One of the issues facing credit card fraud detection systems is that a significant percentage of transactions labeled as fraudulent are in fact legitimate. These “false alarms” delay the detection of fraudulent transactions. Analysis of 11 months of credit card transaction data from a major Canadian bank was conducted to determine savings improvements that can be achieved by identifying truly fraudulent transactions. A meta-classifier model was used in this research. This model consists of 3 base classifiers constructed using the k-nearest neighbour, decision tree, and naïve Bayesian algorithms. The naïve Bayesian algorithm was also used as the meta-level algorithm to combine the base classifier predictions to produce the final classifier. Results from this research show that when a meta-classifier was deployed in series with the Bank’s existing fraud detection algorithm a 24% to 34% performance improvement was achieved resulting in $1.8 to $2.6 million cost savings per year.

The only aeroballistic laboratory of Turkey is the Flight Mechanics Laboratory, FML of T&Uuml / BITAK - SAGE. In FML, flight profiles of projectiles are reconstructed using their tear marks on paper sheets, called yaw cards. Tear marks are created on yaw cards as projectiles pass through them. These yaw cards are tightly stretched to metal frames which are positioned normal to the direction of projectile flight path. The use of yaw cards for flight profile reconstruction is a low cost and reliable solution. However, the yaw card method requires a heavy workload for the analysis of tear marks. Yaw cards collected from the frames are fed through an optical scanner and converted to digital images. These digital images are then processed by operators to calculate the projectile&rsquo / s flight position and angles. To automate this manual process, an algorithm is developed by using histogram based segmentation techniques, custom search algorithms, and Radon transform. This algorithm identifies and locates the projectile marks and finds angle of attack, angle of side slip and roll angle at each frame station by conducting the necessary transformations. Using this automated algorithm, a considerable amount of improvement is accomplished in terms of both decreasing the analysis time and increasing the accuracy of flight profile reconstruction.

Thesis (Ph. D.)--University of Texas Southwestern Medical Center at Dallas, 2006. / Vita. Includes bibliographical references (p. 170-180).

Thesis (M.A.)--University of Toronto, 2004. / Includes bibliographical references (leaves [33]-40).

Zugl.: Augsburg, Universiẗat, Diss., 2008.

Thesis (Ph. D.)--Cornell University, August, 2007. / Vita. Includes bibliographical references (leaves 196-214).

Thesis (M.P.H.M.)--Mahidol University, 1988.

Thesis--University of Wisconsin--Madison. / Typescript. Vita. Description based on print version record. Includes bibliographical references (leaves 231-237).

Thèse (M.Ps.)--Université Laval, 2004. / Bibliogr.: f. 48-55. Publié aussi en version électronique.

Thesis (Ph. D.)--University of Virginia, 1996. / Includes bibliographical references (leaves 65-70).