Note that these assignments are not current any more. They are retained here to provide an idea of possible assignments.
On November 11th, 2016, the IEEE Standards Association has officially published the XES Standard as IEEE Std 1849TM-2016: IEEE Standard for eXtensible Event Stream (XES) for Achieving Interopability in Event Logs and Event Streams. The IEEE Task Force on Process Mining has been driving the standardization process for over six years, because the standard allows for the exchange of event data between different process mining tools.
Through the XES Standard, event data to be transported from the location where it was generated to the location where it can be stored and analyzed, without losing semantics. The XES Standard enforces that this transport and storage is done in a standardized way, that is, in a way that is clear and well-understood. Next to providing a standardized syntax and semantics, the XES Standard also allows for extensions, e.g., adding cost information or domain specific attributes to events.
Sales of electric vehicles are on the rise. This poses a number of challenges for aging grids all across Europe by introducing new peak loads on already stressed grids. The problem is exacerbated by an increasing contribution of renewable energy sources. At the same time, EVs can also form part of the solution as mobile loads which offer flexibility to the grid by offering demand side management. In this context, it is necessary however to balance a number of (often competing) constraints foremost of which is meeting user specifications. These additional constraints include maximal self-consumption of renewable generation (e.g. solar), improving grid quality, taking advantage of market signals directly or by providing flexibility of consumption etc.
The optimization problem is tractable for a single vehicle but becomes more convoluted when applied to many (hundreds or even thousands of) vehicles, each with its own set of constraints. Furthermore, it is problematic both from a logistics (providing communication framework) and privacy (sharing user data) perspective to do completely centralized control. A number of techniques have been proposed to solve for this problem in a general setting ranging from classical optimization algorithms to meta-heuristics, distributed constrained optimization and multi agent reinforcement learning.
Together with KPMG’s department on sustainability, we are looking for a Master student interested in text- and datamining. Part of KPMG’s job is to judge yearly reports on the topic of sustainability. This task is currently done by manually assessing the sentiment of a yearly report against the actual measureable sustainability values to see if the report is too optimistic or too pessimistic.
The goal of this project is to see if this can be done automatically through text- and datamining. KPMG has a large body of test and training data available for the student to start comparing reports. In depth knowledge of both supervised and unsupervised techniques will be needed for this project.
KPMG is a highly competitive company. Therefore, they are looking for a CSE or BIS Master student on track for a Cum-Laude (i.e. an average grade of 8). Furthermore, the student should have a strong interest in datamining. A selection process within KPMG is part of the hiring procedure.
Together with QPR, we are looking for a Master student interested in data-aware process mining.
The goal of this project is to do a case study with data provided by QPR. This data will be made available in their native data format. The case study will investigate what we can learn from the data using both QPR ProcessAnalyzer and the data-aware techniques as available in ProM.
As a part of the project, the Master student needs to implement scripts that convert the native QPR data format to the XES data format (as used by ProM) and back. For this reason, some programming skills are required.