Data Analytics

Data analysis describes the process to convert data into knowledge. In this area, CC IRML is working on the analysis of time series data, the use of Deep Learning for large amounts of data (Big Data) and recommendation systems, that need to give recommendations in real-time.

Time Series: Our ‘time series’ team analyses temporal data, which can be found in domains as diverse as smart homes and vehicle development. In general, a time series is a sequence of data points, measured at successive points in time and spaced at uniform time intervals. Our team is primarily concerned with time series mining, including segmentation, classification, and clustering of temporal data. Many algorithms for these tasks depend upon the choice of distance measure, which is used for the pairwise similarity comparisons of sequences. One important application for time series analysis is the optimization of vehicle engines with regard to exhaust emission.  We have developed a novel approach, which identifies time series representatives that best comprehend the recurring temporal patterns contained in vehicular sensor data recording during car drives. Time series representatives that comprise frequently recurring driving behavior are used by VW to run realistic emission simulations.  

Contact person: Stephan Spiegel

Deep Learning: The "Deep Learning"-Cluster studies deep architectures of artificial neural networks capable of learning representations, concepts and abstractions from complex data applied on industrial application problems in the context of big data. For this, we consider multi-layer perceptrons, convolutional networks, autoencoders, Boltzman machines,and recurrent networks as basic models, Theoretical contributions investigate deep learning architecture for non-Euclidean data.

Contact person: Brijnesh Johannes Jain