Title | ||
---|---|---|
Feature Extraction and Pattern Recognition for Human Motion by a Deep Sparse Autoencoder |
Abstract | ||
---|---|---|
Human motion data is high-dimensional time-series data, and it usually contains measurement error and noise. Recognizing human motion on the basis of such high-dimensional measurement row data is often difficult and cannot be expected for high generalization performance. To increase generalization performance in a human motion pattern recognition task, we employ a deep sparse auto encoder to extract low-dimensional features, which can efficiently represent the characteristics of each motion, from the high-dimensional human motion data. After extracting low-dimensional features by using the deep sparse auto encoder, we employ random forests to classify low-dimensional features representing human motion. In experiments, we compared using the row data and three types of feature extraction methods - principal component analysis, a shallow sparse auto encoder, and a deep sparse auto encoder - for pattern recognition. The experimental results show that the deep sparse auto encoder outperformed the other methods with the highest average recognition accuracy, 75.1%, and the lowest standard deviation, ±3.30%. The proposed method, application of a deep sparse auto encoder, thus enabled higher recognition accuracy, better generalization and more stability than could be achieved with the other methods. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/CIT.2014.144 | CIT |
Keywords | Field | DocType |
measurement errors,image representation,image coding,pattern recognition,low-dimensional feature extraction,measurement uncertainty,random forests,high-dimensional time-series data,feature extraction,image classification,deep learning,measurement error,human motion, feature extraction, pattern recognition, deep sparse autoencoder, deep learning,human motion pattern recognition task,deep sparse autoencoder,human motion recognition,high generalization performance,low-dimensional feature classification,deep sparse auto encoder,principal component analysis,time series,human motion representation,measurement noise,human motion,image motion analysis | Computer vision,Autoencoder,Pattern recognition,Computer science,Sparse approximation,Feature extraction,Artificial intelligence,Deep learning,Random forest,Standard deviation,Principal component analysis,Observational error | Conference |
ISSN | Citations | PageRank |
2474-9648 | 5 | 0.41 |
References | Authors | |
8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hailong Liu | 1 | 39 | 7.57 |
Tadahiro Taniguchi | 2 | 201 | 33.56 |