AI Hidden Markov Model - Natural Language Processing

Project: Sign Language Recognition System | Artificial Intelligence Nanodegree | Udacity

Build a sign language recognition system using Hidden Markov Models

Tissue classification of T1-weighted brain MR acquisitions using a hidden markov random field model.

Modelling of temporal and spatial environmental data with Hidden Markov Models. Dissertation project as part of my MSc programme in "Statistics with Data Science" (University of Edinburgh)

The artificial intelligence application for recognizing American Sign Language signs and 'translating' them into English. The underlying technique is Hidden Markov Model. This project is a part of Artificial Intelligence Nanodegree @udacity.

Collaboration with NTHU Library

Udacity - Artificial Intelligence - Project 4 (Probabilistic Models) - Hidden Markov Model (HMM) - All Files - Passed Sun 22 July 2018

A simple web app that I built to practice Viterbi algorithm on weather prediction exercise.

Hidden Markov Model (HMM) Part of Speech tagger project for the Udacity Natural Language Processing (NLP) Nanodegree

Part of Speech Tagging using Hidden Markov Models.

Implemented normalized, polar and delta feature sets, cross validation folds, Bayesian Information Criterion and Discriminative Information Criterion model selectors, as well as the recognizer in order to detect and translate sign language into text using hidden markov models as part of the Udacity Artificial Intelligence Nanodegree.

My solution of Udacity AI nanodegree project4 Part of Speech Tagging

Hidden Markov Model based POS tagging for 60+ languages on universal dependencies (UD) data

Udacity's NLPND Hidden Markov Model Part of Speech tagger project

Comparison of clustering methods for determining the operational states of a wastewater treatment plant (BSc project in Statistics) 🔧 🚰 🔄 ♻️ 💦

Material for a workshop on Bayesian analysis of capture-recapture data with hidden Markov models and Nimble

In this project, I built a system that can recognize words communicated using the American Sign Language (ASL). I was provided a preprocessed dataset of tracked hand and nose positions extracted from video. My goal was to train a set of Hidden Markov Models (HMMs) using part of this dataset to try and identify individual words from test sequences.