EEE-5020-Time-Series-Analysis-of-Gesture-Phase-Segmentation-Data

This work is completed as a part of EEE 5020: Machine Learning Courses Capstone Project. The 'Gesture Phase Segmentation' Dataset is taken from UCI Dataset Repository.

The Problem

The previous works mentioned below tried to work on this dataset.

About the Dataset

The dataset is composed by features extracted from 7 videos with people gesticulating, aiming at studying Gesture Phase Segmentation. Each video is represented by two files:

1. A Raw File, which contains the position of hands, wrists, head and spine of the user in each frame
2. A Processed File, which contains velocity and acceleration of hands and wrists.

For detailed description, click here

Previous Works

1. Madeo, R. C. B. ; Lima, C. A. M. ; PERES, S. M. . Gesture Unit Segmentation using Support Vector Machines: Segmenting Gestures from Rest Positions. In: Symposium on Applied Computing (SAC), 2013, Coimbra. Proceedings of the 28th Annual ACM Symposium on Applied Computing (SAC), 2013. p. 46-52.

   • In this paper, the videos A1 and A2 were studied.

2. Wagner, P. K. ; PERES, S. M. ; Madeo, R. C. B. ; Lima, C. A. M. ; Freitas, F. A. . Gesture Unit Segmentation Using Spatial-Temporal Information and Machine Learning. In: 27th Florida Artificial Intelligence Research Society Conference (FLAIRS), 2014, Pensacola Beach. Proceedings of the 27th Florida Artificial Intelligence Research Society Conference (FLAIRS). Palo Alto : The AAAI Press, 2014. p. 101-106.

   • In this paper, the videos A1, A2, A3, B1, B3, C1 and C3 were studied.

3. Madeo, R. C. B.. Support Vector Machines and Gesture Analysis: incorporating temporal aspects (in Portuguese). Master Thesis - Universidade de Sao Paulo, Sao Paulo Researcher Foundation. 2013.

   • In this document, the videos named B1 and B3 in the document correspond to videos C1 and C3 in this dataset. Only five videos were explored in this document: A1, A2, A3, C1 and C3.

4. Wagner, P. K. ; Madeo, R. C. B. ; PERES, S. M. ; Lima, C. A. M. . Segmentaçao de Unidades Gestuais com Multilayer Perceptrons (in Portuguese). In: Encontro Nacional de Inteligencia Artificial e Computacional (ENIAC), 2013, Fortaleza. Anais do X Encontro Nacional de Inteligencia Artificial e Computacional (ENIAC), 2013.

   • In this paper, the videos A1, A2 and A3 were studied.