The GenTree Dendroecological Collection, tree-ring and wood density data from seven tree species across Europe

Martínez‐Sancho, Elisabet; Slámová, Lenka; Morganti, Sandro; Grefen, Claudio; Carvalho, Bárbara; Dauphin, Benjamin; Rellstab, Christian; Gugerli, Félix; Opgenoorth, Lars; Heer, Katrin; Knutzen, Florian; Arx, Georg von; Valladares, Fernando; Cavers, Stephen; Fady, Bruno; Alı́a, Ricardo; Aravanopoulos, Filippos; Avanzi, C. Fedeli; Bagnoli, Francesca; Barbas, Evangelos; Bastien, Catherine; Benavides, Raquel; Bernier, Frédéric; Bodineau, Guillaume; Bastías, Cristina C.; Charpentier, Jean-Paul; Climent, José; Corréard, Marianne; Courdier, Florence; Danusevičius, Darius; Farsakoglou, Anna‐Maria; Barrio, José Manuel; Gilg, Olivier; González‐Martínez, Santiago C.; Gray, Alan; Hartleitner, Christoph; Hurel, Agathe; Jouineau, Arnaud; Kärkkäinen, Katri; Kujala, Sonja; Labriola, Mariaceleste; Lascoux, Martin; Lefebvre, Marlène; Lejeune, Vincent; Le-Provost, Grégoire; Liesebach, Mirko; Malliarou, Ermioni; Mariotte, Nicolas; Matesanz, Silvia; Michotey, Célia; Milesi, Pascal; Myking, Tor; Notivol, Eduardo; Pakull, Birte; Piotti, Andrea; Plomion, Christophe; Pringarbe, Mehdi; Pyhäjärvi, Tanja; Raffin, Annie; Ramírez‐Valiente, José Alberto; Ramskogler, Kurt; Robledo‐Arnuncio, Juan J.; Savolainen, Outi; Schueler, Silvio; Семериков, В. Л.; Spanu, Ilaria; Thévenet, Jean; Tollefsrud, Mari Mette; Turion, Norbert; Veisse, Dominique; Vendramin, Giovanni G.; Villar, Marc; Westin, Johan; Fonti, Patrick

doi:10.1038/s41597-019-0340-y

Cited by 430 publications

(298 citation statements)

References 26 publications

Supporting

Mentioning

291

Contrasting

Order By: Relevance

“…The delineation performance shows errors of ms, ms and ms in the onset and of ms, ms and ms in the offset for delineation, with Dice scores of 88.99%, 92.05%, 88.40% for the P, QRS and T waves, respectively. This model was used to predict some registries in 19 , shown in Supplementary Figs. S1 – S10 .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks

Jiménez-Pérez¹,

Alcaine

Cámara³

2021

Sci Rep

View full text Add to dashboard Cite

Detection and delineation are key steps for retrieving and structuring information of the electrocardiogram (ECG), being thus crucial for numerous tasks in clinical practice. Digital signal processing (DSP) algorithms are often considered state-of-the-art for this purpose but require laborious rule readaptation for adapting to unseen morphologies. This work explores the adaptation of the the U-Net, a deep learning (DL) network employed for image segmentation, to electrocardiographic data. The model was trained using PhysioNet’s QT database, a small dataset of 105 2-lead ambulatory recordings, while being independently tested for many architectural variations, comprising changes in the model’s capacity (depth, width) and inference strategy (single- and multi-lead) in a fivefold cross-validation manner. This work features several regularization techniques to alleviate data scarcity, such as semi-supervised pre-training with low-quality data labels, performing ECG-based data augmentation and applying in-built model regularizers. The best performing configuration reached precisions of 90.12%, 99.14% and 98.25% and recalls of 98.73%, 99.94% and 99.88% for the P, QRS and T waves, respectively, on par with DSP-based approaches. Despite being a data-hungry technique trained on a small dataset, a U-Net based approach demonstrates to be a viable alternative for this task.

show abstract

Section: Resultsmentioning

confidence: 99%

“…A second dataset containing outflow tract ventricular arrhythmias in the 12-lead ECG 19 was employed to qualitatively assess the fitness of the trained models, with some results reported in the Supplementary Figs. S1 – S10 .…”

Section: Methodsmentioning

confidence: 99%

Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks

Jiménez-Pérez¹,

Alcaine

Cámara³

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…These values indicated that Alphasense is not suitable for such low-concentration monitoring, while the MEE reference instrument is qualified. The low SO 2 concentrations are largely attributed to the strong implementation of the SO 2 control policy; thus, good monitoring and treatment measures were achieved at the stacks near large individual emissions factories [ 49 ], and coal consumption was largely reduced due to the shift to natural gas [ 50 ]; these measures reduced the SO 2 emissions by 62% from 2010–2017 [ 51 ]. Due to the low SO 2 environmental concentrations and subsequent poor performance of the sensor response, we mainly analyze CO, O 3 , and NO 2 in the following text.…”

Section: Resultsmentioning

confidence: 99%

“…In the research of Spinelle [ 48 ], an Alphasense-O 3 B4 sensor was used, and its effect after MLR correction reached approximately R 2 = 0.5. There are few existing studies on correcting the low-cost sensor of O 3 using deep learning and other algorithms, and the control of O 3 pollution has attracted increasing attention from the public and scientific community [ 49 ], so the correction and application of a low-cost sensor for O 3 is urgently needed. For O 3 sensor calibration in our study ( Figure 4 b), the corrected results of the training set and test set are R 2 = 0.75 (R 2 = 0.54 before correction) and R 2 = 0.77 (R 2 = 0.59 before correction), and the LSTM correction effect of O 3 is significantly improved compared with RFR, especially in the test set.…”

Section: Resultsmentioning

confidence: 99%

Calibrations of Low-Cost Air Pollution Monitoring Sensors for CO, NO2, O3, and SO2

Han

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

Pollutant gases, such as CO, NO2, O3, and SO2 affect human health, and low-cost sensors are an important complement to regulatory-grade instruments in pollutant monitoring. Previous studies focused on one or several species, while comprehensive assessments of multiple sensors remain limited. We conducted a 12-month field evaluation of four Alphasense sensors in Beijing and used single linear regression (SLR), multiple linear regression (MLR), random forest regressor (RFR), and neural network (long short-term memory (LSTM)) methods to calibrate and validate the measurements with nearby reference measurements from national monitoring stations. For performances, CO > O3 > NO2 > SO2 for the coefficient of determination (R2) and root mean square error (RMSE). The MLR did not increase the R2 after considering the temperature and relative humidity influences compared with the SLR (with R2 remaining at approximately 0.6 for O3 and 0.4 for NO2). However, the RFR and LSTM models significantly increased the O3, NO2, and SO2 performances, with the R2 increasing from 0.3–0.5 to >0.7 for O3 and NO2, and the RMSE decreasing from 20.4 to 13.2 ppb for NO2. For the SLR, there were relatively larger biases, while the LSTMs maintained a close mean relative bias of approximately zero (e.g., <5% for O3 and NO2), indicating that these sensors combined with the LSTMs are suitable for hot spot detection. We highlight that the performance of LSTM is better than that of random forest and linear methods. This study assessed four electrochemical air quality sensors and different calibration models, and the methodology and results can benefit assessments of other low-cost sensors.

show abstract

“…Xu group organized them and introduced descriptors for predicting ITR by machine learning method 8 , 9 . Details of the developed descriptors and collected ITR were explained in the previous work 41 . And data could be found in the file named “training dataset for ITR prediction.xlsx” and downloaded directly from https://doi.org/10.5281/zenodo.3564173 .…”

Section: Methodsmentioning

confidence: 99%

Descriptor selection for predicting interfacial thermal resistance by machine learning methods

Tian

Chen

2021

Sci Rep

View full text Add to dashboard Cite

Interfacial thermal resistance (ITR) is a critical property for the performance of nanostructured devices where phonon mean free paths are larger than the characteristic length scales. The affordable, accurate and reliable prediction of ITR is essential for material selection in thermal management. In this work, the state-of-the-art machine learning methods were employed to realize this. Descriptor selection was conducted to build robust models and provide guidelines on determining the most important characteristics for targets. Firstly, decision tree (DT) was adopted to calculate the descriptor importances. And descriptor subsets with topX highest importances were chosen (topX-DT, X = 20, 15, 10, 5) to build models. To verify the transferability of the descriptors picked by decision tree, models based on kernel ridge regression, Gaussian process regression and K-nearest neighbors were also evaluated. Afterwards, univariate selection (UV) was utilized to sort descriptors. Finally, the top5 common descriptors selected by DT and UV were used to build concise models. The performance of these refined models is comparable to models using all descriptors, which indicates the high accuracy and reliability of these selection methods. Our strategy results in concise machine learning models for a fast prediction of ITR for thermal management applications.

show abstract

The GenTree Dendroecological Collection, tree-ring and wood density data from seven tree species across Europe

Cited by 430 publications

References 26 publications

Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks

Delineation of the electrocardiogram with a mixed-quality-annotations dataset using convolutional neural networks

Calibrations of Low-Cost Air Pollution Monitoring Sensors for CO, NO2, O3, and SO2

Descriptor selection for predicting interfacial thermal resistance by machine learning methods

Contact Info

Product

Resources

About