Intelligent Data Analytics

Data is a central phenomenon in our digital information society. It effects our production and economic systems and offers enormous potential to positively influence our behavior and environment in society, business and science. Developing new machine learning methods for intelligent data analysis that can automatically extract and access knowledge in data-intensive environments to create economic value and new business opportunities is one of the central goals of the Intelligent Data Analysis research group.

Intelligent data analytic methods are a central component in many industrial contexts for gaining usable insights into complex data sets and their associated processes. Therefore, it is even more important to adapt both existing and new analysis methods to the corresponding application domains and requirements in order to target and successfully implement profitable information. The development of intelligent methods for (automatic) data analysis is a central step towards a user-centered data analysis process, in which data can be analyzed together with users and with the help of suitable algorithms.

Intelligent solutions for data analysis

We design and develop data-centric analytic solutions to analyze both large historical data sets and real-time data streams. In doing so, our focus is not only solely on the data, but is also particularly oriented towards the needs of the user and the possibilities of the underlying technologies. Closely related with the departments of Fraunhofer FIT, we can develop efficient analysis solutions for complex problems, using state-of-the-art methods from the fields of Machine Learning, Big Data and Data Science.

What does Fraunhofer FIT offer you in the area of Intelligent Data Analysis?

We support you during the planning and implementation of projects in the field of data analysis. In addition to the development and integration of methods and technologies for data analysis, this also includes training of employees and consultation. Benefit from our experience in the collection, processing and analysis of data and implement your ideas and concepts together with us. Thanks to innovative methods and technologies, together with us you will learn about the potential of your data and develop strategies for using it.

Expertise

We aim to solve real-world problems with scientific excellence. We transfer state-of-the-art research from the fields of data science, data analytics, machine learning, artificial intelligence into application problems.

Type of data analytics

  • Descriptive – What happened?​
  • Diagnostic – Why did it happen?​
  • Predictive – What will happen?
  • Prescriptive – How can we achieve it?​

Our research topics include​

  • Exploratory Data Analysis​
  • Time Series Analysis​
  • Machine Learning and Deep Learning​
  • Anomaly detection​
  • Computer Vision​
  • Natural Language Processing​
  • Large Language Models

