Human activity classification with miniature inertial sensors
buir.advisor | Barshan, Billur | |
dc.contributor.author | Tunçel, Orkun | |
dc.date.accessioned | 2016-01-08T18:18:14Z | |
dc.date.available | 2016-01-08T18:18:14Z | |
dc.date.issued | 2009 | |
dc.description | Ankara : The Department of Electrical and Electronics Engineering and the Institute of Engineering and Sciences of Bilkent University, 2009. | en_US |
dc.description | Thesis (Master's) -- Bilkent University, 2009. | en_US |
dc.description | Includes bibliographical references leaves 79-92. | en_US |
dc.description.abstract | This thesis provides a comparative study on activity recognition using miniature inertial sensors (gyroscopes and accelerometers) and magnetometers worn on the human body. The classification methods used and compared in this study are: a rule-based algorithm (RBA) or decision tree, least-squares method (LSM), k-nearest neighbor algorithm (k-NN), dynamic time warping (DTW- 1 and DTW-2), and support vector machines (SVM). In the first part of this study, eight different leg motions are classified using only two single-axis gyroscopes. In the second part, human activities are classified using five sensor units worn on different parts of the body. Each sensor unit comprises a tri-axial gyroscope, a tri-axial accelerometer and a tri-axial magnetometer. Different feature sets extracted from the raw sensor data and these are used in the classification process. A number of feature extraction and reduction techniques (principal component analysis) as well as different cross-validation techniques have been implemented and compared. A performance comparison of these classification methods is provided in terms of their correct differentiation rates, confusion matrices, pre-processing and training times and classification times. Among the classification techniques we have considered and implemented, SVM, in general, gives the highest correct differentiation rate, followed by k-NN. The classification time for RBA is the shortest, followed by SVM or LSM, k-NN or DTW-1, and DTW-2 methods. SVM requires the longest training time, whereas DTW-2 takes the longest amount of classification time. Although there is not a significant difference between the correct differentiation rates obtained by different crossvalidation techniques, repeated random sub-sampling uses the shortest amount of classification time, whereas leave-one-out requires the longest. | en_US |
dc.description.provenance | Made available in DSpace on 2016-01-08T18:18:14Z (GMT). No. of bitstreams: 1 0006155.pdf: 4330388 bytes, checksum: b077bd89af9f33389c192af576f14afd (MD5) | en |
dc.description.statementofresponsibility | Tunçel, Orkun | en_US |
dc.format.extent | xiv, 92 leaves, illustrations | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/15415 | |
dc.language.iso | English | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | inertial sensors | en_US |
dc.subject | gyroscope | en_US |
dc.subject | accelerometer | en_US |
dc.subject | magnetometer | en_US |
dc.subject | human activity recognition | en_US |
dc.subject | motion classification | en_US |
dc.subject | pattern recognition | en_US |
dc.subject | feature | en_US |
dc.subject | principal component analysis | en_US |
dc.subject | cross-validation | en_US |
dc.subject | rule-based algorithm | en_US |
dc.subject | decision tree | en_US |
dc.subject | leastsquares method | en_US |
dc.subject | k-nearest neighbor | en_US |
dc.subject | dynamic time warping | en_US |
dc.subject | support vector machines | en_US |
dc.subject.lcc | TA1650 .T85 2009 | en_US |
dc.subject.lcsh | Optical pattern recognition. | en_US |
dc.subject.lcsh | Computer vision. | en_US |
dc.subject.lcsh | Image processing--Digital techniques. | en_US |
dc.subject.lcsh | Body, Human--Computer simulation. | en_US |
dc.subject.lcsh | Sensors. | en_US |
dc.subject.lcsh | Human locomotion. | en_US |
dc.title | Human activity classification with miniature inertial sensors | en_US |
dc.type | Thesis | en_US |
thesis.degree.discipline | Electrical and Electronic Engineering | |
thesis.degree.grantor | Bilkent University | |
thesis.degree.level | Master's | |
thesis.degree.name | MS (Master of Science) |
Files
Original bundle
1 - 1 of 1