TSViz: Demystification of Deep Learning Models for Time-Series Analysis

TSViz: Demystification of Deep Learning Models for Time-Series Analysis

This paper presents a novel framework for the demystification of convolutional deep learning models for time-series analysis. This is a step toward making informed/explainable decisions in the domain of time series, powered by deep learning. There have been numerous efforts to increase the interpret...

Podrobná bibliografie
Hlavní autoři:	Shoaib Ahmed Siddiqui, Dominique Mercier, Mohsin Munir, Andreas Dengel, Sheraz Ahmed
Médium:	Článek
Jazyk:	English
Vydáno:	IEEE 2019-01-01
Edice:	IEEE Access
Témata:	Deep learning representation learning convolutional neural networks time-series analysis time-series forecasting feature importance
On-line přístup:	https://ieeexplore.ieee.org/document/8695734/

Podobné jednotky

TSInsight: A Local-Global Attribution Framework for Interpretability in Time Series Data
Autor: Shoaib Ahmed Siddiqui, a další
Vydáno: (2021-11-01)

TimeREISE: Time Series Randomized Evolving Input Sample Explanation
Autor: Dominique Mercier, a další
Vydáno: (2022-05-01)

Linear Model and Gradient Feature Elimination Algorithm Based on Seasonal Decomposition for Time Series Forecasting
Autor: Sheng-Tzong Cheng, a další
Vydáno: (2025-03-01)

DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
Autor: Mohsin Munir, a další
Vydáno: (2019-01-01)

Random Noise vs. State-of-the-Art Probabilistic Forecasting Methods: A Case Study on CRPS-Sum Discrimination Ability
Autor: Alireza Koochali, a další
Vydáno: (2022-05-01)

Conditional Temporal Aggregation for Time Series Forecasting Using Feature-Based Meta-Learning
Autor: Anastasios Kaltsounis, a další
Vydáno: (2023-04-01)

DSIPTS: A high productivity environment for time series forecasting models
Autor: Andrea Gobbi, a další
Vydáno: (2024-12-01)

Time-Series Neural Network: A High-Accuracy Time-Series Forecasting Method Based on Kernel Filter and Time Attention
Autor: Lexin Zhang, a další
Vydáno: (2023-09-01)

Skip-RCNN: A Cost-Effective Multivariate Time Series Forecasting Model
Autor: Haitao Song, a další
Vydáno: (2023-01-01)

Probabilistic Forecasting of Sensory Data With Generative Adversarial Networks – ForGAN
Autor: Alireza Koochali, a další
Vydáno: (2019-01-01)

Short-Term Campus Load Forecasting Using CNN-Based Encoder–Decoder Network with Attention
Autor: Zain Ahmed, a další
Vydáno: (2024-09-01)

Deep learning approaches for MIMO time-series analysis
Autor: Fachrul Kurniawan, a další
Vydáno: (2023-07-01)

CNN-Based Time Series Decomposition Model for Video Prediction
Autor: Jinyoung Lee, a další
Vydáno: (2024-01-01)

FuseAD: Unsupervised Anomaly Detection in Streaming Sensors Data by Fusing Statistical and Deep Learning Models
Autor: Mohsin Munir, a další
Vydáno: (2019-05-01)

“Dust in the Wind...”, Deep Learning Application to Wind Energy Time Series Forecasting
Autor: Jaume Manero, a další
Vydáno: (2019-06-01)

Time Series Dataset Survey for Forecasting with Deep Learning
Autor: Yannik Hahn, a další
Vydáno: (2023-03-01)

A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model
Autor: Sang-Ha Sung, a další
Vydáno: (2022-09-01)

A comparative study of demand forecasting based on machine learning methods with time series approach
Autor: Akbar Abbaspour Ghadim Bonab
Vydáno: (2022-07-01)

Explainable deep learning on multi-target time series forecasting: An air pollution use case
Autor: Manuel J. Jiménez-Navarro, a další
Vydáno: (2024-12-01)

Self-Supervised Representation Learning for Document Image Classification
Autor: Shoaib Ahmed Siddiqui, a další
Vydáno: (2021-01-01)

Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting
Autor: Pedro Lara-Benítez, a další
Vydáno: (2020-03-01)

Cheng Fuzzy Time Series Model to Forecast the Price of Crude Oil in Malaysia
Autor: Jasmani Bidin, a další
Vydáno: (2022-09-01)

Cheng Fuzzy Time Series Model to Forecast the Price of Crude Oil in Malaysia
Autor: Jasmani Bidin, a další
Vydáno: (2022-09-01)

Stride-TCN for Energy Consumption Forecasting and Its Optimization
Autor: Le Hoang Anh, a další
Vydáno: (2022-09-01)

A Novel Approach for Temperature Forecasting in Climate Change Using Ensemble Decomposition of Time Series
Autor: Erick Estrada-Patiño, a další
Vydáno: (2024-09-01)

Intermittent Time Series Demand Forecasting Using Dual Convolutional Neural Networks
Autor: Sina Mirshahi, a další
Vydáno: (2024-06-01)

Recurrent neural networks for time series prediction
Autor: Perez Orozco, B
Vydáno: (2019)

Forecasting and time series analysis /
Autor: 246766 Montgomery, Douglas C., a další
Vydáno: (1976)

Forecasting and time series analysis /
Autor: 246766 Montgomery, Douglas C., a další
Vydáno: (1990)

Peramalan Data Kunjungan Wisatawan Mancanegara ke Indonesia menggunakan Fuzzy Time Series
Autor: Indra Jiwana Thira, a další
Vydáno: (2019-04-01)

Introduction to time series analysis and forecasting /
Autor: 246766 Montgomery, Douglas C., a další
Vydáno: (2008)

Time series and forecasting : an applied approach /
Autor: 186292 Bowerman, Bruce L., a další
Vydáno: (1979)

Forecasting and time series : an applied approach /
Autor: 186292 Bowerman, Bruce L., a další
Vydáno: (1993)

Sparse Representation Based Approach to Prediction for Economic Time Series
Autor: Weina Wang, a další
Vydáno: (2019-01-01)

SCALE-BOSS-MR: Scalable Time Series Classification Using Multiple Symbolic Representations
Autor: Apostolos Glenis, a další
Vydáno: (2024-01-01)

What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification
Autor: Maresa Schröder, a další
Vydáno: (2023-05-01)

Forecasting, time series and regression : an applied approach /
Autor: 186292 Bowerman, Bruce L., a další
Vydáno: (2005)

Forecasting time series which are inherently discontinuous /
Autor: 390538 Coopersmith, Lewis W.

Recent Advances in Energy Time Series Forecasting
Autor: Francisco Martínez-Álvarez, a další
Vydáno: (2017-06-01)

DeepTSF: Codeless machine learning operations for time series forecasting
Autor: Sotiris Pelekis, a další
Vydáno: (2024-09-01)