Publications

Jahr
Year
Titel/Autor:in
Title/Author
Publikationstyp
Publication Type
2023 A Knowledge Graph for Query-Induced Analyses of Hierarchically Structured Time Series Information
Graß, Alexander; Beecks, Christian; Chala, Sisay Adugna; Lange-Bever, Christoph; Decker, Stefan
Konferenzbeitrag
Conference Paper
2022 Dynamically Self-adjusting Gaussian Processes for Data Stream Modelling
Hüwel, Jan David; Haselbeck, Florian; Grimm, Dominik; Beecks, Christian
Konferenzbeitrag
Conference Paper
2022 GitSchemas: A Dataset for Automating Relational Data Preparation Tasks
Döhmen, Till; Hulsebos, Madelon; Beecks, Christian; Schelter, Sebastian
Konferenzbeitrag
Conference Paper
2022 A Comparative Performance Analysis of Fast K-Means Clustering Algorithms
Beecks, Christian; Berns, Fabian; Hüwel, Jan David; Linxen, Andrea; Schlake, Georg Stefan; Düsterhus, Tim
Konferenzbeitrag
Conference Paper
2022 Analysis of Extracellular Potential Recordings by High-Density Micro-electrode Arrays of Pancreatic Islets
Hüwel, Jan David; Gresch, Anne; Berger, Tim; Düfer, Martina; Beecks, Christian
Konferenzbeitrag
Conference Paper
2022 Automated Model Inference for Gaussian Processes
Berns, F.; Hüwel, J.; Beecks, C.
Zeitschriftenaufsatz
Journal Article
2022 Tracing Patterns in Electrophysiological Time Series Data
Hüwel, Jan; Gresch, Anne; Berns, Fabian; Koch, Ruben; Düfer, Martina; Beecks, Christian
Konferenzbeitrag
Conference Paper
2022 Evaluating the Lottery Ticket Hypothesis to Sparsify Neural Networks for Time Series Classification
Schlake, Georg Stefan; Hüwel, Jan David; Berns, Fabian; Beecks, Christian
Konferenzbeitrag
Conference Paper
2022 Sample-based Kernel Structure Learning with Deep Neural Networks for Automated Structure Discovery
Graß, Alexander; Döhmen, Till; Beecks, Christian
Konferenzbeitrag
Conference Paper
2021 3CS algorithm for efficient Gaussian process model retrieval
Berns, F.; Schmidt, K.; Bracht, I.; Beecks, C.
Konferenzbeitrag
Conference Paper
2021 knowlEdge Project - Concept, Methodology and Innovations for Artificial Intelligence in Industry 4.0
Alvarez-Napagao, Sergio; Ashmore, Boki; Barroso, Marta; Barrué, Cristian; Beecks, Christian; Berns, Fabian; Bosi, Ilaria; Chala, Sisay Adugna; Ciulli, Nicola; Garcia-Gasulla, Marta; Graß, Alexander; Ioannidis, Dimosthenis; Jakubiak, Natalia; Köpke, Karl; Lämsä, Ville; Megias, Pedro; Nizamis, Alexandros; Pastrone, Claudio; Rossini, Rosaria; Sànchez-Marrè, Miquel; Ziliotti, Luca
Konferenzbeitrag
Conference Paper
2020 Automatic Gaussian Process Model Retrieval for Big Data
Berns, F.; Beecks, C.
Konferenzbeitrag
Conference Paper
2020 Large-scale retrieval of bayesian machine learning models for time series data via gaussian processes
Berns, F.; Beecks, C.
Konferenzbeitrag
Conference Paper
2020 Towards large-scale gaussian process models for efficient bayesian machine learning
Berns, F.; Beecks, C.
Konferenzbeitrag
Conference Paper
2019 A New Approach for Efficient Structure Discovery in IoT
Berns, F.; Schmidt, K.; Grass, A.; Beecks, C.
Konferenzbeitrag
Conference Paper
2019 Data analysis and visualization framework in the manufacturing decision support system of COMPOSITION project
Vafeiadis, T.; Kalatzis, D.; Nizamis, A.; Ioannidis, D.; Apostolou, K.; Metaxa, I.N.; Charisi, V.; Beecks, C.; Insolvibile, G.; Pardi, M.; Vergori, P.; Tzovaras, D.
Zeitschriftenaufsatz
Journal Article
2019 Unsupervised anomaly detection in production lines
Graß, Alexander; Beecks Christian; Carvajal Soto, Jose Angel
Konferenzbeitrag
Conference Paper
2019 Machine Learning for Enhanced Waste Quantity Reduction: Insights from the MONSOON Industry 4.0 Project
Beecks, Christian; Devasya, Shreekantha; Schlutter, Ruben
Konferenzbeitrag
Conference Paper
2019 An Interactive Interface for Bulk Software Deployment in IoT
Tavakolizadeh, Farshid; Zhang, Hanbing; Adugna Chala, Sisay
Konferenzbeitrag
Conference Paper
2018 Video retrieval in laparoscopic video recordings with dynamic content descriptors
Schoeffmann, K.; Husslein, H.; Kletz, S.; Petscharnig, S.; Muenzer, B.; Beecks, C.
Zeitschriftenaufsatz
Journal Article
2018 Efficient Point-based Pattern Search in 3D Motion Capture Databases
Beecks, Christian; Graß, Alexander
Konferenzbeitrag
Conference Paper
2018 Metric Indexing for Efficient Data Access in the Internet of Things
Beecks, Christian; Grass, Alexander; Devasya, Shreekantha
Konferenzbeitrag
Conference Paper
2018 Smart data and the industrial internet of things
Beecks, C.; Rasheed, H.; Grass, A.; Devasya, S.; Jentsch, M.; Soto, J.A.C.; Tavakolizadeh, F.; Linnemann, A.; Eisenhauer, M.
Aufsatz in Buch
Book Article
2017 Industry 4.0: Mining physical defects in production of surface-mount devices
Tavakolizadeh, Farshid; Carvajal Soto, José Ángel; Gyulai, Dávid; Beecks, Christian
Konferenzbeitrag
Conference Paper
2017 Similarity search and applications
Beecks, C.; Borutta, F.; Kröger, P.; Seidl, T.
Konferenzbeitrag
Conference Paper
Diese Liste ist ein Auszug aus der Publikationsplattform Fraunhofer-Publica

This list has been generated from the publication platform Fraunhofer-Publica