Stadt Wien - Call 21 bis 25
-
BioPlastLease
(1)
- ENGINE
-
EspreESSO-IT
(1)
-
Health-CONNECT
(3)
- IoCEST
-
PBL-Problem-based Learning
(6)
-
Maßnahmen zur Förderung des individuellen Lernfortschritts
(7)
-
Servicecenter Lehre
(1)
- StudyATHome Internationally
- RASP
- Human Factors in Automated Driving (HFAD)
- KoLPEQ
Refine
Document Type
- Article (5)
- Lecture (2)
- Conference Proceeding (1)
Keywords
- machine learning (2)
- Ambient Assistive Technologies (1)
- Biomaterials (1)
- Biomedical Engineering (1)
- Biomphalaria Glabrata (1)
- Breathing Simulation (1)
- COVID-19 (1)
- Didaktik (1)
- Ecotoxicology (1)
- Electromechanical lung simulator (1)
Department
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
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
Hybrid courses with a focus on practice-orientated education and self-guided learning phases are on the rise on the higher education sector. Disciplines in Life Sciences implicate a high degree of practical laboratory expertise. The University of Applied Sciences (UAS) in Vienna, Austria, has thus been endeavoured offering students a high qualitative education integrating hybrid courses based on PBL principles, which consist of on-site (including the transmission of necessary background and practical laboratory training) and off-site (including self-study phases) sessions. As practical laboratory units are central in those courses, the restrictive measures, including the transition to a complete online teaching format due to the first Covid-19-pandemic lock-down, had severe effects on the implementation and the quality of the curriculum. According to surveys made specifically to address this problematic situation, it can be concluded that on-site practical units are fundamental for certain disciplines such as Life Sciences.
The responsibility of a lecturer is not only to share his or her knowledge with the students in an easy to understand manner, but also to help the students to embed new knowledge and to encourage the development of higher-order cognitive skills via applied exercises.
In order to meet the growing demand for blended learning approaches a new course concept was established in autumn 2018. To enhance comprehension and to provide opportunities for self-assessment, web-based training units were implemented by using the interactive learning software “Articulate Storyline”. Students had to prepare at home for the course units by completing interactive chapters. Their learning outcome was assessed by online quizzes at the end of each chapter. Online Training chapters allowed time to focus on selected topics and to repeat key messages in following presence units.
Additionally, guided group exercises were performed to promote analytic skills and abstract thinking. The students had to apply and combine their knowledge to solve problem-based challenges.
An optional revision course was offered to the students, which allowed for interactive repetition of the acquired knowledge with the focus on student-to-lecturer dialog.
An analysis based on a written evaluation of this course resulted in a positive feedback from the students, in particular regarding the guided exercises and the offered revision course. According to the students the group exercises allowed to process the learned subjects, promoted the group climate and were a convenient diversion from the frontal lecture format. Students who attended the revision course on a regular basis showed a better performance at the final exam and exceeded especially at interdisciplinary questions.
The first implementation of this master´s degree course indicated that the combination of web-based training elements with frontal lecture elements, guided exercises stimulating cognitive skills and an optional revision course can teach students the basics of biology in an understandable way. This course structure is especially applicable to teach basic subjects for groups of students with varying initial knowledge.
Financial support from the City of Vienna project PBL in Molecular Life Science (21-06) is gratefully acknowledged.
During mechanical ventilation, a disparity between flow, pressure and volume demands of the patient and the assistance delivered by the mechanical ventilator often occurs. This paper introduces an alternative approach of simulating and evaluating patient–ventilator interactions with high fidelity using the electromechanical lung simulator xPULM™. The xPULM™ approximates respiratory activities of a patient during alternating phases of spontaneous breathing and apnea intervals while connected to a mechanical ventilator. Focusing on different triggering events, volume assist-control (V/A-C) and pressure support ventilation (PSV) modes were chosen to test patient–ventilator interactions. In V/A-C mode, a double-triggering was detected every third breathing cycle, leading to an asynchrony index of 16.67%, which is classified as severe. This asynchrony causes a significant increase of peak inspiratory pressure (7.96 ± 6.38 vs. 11.09 ± 0.49 cmH2O, p < 0.01)) and peak expiratory flow (−25.57 ± 8.93 vs. 32.90 ± 0.54 L/min, p < 0.01) when compared to synchronous phases of the breathing simulation. Additionally, events of premature cycling were observed during PSV mode. In this mode, the peak delivered volume during simulated spontaneous breathing phases increased significantly (917.09 ± 45.74 vs. 468.40 ± 31.79 mL, p < 0.01) compared to apnea phases. Various dynamic clinical situations can be approximated using this approach and thereby could help to identify undesired patient–ventilation interactions in the future. Rapidly manufactured ventilator systems could also be tested using this approach. View Full-Text
Treatment of peripheral nerve injuries has evolved over the past several decades to include the use of sophisticated new materials endowed with trophic and topographical cues that are essential for in vivo nerve fibre regeneration. In this research, we explored the use of an advanced design strategy for peripheral nerve repair, using biological and semi-synthetic hydrogels that enable controlled environmental stimuli to regenerate neurons and glial cells in a rat sciatic nerve resection model. The provisional nerve growth conduits were composed of either natural fibrin or adducts of synthetic polyethylene glycol and fibrinogen or gelatin. A photo-patterning technique was further applied to these 3D hydrogel biomaterials, in the form of laser-ablated microchannels, to provide contact guidance for unidirectional growth following sciatic nerve injury. We tested the regeneration capacity of subcritical nerve gap injuries in rats treated with photo-patterned materials and compared these with injuries treated with unpatterned hydrogels, either stiff or compliant. Among the factors tested were shear modulus, biological composition, and micropatterning of the materials. The microchannel guidance patterns, combined with appropriately matched degradation and stiffness properties of the material, proved most essential for the uniform tissue propagation during the nerve regeneration process.
