Main Content

Neural Networks

Several connected neurons suspended in a grey void.

Artificial neural networks inspired by biological nervous systems have proven to be very powerful thanks to their capabilities of learning hierarchical feature representations through a possibly large number of intermediate neural layers (a.k.a. "deep learning"). We have developed neural network approaches already in the 90s for a variety of applications, including (financial) timeseries predictions, anomaly detection for credit card fraud detection and partial discharge diagnosis, facility optimization, pattern classification, blind signal source separation, and independent component analysis.

Recently, we used deep learning algorithms for a variety of tasks in the areas of wireless networking, cloud computing, medical data analysis, and audiovisual analytics. Our neural network approach to learn Wi-Fi connection loss predictions for seamless vertical handovers using multipath TCP received the "Best Paper Award" at the 44th IEEE Conference on Local Computer Networks. Our approach to optimize the architecture of a deep neural network to recognize bird species in audio recordings won the BirdCLEF 2020 challenge with the best overall result.

Selected Publications

  • Daniel Schneider, Nikolaus Korfhage, Markus Mühling, Peter Lüttig, Bernd Freisleben: 
    Automatic Transcription of Organ Tablature Music Notation with Deep Neural Networks. Transactions of the International Society for Music Information Retrieval, 2021
  • Nikolaus Korfhage, Markus Mühling, Stefan Ringshandl, Anke Becker, Bernd Schmeck, Bernd Freisleben:
    Detection and Segmentation of Morphologically Complex Eukaryotic Cells in Fluorescence Microscopy Images via Feature Pyramid Fusion. PLOS Computational Biology 16(9): e1008179, 2020
  • Nikolaus Korfhage, Markus Mühling, Bernd Freisleben:
    Intentional Image Similarity Search. 9th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition, Winterthur, Switzerland, LNCS 12294, 23-35, Springer, 2020
  • Markus Mühling, Jakob Franz, Nikolaus Korfhage, Bernd Freisleben:
    Bird Species Recognition via Neural Architecture Search. CLEF 2020, CEUR Proceedings, Vol. 2696, 2020
    (Winner of BirdCLEF 2020)
  • Salma Daoud, Afef Mdhaffar, Mohamed Jmaiel, Bernd Freisleben:
    Q-Rank: Reinforcement Learning for Recommending Algorithms to Predict Drug Sensitivity to Cancer Therapy. IEEE Journal of Biomedical and Health Informatics 24(11): 3154-3161, 2020
  • Jonas Höchst, Artur Sterz, Alexander Frömmgen, Denny Stohr, Ralf Steinmetz, Bernd Freisleben:
    Learning Wi-Fi Connection Loss Predictions for Seamless Vertical Handovers Using Multipath TCP. 44th IEEE Conference on Local Computer Networks, Osnabrueck, Germany, 18-25, IEEE, 2019
    (Best Paper Award)
  • Markus Mühling, Manja Meister, Nikolaus Korfhage, Jörg Wehling, Angelika Hörth, Ralph Ewerth, Bernd Freisleben:
    Content-based Video Retrieval in Historical Collections of the German Broadcasting Archive. International Journal on Digital Libraries 20(2): 167-183, 2019
  • Abir Affes, Afef Mdhaffar, Chahnez Triki, Mohamed Jmaiel, Bernd Freisleben:
    A Convolutional Gated Recurrent Neural Network for Epileptic Seizure Prediction. 17th International Conference on Smart Living and Public Health, New York City, NY, USA, LNCS 11862, 85-96, Springer, 2019
  • Afef Mdhaffar, Fedi Cherif, Yousri Kessentini, Manel Maalej, Jihen Ben Thabet, Mohamed Maalej, Mohamed Jmaiel, Bernd Freisleben:
    DL4DED: Deep Learning for Depressive Episode Detection on Mobile Devices. 17th International Conference on Smart Living and Public Health, New York City, NY, USA, LNCS 11862, 109-121, Springer, 2019
  • Hatem Bellaaj, Afef Mdhaffar, Mohamed Jmaiel, Sondes Hdiji Mseddi, Bernd Freisleben:
    An Adaptive Neuro-Fuzzy Inference System for Improving Data Quality in Disease Registries. 33rd Annual ACM Symposium on Applied Computing, Pau, France, 30-33, ACM, 2018
  • Johannes Drönner, Nikolaus Korfhage, Sebastian Egli, Markus Mühling, Boris Thies, Jörg Bendix, Bernd Freisleben, Bernhard Seeger:
    Fast Cloud Segmentation Using Convolutional Neural Networks. Remote Sensing 10(11): 1782, 2018
  • Markus Mühling, Nikolaus Korfhage, Eric Müller, Christian Otto, Matthias Springstein, Thomas Langelage, Uli Veith, Ralph Ewerth, Bernd Freisleben:
    Deep Learning for Content-based Video Retrieval in Film and Television Production. Multimedia Tools and Applications 76(21): 22169-22194, 2017
  • Jonas Höchst, Lars Baumgärtner, Matthias Hollick, Bernd Freisleben:
    Unsupervised Traffic Flow Classification Using a Neural Autoencoder. 42nd IEEE Conference on Local Computer Networks, Singapore, 523-526, IEEE, 2017
  • Dorian Minarolli, Bernd Freisleben:
    Distributed Resource Allocation to Virtual Machines via Artificial Neural Networks. 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, Torino, Italy, 490-499, IEEE, 2014
  • Olaf Arndt, Thomas Barth, Bernd Freisleben, Manfred Grauer:
    Approximating a Finite Element Model by Neural Network Prediction for Facility Optimization in Groundwater Engineering. European Journal on Operations Research 166(3): 769-781, 2005
  • Francesco Virili, Bernd Freisleben:
    Neural Network Model Selection for Financial Time Series Prediction. Computational Statistics 16(3): 451-463, 2001
  • Francesco Virili, Bernd Freisleben:
    Nonstationarity and Data Preprocessing for Neural Network Predictions of an Economic Time Series. IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy, (5) 2000, 129-136, IEEE, 2000
  • Bernd Freisleben, Martin Hoof, Rainer Patsch:
    Using Counterpropagation Neural Networks for Partial Discharge Diagnosis. Neural Computing and Applications 7(4): 318-333, 1998
  • Emin Aleskerov, Bernd Freisleben, Bharat Rao:
    CARDWATCH: A Neural Network Based Database Mining System for Credit Card Fraud Detection. IEEE/IAFE 1997 Computational Intelligence for Financial Engineering, New York City, USA, 220-226, IEEE, 1997
  • Bernd Freisleben, Klaus Ripper:
    Volatility Estimation with a Neural Network. IEEE/IAFE Computational Intelligence for Financial Engineering, New York City, USA, 177-181, IEEE, 1997
  • Bernd Freisleben, Claudia Hagen, Markus Borschbach:
    Blind Source Separation via Unsupervised Learning. International Conference on Artificial Neural Nets and Genetic Algorithms, Norwich, UK, 116-120, Springer, 1997
  • Bernd Freisleben, Claudia Hagen:
    A Hierarchical Learning Rule for Independent Component Analysis. International Conference, on Artificial Neural Networks, Bochum, Germany, LNCS 1112, 252-530, Springer, 1996
  • Bernd Freisleben, Klaus Ripper:
    Economic Forecasting Using Neural Networks. International Conference on Neural Networks, Perth, WA, Australia 833-838, IEEE, 1995
  • Bernd Freisleben:
    Pattern Classification with Vigilant Counterpropagation. Second International Conference on Artificial Neural Networks, Bournemouth, UK, 252-256, IET, 1991

Further information