LSTM Fully Convolutional Networks for Time Series Classification

Abstract

Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our proposed models significantly enhance the performance of fully convolutional networks with a nominal increase in model size and require minimal preprocessing of the dataset. The proposed Long Short Term Memory Fully Convolutional Network (LSTM-FCN) achieves state-of-the-art performance compared to others. We also explore the usage of attention mechanism to improve time series classification with the Attention Long Short Term Memory Fully Convolutional Network (ALSTM-FCN). Utilization of the attention mechanism allows one to visualize the decision process of the LSTM cell. Furthermore, we propose fine-tuning as a method to enhance the performance of trained models. An overall analysis of the performance of our model is provided and compared to other techniques.

7 pages, 3 figures and 2 tables

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Machine Translation by Jointly Learning to Align and Translate
• How transferable are features in deep neural networks?
• Multi-Scale Convolutional Neural Networks for Time Series Classification
• Fast and Accurate Time Series Classification with WEASEL
• How to Construct Deep Recurrent Neural Networks
• Snapshot Ensembles: Train 1, get M for free

Cited by in corpus (68)

• Multivariate LSTM-FCNs for Time Series Classification
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• Benchmarking Multivariate Time Series Classification Algorithms
• Data Augmentation techniques in time series domain: A survey and taxonomy
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
• Detecting and interpreting myocardial infarction using fully convolutional neural networks
• A Survey on Device Behavior Fingerprinting: Data Sources, Techniques, Application Scenarios, and Datasets
• Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
• Gated Transformer Networks for Multivariate Time Series Classification
• Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
• Time Series Forecasting Using LSTM Networks: A Symbolic Approach
• Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
• Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication
• Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
• A comparative study of different machine learning methods for dissipative quantum dynamics
• Scoring and Assessment in Medical VR Training Simulators with Dynamic Time Series Classification
• CLPVG: Circular limited penetrable visibility graph as a new network model for time series
• An Evaluation of Machine Learning and Deep Learning Models for Drought Prediction using Weather Data
• Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
• Similarity Learning based Few Shot Learning for ECG Time Series Classification
• ROSpace: Intrusion Detection Dataset for a ROS2-Based Cyber-Physical System
• Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification
• Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning
• NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting
• Detecting COVID-19 from digitized ECG printouts using 1D convolutional neural networks
• TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services
• Multi-Task Learning for Arousal and Sleep Stage Detection Using Fully Convolutional Networks
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Soft Sensing Regression Model: from Sensor to Wafer Metrology Forecasting
• MedLens: Improve Mortality Prediction Via Medical Signs Selecting and Regression
• Heimdallr: Fingerprinting SD-WAN Control-Plane Architecture via Encrypted Control Traffic
• Detection Latencies of Anomaly Detectors: An Overlooked Perspective ?
• Is the PPG signal chaotic?
• Discovery of Dynamics Using Linear Multistep Methods
• Towards Biologically Plausible Convolutional Networks
• Residual Attention Net for Superior Cross-Domain Time Sequence Modeling
• Performance versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems
• Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
• Timage -- A Robust Time Series Classification Pipeline
• DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification
• Fast CRDNN: Towards on Site Training of Mobile Construction Machines
• Convolutional LSTM models to estimate network traffic
• Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models
• Condition Assessment of Stay Cables through Enhanced Time Series Classification Using a Deep Learning Approach
• Extreme-SAX: Extreme Points Based Symbolic Representation for Time Series Classification
• Leveraging Deep Learning for Time Series Extrinsic Regression in predicting photometric metallicity of Fundamental-mode RR Lyrae Stars
• Adversarial Attacks on Multivariate Time Series
• Explainable Failure Predictions with RNN Classifiers based on Time Series Data
• Consumer Behaviour in Retail: Next Logical Purchase using Deep Neural Network
• ScarceGAN: Discriminative Classification Framework for Rare Class Identification for Longitudinal Data with Weak Prior
• Loss Bounds for Approximate Influence-Based Abstraction
• A Hybrid Deep Learning Model for Predictive Flood Warning and Situation Awareness using Channel Network Sensors Data
• On Technical Trading and Social Media Indicators in Cryptocurrencies' Price Classification Through Deep Learning
• Machine Learning Prediction of Time-Varying Rayleigh Channels
• Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial network
• Driver Identification through Stochastic Multi-State Car-Following Modeling
• FlexParser -- the adaptive log file parser for continuous results in a changing world
• Benchmarking Hybrid Deep Learning Architectures for Predictive Maintenance in Industry 4.0
• Feasible Architecture for Quantum Fully Convolutional Networks
• Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
• Leaked-Web: Accurate and Efficient Machine Learning-Based Website Fingerprinting Attack through Hardware Performance Counters
• A deep neural network for multi-species fish detection using multiple acoustic cameras
• KabOOM: Unsupervised Crash Categorization through Timeseries Fingerprinting
• Improving Time Series Classification Algorithms Using Octave-Convolutional Layers
• Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
• That was not what I was aiming at! Differentiating human intent and outcome in a physically dynamic throwing task
• Hardware realisation of nonlinear dynamical systems for and from biology
• Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble