Video analytics, also called intelligent video surveillance, is a technology that uses software to automatically identify specific objects, behaviors or attitudes in video footage. It transforms the video into data to be transmitted or archived so that the video surveillance system can act accordingly.
The proposed solutions including adaptive workflow, rule-based process management, and policy management in process modeling tackle the problem by using rules to capture and control the decision points in processes. The popular demand for flexibility and reliability has driven the Service Oriented Architecture (SOA) to a next wave of Event Driven-SOA (ED-SOA) and cloud computing.
This research combines machine learning techniques and statistical techniques to develop an Autonomy Artificial Intelligence Prediction System for Panoramic Enhanced Cost Estimation. With this approach, the prediction powers of the COCOMO parametric software cost model are shown to be significantly improved while the variability is decreased with respect to the dataset being analyzed.
The main objective of the dissertation is to present work describing theoretical studies of planar structures with erbium doped regions and characterization of erbium doped particles. Numerical models of erbium doped Al2O3 were formulated, taking into account the up-conversion from the metastable Er3+ levels and the cross-relaxation process as a mechanism of energy transfer between Er3+ ions.
This dissertation addresses the multicriterion nature of market segmentation with a new unified segmentation model that is derived from a multiobjective conceptual framework. The unified model elegantly solves the intrinsic antagonistic problem of market segmentation by generating a set of Pareto optimal solutions that represent different tradeoffs among multiple conflicting objectives.