Features Fusion Framework for Multimodal Irregular Time-series Events

09/05/2022
by   Peiwang Tang, et al.
0

Some data from multiple sources can be modeled as multimodal time-series events which have different sampling frequencies, data compositions, temporal relations and characteristics. Different types of events have complex nonlinear relationships, and the time of each event is irregular. Neither the classical Recurrent Neural Network (RNN) model nor the current state-of-the-art Transformer model can deal with these features well. In this paper, a features fusion framework for multimodal irregular time-series events is proposed based on the Long Short-Term Memory networks (LSTM). Firstly, the complex features are extracted according to the irregular patterns of different events. Secondly, the nonlinear correlation and complex temporal dependencies relationship between complex features are captured and fused into a tensor. Finally, a feature gate are used to control the access frequency of different tensors. Extensive experiments on MIMIC-III dataset demonstrate that the proposed framework significantly outperforms to the existing methods in terms of AUC (the area under Receiver Operating Characteristic curve) and AP (Average Precision).

READ FULL TEXT
research
09/27/2018

Using Autoencoders To Learn Interesting Features For Detecting Surveillance Aircraft

This paper explores using a Long short-term memory (LSTM) based sequence...
research
05/02/2021

TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data

Prediction based on Irregularly Sampled Time Series (ISTS) is of wide co...
research
02/19/2022

A Novel Anomaly Detection Method for Multimodal WSN Data Flow via a Dynamic Graph Neural Network

Anomaly detection is widely used to distinguish system anomalies by anal...
research
07/12/2022

Improved Batching Strategy For Irregular Time-Series ODE

Irregular time series data are prevalent in the real world and are chall...
research
05/10/2019

Large-Scale Spectrum Occupancy Learning via Tensor Decomposition and LSTM Networks

A new paradigm for large-scale spectrum occupancy learning based on long...
research
09/08/2019

Feature-Set-Engineering for Detecting Freezing of Gait in Parkinson's Disease using Deep Recurrent Neural Networks

Freezing of gait (FoG) is a common gait disability in Parkinson's diseas...

Please sign up or login with your details

Forgot password? Click here to reset