Hierarchical Visualization of Co-Occurrence Patterns on Diagnostic Data

Author(s):  
Jose Luis Balcazar ◽  
Marie Ely Piceno ◽  
Laura Rodriguez-Navas
Author(s):  
Marie Ely Piceno ◽  
Laura Rodríguez-Navas ◽  
José Luis Balcázar

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Siul A. Ruiz ◽  
Samuel Bickel ◽  
Dani Or

AbstractEarthworm activity modifies soil structure and promotes important hydrological ecosystem functions for agricultural systems. Earthworms use their flexible hydroskeleton to burrow and expand biopores. Hence, their activity is constrained by soil hydromechanical conditions that permit deformation at earthworm’s maximal hydroskeletal pressure (≈200kPa). A mechanistic biophysical model is developed here to link the biomechanical limits of earthworm burrowing with soil moisture and texture to predict soil conditions that permit bioturbation across biomes. We include additional constraints that exclude earthworm activity such as freezing temperatures, low soil pH, and high sand content to develop the first predictive global map of earthworm habitats in good agreement with observed earthworm occurrence patterns. Earthworm activity is strongly constrained by seasonal dynamics that vary across latitudes largely due to soil hydromechanical status. The mechanistic model delineates the potential for earthworm migration via connectivity of hospitable sites and highlights regions sensitive to climate.


Processes ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 1115
Author(s):  
Gilseung Ahn ◽  
Hyungseok Yun ◽  
Sun Hur ◽  
Si-Yeong Lim

Accurate predictions of remaining useful life (RUL) of equipment using machine learning (ML) or deep learning (DL) models that collect data until the equipment fails are crucial for maintenance scheduling. Because the data are unavailable until the equipment fails, collecting sufficient data to train a model without overfitting can be challenging. Here, we propose a method of generating time-series data for RUL models to resolve the problems posed by insufficient data. The proposed method converts every training time series into a sequence of alphabetical strings by symbolic aggregate approximation and identifies occurrence patterns in the converted sequences. The method then generates a new sequence and inversely transforms it to a new time series. Experiments with various RUL prediction datasets and ML/DL models verified that the proposed data-generation model can help avoid overfitting in RUL prediction model.


2021 ◽  
pp. 112311
Author(s):  
Giulia Poma ◽  
Yukiko Fujii ◽  
Siebe Lievens ◽  
Jasper Bombeke ◽  
Beibei Gao ◽  
...  

Author(s):  
A. Rigoni Garola ◽  
R. Cavazzana ◽  
M. Gobbin ◽  
R.S. Delogu ◽  
G. Manduchi ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document