Visualization of machine learning data for radio networks : A case study at Ericsson
Abstract: This thesis presents a method to develop a visualization software for time-varying and geographic-based data. The machine learning team at Ericsson has collected data from their machine learning algorithms. The data set contains timestamped and geographic information. To have a better understanding of the result made by the machine learning algorithms, it is important to understand the pattern of the data. It is hard to see the pattern of the data by only looking at the raw data set, and data visualization software will help the users to have a more intuitive view of the data. To choose a suitable GUI library, three common GUI libraries were compared. The Qt framework was chosen as the GUI library and development framework because of its wide-range support to user interface design. Animation is the main method to visualize the data set. The performance evaluation of the software shows that it handles the back-end data efficiently, renders fast in the front-end and has low memory and CPU usage. The usability testing indicates that the software is easy to use. In the end, the thesis compares its method to a previous method, developed in R. The comparison shows that even though the old method is easier to develop, it has worse performance.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)