Comparison Between Micro- and Macrosurgical Techniques for the Treatment of Localized Gingival Recessions Using Coronally Positioned Flaps and Enamel Matrix Derivative

Background: The aim of this study is to compare the macro- and microsurgery techniques for root coverage using a coronally positioned flap (CPF) associated with enamel matrix derivative (EMD). Methods: Thirty patients were selected for the treatment of localized gingival recessions (GRs) using CPF associated to EMD. Fifteen patients were randomly assigned to the test group (TG), and 15 patients were randomly assigned to the control group (CG). The microsurgical approach was performed in the TG, and the conventional macrosurgical technique was performed in the CG. The clinical parameters evaluated before surgery and after 6 months were GR, probing depth, relative clinical attachment level, width of keratinized tissue (WKT), and thickness of keratinized tissue (TKT). The discomfort evaluation was performed 1 week postoperative. Results: There were no statistically significant differences between groups for all parameters at baseline. At 6 months, there was no statistically significant difference between the techniques in achieving root coverage. The percentage of root coverage was 92% and 83% for TG and CG, respectively. After 6 months, there was a statistically significant increase of WKT and TKT in TG only. Both procedures were well tolerated by all patients. Conclusions: The macro- and microsurgery techniques provided a statistically significant reduction in GR height. After 6 months, there was no statistically significant difference between the techniques regarding root coverage, and the microsurgical technique demonstrated a statistically significant increase in WKT and TKT. J Periodontol 2010;81:1572-1579.

Combining meta-learning and search techniques to select parameters for support vector machines

Support Vector Machines (SVMs) have achieved very good performance on different learning problems. However, the success of SVMs depends on the adequate choice of the values of a number of parameters (e.g., the kernel and regularization parameters). In the current work, we propose the combination of meta-learning and search algorithms to deal with the problem of SVM parameter selection. In this combination, given a new problem to be solved, meta-learning is employed to recommend SVM parameter values based on parameter configurations that have been successfully adopted in previous similar problems. The parameter values returned by meta-learning are then used as initial search points by a search technique, which will further explore the parameter space. In this proposal, we envisioned that the initial solutions provided by meta-learning are located in good regions of the search space (i.e. they are closer to optimum solutions). Hence, the search algorithm would need to evaluate a lower number of candidate solutions when looking for an adequate solution. In this work, we investigate the combination of meta-learning with two search algorithms: Particle Swarm Optimization and Tabu Search. The implemented hybrid algorithms were used to select the values of two SVM parameters in the regression domain. These combinations were compared with the use of the search algorithms without meta-learning. The experimental results on a set of 40 regression problems showed that, on average, the proposed hybrid methods obtained lower error rates when compared to their components applied in isolation.