Merrimack Intelligencer Vol. 5 No. 48

This was a weekly paper that was published every Saturday. The motto of the Merrimack was: "Not too rash--Yet not fearful--We aim to be just." It was published from 1808-1817. Topics of interest include: Page 1: State of New York Republicans published a statement arguing against the war and the policies of John Adams and James Madison; account of the capture of York by the Americans, 27 April 1813; Page 2: account of the capture of York by the Americans, 27 April 1813; letter from American Brig. Gen. Henry Miller to Sir John B. Warren warning the British not to execute captured U.S. citizen O'Neal; response from Sir John B. Warren to Brig. Gen. Henry Miller stating that O'Neal had been released; account of Stephen Girard buying back his ransomed ship from the British; Page 3: account of Stephen Girard buying back his ransomed ship from the British; U.S. General Harrison repels British and Indian forces that attack Fort Meigs; account of British forces capturing U.S. privateer ship Alexander; report of British forces near Newport, New York, the Delaware river, and the Potomac River; report of Indian attacks in Kaskaskia, Randolph County; report of a boat load of provisions attacked by Indians near Fort Harrison; Commodore Isaac Chauncey arrived at Sacket's Harbor to unload stores taken from York before leaving for Niagara to commence attack against Fort George; U.S. Army announcement recruiting men 18 to 45 years of age to enlist in the army;

Real-Time Automatic Object Classification and Tracking using Genetic Programming and NVIDIA R CUDA TM

Genetic Programming (GP) is a widely used methodology for solving various computational problems. GP's problem solving ability is usually hindered by its long execution times. In this thesis, GP is applied toward real-time computer vision. In particular, object classification and tracking using a parallel GP system is discussed. First, a study of suitable GP languages for object classification is presented. Two main GP approaches for visual pattern classification, namely the block-classifiers and the pixel-classifiers, were studied. Results showed that the pixel-classifiers generally performed better. Using these results, a suitable language was selected for the real-time implementation. Synthetic video data was used in the experiments. The goal of the experiments was to evolve a unique classifier for each texture pattern that existed in the video. The experiments revealed that the system was capable of correctly tracking the textures in the video. The performance of the system was on-par with real-time requirements.