Deep Learning for Time-Series Analysis

Abstract

In many real-world application, e.g., speech recognition or sleep stage classification, data are captured over the course of time, constituting a Time-Series. Time-Series often contain temporal dependencies that cause two otherwise identical points of time to belong to different classes or predict different behavior. This characteristic generally increases the difficulty of analysing them. Existing techniques often depended on hand-crafted features that were expensive to create and required expert knowledge of the field. With the advent of Deep Learning new models of unsupervised learning of features for Time-series analysis and forecast have been developed. Such new developments are the topic of this paper: a review of the main Deep Learning techniques is presented, and some applications on Time-Series analysis are summaried. The results make it clear that Deep Learning has a lot to contribute to the field.

Written as part of the Seminar on Collaborative Intelligence in the TU Kaiserslautern. January 2016

References in corpus (4)

• Deep Learning in Neural Networks: An Overview
• Fully Convolutional Networks for Semantic Segmentation
• Time-series modeling with undecimated fully convolutional neural networks
• Deep Learning for Tactile Understanding From Visual and Haptic Data

Cited by in corpus (32)

• Deep learning for time series classification: a review
• Deep Learning for Anomaly Detection: A Survey
• Human Activity Recognition using Inertial, Physiological and Environmental Sensors: a Comprehensive Survey
• Transfer learning for time series classification
• XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification
• Broad-UNet: Multi-scale feature learning for nowcasting tasks
• Estimation of energy consumption of electric vehicles using Deep Convolutional Neural Network to reduce driver's range anxiety
• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• Autoregressive Convolutional Neural Networks for Asynchronous Time Series
• Recurrent Neural Networks for Time Series Forecasting
• A long short-term memory embedding for hybrid uplifted reduced order models
• Forecasting Economics and Financial Time Series: ARIMA vs. LSTM
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• AR-Net: A simple Auto-Regressive Neural Network for time-series
• Deep Air Quality Forecasting Using Hybrid Deep Learning Framework
• Multivariate Time Series Classification using Dilated Convolutional Neural Network
• Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification
• Adjusting for Autocorrelated Errors in Neural Networks for Time Series
• Encoding Candlesticks as Images for Patterns Classification Using Convolutional Neural Networks
• Optimisation of non-pharmaceutical measures in COVID-19 growth via neural networks
• Deep learning for time series classification
• Deep Learning in Multiple Multistep Time Series Prediction
• Fast CRDNN: Towards on Site Training of Mobile Construction Machines
• Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
• Should I Raise The Red Flag? A comprehensive survey of anomaly scoring methods toward mitigating false alarms
• PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification
• DTWSSE: Data Augmentation with a Siamese Encoder for Time Series
• Challenges and approaches to time-series forecasting in data center telemetry: A Survey
• Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?
• MegazordNet: combining statistical and machine learning standpoints for time series forecasting
• Deep Learning based Estimation of Weaving Target Maneuvers
• Dynamic Time Warp Convolutional Networks