1,716
edits
Changes
Jump to navigation
Jump to search
mLine 108:
Line 108: + Line 120:
Line 121: + + + + + + + +
Talk:Finding relations between variables in time series (edit)
Revision as of 23:31, 22 July 2022
, 23:31, 22 July 2022→even more sources
https://arxiv.org/abs/2207.06414 ER time series "robustness of this approach" deep learning interpretable
https://arxiv.org/abs/2207.06414 ER time series "robustness of this approach" deep learning interpretable
https://arxiv.org/abs/2207.06414 DEEP, irregular time intervals, EHR, Long-term Dependencies and Short-term Correlations
https://arxiv.org/abs/2206.12414 !!!? marked temporal point processes DEEP missing events
https://arxiv.org/abs/2206.12414 !!!? marked temporal point processes DEEP missing events
https://arxiv.org/abs/2110.05357 !! irregular sampling, graph neural network, dynamics of sensors purely from observational data, classify time series, healthcare
https://arxiv.org/abs/2110.05357 !! irregular sampling, graph neural network, dynamics of sensors purely from observational data, classify time series, healthcare
https://arxiv.org/abs/2204.00961 ... ? LSTM DEEP REINFORCEMENT recommend exercise routines to user sepcific needs
https://arxiv.org/abs/2106.03211 extreme events RNN s&p500 stocks
https://arxiv.org/abs/2107.05489 !!! ML for time series LSTM ....walk-forward algorithm that also calculates point-wise confidence intervals for the predictions
https://arxiv.org/abs/2108.13461 !!!!!!! healthcare predictive analytics, DEEP ?feature selection is not an issue? " feature engineering to capture the sequential nature of patient data, which may not adequately leverage the temporal patterns" " representations of key factors (e.g., medical concepts or patients) and their interactions from high-dimensional raw" summarises key research streams
https://arxiv.org/abs/2204.13451 EHR predicting "The common time-series representation is indirect in extracting such information from EHR because it focuses on detailed dependencies between values in successive observations, not cumulative information. "