Emotion analysis is an important field of study, with many applications for security, financial, and politician. Despite beinga subjective branch of study, emotion analysis can be simulated by Machine Learning algorithms that are trained for this purpose, throughcataloged audio datasets, they can recognize patterns in these media that could be related to corresponding emotion. Neural NetworkAlgorithms are able to work on the recognition of these emotions, with a focus only on audio, known as Speech Emotion Recognition(SER). Neural Network Algorithms generally obtain unequal averages of referring results such as recognition of emotions when applied todifferent audio datasets. This research evaluates a Data Augmentation method called Slide Window, which generates more data samplesin order to increase the averages of classification rates. The method has been applied to three public datasets: EMO-DB, SAVEE, and RAVEDESS. The experiments have shown effectiveness in the increasing of the recognition rates of about to 11.95% on the EMO-DBbase, 22.76% on SAVEE, and 18.82% on RAVEDESS when compared to other approaches in the literature.

Theme: Analysis of geospatial data to identify economic, social and technological factors for the structure of implantation of innovative companies of technological base in the State of Tocantins. Objective: To analyze the impact of economic, social and technological indicators in the process of creating innovative environments for companies of technological base in the context of the State of Tocantins using geospatial data presented in a computer system for visualizing economic, social and technological information called VICS. Method: The inductive approach was adopted based on the observation of technological factors of innovation references in Tocantins for replication to other potential locations, applying bibliographic research, to survey the state of the existing art, and exploratory, to collect data and discoveries with descriptive and quantitative procedures for the interpretation of the discovered data, resulting in the structuring of the methodology in five stages: search, collection, extraction, crossing and data analysis. Results: It was identified that economic, social and technological indicators raised in this work influence the emergence and consolidation of favorable environments for the implantation and maintenance of companies of technological base in Tocantins, highlighting that such evidence was obtained through the VICS system, which provides a visual analysis of the geospatial information of the State of Tocantins. Methodological contributions: Based on the principles of Analysis and Data Mining, a methodology with an inductive approach was developed, which, organized in five stages, favors the design of mechanisms for visualizing indicators, allowing economic, social and technological aspects to be observed and considered in decision making.