Characterization of texture in image of skin lesions by support vector machine

Due to the increased incidence of skin cancer, computational methods based on intelligent approaches have been developed to aid dermatologists in the diagnosis of skin lesions. This paper proposes a method to classify texture in images, since it is an important feature for the successfully identification of skin lesions. For this is defined a feature vector, with the fractal dimension of images through the box-counting method (BCM), which is used with a SVM to classify the texture of the lesions in to non-irregular or irregular. With the proposed solution, we could obtain an accuracy of 72.84%. © 2012 AISTI.

Desenvolvimento de um objeto de aprendizagem para análise de sistemas de energia elétrica

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Ambiente data cleaning: suporte extensível, semântico e automático para análise e transformação de dados

Pós-graduação em Ciência da Computação - IBILCE

Significações e sentimentos sobre o erro: alunos que frequentam a sala de apoio à aprendizagem

Pós-graduação em Psicologia - FCLAS

HOW FAR do WE GET USING MACHINE LEARNING BLACK-BOXES?

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Evaluation of Bone Insertion Level of Support Teeth in Class I Mandibular Removable Partial Denture Associated With an Osseointegrated Implant: A Study Using Finite Element Analysis

Purpose: This study evaluated the influence of distal extension removable partial denture associated with implant in cases of different bone level of abutment tooth, using 2D finite element analysis.Materials and Methods: Eight hemiarch models were simulated: model A-presenting tooth 33 and distal extension removable partial denture replacing others teeth, using distal rest connection and no bone lost; model B-similar to model A but presenting distal guide plate connection; model C-similar to model A but presenting osseointegrated implant with ERA retention system associated under prosthetic base; model D-similar to model B but presenting osseointegrated implant as described in model C; models E, F, G, and H were similar to models A, B, C, and D but presenting reduced periodontal support around tooth 33. Using ANSYS 9.0 software, the models were loaded vertically with 50 N on each cusp tip. For results, von Mises Stress Maps were plotted.Results: Maximum stress value was encountered in model G (201.023 MPa). Stress distribution was concentrated on implant and retention system. The implant/removable partial denture association decreases stress levels on alveolar mucosa for all models.Conclusions: Use of implant and ERA system decreased stress concentrations on supporting structures in all models. Use of distal guide plate decreased stress levels on abutment tooth and cortical and trabecular bone. Tooth apex of models with reduced periodontal support presented increased stress when using distal rest. (Implant Dent 2011;20:192-201)

Information Visualization to support decision making in the context of distance learning: A study with VLE TelEduc

Digital data sets constitute rich sources of information, which can be extracted and evaluated applying computational tools, for example, those ones for Information Visualization. Web-based applications, such as social network environments, forums and virtual environments for Distance Learning, are good examples for such sources. The great amount of data has direct impact on processing and analysis tasks. This paper presents the computational tool Mapper, defined and implemented to use visual representations - maps, graphics and diagrams - for supporting the decision making process by analyzing data stored in Virtual Learning Environment TelEduc-Unesp. © 2012 IEEE.

Learning kernels for support vector machines with polynomial powers of sigmoid

In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets.

Aquatic weed automatic classification using machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Efficient supervised optimum-path forest classification for large datasets

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Influence of Implant Inclination Associated With Mandibular Class I Removable Partial Denture

The aim of this study was to use two-dimensional finite element method to evaluate the displacement and stress distribution transmitted by a distal extension removable partial denture (DERPD) associated with an implant placed at different inclinations (0, 5, 15, and 30 degrees) in the second molar region of the edentulous mandible ridge. Six hemimandibular models were created: model A, only with the presence of the natural tooth 33; model B, similar to model A, with the presence of a conventional DERPD replacing the missing teeth; model C, similar to the previous model, with a straight implant (0 degrees) in the distal region of the ridge, under the denture base; model D, similar to model C, with the implant angled at 5 degrees in the mesial direction; model E, similar to model C, with the implant angled at 15 degrees in the mesial direction; and model F, similar to ME, with the implant angled at 30 degrees in the mesial direction. The models were created with the use of the AutoCAD 2000 program (Autodesk, Inc, San Rafael, CA) and processed for finite element analysis by the ANSYS 8.0 program (Swanson Analysis Systems, Houston, PA). The force applied was vertical of 50 N on each cusp tip. The results showed that the introduction of the RPD overloaded the supporting structures of the RPD and that the introduction of the implant helped to relieve the stresses of the mucosa alveolar, cortical bone, and trabecular bone. The best stress distribution occurred in model D with the implant angled at 5 degrees. The use of an implant as a support decreased the displacement of alveolar mucosa for all inclinations simulated. The stress distribution transmitted by the DERPD to the supporting structures was improved by the use of straight or slightly inclined implants. According to the displacement analysis and von Mises stress, it could be expected that straight or slightly inclined implants do not represent biomechanical risks to use.

Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Uma proposta de material didático baseado nas espécies de Vochysiaceae existentes em uma trilha no cerrado de Bauru - SP

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The application of preprocessing and cutting plane techniques for a class of production planning problems

This paper investigates properties of integer programming models for a class of production planning problems. The models are developed within a decision support system to advise a sales team of the products on which to focus their efforts in gaining new orders in the short term. The products generally require processing on several manufacturing cells and involve precedence relationships. The cells are already (partially) committed with products for stock and to satisfy existing orders and therefore only the residual capacities of each cell in each time period of the planning horizon are considered. The determination of production recommendations to the sales team that make use of residual capacities is a nontrivial optimization problem. Solving such models is computationally demanding and techniques for speeding up solution times are highly desirable. An integer programming model is developed and various preprocessing techniques are investigated and evaluated. In addition, a number of cutting plane approaches have been applied. The performance of these approaches which are both general and application specific is examined.

Development of an open case-based decision-support system for diagnosis in oral pathology

Making diagnoses in oral pathology are often difficult and confusing in dental practice, especially for the lessexperienced dental student. One of the most promising areas in bioinformatics is computer-aided diagnosis, where a computer system is capable of imitating human reasoning ability and provides diagnoses with an accuracy approaching that of expert professionals. This type of system could be an alternative tool for assisting dental students to overcome the difficulties of the oral pathology learning process. This could allow students to define variables and information, important to improving the decision-making performance. However, no current open data management system has been integrated with an artificial intelligence system in a user-friendly environment. Such a system could also be used as an education tool to help students perform diagnoses. The aim of the present study was to develop and test an open case-based decisionsupport system.Methods: An open decision-support system based on Bayes' theorem connected to a relational database was developed using the C++ programming language. The software was tested in the computerisation of a surgical pathology service and in simulating the diagnosis of 43 known cases of oral bone disease. The simulation was performed after the system was initially filled with data from 401 cases of oral bone disease.Results: the system allowed the authors to construct and to manage a pathology database, and to simulate diagnoses using the variables from the database.Conclusion: Combining a relational database and an open decision-support system in the same user-friendly environment proved effective in simulating diagnoses based on information from an updated database.