Recognition of Human Activities by Using Machine Learning Methods

Please enable javascript in your browser.

Ghazvininejad, Marjan | 2011

541 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 42526 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Rabiee, Hamid Reza
Abstract:
In this research, we have used machine learning methods to approach the problem of human activity recognition. As the process of labeling the data in this problem is so costly and time consuming, and regarding the copious available unlabeled data, semi supervised methods have a high performance in this problem. In recent years, graph based methods have became very populaer among semi supervised learning methods. However, constructing a graph on the data which presents their structure in a proper manner has remained a main challenge in these methods. One of the causes of this problem is the existance of the shortcut edges. In this report, we will first introduce a method to solve the problem of the shortcut edges to a good extent and amend the structure of the graph in a way that it become a good representator of the structure of the data. Next, we will introduce a method which considering the time structure of the data along whith the constructed graph on them, predicts the label of the forthcoming data. This aim is achieved by combining hidden Markov models with graph based methods. Experiments on various datasets demonstrate the high performance of the proposed method in practice
Keywords:
Activity Recognition ; Hidden Markov Model ; Manifolds ; Semi-Supervised Learning ; Gragh Based Method

No TOC