Abstract: In this paper, we present human activity recognition on static images. First, for feature extraction we employ Histograms of Oriented Gradients (HOG). The HOG is invariant to geometric transformations and photometric transformation such as changes in illumination or shadowing effect. The extracted features are then classified using Back- Propagation Neural Network (BPNN) classifier. Experimental results on Images from Weizmann dataset using proposed methodology show the accuracy of 99.2%. The results show that the human activity recognition can effectively be done using HOG features and BPNN as classifier.

• Publication Date: 25-May-2014
• DOI: 10.15224/978-1-63248-028-6-02-35
• Views: 0
• Downloads: 0

Abstract: The remarkable growth in the control mechanisms has been evidently seen in the last two decades. The controller Design has always been an important concern. In this paper we have chosen a real time Single Spherical Tank Liquid Level System (SSTLLS) for our investigation. The real time system is chosen to model the non-linear spherical system. This paper deals with the modeling of identified system in Simulink. System identification of this nonlinear process is done using black box model, which is identified to be nonlinear and approximated to be a First Order Plus Dead Time (FOPDT) model. A proportional and integral controller is designed in Simulink and various tuning methods including, Skogestad’s, Ziegler Nicolas(ZN) , Cheng and Hung(CH), and SIMC PID(SPD) are implemented. The paper will provide details about the implementation of the controller, and compare the results of PI tuning methods used.

• Publication Date: 25-May-2014
• DOI: 10.15224/978-1-63248-028-6-02-36
• Views: 0
• Downloads: 0