Machine Learning

Data analytics and deep learning applied to health, work and Industry 4.0

»Data Analytics« und »Deep Learning« Verfahren für Gesundheit, Arbeit und Industrie 4.0
»Data Analytics« und »Deep Learning« Verfahren für Gesundheit, Arbeit und Industrie 4.0

Across the world, the quantity of digital data continues to multiply, and we can expect it to be 10 times what it is today by 2020. Affordable computing resources, optimized algorithms, and the huge volumes of available data have enabled the application of deep learning techniques, paving the way for the breakthrough of artificial intelligence. Now, things that seemed impossible just a few years ago are already a reality and even more efficiently. Nevertheless, these developments present researchers and developers with some weighty challenges. We still have difficulty explaining exactly how and why deep neural networks (DNNs) reach specific conclusions, and what exactly they use to acquire their knowledge. And yet, it is precisely this information that forms the basis of strategic business decisions, medical diagnostics and treatment (pain detection, for example), and the acceptance of these machine-driven techniques in everyday application (smart tools).

Your benefits at a glance – Everything from a single source

High Performance Deep Learning 34 Node Cluster, 72x NVidia P100 GPU, 16x NVidia P40 GPU, 2.8 TB RAM
© Fraunhofer IIS/Thomas Hauenstein
Deep Learning Data Processing at Fraunhofer IIS
Erweiterbares Kino-Labor, derzeit ausgestattet mit 70 Sitzplätzen und Infrarot-Kamerasystemen am Fraunhofer IIS
© Fraunhofer IIS/Bianca Möller
Cinema Theatre at Fraunhofer IIS
  • Pooled, wide-ranging expertise encompassing medical technology, signal analysis and signal processing, machine learning and implementation
  • Access to annotated visual material and databases for use in gesture and facial analysis, biosignals, endoscopy/ mammography/ hematology, and pathology
  • Cross-discipline connections with companies, universities and hospitals
  • Sensors and sensor systems for different physical and technical parameters
  • One-stop-shop for the realization of a customer-specific data processing chain from data capture, analysis to data output 


Infrastructure available

  • High-performance deep learning 34-node cluster, 72x NVidia P100 GPU, 16x NVidia P40 GPU, 2.8 TB RAM
  • Cinema theatre with seating for 70 persons and infrared camera systems
  • Microscopy- and digital pathology laboratory as well as endoscopic laboratory
  • Laboratory for multispectral and polarization imaging solutions
  • Electronic laboratory with extensive test equipment



Core research topics

Applying machine learning for the comprehensive gathering and analysis of biosignals

Because vital biosignals are now being continually monitored on a daily basis thanks to wearables and smart integrated sensor technology, we have access to large quantities of medical data that are extremely useful in diagnosis and treatment. When applied correctly, deep leaning techniques help find patterns in biosignals and allow us to accurately classify them according to various clinical categories (benign/malignant etc.). The information we glean from this process regarding the way in which biosignals interact with one another forms the basis of important medical decisions and preventative treatment.

Applying machine learning and deep learning for user-focused human-machine interaction

Another key topic of research is the development of methods and systems for machine learning. Our focus in on (real-time) computer vision applications (including facial analysis) that deliver high performance and detection rates even in uncontrolled environments. Another of our goals is to make our technology available across a wide range of platforms and in the embedded sector – which calls for efficient implementation and intelligent algorithm design. Our topics of research encompass state-of-the art techniques, such as those from deep learning, as well as approaches based on classic machine learning. Our technology is implemented in a range of applications, including market research, robotics, stress detection and the automotive sector.


Diagnostic endoscopy

Endoscopes have been used by physicians for over a century to diagnose and treat diseases and injuries affecting the body’s internal tissues and organs. But endoscopic examinations are still a purely visual technique and must often be complemented by biopsies to provide a full diagnosis.
The interpretation of endoscopic images depends to a large extent on the physician’s prior experience and is thus quite subjective. Fraunhofer IIS is investigating and developing methods for characterizing and classifying tissue damage and detecting suspect lesions, such as intestinal polyps, based on machine learning and using, for instance, specific color and texture features. The methods are intended for applications in diagnostic endoscopy.

Digital pathology and computer-assisted microscopy

The trend toward precision medicine calls for ever more nuanced diagnoses that take a multitude of histologically defined biomarkers and a growing number of prognostic factors into account. The application of machine learning methods in digital pathology holds much promise as an efficient means of mastering these challenges. The pathologist is relieved of routine diagnostic tasks that can now be automated, such as detecting and analyzing relevant cells and areas of tissue, and the results can be visualized in context. In research, deep learning methods assist in identifying and validating new prognostic markers and therapeutic targets.
Our researchers are well versed not only in conventional machine learning and image analysis methods, but also in the new, often superior, deep learning methods, and possess many years of experience in the development of applications to support computer-assisted diagnosis. These applications range from microscope and scanner control functions and automated analysis routines to the presentation of reproducible results in an easily comprehensible visual format.



SEMULIN – natural, multimodal interaction for automated driving

Development of a self-supporting natural human-machine interface for automated driving using multimodal input and output modes including facial expressions, gestures, gaze, and speech.



TraMeExCo (Transparent Medical Expert Companion) is a project funded by Germany’s Federal Ministry of Education and Research (BMBF). Its purpose is to investigate and develop suitable new methods to enable robust and explainable machine learning in complementary applications (digital pathology, pain analysis, cardiology) in the field of medical engineering.


Emotion-sensitive robotic platform for therapy

Video-based emotion recognition and multimodal analysis and evaluation of biosignals for better Human-Machine-Interaction


Affective Sensing

Cognitive Sensor Technology for Improved Healtcare and Quality of Life


ADA Lovelace Center for Analytics, Data and Applications

Explainable AI in medical technology and automotive applications


Department Positioning and Networks

Machine Learning

In various seminars on the subject of Machine Learning, we offer comprehensive training opportunities in the areas of Machine Learning and Reinforcement Learning. These in-depth courses offer an exciting mix of theory and practice.

Facial Analysis Solutions

One focus of our research activities is the development of processes for automatically detecting and analyzing objects.  

Digital Health Systems

  • Medical Image Analysis
  • Medical Sensors and Analytics
  • Communication and Integrated Care


Integrated Sensor Systems

Intelligent sensors are key elements of modern, autonomous systems.