Two daily weather datasets for experimenting data-driven models on two different weather types:
1. Chiang Mai International Airport, Chiang Mai, Thailand from January 1st 1998 to July 31st 2019. The data were acquired from the station via personal communication. The following files are provided:
- chiang_mai_1998-2019_raw.csv : the raw data.
- chiang_mai_1998-2019.csv : the preprocessed data: the dates and redundant variables were removed, the missing data were imputed with MICE algorithm and all units were changed to SI units.
2. Theodore Francis Green State Airport, Providence, RI from January 1st 2006 to October 31st 2019. The data were acquired from the National Oceanic and Atmospheric Administration (https://www.ncdc.noaa.gov/cdo-web/datatools/lcd). The following files are provided:
- providence_2006-2019_raw.csv : the raw data.
- providence_2006-2019.csv : the preprocessed data: the dates were removed, the missing data were imputed with MICE algorithm and all units were changed to SI units.
Additionally, we provide code in Python and shell scripts for reproducibility of the three autoencoder models in "Short-term Daily Precipitation Forecasting with
Seasonally-Integrated Autoencoder". The code have the following requirements:
- Python 3.6 or higher
- Keras 2.2 or higher (Python library)
- Tensorflow 1.x.y or where x.y is 12.0 or higher (Python library)
The proposed model can be trained by simply running the following command:
After the training is done, the RMSE and CORR scores will be reported, and the forecast values will be saved in `path/to/data_XXXXXX-xxxxxx.csv`. The README.md file provides additional information on code usage.
#### Changing arguments
You can modify the arguments in the script files. For example, `--model` and `horizon` let you specify the model and the forecast horizon, respectively. The descriptions of all available options can be accessed via the command:
python3 main.py -h
#### Running the script in different modes
We have prepared the scripts for `prediction` mode and `evaluation` mode, namely `Providence_predict.sh` and `Providence_eval.sh`, as well as the pretrained weights for all three models in the `model` folder. To use these two modes, you need to specify the location of the pretrained weights using `--load` option. For example, the weights of SSAE that makes forecast over the next three days on Providence dataset are stored in `pvd_ssae_3.h5`
You also need to specify the test data.
- Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., Han, J., 2019. On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265.
- Zaytar, M.A., Amrani, C.E., 2016. Sequence to sequence weather forecasting with long short-term memory recurrent neural networks. International Journal of Computer Applications 143, 7–11. doi:10.5120/ijca2016910497.
We hypothesize that biotin favors BCAA utilization and its deficiency accumulates BCAA to prolong autophagy inhibition and ER stress by chronic activation of mTORC1.
Ganesan, D, Ramaian Santhaseela, A, Rajasekaran, S, Selvam, S, Jayavelu, T. Astroglial biotin deprivation under endoplasmic reticulum stress uncouples BCAA‐mTORC1 role in lipid synthesis to prolong autophagy inhibition in the aging brain. J. Neurochem. 2020; 00: 1– 14. https://doi.org/10.1111/jnc.14979
Direct lung ultrasound evaluation (CLUE) technique was proven to be an accurate method for monitoring extravascular lung water in donor lungs during ex-vivo lung perfusion (EVLP) in an experimental model. The aim of this study was to examine the application of CLUE in clinical setting.
Lungs were evaluated using acellular EVLP protocol. Ultrasound images were obtained directly from the lung surface. Images were graded according to the percentage of B-lines seen on ultrasound. CLUE scores were calculated at the beginning and end of EVLP for the whole lung, each side, and lobe based on the number of images in each grade and the total number of images taken.
Out of the 45 lungs, 22 were deemed suitable resulting in 13 lung transplants (LTx) with no hospital mortality. Primary graft dysfunction occurred in only one recipient (PGD3 no PGD2). Significant differences were found between suitable and non-suitable lungs in CLUE scores (1.03 vs 1.85, p<0.001) unlike PaO2/FiO2 ratio. CLUE had the highest area under the receiver-operating characteristic curve (0.98) when compared to other evaluation parameters. The initial CLUE score of standard donor lungs was significantly better than marginal lungs. Final CLUE score in proned lungs showed improvement when compared to initial CLUE score, especially in the upper lobes.
CLUE technique shows the highest accuracy in evaluating donor lungs for LTx suitability compared to other parameters used in EVLP. CLUE can optimize the outcomes of LTx by guiding the decision making through the whole process of clinical EVLP.
The dataset includes data and the code for the paper of "Vertical interlock and investment efficiency".
Data used in the article: http://www.mdpi.com/1424-8220/19/1/190. Please cite this if you make use of this data.
EEG data recorded from a phantom head model during the applications of tACS. These can be used to test the performance of artefact removal algorithms, knowing what the 'true' EEG signal is. The true signal is given in the *Sham*.mat files. The other files record the EEG for different stimulation settings. Recordings where the inputted EEG was an alpha test, and an N170 ERP are present. (ERP records not used in the paper above.)
Contributors:Abel Osagie, Ismail Abir
List of input and output files
1. PICKS-BISC-1964-2017: Arrival time data the bulletin of International Seismological Center (ISC) for earthquakes that have occurred around the Sumatran Fault System spanning latitudes 10º N - 10º S and longitudes 93º E-114º E.
2. SFILE-06-18: Hand-picked data using SEISAN software. Waveform is obtained from Incorporated Research Institutions for Seismology (IRIS)
3. Global list of seismic stations and their locations (courtesy ISC)
4. A_VMD2: The algorithm used to generated the final model
5. A11-MODEL-DEP-SLICE: Output file for representative depths
6. A11-MODEL-LAT-SLICE: Output file for North-South vertical cross-sections
7. A11-MODEL-LON-SLICE: Output file for East-West vertical cross-sections
8. A11_MODEL-3D: Output file for 3-D model of the study region
9. A_VMD.INC: A common file required by many subroutines in the main algorithm
10. EVENTS: All earthquakes used in the study
11. A13-RESIDUALS: Computed traveltime residuals for all stations and for all events.
12. List of 1-D velocity models. (the iasp91 model is used)
Tomographic results show low-velocity (low-V) anomalies that reflect both accretion and possibly, asthenospheric upwelling associated with subduction of the Australian plate beneath the Eurasian plate around the Sumatra subduction zone (SSZ). The prominent low-V anomaly is thickest around the Conrad, extending beneath Malacca Strait and parts of Peninsular Malaysia, but disappears around the Moho (which appears to be less than 35 km) in the region. Below the Moho, the subducting Australian slab, represented by a high-velocity (high-V) anomaly, trends in the orientation of Sumatra. At these depths, the eastern shorelines of Sumatra, most parts of Malacca Strait and the west coast of Peninsular Malaysia show varying degrees of positive velocity anomalies. We consider that asthenospheric upwelling around the SSZ provide heat source for the 40 or more hot springs distributed North-South in Peninsular Malaysia. Different East-West and North-South cross-sections reveal the subsurface anomalies at various parts of the region. The predominant low-V anomaly is less than 35 km in depth but other low-V anomalies are deeper.
Contributors:Amal Akour, Ruba Tarawneh, bayan anati, Suha Al Muhaissen, Noor Alhourani, VIOLET KASABRI, Nailya Bulatova
The study was designed to asses whether removing clots and contents of the uterine cavity before hysteroscopy would lead to better procedure outcomes(bleeding, media use, procedure duration, and hospital stay duration)
Bleeding Categories are created based on the surgeon and operating nurse's estimation on the bleeding amount.
The dataset contains the Shu-Talas Transboundary Basin shapefiles. The shapefiles are produced using the data from HydroSHEDS project that provides watershed delineations at a global scale.
Shu-Talas Basin has two major rivers, Shu and Talas. Their boundary shapefiles are included separately. Very small sub-basins within the Shu-Talas Basin are merged and dissolved.