TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars T1 - Optical tissue absorption sensor on the thorax: Possibilities and restrictions JF - International Journal of Applied Electromagnetics and Mechanics KW - Tissue Absorption KW - Sensor KW - Thorax Y1 - 2018 VL - 25 IS - 1-4 SP - 649 EP - 655 ER - TY - JOUR A1 - Wöber, Wilfried A1 - Mehnen, Lars A1 - Curto, Manuel A1 - Dias Tibihika, Papius A1 - Tesfaye, Genanaw A1 - Meimberg, Harald T1 - Investigating Shape Variation Using Generalized Procrustes Analysis and Machine Learning JF - Applied Sciences N2 - Abstract: The biological investigation of a population’s shape diversity using digital images is typi- cally reliant on geometrical morphometrics, which is an approach based on user-defined landmarks. In contrast to this traditional approach, the progress in deep learning has led to numerous applications ranging from specimen identification to object detection. Typically, these models tend to become black boxes, which limits the usage of recent deep learning models for biological applications. However, the progress in explainable artificial intelligence tries to overcome this limitation. This study compares the explanatory power of unsupervised machine learning models to traditional landmark-based approaches for population structure investigation. We apply convolutional autoencoders as well as Gaussian process latent variable models to two Nile tilapia datasets to investigate the latent structure using consensus clustering. The explanatory factors of the machine learning models were extracted and compared to generalized Procrustes analysis. Hypotheses based on the Bayes factor are formulated to test the unambiguity of population diversity unveiled by the machine learning models. The findings show that it is possible to obtain biologically meaningful results relying on unsupervised machine learning. Furthermore we show that the machine learning models unveil latent structures close to the true population clusters. We found that 80% of the true population clusters relying on the convolutional autoencoder are significantly different to the remaining clusters. Similarly, 60% of the true population clusters relying on the Gaussian process latent variable model are significantly different. We conclude that the machine learning models outperform generalized Procrustes analysis, where 16% of the population cluster was found to be significantly different. However, the applied machine learning models still have limited biological explainability. We recommend further in-depth investigations to unveil the explanatory factors in the used model. Keywords: generalized procrustes analysis; machine learning; convolutional autoencoder; Gaussian process latent variable models KW - generalized procrustes analysis KW - machine learning KW - convolutional autoencoder KW - Gaussian process latent variable models Y1 - VL - 2022 IS - 12(6), 3158 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Meydan, Turgut A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Merlo, Alberto Maria A1 - Marquardt, Bernd T1 - Dynamic Measuring of Inductivity Changes by Adaptive Controlling and Lock-in Technique JF - Journal of Electrical Engineering KW - Adaptive Controlling KW - Dynamic Measuring Y1 - 2019 VL - 2004 IS - 55 / 10 SP - 49 EP - 52 ER - TY - JOUR A1 - Pfützner, Helmut A1 - Kaniusas, Eugenijus A1 - Mehnen, Lars A1 - Meydan, Turgut A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Merlo, Alberto A1 - Marquardt, Bernd T1 - Magnetorestrictive bilayers for multi-functional sensor families JF - Sensors and Actuators A KW - Magnetism KW - Sensor Y1 - 2018 VL - 129 IS - 1 SP - 154 EP - 158 ER - TY - JOUR A1 - Obergruber, Julian A1 - Mehnen, Lars T1 - Development of a paraglide control system for automatic pitch JF - Proceedings of the 11th Conference of the International Sports Engineering Association (ISEA) 2016 KW - Control System Y1 - 2018 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Mehnen, Lars A1 - Pfützner, Helmut T1 - Magnetostrictive amorphous bilayers and trilayers for thermal sensors JF - Journal of Magnetism and Magnetic Materials KW - Magnetism KW - Sensor Y1 - IS - 