Deep learning for time series classification

2020/10/01 by Hassan Ismail Fawaz, Fawaz, Hassan Ismail · 9 citations
Computer Science · Decision Sciences · Mathematics · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer science #FOS: Computer and information sciences #Geology #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Paleontology #Series (stratigraphy) #Stock Market Forecasting Methods #Time Series Analysis and Forecasting #Time series #cs.AI #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2010.00567

published in arXiv (Cornell University) (Cornell University) · PhD thesis

arxiv created 2020/10/01 · openalex publication_date 2020/10/01 · arxiv updated 2020/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Time series analysis is a field of data science which is interested in analyzing sequences of numerical values ordered in time. Time series are particularly interesting because they allow us to visualize and understand the evolution of a process over time. Their analysis can reveal trends, relationships and similarities across the data. There exists numerous fields containing data in the form of time series: health care (electrocardiogram, blood sugar, etc.), activity recognition, remote sensing, finance (stock market price), industry (sensors), etc. Time series classification consists of constructing algorithms dedicated to automatically label time series data. The sequential aspect of time series data requires the development of algorithms that are able to harness this temporal property, thus making the existing off-the-shelf machine learning models for traditional tabular data suboptimal for solving the underlying task. In this context, deep learning has emerged in recent years as one of the most effective methods for tackling the supervised classification task, particularly in the field of computer vision. The main objective of this thesis was to study and develop deep neural networks specifically constructed for the classification of time series data. We thus carried out the first large scale experimental study allowing us to compare the existing deep methods and to position them compared other non-deep learning based state-of-the-art methods. Subsequently, we made numerous contributions in this area, notably in the context of transfer learning, data augmentation, ensembling and adversarial attacks. Finally, we have also proposed a novel architecture, based on the famous Inception network (Google), which ranks among the most efficient to date.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Loss Surfaces of Multilayer Networks
• Ridge Regression: Applications to Nonorthogonal Problems
• A Comparison of Alternative Tests of Significance for the Problem of m Rankings
• Gradient-based learning applied to document recognition
• ImageNet Large Scale Visual Recognition Challenge
• Dynamic programming algorithm optimization for spoken word recognition
• Sequence to Sequence Learning with Neural Networks
• Distributed Representations of Sentences and Documents
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
• ImageNet classification with deep convolutional neural networks
• A Survey on Transfer Learning
• Multi-Scale Convolutional Neural Networks for Time Series Classification
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Deep Learning for Time-Series Analysis
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Echo State Network (DeepESN): A Brief Survey
• Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification
• Data Augmentation for Brain-Computer Interfaces: Analysis on Event-Related Potentials Data
• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
• Genesis of Basic and Multi-Layer Echo State Network Recurrent Autoencoders for Efficient Data Representations
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Deep neural network ensemble by data augmentation and bagging for skin lesion classification
• Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey

Cited by

• DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks
• MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series
• MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encoder
• Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomalies

Related

• Deep Learning for Time-Series Analysis
• Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
• Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
• Deep learning for time series classification: a review
• Deep Unsupervised Domain Adaptation for Time Series Classification: a Benchmark