Static Seeding and Clustering of LSTM Embeddings to Learn from Loosely Time-Decoupled Events

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Manasseh, Christian, Veliche, Razvan, Bennett, Jared, Clouse, Hamilton
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911739856027648
author Manasseh, Christian
Veliche, Razvan
Bennett, Jared
Clouse, Hamilton
author_facet Manasseh, Christian
Veliche, Razvan
Bennett, Jared
Clouse, Hamilton
contents Humans learn from the occurrence of events in a different place and time to predict similar trajectories of events. We define Loosely Decoupled Timeseries (LDT) phenomena as two or more events that could happen in different places and across different timelines but share similarities in the nature of the event and the properties of the location. In this work we improve on the use of Recurring Neural Networks (RNN), in particular Long Short-Term Memory (LSTM) networks, to enable AI solutions that generate better timeseries predictions for LDT. We use similarity measures between timeseries based on the trends and introduce embeddings representing those trends. The embeddings represent properties of the event which, coupled with the LSTM structure, can be clustered to identify similar temporally unaligned events. In this paper, we explore methods of seeding a multivariate LSTM from time-invariant data related to the geophysical and demographic phenomena being modeled by the LSTM. We apply these methods on the timeseries data derived from the COVID-19 detected infection and death cases. We use publicly available socio-economic data to seed the LSTM models, creating embeddings, to determine whether such seeding improves case predictions. The embeddings produced by these LSTMs are clustered to identify best-matching candidates for forecasting an evolving timeseries. Applying this method, we show an improvement in 10-day moving average predictions of disease propagation at the US County level.
format Preprint
id arxiv_https___arxiv_org_abs_2208_12389
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Static Seeding and Clustering of LSTM Embeddings to Learn from Loosely Time-Decoupled Events
Manasseh, Christian
Veliche, Razvan
Bennett, Jared
Clouse, Hamilton
Machine Learning
Artificial Intelligence
68T07
I.2; I.5; G.1
Humans learn from the occurrence of events in a different place and time to predict similar trajectories of events. We define Loosely Decoupled Timeseries (LDT) phenomena as two or more events that could happen in different places and across different timelines but share similarities in the nature of the event and the properties of the location. In this work we improve on the use of Recurring Neural Networks (RNN), in particular Long Short-Term Memory (LSTM) networks, to enable AI solutions that generate better timeseries predictions for LDT. We use similarity measures between timeseries based on the trends and introduce embeddings representing those trends. The embeddings represent properties of the event which, coupled with the LSTM structure, can be clustered to identify similar temporally unaligned events. In this paper, we explore methods of seeding a multivariate LSTM from time-invariant data related to the geophysical and demographic phenomena being modeled by the LSTM. We apply these methods on the timeseries data derived from the COVID-19 detected infection and death cases. We use publicly available socio-economic data to seed the LSTM models, creating embeddings, to determine whether such seeding improves case predictions. The embeddings produced by these LSTMs are clustered to identify best-matching candidates for forecasting an evolving timeseries. Applying this method, we show an improvement in 10-day moving average predictions of disease propagation at the US County level.
title Static Seeding and Clustering of LSTM Embeddings to Learn from Loosely Time-Decoupled Events
topic Machine Learning
Artificial Intelligence
68T07
I.2; I.5; G.1
url https://arxiv.org/abs/2208.12389