254 - 255 SP - 624 EP - 626 ER - TY - JOUR A1 - Wöber, Wilfried A1 - Curto, Manuel A1 - Tibihika, Papius D. A1 - Meulenboek, Paul A1 - Alemayehu, Esayas A1 - Mehnen, Lars A1 - Meimberg, Harald A1 - Sykacek, Peter T1 - Identifying geographically differentiated features of Ethopian Nile tilapia (Oreochromis niloticus) morphology with machine learning JF - PlosONE KW - Machine Learning Y1 - VL - 16 IS - 4 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Hasenzagl, Andreas T1 - Optimisation of Magnetostrictive Bilayer Sensors for Medical Applications JF - International Journal of Applied Electromagnetics and Mechanics KW - Magnetism KW - Medical Technology Y1 - 2018 VL - 28 IS - 1,2 SP - 193 EP - 199 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Varoneckas, Giedrius A1 - Alonderis, Audrius A1 - Meydan, Turgut A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Merlo, Alberto A1 - Marquardt, Bernd T1 - Magnetoelastic bilayer concept for skin curvature sensor JF - Ultrasound KW - Magnetism KW - Skin Curvature KW - Sensor Y1 - 2019 VL - 52 IS - 3 SP - 42 EP - 46 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Tellez-Blanco, Juan C. A1 - Varoneckas, Giedrius A1 - Alonderis, Audrius A1 - Meydan, Turgut A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Merlo, Alberto A1 - Marquardt, Bernd T1 - Method for continuous non-disturbing monitoring of blood pressure by magnetoelastic skin curvature sensor and ECG JF - IEEE Sensors Journal KW - Blood Pressure KW - Magnetism KW - Sensor KW - Curvature Y1 - 2018 VL - 6 IS - 3 SP - 819 EP - 828 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Varoneckas, Giedrius A1 - Alonderis, Audrius A1 - Zakarevicius, Linas T1 - Cardiovascular Oscillations of the Carotid Artery Assessed by Magnetoelastic Skin Curvature Sensor JF - IEEE Transactions on Biomedical Engineering KW - Artery KW - Oscillations KW - Medical Technology Y1 - 2018 VL - 55 IS - 1 SP - 369 EP - 372 ER - TY - JOUR A1 - Pfützner, Helmut A1 - Eugenijus, Kaniusas A1 - Kosel, Jürgen A1 - Mehnen, Lars A1 - Meydan, Turgut A1 - Borza, Firuta A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Merlo, Alberto A1 - Marquardt, Bernd T1 - First magnetic material with sensitivity for the physical quantity 'curvature' JF - Journal of Material Processing Technology KW - Magnetism KW - Material Sensitivity KW - Curvature Y1 - 2018 VL - 181 IS - 1 SP - 186 EP - 189 ER - TY - JOUR A1 - Wöber, Wilfried A1 - Novotny, Georg A1 - Mehnen, Lars A1 - Olaverri-Monreal, Cristina T1 - Autonomous Vehicles: Vehicle Parameter Estimation Using Variational Bayes and Kinematics JF - Applied Sciences KW - Variational bayes KW - Vehicle parameter estimation KW - Probabilistic robotics Y1 - VL - 10 IS - 18 ER - TY - JOUR A1 - Traxler, Stefan A1 - Kosel, Jürgen A1 - Pfützner, Helmut A1 - Kaniusas, Eugenijus A1 - Mehnen, Lars A1 - Giouroudi, Ioanna T1 - Contactless flow detection with magnetostrictive bilayers JF - Sensors and Actuators A KW - Magnetism Y1 - 2018 VL - A 142 IS - 2 SP - 491 EP - 495 ER - TY - JOUR A1 - Mehnen, Lars A1 - Svec, Peter A1 - Pfützner, Helmut A1 - Duhaj, Pavel T1 - Displacement sensor based on an amorphous bilayer including a magnetostrictive component JF - Journal of Magnetism and Magnetic Materials KW - Magnetism KW - Sensor Y1 - 2019 IS - 254-255 SP - 627 EP - 629 ER - TY - JOUR A1 - Kaniusas, Eugenijus A1 - Pfützner, Helmut A1 - Mehnen, Lars A1 - Kosel, Jürgen A1 - Tellez-Blanco, Juan C. A1 - Mulasalihovic, Edin A1 - Meydan, Turgut A1 - Vazquez, Manuel A1 - Rohn, Michael A1 - Malvicino, Carlo A1 - Marquardt, Bernd T1 - Optimisation of sensitivity and time constant of thermal sensors based on magnetoelastic amorphous bilayers JF - Journal of Alloys and Compounds KW - Thermal Sensors KW - Magnetism Y1 - 2019 IS - 369 SP - 198 EP - 201 ER - TY - JOUR A1 - Wöber, Wilfried A1 - Mehnen, Lars A1 - Sykacek, Peter A1 - Meimberg, Harald T1 - Investigating Explanatory Factors of Machine Learning Models for Plant Classification JF - Plants N2 - 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 KW - deep learning KW - machine learning KW - plant leaf morphometrics KW - explainable AI Y1 - VL - 2021 IS - 10(12):2674 ER -