Awesome-time-series

A comprehensive survey on the time series domains
https://github.com/cure-lab/Awesome-time-series

Last synced: 13 days ago
JSON representation

Anomaly Detection

Unsupervised Model Selection For Time-series Anomaly Detection - series anomaly detection models given an unlabeled dataset and a set of candidate models. I’d like to point out that we use adjusted F1. The adjustment ensures that once an algorithm detects even a part of the anomaly, we consider that it has detected the entire anomaly.|
Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection - guided probabilistic generative network. We combine it with adaptive Variational Graph Convolutional Recurrent Network (VGCRN) to model both spatial and temporal fine-grained correlations in MTS. To explore hierarchical latent representations, we further extend VGCRN into a deep variational network, which captures multilevel information at different layers and is robust to noisy time series.|
A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems - | online cloud server data from two different types of game business | SLA-VAE first defines anomalies based on feature extraction module, introduces semi-supervised VAE to identify anomalies in multivariate time series, and employs active learning to update the online model via a small number of uncertain samples. |
Towards a Rigorous Evaluation of Time-series Anomaly Detection - | Secure water treatment (SWaT), ...... | applying PA can severely overestimate a TAD model’s capability.|
DeepGPD: A Deep Learning Approach for Modeling Geospatio-Temporal Extreme Events - daily-description) |proposed a novel deep learning architecture (DeepGPD) capable of learning the parameters of the generalized Pareto distribution while satisfying the conditions placed on those parameters.|
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series - | PMU-B, PMU-C, SWaT, METR-LA | propose a novel flow model by imposing a Bayesian network among constituent series. |
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy - | SMD MSL SMAP SWaT PSM | propose the Anomaly Transformer with a new Anomaly-Attention mechanism to compute the association discrepancy. A minimax strategy is devised to amplify the normal-abnormal distinguishability of the association discrepancy. |
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series - | SWaT and WADI | proposed our Graph Deviation Network (GDN) approach, which learns a graph of relationships between sensors, and detects deviations from these patterns, while incorporating sensor embeddings |
Time Series Anomaly Detection with Multiresolution Ensemble Decoding - | ECG, 2D-gesture and Power-demand, Yahoo’s S5 | Its core is to use lower-resolution information to help long-range decoding at layers with higher resolutions. This is achieved by jointly learning multiple recurrent decoders where each decoder is with a different decoding length.|
Outlier Impact Characterization for Time Series Data - Relations), Physionet | study recurring outliers in time series data and aim to provide a systematic way of measuring the impact of such outliers on time series analysis |
F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams - fade/) | - | a new approach for detection of anomalies in edge streams, which uses a novel frequency-factorization technique to efficiently model the time-evolving distributions of frequencies of interactions between node-pairs. |
FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection - | By converting the non-extreme anomalies to extreme values, our framework addresses the limitation of SPOT and achieves a huge improvement in the detection accuracy. Moreover, Method of Moments is adopted to speed up the parameter estimation in the automatic thresholding. |
Event Outlier Detection in Continuous Time
Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding - |Its core idea is to model the normal patterns inside MTS data through hierarchical Variational AutoEncoder with two stochastic latent variables, each of which learns low-dimensional inter-metric or temporal embeddings. Furthermore, we propose an MCMC-based method to obtain reasonable embeddings and reconstructions at anomalous parts for MTS anomaly interpretation. |
Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering - | a specially crafted neural network architecture is posed for system identification, i.e., capturing the dynamics of CPS in a dynamical state-space model; then a Bayesian filtering algorithm is naturally applied on top of the "identified" state-space model for robust anomaly detection by tracking the uncertainty of the hidden state of the system recursively over time.|
Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection - Scale-One-Class-Recurrent-Neural-Networks) | - |a multi-scale one-class recurrent neural network for detecting anomalies in discrete event sequences. |
Online false discovery rate control for anomaly detection in time series - | - | The methods proposed in this article overcome short-comings of previous FDRC rules in the context of anomaly detection, in particular ensuring that power remains high even when the alternative is exceedingly rare (typical in anomaly detection) and the test statistics are serially dependent (typical in time series). |
Detecting Anomalous Event Sequences with Temporal Point Processes - | LOGS,STEAD | The proposed method can be combined with various TPP models, such as neural TPPs, and is easy to implement. |
