Testability of robotic applications is difficult due to several reasons including the battery limitations of mobile robots, hardware wear and tear, inadequate number of the robots, etc.

A multi-word expression (MWE) is a lexeme (term) made up of a sequence of two or more lexemes that has properties that are not predictable from the properties of the individual lexemes or their normal mode of combination. In short, a MWE is like an idiom. In several languages, there are built-in dictionaries of MWEs. In this project, we aim at forming a dictionary (lexicon) of MWEs for Turkish.

Given a text document and a predetermined set of classes, text classification (categorization) is the task of finding the correct class of the document. Centroid-based classification is a simple type of classification in which the given document is assigned to a class based on the similarity between the document and the centroids of the classes. In this project, we begin with reading the paper “A New Centroid Based Classification Model for Text Categorization”, Liu, C., Wang, W., Tu, G., Xiang, Y. and Konan, M., 2016.

In this two-terms project, we aim at identifying some architectural properties of buildings using machine learning techniques. The properties may be the architect of the building, the era of the building, the architectural type of the building, etc. First a number of photographs of the buildings will be compiled. Then they will be analyzed using the OpenCV (Open Source Computer Vision) library and important features will be extracted. Then a machine learning method (artificial neural network) will be applied to determine the desired properties.