SISteffen Illium

Steffen Illium

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Steffen Illium has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Improving Primate Sounds Classification Using Binary Presorting for Deep Learning

    by Michael Kölle, Steffen Illium, Maximilian Zorn, Jonas Nüßlein, Patrick Suchostawski, Claudia Linnhoff-Popien


  • Open Access

    Improving Primate Sounds Classification using Binary Presorting for Deep Learning

    by Michael Kölle, Steffen Illium, Maximilian Zorn, Jonas Nüßlein, Patrick Suchostawski, Claudia Linnhoff-Popien

    In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning material; Samples can be weakly labeled, of different lengths or come with a poor signal-to-noise ratio. In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations, to achieve higher performances on the actual multi-class classification tasks. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging \textit{ComparE 2021} dataset, with the task of classifying between different primate species sounds, and report significantly higher Accuracy and UAR scores in contrast to comparatively equipped model baselines.

  • Open Access

    Constructing Organism Networks from Collaborative Self-Replicators

    by Steffen Illium, Maximilian Zorn, Cristian Lenta, Michael Kölle, Claudia Linnhoff-Popien, Thomas Gabor

    We introduce organism networks, which function like a single neural network but are composed of several neural particle networks; while each particle network fulfils the role of a single weight application within the organism network, it is also trained to self-replicate its own weights. As organism networks feature vastly more parameters than simpler architectures, we perform our initial experiments on an arithmetic task as well as on simplified MNIST-dataset classification as a collective. We observe that individual particle networks tend to specialise in either of the tasks and that the ones fully specialised in the secondary task may be dropped from the network without hindering the computational accuracy of the primary task. This leads to the discovery of a novel pruning-strategy for sparse neural networks

  • Open Access

    VoronoiPatches: Evaluating A New Data Augmentation Method

    by Steffen Illium, Gretchen Griffin, Michael Kölle, Maximilian Zorn, Jonas Nüßlein, Claudia Linnhoff-Popien

    Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augmentation methods (DA) have been proposed to supplement or generate more training data, and thereby increase its quality. In this work, we propose a new data augmentation algorithm: VoronoiPatches (VP). We primarily utilize non-linear recombination of information within an image, fragmenting and occluding small information patches. Unlike other DA methods, VP uses small convex polygon-shaped patches in a random layout to transport information around within an image. Sudden transitions created between patches and the original image can, optionally, be smoothed. In our experiments, VP outperformed current DA methods regarding model variance and overfitting tendencies. We demonstrate data augmentation utilizing non-linear re-combination of information within images, and non-orthogonal shapes and structures improves CNN model robustness on unseen data.

  • Open Access

    Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks

    by Steffen Illium, Thore Schillman, Robert Müller, Thomas Gabor, Claudia Linnhoff-Popien

    Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even a loose connection between data points) and subject to various constraints imposed by the type and size of the RNN in question. This implies the existence of a hard limit (way below the information-theoretic one) for the distance between related data points within which RNNs are still able to recognize said relation.

  • Open Access

    Visual Transformers for Primates Classification and Covid Detection

    by Steffen Illium, Robert Müller, Andreas Sedlmeier, Claudia-Linnhoff Popien

    We apply the vision transformer, a deep machine learning model build around the attention mechanism, on mel-spectrogram representations of raw audio recordings. When adding mel-based data augmentation techniques and sample-weighting, we achieve comparable performance on both (PRS and CCS challenge) tasks of ComParE21, outperforming most single model baselines. We further introduce overlapping vertical patching and evaluate the influence of parameter configurations. Index Terms: audio classification, attention, mel-spectrogram, unbalanced data-sets, computational paralinguistics

  • Case-Based Inverse Reinforcement Learning Using Temporal Coherence

    by Jonas Nüßlein, Steffen Illium, Robert Müller, Thomas Gabor, Claudia Linnhoff-Popien


  • Open Access

    Acoustic Leak Detection in Water Networks

    by Robert Müller, Steffen Illium, Fabian Ritz, Tobias Schröder, Christian Platschek, Jörg Ochs, Claudia Linnhoff-Popien

    In this work, we present a general procedure for acoustic leak detection in water networks that satisfies multiple real-world constraints such as energy efficiency and ease of deployment. Based on recordings from seven contact microphones attached to the water supply network of a municipal suburb, we trained several shallow and deep anomaly detection models. Inspired by how human experts detect leaks using electronic sounding-sticks, we use these models to repeatedly listen for leaks over a predefined decision horizon. This way we avoid constant monitoring of the system. While we found the detection of leaks in close proximity to be a trivial task for almost all models, neural network based approaches achieve better results at the detection of distant leaks.


  • Open Access

    Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

    by Robert Müller, Fabian Ritz, Steffen Illium, Claudia Linnhoff-Popien

    In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.

  • Open Access

    Soccer Team Vectors

    by Robert Müller, Stefan Langer, Fabian Ritz, Christoph Roch, Steffen Illium, Claudia Linnhoff-Popien

    In this work we present STEVE - Soccer TEam VEctors, a principled approach for learning real valued vectors for soccer teams where similar teams are close to each other in the resulting vector space. STEVE only relies on freely available information about the matches teams played in the past. These vectors can serve as input to various machine learning tasks. Evaluating on the task of team market value estimation, STEVE outperforms all its competitors. Moreover, we use STEVE for similarity search and to rank soccer teams.