room 080 Roman Kern is the head of Knowledge Discovery at the Know-Center (competence centre for Big Data analytics and data-driven business) and works at the Institute for Interactive Systems and Data Science at the Technical University of Graz. He was awarded his Ph.D. by the Graz University of Technology. Before working in research he gained experience in industry projects as project manager, software architect and software engineer ranging from big and medium sized companies to small start-ups.
Roman's research interest are multi-disciplinary and include Natural Language Processing, Machine Learning and Information Retrieval - with a focus on Data Science and Big Data Analytics. He applies these methods in fields like Scientific Publication Mining, Intelligent Transportation Systems, and Smart Production. His work includes writing of proposals for national and international research projects; he served as coordinator, work package lead, scientist in charge and national contact point for numerous research projects, ranging from small national projects to big European projects.
In his work at the Know-Center his mission is to close the gap between science and industry via applied research projects, consulting and knowledge transfer. The demand in skills from the real world application scenarios also influences his teaching activities and shape the Computer Science curriculum of the Graz University of Technology.
List of courses at the Graz University of Technology.
List of upcoming dates for presentation (Bachelor & Master).
- Mo, 04.03., 14:00 - 15:30, HS i8 (fully booked)
Feel free to use the Latex thesis template (based on input from Karl Voit and Keith Andrews):
Collection of a few helpful tips for Master's thesis, provided by Annemarie Harzl.
List of open topics together with their domain
Deep learning for classification of pictures of ships in the Adriatic sea
Ship classification from images#deep-learning
Classification of exisiting non-linear relationships in data sets (e.g., log, cosine, …)
Comparison of maximum correlation vs. deep learning#data-science, #deep-learning
Study the copy'n'paste of informance in journalistic text (information diffusion)
Can one detect the author just on the writing of a text?
Including scanned in documents
Text reuse in the journalistic domain#text-mining, #nlp
Authorship attribution based on style information#text-mining, #nlp
Table extraction from PDF documents#document-mining
Learn about the inner working of classification algorithms
Learn about how a to derive measures for decision tress
PCA can be used for dimensionality reduction based on linear co-variance, extend this concept to non-linear relationships
Identify ranges where two variables have a high maximal correlation
Evaluation of an existing algorihtm, in an query-expansion setting
Are closed frequent patterns suited for text classification?
Combine time series forecast for efficient outlier detection
Keep track of recently important features for effective feature selection
e.g., use a deep learning model to restrict the search space of evolutionary algorithms (looks like sine-wave)
Can reinforcement learning automate the task of data science?
Can we improve the back-propagation by implicit clustering of activations/gradients?
When should be we use a specific cluster evaluation measure, how much bias do they have?
Classification via minimal hyperspheres#machine-learning
One-class decision tree#machine-learning, #data-science
Non-linear correlation (e.g., distance correlation) for dimensionality reduction#data-science, #machine-learning
Piecewise maximal correlation#data-science
Evaluation of FP-Growth#pattern-mining, #data-science
Closed frequent pattern mining for multi-label classification#pattern-mining, #nlp, #machine-learning
Streaming RANSAC for outlier detection in time series#timeseries, #data-science
Boruta for streaming data-augmentation#data-science, #machine-learning
Speed-up symbolic regression with deep learning methods#deep-learning
Deep reinforcement learning for black-box modelling#reinforcement-learning, #deep-learning, #data-science
Deep clustering for partitioned error propagation#deep-learning, #machine-learning
Comparison of intrinsic cluster evaluation measures#data-science, #machine-learning
Mirco-services vs. monolithic architecture
e.g., using kubernetes
Best practice in software development #software-architecture, #big-data
Scalability of timeseries management and processing pipelines#software-architecture, #timeseries
e.g., identify pages about emergent technologies not labelled as such
Classification of Wikipedia Pages#machine-learning, #data-science
e.g., using the microphone of the mobile phone to detect Haupplatz, Bahnhof, …
Mobile app for place detection#software-development, #data-science
Please have a look at my Mendeley page or my Google Scholar page for a full list of publications.
List of scientific workshops.