 Declaring Global Variables
		6.4.6 Handling an HTTP POST Request from a Client
		6.4.7 Extracting the LBP Features
			LBP Pattern for Original Image
			Binarization Process for Gaussian Blur
			Binarization Process for White Noise
			Binarization Process for JPEG Compression
			Binarization Process for JPEG2000 Compression
		6.4.8 Applying Distortions
			Applying Gaussian Blur for Blurring
			Applying White Noise for Noising
			Applying JPEG Compression for Blocking
			Applying JPEG2000 Compression for Ringing
		6.4.9 Calculating the Similarity Index
		6.4.10 Scaling the Similarity Scores
			Implementing the Runner
			Displaying Usage Information
			File Handling and Buffer Management
			Scaling Target and Attribute Values
		6.4.11 Printing Utilities
		6.4.12 Predicting the MOS
	6.5 VQA Application Testing and Deployment
	6.6 Summary
	6.7 References – Chapter 6
Chapter 7: NTMA and VQA Integration
	7.1 System Model for Integrated NTMA and VQA Application
		7.1.1 Components and Functionalities
		7.1.2 Prediction and Classification of Network Traffic with Video Quality Metrics
		7.1.3 Integrated NTMA/VQA Application Layout
		7.1.4 Client–Server–Servlet Interaction
	7.2 Client Program Structure for Integrated NTMA/VQA Application
		7.2.1 Configuring Extension Settings and Permissions
		7.2.2 Configuring the Background Script
		7.2.3 Building the User Interface
			File Functionality
			Libraries and Required Resources
			Creating the Document Structure
			Adding the Document Details and References to External Resources
			Adding the Toggle, Graphs, and Dashboard Components
			Styling the Components through Internal CSS
			Adding the User Interface to Google Chrome
			Visualizing the User Interface
		7.2.4 Building the Client Script
			File Functionality
			Creating the Script Structure
			Initializing and Configuring the Charts on Page Load
			Real-Time WebSocket Communication and Dynamic Graph Updates
			Real-Time Chart Update Mechanism
	7.3 Server Program Structure for Integrated NTMA/VQA Application
		7.3.1 Libraries and Required Resources
		7.3.2 Adding Libraries
		7.3.3 Declaring Global Variables
		7.3.4 Emptying the Screenshot Folders
		7.3.5 Fetching the Local Databases
		7.3.6 Creating a WebSocket Server
		7.3.7 Listening for a Client Connection
			Adding the VQA Block
			Adding the NTMA Block
		7.3.8 Prediction, Classification, and Network Score Computation Methods
	7.4 Integrated NTMA/VQA Application Testing and Deployment
	7.5 Summary
	7.6 References–Chapter 7
Index