Gesture recognition plays an important role in human computer Interaction for intelligent computing. Major applications like Gaming, Robotics and Automated Homes uses gesture recognition techniques which diminishes the usage of mechanical devices. The main goal of my thesis is to interpret SWAT team gestures using different types of sensors. Accelerometer and flex sensors were explored extensively to build a prototype for soldiers to communicate in the absence of line of sight. Arm movements were recognized by flex sensors and motion gestures by Accelerometers. Accelerometers are used to measure acceleration in respect to movement of the sensor in 3D. Flex sensors changes its resistance based on the amount of bend in the sensor. SVM is the classification algorithm used for classification of the samples. LIBSVM (Library for Support Vector Machines) is integrated software for support vector classification, regression and distribution estimation which supports multi class classification. Sensors data is connected to the WI micro dig to digitize the signal and to transmit it wirelessly to the computing device. Feature extraction and Signal windowing were the two major factors which contribute for the accuracy of the system. Mean Average value and Standard Deviation are the two features considered for accelerometer sensor data classification and Standard deviation is used for the flex sensor analysis for optimum results. Filtering of the signal is done by identifying the different states of signals which are continuously sampled.
Dallas is the third largest growing industrialized city in the state of Texas. the prevailing air quality here is highly influenced by the industrialization and particulate matter 2.5µm (PM2.5) has been found to be one of the main pollutants in this region. Exposure to PM2.5 in elevated levels could cause respiratory problems and other health issues, some of which could be fatal. the current study dealt with the quantification and analysis of the sources of emission of PM2.5 and an emission inventory for PM2.5 was assessed. 24-hour average samples of PM2.5 were collected at two monitoring sites under the Texas Commission on Environmental Quality (TCEQ) in Dallas, Dallas convention Centre (CAMS 312) and Dallas Hinton sites (CAMS 60). the data was collected from January 2003 to December 2009 and by using two positive matrix models PMF 2 and EPA PMF the PM2.5 source were identified. 9 sources were identified from CAMS 312 of which secondary sulfate (31% by PMF2 and 26% by EPA PMF) was found to be one of the major sources. Data from CAMS 60 enabled the identification of 8 sources by PMF2 and 9 by EPA PMF. These data also confirmed secondary sulfate (35% by PMF2 and 34% by EPA PMF) as the major source. to substantiate the sources identified, conditional probability function (CPF) was used. the influence of long range transport pollutants such as biomass burns from Mexico and Central America was found to be influencing the region of study and was assessed with the help of potential source contribution function (PSCF) analysis. Weekend/weekday and seasonal analyses were useful in understanding the behavioral pattern of pollutants. Also an inter comparison of the model results were performed and EPA PMF results was found to be more robust and accurate than PMF 2 results.
While conventional turbines have been extensively researched and tested, Tesla and boundary layer type turbines have not. In order to construct a dynamometer, thermodynamic flow apparatus and future turbines, we modeled the Tesla turbine using theoretical calculations and preliminary experiments. Thus a series of experiments were run to determine stall torque and maximum run speed for a known pressure range. This data was then applied to modeling formulas to estimate stall torque over an extended range of variables. The data were then used to design an appropriate dynamometer and airflow experiment. The model data also served to estimate various specifications and power output of the future turbine. An Obi Laser SSTG‐001 Tesla turbine was used in the experiments described. Experimental stall torque measurements were conducted in two stages. Shaft speed measurements were taken with an optical laser tachometer and Tesla turbine stall torque was measured using a spring force gauge. Two methods were chosen to model Tesla turbine stall torque: 1) flow over flat plate and 2) free vortex with a sink. A functional dynamometer and thermodynamic apparatus were constructed once the model was confirmed to be within the experimental uncertainty. Results of the experiments show that the experimental turbine at 65 PSI has a speed of approximately 27,000 RPM and a measured stall torque of 0.1279 N‐m. 65 PSI is an important data point because that data set is the cut‐off from laminar to turbulent flow. Thus at 65 PSI, a rejection of the null hypothesis for research question one with respect to the flow over flat plate method can be seen from the data, while the vortex model results in a failure to reject the null hypothesis. In conclusion, the experimental turbine was seen to have a laminar and a turbulent flow regime at different air pressures, rather ...
Manual video analysis is apparently a tedious task. An efficient solution is of highly importance to automate the process and to assist operators. A major goal of video analysis is understanding and recognizing human activities captured by surveillance cameras, a very challenging problem; the activities can be either individual or interactional among multiple objects. It involves extraction of relevant spatial and temporal information from visual images. Most video analytics systems are constrained by specific environmental situations. Different domains may require different specific knowledge to express characteristics of interesting events. Spatial-temporal trajectories have been utilized to capture motion characteristics of activities. The focus of this dissertation is on how trajectories are utilized in assist in developing video analytic system in the context of surveillance. The research as reported in this dissertation begins real-time highway traffic monitoring and dynamic traffic pattern analysis and in the end generalize the knowledge to event and activity analysis in a broader context. The main contributions are: the use of the graph-theoretic dominant set approach to the classification of traffic trajectories; the ability to first partition the trajectory clusters using entry and exit point awareness to significantly improve the clustering effectiveness and to reduce the computational time and complexity in the on-line processing of new trajectories; A novel tracking method that uses the extended 3-D Hungarian algorithm with a Kalman filter to preserve the smoothness of motion; a novel camera calibration method to determine the second vanishing point with no operator assistance; and a logic reasoning framework together with a new set of context free LLEs which could be utilized across different domains. Additional efforts have been made for three comprehensive surveillance systems together with main contributions mentioned above.
Piezoelectric energy harvester has become a new powering choice for small electronic device. Due to its piezoelectric effect, electric energy can be obtained from ambient vibrations. This thesis is intending to build a frequency-adjustable piezoelectric energy harvester system. The system is structured with two piezoelectric bimorph beams, which are connected to each other by a spring. The feasibility of the frequency-adjustable piezoelectric energy harvester has been proved by investigating effects of the spring, loading mass and impedance on the operation frequencies.