Lars Heiko Mehnen

Prof. Dr. Lars Heiko Mehnen

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 December 2021 in Plants
Verified
Journal Article
Open access
PDF file
Wilfried WöberWilfried Wöber
Wilfried Wöber
LMLars Heiko Mehnen
Lars Heiko Mehnen
PSPeter Sykacek
Peter Sykacek
Harald MeimbergHarald Meimberg
Harald Meimberg
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.

10 September 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Wilfried WöberWilfried Wöber
Wilfried Wöber
GNGeorg Novotny
Georg Novotny
LMLars Heiko Mehnen
Lars Heiko Mehnen
Cristina Olaverri-MonrealCristina Olaverri-Monreal
Cristina Olaverri-Monreal
On-board sensory systems in autonomous vehicles make it possible to acquire information about the vehicle itself and about its relevant surroundings. With this information the vehicle actuators are able to follow the corresponding control commands and behave accordingly. Localization is thus a critical feature in autonomous driving to define trajectories to follow and enable maneuvers. Localization approaches using sensor data are mainly based on Bayes filters. Whitebox models that are used to this end use kinematics and vehicle parameters, such as wheel radii, to interfere the vehicle’s movement. As a consequence, faulty vehicle parameters lead to poor localization results. On the other hand, blackbox models use motion data to model vehicle behavior without relying on vehicle parameters. Due to their high non-linearity, blackbox approaches outperform whitebox models but faulty behaviour such as overfitting is hardly identifiable without intensive experiments. In this paper, we extend blackbox models using kinematics, by inferring vehicle parameters and then transforming blackbox models into whitebox models. The probabilistic perspective of vehicle movement is extended using random variables representing vehicle parameters. We validated our approach, acquiring and analyzing simulated noisy movement data from mobile robots and vehicles. Results show that it is possible to estimate vehicle parameters with few kinematic assumptions.

20 March 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Wilfried WöberWilfried Wöber
Wilfried Wöber
LMLars Heiko Mehnen
Lars Heiko Mehnen
MCManuel Curto
Manuel Curto
PTPapius Dias Tibihika
Papius Dias Tibihika
GWGenanaw Woldetsadik
Genanaw Woldetsadik
Harald MeimbergHarald Meimberg
Harald Meimberg
The biological investigation of a population’s shape diversity using digital images is typically 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.

18 April 2006 in Journal of Materials Processing Technology
Verified
Journal Article
Closed access
HPH. Pfützner
H. Pfützner
EKEugenijus Kaniusas
Eugenijus Kaniusas
JKJürgen Kosel
Jürgen Kosel
LMLars Heiko Mehnen
Lars Heiko Mehnen
TMTurgut Meydan
Turgut Meydan
BMB. Marquardt
B. Marquardt