-

-

 

Needless to say that, for any act of team organisation like task management the importance of having an overview of the activities and the strength of the team members in different fields is of no doubt. As elements of task management, the features of task board management and assignee recommender cover the former and the latter respectively. Through task board management, the organiser tracks the sequence of the tasks and the arrangement of the assigned tasks, so he or she could minimize the idle status of the team. To this end, the task should be distributed optimally among the developers based on their level of desirability. This implicitly brings the necessity of a mechanism to evaluate their desirability quantitatively which is normally assessed intuitively and qualitatively. As a result, through more rational assignment of the tasks among the developers based on their quantitative desirability, more tasks would be accomplished in the same specific sprint. Therefore, the effectiveness of the team would be improved. In this thesis we develop a light weight assignee recommendation and association algorithm, which is integrated within an android application for task management

A new approach to create datasets for classification of different nuts, considering the inner threads and camera angle. The challenge is to preserve the size information of the small part, using a fixed camera and fixed distance to that, while pointing out the camera lens to the nut in specific angles that it can capture its threads, length and overall shape. Using this setup and also other pictures, you will train a model with convolutional neural network to classify different nuts.

Studying different methods to visually detect the damages on metallic surfaces, from simple background subtraction to supervised and unsupervised machine learning approaches, and performing an experiment to compare the results. 

Creating dataset for the diatoms (small algae which can be found in all waters), train a model using convolutional neural nets to classify them, and compare the results with the traditional methods.

Study the popular offline open-source speech recognition systems and training/tuning them in order to compare with the cloud-based solutions

Studying methods to create datasets from 3D models and use them in training a model for small parts classifier. This method will be compared with the normal manually photographing approach in terms of usability of dataset creation and performance of the classifiers.

Creating a model to detect damaged small parts (screws, bolts, nuts, pins, washers, etc.) in overhauling industrial machineries, using deep learning and convolutinal neural networks

Since the small parts and fasteners are scale-variant (which means that with scaling them we'll end up having another small part), classification of them needs a fixed camera to ensure that the distance between the camera lens and the object is always fixed. However, using two or more cameras, we are able to get the depth information of the objects, including their size. In this bachelor thesis, you will work on getting these depth images, using two or more cameras. The true challenge is to consider the small parts characteristics (their small size and their shiny surface) and find solutions to handle them.

Implementing a Speech Recognition System, which can learn from the user input. The idea is to build an application to be able to monitor the system performance and give feedback regarding the recognized phrases. The samples, together with the corrected labels, will be used to retrain the model to improve the performance.

An expert level know-how is considered as one of the most important factors in dealing with overhauling processes. What has been already done and what has to be done now? The aim of this master thesis is to be able to understand the process, the already done tasks and still to-do tasks using the computer vision and machine learning based approaches. The challenge is to come up with a proper representation of the whole process to the system that helps us to fetch the needed information.

Study the current approaches to get the right dataset for deep learning processes and implementation of an application for automatic data augmentation to enrich the training dataset