Investigation of data glove grasping features : Sum of movement and area under curve /
The objectives of this research are as follow to construct voltage output into angle conversion, gloveMAP output currently in-form of voltage over time. These outputs are considered as difficult to understand for some user without signal analysis background. Hence, GloveMAP voltage output will be re...
Saved in:
| Main Author: | |
|---|---|
| Corporate Author: | |
| Format: | Thesis Book |
| Language: | English |
| Published: |
Perlis, Malaysia
School of Mechatronic Engineering
2016
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The objectives of this research are as follow to construct voltage output into angle conversion, gloveMAP output currently in-form of voltage over time. These outputs are considered as difficult to understand for some user without signal analysis background. Hence, GloveMAP voltage output will be representing into angle information. To extract feature for grasping object analysis, including the entire GloveMAP voltage output into classification algorithm can increase the processing time, increase the complexity of algorithm and also decrease the capability of the classification algorithm. Therefore, the GloveMAP voltage output will be represent into a set of feature using appropriate feature extraction method. To classify grasping signal by using classification technique, classification can be separated into two learning method; supervised learning and unsupervised learning. Both have its own advantage in data classification. K-means and LDA is selected for GloveMAP output assessment. To recognize the grasping objects by referring to the outcome from classification training, outcome variable obtain from K-means and LDA classification learning process will be used to recognize the grasping object. |
|---|---|
| Physical Description: | x, 116 pages colour illustrations 30 cm. |
| Bibliography: | Includes bibliographical references. |