Refine
Document Type
- Article (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- Comparative analysis (1)
- Deep neural network (1)
- Gradient boosting (1)
- Multi-syndrome classification (1)
- Neurodegenerative syndromes (1)
- Random forest (1)
- Support vector machine (1)
- biogeography (1)
- climate (1)
- dispersal (1)
Institute
Aim: Biological invasions are likely determined by species dispersal strategies as well as environmental characteristics of a recipient region, especially climate and human impact. However, the contribution of climatic factors, human impact, and dispersal strategies in driving invasion processes is still controversial and not well embedded in the existing theoretical considerations. Here, we study how climate, species dispersal strategies, and human impact determine plant invasion processes on islands distributed in all major oceans in the context of directional ecological filtering.
Location: Six mountainous, tropical, and subtropical islands in three major oceans: Island of Hawai'i and Maui (Pacific), Tenerife and La Palma (Atlantic), and La Réunion and Socotra (Indian Ocean).
Taxon: Vascular Plants.
Methods: We recorded 360 non-native species in 218 plots along roadside elevational transects covering the major temperature, precipitation and human impact (i.e., road density) gradients of the islands. We collected dispersal strategies for a majority of the recorded species and calculated the environmental niche per species using a hypervolume approach.
Results: Non-native species’ generalism (i.e., mean community niche width) increased with precipitation, elevation and human impact but showed no relationship with temperature. Increasing precipitation led to environmental filtering of non-native species resulting in more generalist species under high precipitation conditions. We found no directional filtering for temperature but an optimum range of most species between 10 and 20°C. Niche widths of non-native species increased with the prevalence of certain dispersal strategies, particularly anemochory and anthropochory.
Main conclusions: Plant invasion on tropical and subtropical islands seems to be mainly driven by precipitation and human impact, while temperature seems to be of little importance. Furthermore, anemochory and anthropochory are dispersal strategies associated with large niche widths of non-native species. Our study allows a more detailed look at the mechanisms behind directional ecological filtering of non-native plant species in non-temperature-limited ecosystems.
Importance: The entry of artificial intelligence into medicine is pending. Several methods have been used for the predictions of structured neuroimaging data, yet nobody compared them in this context.
Objective: Multi-class prediction is key for building computational aid systems for differential diagnosis. We compared support vector machine, random forest, gradient boosting, and deep feed-forward neural networks for the classification of different neurodegenerative syndromes based on structural magnetic resonance imaging.
Design, setting, and participants: Atlas-based volumetry was performed on multi-centric T1-weighted MRI data from 940 subjects, i.e., 124 healthy controls and 816 patients with ten different neurodegenerative diseases, leading to a multi-diagnostic multi-class classification task with eleven different classes.
Interventions: N.A.
Main outcomes and measures: Cohen’s kappa, accuracy, and F1-score to assess model performance.
Results: Overall, the neural network produced both the best performance measures and the most robust results. The smaller classes however were better classified by either the ensemble learning methods or the support vector machine, while performance measures for small classes were comparatively low, as expected. Diseases with regionally specific and pronounced atrophy patterns were generally better classified than diseases with widespread and rather weak atrophy.
Conclusions and relevance: Our study furthermore underlines the necessity of larger data sets but also calls for a careful consideration of different machine learning methods that can handle the type of data and the classification task best.
Die Fundmeldungen in Band 34 von Botanik und Naturschutz in Hessen stammen von: Dirk Bönsel, Martin De Jong, Klaus Dühr, Uta Engel, Benjamin Feller, Christian Feuring, Thomas Gregor, Arthur Händler, Karsten Horn, Diemut Klärner, Julia Kruse, Eric Martiné, Hasko Friedrich Nesemann, Kai Uwe Nierbauer, Uwe Raabe, Susanne Raehse, Felix Reischmann, Bernd Sauerwein, Petra Schmidt, Fabian Schrauth, Christof Nikolaus Schröder, Helmut Siebert, Michael Thieme, Otto Wacker und Rüdiger Wittig.