ATCN: Resource-efficient Processing of Time Series on Edge (2020-11-10T00:00:00.000000Z)

TL;DR

Agile Temporal Convolutional Network is the first time series classifier based on deep learning that can be run bare-metal on embedded microcontrollers (Cortex-M7) with limited computational performance and memory capacity while delivering state-of-the-art accuracy.

Abstract

This article presents a scalable deep learning model called Agile Temporal Convolutional Network (ATCN) for highly accurate fast classification and time series prediction in resource-constrained embedded systems. ATCN is a family of compact networks with formalized hyperparameters that enable application-specific adjustments to be made to the model architecture. It is primarily designed for embedded edge devices with very limited performance and memory, such as wearable biomedical devices and real-time reliability monitoring systems. ATCN makes fundamental improvements over the mainstream temporal convolutional neural networks, including residual connections to increase the network depth and accuracy and the incorporation of separable depth-wise convolution to reduce the computational complexity of the model. As part of the present work, two ATCN families, namely T0 and T1, are also presented and evaluated on different ranges of embedded processors: Cortex-M7 and Cortex-A57 processors. An evaluation of the ATCN models against the best-in-class InceptionTime and MiniRocket shows that ATCN almost maintains accuracy while improving the execution time on a broad range of embedded and cyber-physical applications with demand for real-time processing on the embedded edge. At the same time, in contrast to existing solutions, ATCN is the first time series classifier based on deep learning that can be run bare-metal on embedded microcontrollers (Cortex-M7) with limited computational performance and memory capacity while delivering state-of-the-art accuracy.

Authors

Mohammadreza Baharani

1 papers

Hamed Tabkhi

1 papers

TL;DR

Abstract

Authors

References49 items

Convolutional Neural Network with an Elastic Matching Mechanism for Time Series Classification

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance

MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification

An empirical survey of data augmentation for time series classification with neural networks

DeepDive: An Integrative Algorithm/Architecture Co-Design for Deep Separable Convolutional Neural Networks

Mcfly: Automated deep learning on time series

Optimizing Temporal Convolutional Network Inference on FPGA-Based Accelerators

Standalone Systolic Profile Detection of Non-Contact SCG Signal With LSTM Network

Neural Machine Translation With GRU-Gated Attention Model

REVAMP2T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels

Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting

InceptionTime: Finding AlexNet for time series classification

Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting

TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain

Real-Time Deep Learning at the Edge for Scalable Reliability Modeling of Si-MOSFET Power Electronics Converters

Implementing neural machine translation with bi-directional GRU and attention mechanism on FPGAs using HLS

LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices

Towards Understanding ECG Rhythm Classification Using Convolutional Neural Networks and Attention Mappings

Temporal Recurrent Networks for Online Action Detection

The UCR time series archive

Deep learning for time series classification: a review

Scalable Reliability Monitoring of GaN Power Converter Through Recurrent Neural Networks

Deep Learning-Based Multiple Object Visual Tracking on Embedded System for IoT and Mobile Edge Computing Applications

Convolutional Social Pooling for Vehicle Trajectory Prediction

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

Channel Pruning for Accelerating Very Deep Neural Networks

Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks

Convolutional Sequence to Sequence Learning

HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles for Time Series Classification

Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning

Temporal Convolutional Networks for Action Segmentation and Detection

Data Augmentation for Time Series Classification using Convolutional Neural Networks

WaveNet: A Generative Model for Raw Audio

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding

Distilling the Knowledge in a Neural Network

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Statistical Comparisons of Classifiers over Multiple Data Sets

Long Short-Term Memory

Phoneme recognition using time-delay neural networks

Individual Comparisons by Ranking Methods

A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings

AFNet: Temporal Locality-Aware Network With Dual Structure for Accurate and Fast Action Detection

A Simple Sequentially Rejective Multiple Test Procedure

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names