• German

Main Navigation

Collaborative Research Center SFB 876 - Providing Information by Resource-Constrained Data Analysis

The collaborative research center SFB876 brings together data mining and embedded systems. On the one hand, embedded systems can be further improved using machine learning. On the other hand, data mining algorithms can be realized in hardware, e.g. FPGAs, or run on GPGPUs. The restrictions of ubiquitous systems in computing power, memory, and energy demand new algorithms for known learning tasks. These resource bounded learning algorithms may also be applied on extremely large data bases on servers.

Best Paper Awards for Jens Teubner in projects A2 and C5

At BTW 2017 in Stuttgart, Jens Teubner received the Best Paper Award for his Paper "Efficient Storage and Analysis of Genome Data in Databases". He developed this work together with the University Magdeburg, Bayer AG, and TU Berlin.

The paper discusses technique to store genome data efficiently in a relational database. This makes the flexibility and performance of modern relational database engines accessible to the analysis of genome data.

At the same day, Stefan Noll, a Master Student of Jens Teubner, received the Best Student Paper Award ath BTW 2017 in Stuttgart. His contribution "Energy Efficiency in Main Memory Databases" reports on the key results of his Master Thesis. The Master Thesis was prepared within the DBIS Group and in the context of the Collaborative Research Center SFB876, Project A2.

His paper shows how the energy efficiency of a database system can be improved by balancing the compute capacity of the system with the available main memory bandwidth. To this end, he proposes to use Dynamic Voltage and Frequency Scaling (DVFS) as well as the selective shutdown of individual cores.

Abstract: "Efficient Storage and Analysis of Genome Data in Databases"
Genome-analysis enables researchers to detect mutations within genomes and deduce their consequences. Researchers need reliable analysis platforms to ensure reproducible and comprehensive analysis results. Database systems provide vital support to implement the required sustainable procedures. Nevertheless, they are not used throughout the complete genome-analysis process, because (1) database systems suffer from high storage overhead for genome data and (2) they introduce overhead during domain-specific analysis. To overcome these limitations, we integrate genome-specific compression into database systems using a specialized database schema. Thus, we can reduce the storage overhead to 30%. Moreover, we can exploit genome-data characteristics during query processing allowing us to analyze real-world data sets up to five times faster than specialized analysis tools and eight times faster than a straightforward database approach.

Resource-aware Machine Learning - International Summer School 2017


Big data in machine learning is the future. But how to deal with data analysis and limited resources: Computational power, data distribution, energy or memory? From September 25th to 28th, TU Dortmund University, Germany, hosts the 4th summer school on resource-aware machine learning. Further information and online registration at: http://sfb876.tu-dortmund.de/SummerSchool2017

Topics of the lectures include: Machine learning on FPGAs, Deep Learning, Probabilistic Graphical Models and Ultra Low Power Learning.

Exercises help bringing the contents of the lectures to life. The PhyNode low power computation platform was developed at the collaborative research center SFB 876. It enables sensing and machine learning for transport and logistic scenarios. These devices provide the background for hands-on experiments with the nodes in the freshly built logistics test lab. Solve prediction tasks under very constrained resources and balance accuracy versus energy.

The summer school is open to advanced graduate, post-graduate students as well as industry professionals from across the globe, who are eager to learn about cutting edge techniques for machine learning with constrained resources.

Excellent students may apply for a student grant supporting travel and accommodation. Deadline for application is July 15th.

more ...

B2-Project PAMONO publication selected as leading article for current Sensors journal issue

Sensors Journal Cover

The most recent B2-Project publication "Application of the PAMONO-sensor for Quantification of Microvesicles and Determination of Nano-particle Size Distribution" has been selected by the journal Sensors as the leading article for their current issue. The article is available via Open Access on the journals web site. The article was co-authored by Alexander Schramm, project leader of SFB-project C1.


The PAMONO-sensor (plasmon assisted microscopy of nano-objects) demonstrated an ability to detect and quantify individual viruses and virus-like particles. However, another group of biological vesicles—microvesicles (100–1000 nm)—also attracts growing interest as biomarkers of different pathologies and needs development of novel techniques for characterization. This work shows the applicability of a PAMONO-sensor for selective detection of microvesicles in aquatic samples. The sensor permits comparison of relative concentrations of microvesicles between samples. We also study a possibility of repeated use of a sensor chip after elution of the microvesicle capturing layer. Moreover, we improve the detection features of the PAMONO-sensor. The detection process utilizes novel machine learning techniques on the sensor image data to estimate particle size distributions of nano-particles in polydisperse samples. Altogether, our findings expand analytical features and the application field of the PAMONO-sensor. They can also serve for a maturation of diagnostic tools based on the PAMONO-sensor platform.

more ...

Show news archive
Newsletter RSS Twitter