Beginning machine learning in the browser quick-start guide to gait analysis with JavaScript and TensorFlow.js
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
[Place of publication not identified] :
APress
[2021]
|
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009631697006719 |
Tabla de Contenidos:
- Intro
- Table of Contents
- About the Author
- About the Technical Reviewer
- Acknowledgments
- Preface
- Chapter 1: Web Development
- Machine Learning Overview
- Web Communication
- Organizing the Web with HTML
- Web Development Using IDEs/Editors
- Building Blocks of Web Development
- HTML and CSS Programming
- Dynamic HTML
- Cascading Style Sheets
- Inline Style Sheets
- Embedded Style Sheets
- External Style Sheets
- JavaScript Basics
- Including the JavaScript
- Where to Insert JS Scripts
- JavaScript for an Event-Driven Process
- Document Object Model Manipulation
- Introduction to jQuery
- Summary
- References
- Chapter 2: Browser-Based Data Processing
- JavaScript Libraries and API for ML on the Web
- W3C WebML CG (Community Group)
- Manipulating HTML Elements Using JS Libraries
- p5.js
- Drawing Graphical Objects
- Manipulating DOM Objects
- DOM onEvent(mousePressed) Handling
- Multiple DOM Objects onEvent Handling
- HTML Interactive Elements
- Interaction with HTML and CSS Elements
- Hierarchical (Parent-Child) Interaction of DOM Elements
- Accessing DOM Parent-Child Elements Using Variables
- Graphics and Interactive Processing in the Browser Using p5.js
- Interactive Graphics Application
- Object Instance, Storage of Multiple Values, and Loop Through Object
- Getting Started with Machine Learning in the Browser Using ml5.js and p5.js
- Design, Develop, and Execute Programs Locally
- Method 1: Using Python - HTTP Server
- Method 2: Using Visual Studio Code Editor with Node.js Live Server
- Summary
- References
- Chapter 3: Human Pose Estimation in the Browser
- Human Pose at a Glance
- PoseNet vs. OpenPose
- Human Pose Estimation Using Neural Networks
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Efficient Object Localization Using Convolutional Networks.
- Convolutional Pose Machines
- Human Pose Estimation with Iterative Error Feedback
- Stacked Hourglass Networks for Human Pose Estimation
- Simple Baselines for Human Pose Estimation and Tracking
- Deep High-Resolution Representation Learning for Human Pose Estimation
- Using the ml5.js:posenet() Method
- Input, Output, and Data Structure of the PoseNet Model
- Input
- Output
- .on() Function
- Summary
- References
- Chapter 4: Human Pose Classification
- Need for Human Pose Estimation in the Browser
- ML Classification Techniques in the Browser
- ML Using TensorFlow.js
- Changing Flat File Data into TensorFlow.js Format
- Artificial Neural Network Model in the Browser Using TensorFlow.js
- Trivial Neural Network
- Example 1: Neural Network Model in TensorFlow.js
- Example 2: A Simple ANN to Realize the "Not AND" (NAND) Boolean Operation
- Human Pose Classification Using PoseNet
- Setting Up a PoseNet Project
- Step 1: Including TensorFlow.js and PoseNet Libraries in the HTML Program (Main File)
- Step 2: Single-Person Pose Estimation Using a Browser Webcam
- PoseNet Model Confidence Values
- Summary
- References
- Chapter 5: Gait Analysis
- Gait Measurement Techniques
- Gait Cycle Measurement Parameters and Terminology
- Web User Interface for Monitoring Gait Parameters
- index.html
- Real-Time Data Visualization of the Gait Parameters (Patterns) on the Browser
- Determining Gait Patterns Using Threshold Values
- Summary
- References
- Chapter 6: Future Possibilities for Running AI Methods in a Browser
- Introduction
- Additional Machine Learning Applications with TensorFlow
- Face Recognition Using face-api.js
- Hand Pose Estimation
- Summary
- References
- Conclusion
- Index.
