Indiana University-Purdue University Indianapolis (IUPUI) / Emotions are essential for our existence, as they exert great influence on the mental health of people. Speech is the most powerful mode to communicate. It controls our intentions and emotions. Over the past years many researchers worked hard to recognize emotion from speech samples. Many systems have been proposed to make the Speech Emotion Recognition (SER) process more correct and accurate. This thesis research discusses the design of speech emotion recognition system implementing a comparatively new method, i-vector model. I-vector model has found much success in the areas of speaker identification, speech recognition, and language identification. But it has not been much explored in recognition of emotion. In this research, i-vector model was implemented in processing extracted features for speech representation. Two different classification schemes were designed using two different classifiers - Gaussian Mixture Model (GMM) and Support Vector Machine (SVM), along with i-vector algorithm. Performance of these two systems was evaluated using the same emotional speech database to identify four emotional speech signals: Angry, Happy, Sad and Neutral. Results were analyzed, and more than 75% of accuracy was obtained by both systems, which proved that our proposed i-vector algorithm can identify speech emotions with less error and with more accuracy.

No / A comparison is presented between two indoor localization algorithms using received signal strength, namely the vector algorithm and the Comparative Received Signal Strength (CRSS) algorithm. Signal values were obtained using ray tracing software and processed with MATLAB to ascertain the effects on localization accuracy of radio map resolution, number of access points and operating frequency. The vector algorithm outperforms the CRSS algorithm, which suffers from ambiguity, although that can be reduced by using more access points and a higher operating frequency. Ambiguity is worsened by the addition of more reference points. The vector algorithm performance is enhanced by adding more access points and reference points while it degrades with increasing frequency provided that the statistical mean of error increased to about 60 cm for most studied cases. / No full text available. Unable to contact the publisher.

This thesis deals with control of three phase inverter as three phase sinusoidal voltage source for UPS application. Thesis is split to two parts, teoretical and practical. Teoretical part deals with three phase inverter topology analysis according requirement of neutral line wire and possibilities of generating sinusoidal PWM in depend of topology. There are also analysed properties of contorled system and designed 3 regulation methods with simulations. Second part of thesis deals with realisation of sinusoidal power source with inverter borrowed by Elcom company. To inverter control is used digital signal controler TMS320F28335 with implemented control algorithms. There are also presented the measurement results of the prototype of power source. In conclusion, simulation results are compared with measurements and achieved results are summarized.