Short and long time series classification using convolutional neural networks

Overview

time-series-classification

Short and long time series classification via convolutional neural networks

In this project, we present a novel framework for time series classification, which is based on Gramian Angular Summation/Difference Fields and Markov Transition Fields (GAF-MTF), a recently published image feature extraction method. A convolutional neural network (CNN) was employed as the classifier. This framework enables the use of CNN to learn high-level features and classify time series. Its performance was evaluated on 16 standard datasets. Experiment results show that our framework outperforms or achieves the same level at least with the GAF-MTF+Tiled CNN framework on 14 of the 16 datasets. And it obtained competitive performance compared with other 8 representive approaches. Furthermore, we compared the performance of GAF-MTF feature with other 5 image features on a large-scale cough dataset. Results indicates that the GAF-MTF feature is not suitable for large-scale cough datasets while its competitive performance on the standard datasets.

Image features extraction

Short time series

Image features for short time series:

  • GASF

- GADF

- MTF

Large-scale cough dataset

Image features for cough dataset:

  • Comparision of the six image features:

CNN

  • Framework for short time series classification:

- AlexNet/CaffeNet

Results

  • short time series classification:

- long time series classificaiton:

Appendix

Dataset information:

Software Links:

This project is partly motivated by @Zhiguang Wang, who is the author of "Imaging Time-Series to Improve Classification and Imputation". He provided me the source code to extract GASF-GADF-MTF features and pointed out that "The tiled CNN is not the best one and the TICA pre-training stage seems unnecessary". His advice helped us save a great deal of time. Thanks for his kindness and if you use this repository for GAF/MTF feature extraction, please cite the work in your publication:

@inproceedings{Wang:2015:ITI:2832747.2832798,
 author = {Wang, Zhiguang and Oates, Tim},
 title = {Imaging Time-series to Improve Classification and Imputation},
 booktitle = {Proceedings of the 24th International Conference on Artificial Intelligence},
 series = {IJCAI'15},
 year = {2015},
 isbn = {978-1-57735-738-4},
 location = {Buenos Aires, Argentina},
 pages = {3939--3945},
 numpages = {7},
 url = {http://dl.acm.org/citation.cfm?id=2832747.2832798},
 acmid = {2832798},
 publisher = {AAAI Press},
}

NOTE: The cough dataset used in this work can not be accessed now for some privacy issues!

Python Auto-ML Package for Tabular Datasets

Tabular-AutoML AutoML Package for tabular datasets Tabular dataset tuning is now hassle free! Run one liner command and get best tuning and processed

Sagnik Roy 18 Nov 20, 2022
BTC-Generator - BTC Generator With Python

Что такое BTC-Generator? Это генератор чеков всеми любимого @BTC_BANKER_BOT Для

DoomGod 3 Aug 24, 2022
Zeyuan Chen, Yangchao Wang, Yang Yang and Dong Liu.

Principled S2R Dehazing This repository contains the official implementation for PSD Framework introduced in the following paper: PSD: Principled Synt

zychen 78 Dec 30, 2022
Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Dangers of Bayesian Model Averaging under Covariate Shift This repository contains the code to reproduce the experiments in the paper Dangers of Bayes

Pavel Izmailov 25 Sep 21, 2022
A PyTorch library and evaluation platform for end-to-end compression research

CompressAI CompressAI (compress-ay) is a PyTorch library and evaluation platform for end-to-end compression research. CompressAI currently provides: c

InterDigital 680 Jan 06, 2023
Pytorch implementation of few-shot semantic image synthesis

Few-shot Semantic Image Synthesis Using StyleGAN Prior Our method can synthesize photorealistic images from dense or sparse semantic annotations using

40 Sep 26, 2022
A library for using chemistry in your applications

Chemistry in python Resources Used The following items are not made by me! Click the words to go to the original source Periodic Tab Json - Used in -

Tech Penguin 28 Dec 17, 2021
AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models Descrip

Angel de Paula 1 Jun 08, 2022
Predictive Maintenance LSTM

Predictive-Maintenance-LSTM - Predictive maintenance study for Complex case study, we've obtained failure causes by operational error and more deeply by design mistakes.

Amir M. Sadafi 1 Dec 31, 2021
8-week curriculum for AI Builders

curriculum 8-week curriculum for AI Builders สารบัญ บทที่ 1 - Machine Learning คืออะไร บทที่ 2 - ชุดข้อมูลมหัศจรรย์และถิ่นที่อยู่ บทที่ 3 - Stochastic

AI Builders 134 Jan 03, 2023
code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification

On Robust Prefix-Tuning for Text Classification Prefix-tuning has drawed much attention as it is a parameter-efficient and modular alternative to adap

Zonghan Yang 12 Nov 30, 2022
A Partition Filter Network for Joint Entity and Relation Extraction EMNLP 2021

EMNLP 2021 - A Partition Filter Network for Joint Entity and Relation Extraction

zhy 127 Jan 04, 2023
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation, available for both PyTorch and Tensorflow.

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation, available for both PyTorch and Tensorflow.

730 Jan 09, 2023
COIN the currently largest dataset for comprehensive instruction video analysis.

COIN Dataset COIN is the currently largest dataset for comprehensive instruction video analysis. It contains 11,827 videos of 180 different tasks (i.e

86 Dec 28, 2022
Deep Learning ❤️ OneFlow

Deep Learning with OneFlow made easy 🚀 ! Carefree? carefree-learn aims to provide CAREFREE usages for both users and developers. User Side Computer V

21 Oct 27, 2022
A Japanese Medical Information Extraction Toolkit

JaMIE: a Japanese Medical Information Extraction toolkit Joint Japanese Medical Problem, Modality and Relation Recognition The Train/Test phrases requ

7 Dec 12, 2022
Improving Object Detection by Estimating Bounding Box Quality Accurately

Improving Object Detection by Estimating Bounding Box Quality Accurately Abstrac

2 Apr 14, 2022
.NET bindings for the Pytorch engine

TorchSharp TorchSharp is a .NET library that provides access to the library that powers PyTorch. It is a work in progress, but already provides a .NET

Matteo Interlandi 17 Aug 30, 2021
A simple but complete full-attention transformer with a set of promising experimental features from various papers

x-transformers A concise but fully-featured transformer, complete with a set of promising experimental features from various papers. Install $ pip ins

Phil Wang 2.3k Jan 03, 2023
Library to enable Bayesian active learning in your research or labeling work.

Bayesian Active Learning (BaaL) BaaL is an active learning library developed at ElementAI. This repository contains techniques and reusable components

ElementAI 687 Dec 25, 2022