Time Series

Time series analysis focuses on understanding and modeling data points collected over time, aiming to extract patterns, make predictions, and gain insights from sequential information. Current research emphasizes developing advanced model architectures, such as transformers and recurrent neural networks (RNNs/LSTMs), to handle increasingly complex, high-dimensional, and non-stationary time series data, often incorporating techniques like attention mechanisms and mixture-of-experts models for improved efficiency and accuracy. This field is crucial for numerous applications across diverse domains, including finance, healthcare, and environmental monitoring, enabling better forecasting, anomaly detection, and decision-making based on temporal data.

Papers

April 9, 2023

Embarrassingly Simple MixUp for Time-series
Karan Aggarwal, Jaideep Srivastava
Time Series Semi Supervised Learning Time Series Classification Data Augmentation Technique Pseudo Labeled Data

April 6, 2023

April 3, 2023

March 30, 2023

Inferring networks from time series: a neural approach
Thomas Gaskin, Grigorios A. Pavliotis, Mark Girolami
Time Series Network Programming Markov Chain Monte Carlo Network Structure Parameter Space Network Inference Large Network Neural Approach

March 28, 2023

From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
Dominique Mercier, Andreas Dengel, Sheraz Ahmed
Deep Learning Time Series GAN Model Context Information Private Data

March 26, 2023

Galaxy Classification Using Transfer Learning and Ensemble of CNNs With Multiple Colour Spaces
Yevonnael Andrew
Transfer Learning Time Series CNN Model Diverse Ensemble Color Space Astronomical Image Galaxy Classification Color Transformation Galaxy Zoo Dataset

March 24, 2023

Towards Diverse and Coherent Augmentation for Time-Series Forecasting
Xiyuan Zhang, Ranak Roy Chowdhury, Jingbo Shang, Rajesh Gupta, Dezhi Hong
Data Augmentation Time Series Time Series Forecasting Time Series Data Diverse Set Self Augmentation Real World Time Series Time Augmentation

March 22, 2023

March 21, 2023

March 18, 2023

Discovering Predictable Latent Factors for Time Series Forecasting
Jingyi Hou, Zhen Dong, Jiayu Zhou, Zhijie Liu
Time Series Time Series Forecasting Latent Factor Predictability Problem Time Series Forecasting Method

March 16, 2023

March 15, 2023

The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression
Tarek Allam, Julien Peloton, Jason D. McEwen
Time Series Large Scale Neural Network Compression Fast Classification Astronomical Transient Real Time Classification Transient Histogram

March 14, 2023

Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates
Mari Dahl Eggen, Alise Danielle Midtfjord
Time Series High Uncertainty Anticipation Deep Learning Approach Memory Trace Neural Network Model Stochastic Model Stochastic Delay

March 13, 2023

Time Series

Papers

Embarrassingly Simple MixUp for Time-series

Adaptive Student's t-distribution with method of moments moving estimator for nonstationary time series

SE-shapelets: Semi-supervised Clustering of Time Series Using Representative Shapelets

Conformal Prediction Regions for Time Series using Linear Complementarity Programming

Astronomical image time series classification using CONVolutional attENTION (ConvEntion)

Inferring networks from time series: a neural approach

From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification

Galaxy Classification Using Transfer Learning and Ensemble of CNNs With Multiple Colour Spaces

Towards Diverse and Coherent Augmentation for Time-Series Forecasting

Conformal Prediction for Time Series with Modern Hopfield Networks

Wasserstein Adversarial Examples on Univariant Time Series Data

Time Series Contrastive Learning with Information-Aware Augmentations

Style Miner: Find Significant and Stable Explanatory Factors in Time Series with Constrained Reinforcement Learning

Discovering Predictable Latent Factors for Time Series Forecasting

Effectively Modeling Time Series with Simple Discrete State Spaces

Generating synthetic multi-dimensional molecular-mediator time series data for artificial intelligence-based disease trajectory forecasting and drug development digital twins: Considerations

The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression

Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates

Comparing statistical and machine learning methods for time series forecasting in data-driven logistics -- A simulation study

Spacecraft Anomaly Detection with Attention Temporal Convolution Network