This paper reviews several computational frameworks for recognizing and learning events from a video stream. Approaches to event recognition are largely classified into 1) statistical pattern recognition, and 2) symbolic reasoning. In a statistical approach, the types of event patterns that can be recognized are governed by the choice of probabilistic models, and are difficult to generalize. A ...

Let A be a 0 − 1 matrix with precisely two 1’s in each column and let 1 be the all-one vector. We show that the problems of deciding whether the linear system Ax ≥ 1, x ≥ 0 (1) defines an integral polyhedron, (2) is totally dual integral (TDI), and (3) is box-totally dual integral (box-TDI) are all co-NP-complete, thereby confirming the conjecture on NP-hardness of recognizing TDI systems made ...

Examining the impacts of data modification is considered as sensitivity analysis. A lot of studies have considered the data modification of inputs and outputs in DEA. The issues which has not heretofore been considered in DEA sensitivity analysis is modification in the number of inputs and (or) outputs and determining the impacts of this modification in the status of efficiency of DMUs. This pa...

This paper describes a new method for the evaluation of non-utility generation impacts on preventive-corrective control of power systems. The proposed method relies on a mixed integer nonlinear optimization and is capable of recognizing the effectiveness of demand side preventive-corrective actions. A number of cases are presented to illustrate the consequences of introducing demand side action...

This paper describes a new method for the evaluation of non-utility generation impacts on preventive-corrective control of power systems. The proposed method relies on a mixed integer nonlinear optimization and is capable of recognizing the effectiveness of demand side preventive-corrective actions. A number of cases are presented to illustrate the consequences of introducing demand side action...

Optimizing Neural Networks that Generate Images Tijmen Tieleman Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2014 Image recognition, also known as computer vision, is one of the most prominent applications of neural networks. The image recognition methods presented in this thesis are based on the reverse process: generating images. Generating images is easi...

Accurate estimations of local precipitation are necessary for assessing water resources and water-related disaster risks. Numerical models typically used to estimate precipitation, but biases can result from insufficient resolution incomplete physical processes. To correct these biases, various bias correction methods have been developed. Recently, using machine learning developed improved perf...