· 2018
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
- 2,077citations
- 2018year
Short summary
A novel Long- and Short-term Time-series network (LSTNet) framework, combining CNN, RNN, and autoregressive models, significantly improves multivariate time series forecasting by capturing both short-term dependencies and long-term trends.
AI-generated from the title and abstract; the full text is not read.
Key points
- LSTNet is a novel deep learning framework for multivariate time series forecasting.
- It combines CNNs for short-term local dependencies and RNNs for long-term patterns.
- An autoregressive model is incorporated to handle scale insensitivity.
- LSTNet demonstrated significant performance improvements over baseline methods on real-world data.
AI-generated from the title and abstract; the full text is not read.
Abstract
Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. Temporal data arise in these real-world applications often involves a mixture of long-term and short-term patterns, for which traditional approaches such as Autoregressive models and Gaussian Process may fail. In this paper, we proposed a novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge. LSTNet uses the Convolution Neural Network (CNN) and the Recurrent Neural Network (RNN) to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends. Furthermore, we leverage traditional autoregressive model to tackle the scale insensitive problem of the neural network model. In our evaluation on real-world data with complex mixtures of repetitive patterns, LSTNet achieved significant performance improvements over that of several state-of-the-art baseline methods. All the data and experiment codes are available online.
The authors' abstract, as published at the source., 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science