Comparative study on classifying human activities with miniature inertial and magnetic sensors
| Autor: | Orkun Tuncel, Kerem Altun, Billur Barshan |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2010 |
| Předmět: |
Dynamic time warping
Computer science Liquid state machine Least-squares Method Feature extraction Decision Tree Decision tree K-nearest Neighbor Machine learning computer.software_genre Feature Extraction k-nearest neighbors algorithm Artificial Intelligence Support Vector Machines Activity Recognition And Classification Feature Reduction Rule-based Algorithm Artificial Neural Networks Dynamic Time Warping Inertial Sensors Artificial neural network business.industry Pattern recognition Gyroscope Magnetometer Bayesian Decision Making Support vector machine Accelerometer ComputingMethodologies_PATTERNRECOGNITION Signal Processing Principal component analysis Computer Vision and Pattern Recognition Artificial intelligence business computer Software |
| Zdroj: | Pattern Recognition |
| Popis: | Cataloged from PDF version of article. This paper provides a comparative study on the different techniques of classifying human activities that are performed using body-worn miniature inertial and magnetic sensors. The classification techniques implemented and compared in this study are: Bayesian decision making (BDM), a rule-based algorithm (RBA) or decision tree, the least-squares method (LSM), the k-nearest neighbor algorithm (k-NN), dynamic time warping (DTW), support vector machines (SVM), and artificial neural networks (ANN). Human activities are classified using five sensor units worn on the chest, the arms, and the legs. Each sensor unit comprises a tri-axial gyroscope, a tri-axial accelerometer, and a tri-axial magnetometer. A feature set extracted from the raw sensor data using principal component analysis (PCA) is used in the classification process. A performance comparison of the classification techniques is provided in terms of their correct differentiation rates, confusion matrices, and computational cost, as well as their preprocessing, training, and storage requirements. Three different cross-validation techniques are employed to validate the classifiers. The results indicate that in general, BDM results in the highest correct classification rate with relatively small computational cost. (C) 2010 Elsevier Ltd. All rights reserved |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|