@article{WoeberCurtoTibihikaetal.,
  author    = {W{\"o}ber, Wilfried and Curto, Manuel and Tibihika, Papius D. and Meulenboek, Paul and Alemayehu, Esayas and Mehnen, Lars and Meimberg, Harald and Sykacek, Peter},
  title     = {Identifying geographically differentiated features of Ethopian Nile tilapia (Oreochromis niloticus) morphology with machine learning},
  series = {PlosONE},
  volume    = {16},
  journal   = {PlosONE},
  number    = {4},
  subject      = {Machine Learning},
  language  = {en}
}
@inproceedings{WoeberTibihikaOlaverriMonrealetal.,
  author    = {W{\"o}ber, Wilfried and Tibihika, Papius D and Olaverri-Monreal, Cristina and Mehnen, Lars and Sykacek, Peter and Meimberg, Harald},
  title     = {Comparison of Unsupervised Learning Methods for Natural Image Processing},
  series = {Biodiversity Information Science and Standards},
  booktitle = {Biodiversity Information Science and Standards},
  number    = {3},
  subject      = {Machine Learning},
  language  = {en}
}
@inproceedings{WoeberSzuegyiKubingeretal.,
  author    = {W{\"o}ber, Wilfried and Szuegyi, Daniel and Kubinger, Wilfried and Mehnen, Lars},
  title     = {A principal component analysis based object detection for thermal infra-red images},
  series = {Proceedings of the 55th International Symposium ELMAR},
  booktitle = {Proceedings of the 55th International Symposium ELMAR},
  subject      = {Principal Component Analysis},
  language  = {en}
}
@misc{SpulakOtrebskiKubinger,
  author    = {Spulak, David and Otrebski, Richard and Kubinger, Wilfried},
  title     = {Object Tracking by Combining Supervised and Adaptive Online Learning through Sensor Fusion of Multiple Stereo Camera Systems},
  subject      = {Object Tracking},
  language  = {en}
}
@inproceedings{WoeberAburaiaOlaverriMonreal,
  author    = {W{\"o}ber, Wilfried and Aburaia, Mohamed and Olaverri-Monreal, Cristina},
  title     = {Classification of Streetsigns Using Gaussian Process Latent Variable Models},
  series = {2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE), Graz, Austria},
  booktitle = {2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE), Graz, Austria},
  subject      = {Streetsigns},
  language  = {en}
}
@article{SattingerPapaStujaetal.,
  author    = {Sattinger, Vinzenz and Papa, Maximilian and Stuja, Kemajl and Kubinger, Wilfried},
  title     = {Methodik zur Entwicklung sicherer kollaborativer Produktionssysteme im Rahmen von Industrie 4.0},
  series = {e \& i Elektrotechnik und Informationstechnik},
  journal   = {e \& i Elektrotechnik und Informationstechnik},
  subject      = {Robotics},
  language  = {de}
}
@inproceedings{PapaKaselautzkeRadingeretal.,
  author    = {Papa, Maximilian and Kaselautzke, David and Radinger, Thomas and Stuja, Kemajl},
  title     = {Development of a safety industry 4.0 production environment},
  series = {28th DAAAM International Symposium on Intelligent Manufacturing and Automation},
  booktitle = {28th DAAAM International Symposium on Intelligent Manufacturing and Automation},
  subject      = {Saftey},
  language  = {en}
}
@book{LacknerChenSuzuki,
  author    = {Lackner, Maximilian and Chen, Wei-Ying, and Suzuki, Toshio},
  title     = {Handbook of Climate Change Mitigation and Adaptation},
  publisher      = {Fachhochschule Technikum Wien},
  subject      = {Climate Change},
  language  = {en}
}
@article{WoeberMehnenSykaceketal.,
  author    = {W{\"o}ber, Wilfried and Mehnen, Lars and Sykacek, Peter and Meimberg, Harald},
  title     = {Investigating Explanatory Factors of Machine Learning Models for Plant Classification},
  series = {Plants},
  volume    = {2021},
  journal   = {Plants},
  number    = {10(12):2674},
  pages     = {20},
  abstract  = {Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to become black-box models, in the sense that it is difficult to trace characters that are the base for the classification. The interpretability is therefore limited and the explanatory factors may not be based on reasonable visible characters. We investigate the explanatory factors of recent machine learning and deep learning models for plant classification tasks. Based on a Daucus carota and a Beta vulgaris image data set, we implement plant classification models and compare those models by their predictive performance as well as explainability. For comparison we implemented a feed forward convolutional neuronal network as a default model. To evaluate the performance, we trained an unsupervised Bayesian Gaussian process latent variable model as well as a convolutional autoencoder for feature extraction and rely on a support vector machine for classification. The explanatory factors of all models were extracted and analyzed. The experiments show, that feed forward convolutional neuronal networks (98.24\% and 96.10\% mean accuracy) outperforms the Bayesian Gaussian process latent variable pipeline (92.08\% and 94.31\% mean accuracy) as well as the convolutional autoenceoder pipeline (92.38\% and 93.28\% mean accuracy) based approaches in terms of classification accuracy, even though not significant for Beta vulgaris images. Additionally, we found that the neuronal network used biological uninterpretable image regions for the plant classification task. In contrast to that, the unsupervised learning models rely on explainable visual characters. We conclude that supervised convolutional neuronal networks must be used carefully to ensure biological interpretability. We recommend unsupervised machine learning, careful feature investigation, and statistical feature analysis for biological applications. View Full-Text Keywords: deep learning; machine learning; plant leaf morphometrics; explainable AI},
  subject      = {deep learning},
  language  = {en}
}