Refine
Document Type
- Article (3)
- Conference Proceeding (1)
Keywords
- machine learning (2)
- Gaussian process latent variable models (1)
- Learning management systems (1)
- Probabilistic robotics (1)
- Variational bayes (1)
- Vehicle parameter estimation (1)
- artificial intelligence (1)
- convolutional autoencoder (1)
- deep learning (1)
- explainable AI (1)
- generalized procrustes analysis (1)
- learning analytics (1)
- learning management systems (1)
- plant leaf morphometrics (1)
- teaching analytics (1)
Department
- Department Computer Science (4) (remove)
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
Learning Management Systems (LMS), such as Moodle, enable the rapid progress of digitisation in teaching, which is no longer only taking place in the lecture hall, but increasingly “online” and asynchronously. New didactic concepts (blended learning, “flipped classroom”) consist of alternating self-learning and face-to-face phases, with the former taking place in the LMS, i.e. online. However, no analysis has yet been carried out as to how students act with the material in the self-learning phase, or the teachers are not provided with any information about the learning progress of the students during the self-learning phase. In this paper, concepts of learning and teaching analytics are presented to answer these questions and to integrate the measures derived from them into the teaching processes in a sustainable manner.
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