| Grant number: | 15/24652-2 |
| Support Opportunities: | Scholarships abroad - Research Internship - Scientific Initiation |
| Start date: | February 01, 2016 |
| End date: | May 31, 2016 |
| Field of knowledge: | Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques |
| Principal Investigator: | Moacir Antonelli Ponti |
| Grantee: | Mateus Riva |
| Supervisor: | Teófilo Emidio de Campos |
| Host Institution: | Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil |
| Institution abroad: | University of Surrey, England |
| Associated to the scholarship: | 14/04889-5 - Incremental supervised learning in optimum-path forests, BP.IC |
Abstract Anomaly detection is the problem of finding patterns with an unexpected behavior. Classification-based techniques are usually a good choice in this scenario, but require sufficient labeled data from both normal and abnormal classes. In this project we focus on a method which models relationship among examples in the feature space, by using a optimum path forest (OPF). This method interprets the examples (observations) as the vertices of a graph.We propose an investigation of anomaly detection based on the optimum path trees formed by the OPF algorithm, by taking advantage of the properties of this model, that does not assume a fixed class distribution and allow for some degree of overlap between classes. The idea behind it is to capture perturbations on the trees after including a new example, and detecting it as an anomaly if the tree for which the example is assigned has significantly changed its distribution. (AU) | |
| News published in Agência FAPESP Newsletter about the scholarship: | |
| More itemsLess items | |
| TITULO | |
| Articles published in other media outlets ( ): | |
| More itemsLess items | |
| VEICULO: TITULO (DATA) | |
| VEICULO: TITULO (DATA) | |