Browsing by Subject "Real-time application"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Human activity recognition using inertial/magnetic sensor units(Springer, Berlin, Heidelberg, 2010) Altun, Kerem; Barshan, BillurThis 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), 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). Daily and sports activities are classified using five sensor units worn by eight subjects on the chest, the arms, and the legs. Each sensor unit comprises a triaxial gyroscope, a triaxial accelerometer, and a triaxial magnetometer. Principal component analysis (PCA) and sequential forward feature selection (SFFS) methods are employed for feature reduction. For a small number of features, SFFS demonstrates better performance and should be preferable especially in real-time applications. The classifiers are validated using different cross-validation techniques. Among the different classifiers we have considered, BDM results in the highest correct classification rate with relatively small computational cost. © 2010 Springer-Verlag Berlin Heidelberg.Item Open Access Thereconstruction quality improvement of holographic stereograms via variable size segmentation(IEEE, 2010) Şahin, Erdem; Onural, Levent; Kang, HoonjongAs computer generated holograms becomes more common, the fast computation of holographic interference patterns in digital environment becomes a necessity. Since the computation time of holograms via Fresnel (or Rayleigh-Sommerfeld) diffraction models makes real time applications impossible, the holographic stereograms are developed to be a solution for this problem. Holographic stereograms divide the hologram plane into segments. In phase added stereograms the coordinates of 3D source points are used while calculating the diffraction field. And that enables to calculate the diffraction field with appropriate sized FFTs. Although the phase added stereograms are advantageous in terms of computation time, the quality of the reconstructed three dimensional images may not be satisfactory. The main reason is that the diffraction field of a given point source is approximated as a pure complex sinusuoid in each segment. To increase the reconstruction quality, we propose a method that uses variable sized segments, as opposed to previously developed holographic stereograms that use fixed sized segments. While approximating the diffraction field of a point source, higher frequency regions are covered with smaller segments and lower frequency regions with larger segments. As a result of this, we keep the total number of oscillations of pure sinusoidal waves constant in each segment. The simulations that we carried out for a point source show that we are able to obtain better quality reconstruction with our method. ©2010 IEEE.