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection - | have explored the transferability of the vanilla ViT pre-trained on mid-sized ImageNet-1k dataset to the more challenging COCO object detection benchmark |
Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers - | MNIST | introduced an extension to the classic DTW algorithm, which relaxes the constraints of matching endpoints of paired sequences and the continuity of the path cost. |
Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs - | - | Our key insight is that different KPIs are constrained by certain time-invariant characteristics of the underlying system, and that explicitly modelling such invariance may help resist noise in the data. We thus propose a novel anomaly detection method called SDFVAE, short for Static and Dynamic Factorized VAE, that learns the representations of KPIs by explicitly factorizing the latent variables into dynamic and static parts. |
Time-series Change Point Detection with Self-Supervised Contrastive Predictive Coding - | Yahoo!Benchmark, HASC, USC-HAD | propose a novel self-supervised CPD method, 𝑇𝑆 − 𝐶𝑃2 for time series. 𝑇𝑆 − 𝐶𝑃2 learns an embedded representation predict a future interval of a times series from historical samples. |
NTAM: Neighborhood-Temporal Attention Model for Disk Failure Prediction in Cloud Platforms - | industrial datasets collected from millions of disks in Microsoft Azure,....... | NTAM is a novel approach that not only utilizes a disk’s own status data, but also considers its neighbors’ status data. Moreover, NTAM includes a novel attention-based temporal component to capture the temporal nature of the disk status data. Besides, we propose a data enhancement method, called Temporal Progressive Sampling (TPS), to handle the extreme data imbalance issue. |
Improving Irregularly Sampled Time Series Learning with Time-Aware Dual-Attention Memory-Augmented Networks - | The proposed model can leverage both time irregularity, multi-sampling rates and global temporal patterns information inherent in IASS-MTS so as to learn more effective representations for improving prediction performance. |
BiCMTS: Bidirectional Coupled Multivariate Learning of Irregular Time Series with Missing Values - | - | BiCMTS method to represent both forward and backward value couplings within a time series by RNNs and between MTS by self-attention networks; the learned bidirectional intra- and inter-time series coupling representations are fused to estimate missing values. |
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network - | 2D-gesture, Power demand, KDD-Cup99 data, SWaT, MSL, SMAP | based on a set of hierarchical structured hyperspheres. The solution uses a probabilistic relevance on cluster centers to help the model access the whole temporal history. A center orthogonality loss and a temporal self-supervision loss are also introduced for improved feature representation. |
Application Performance Anomaly Detection with LSTM on Temporal Irregularities in Logs - | present a new method to perform anomaly detection, while maintaining the quantitative aspect of time, using a count of event types over time. |
Multivariate Time-series Anomaly Detection via Graph Attention Network - series anomaly detection. |
MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives - | - | an algorithm that can efficiently and exactly find discords of all lengths in massive time series archives. |
Outlier Detection for Time Series with Recurrent Autoencoder Ensembles - dent framework and a shared framework, both of which combine multiple S-RNN based autoencoders to enable outlier detection. |
Regularization for Time Series Trend Filtering - | - | we adopt the Hu- ber loss to suppress outliers, and utilize a combina- tion of the first order and second order difference on the trend component as regularization to cap- ture both slow and abrupt trend changes. Further- more, an efficient method is designed to solve the proposed robust trend filtering based on majoriza- tion minimization (MM) and alternative direction method of multipliers (ADMM). |
F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams - fade/) | - | a new approach for detection of anomalies in edge streams, which uses a novel frequency-factorization technique to efficiently model the time-evolving distributions of frequencies of interactions between node-pairs. |
Detecting Anomalous Event Sequences with Temporal Point Processes - | LOGS,STEAD | The proposed method can be combined with various TPP models, such as neural TPPs, and is easy to implement. |
Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
Time-series Change Point Detection with Self-Supervised Contrastive Predictive Coding - | Yahoo!Benchmark, HASC, USC-HAD | propose a novel self-supervised CPD method, 𝑇𝑆 − 𝐶𝑃2 for time series. 𝑇𝑆 − 𝐶𝑃2 learns an embedded representation predict a future interval of a times series from historical samples. |
Multivariate Time-series Anomaly Detection via Graph Attention Network - series anomaly detection. |
Practical Approach to Asynchronous Multi-variate Time Series Anomaly Detection and Localization - |Our solution is designed to leverage this behavior. The solution utilizes spectral analysis on the latent representation of a pre-trained autoencoder to extract dominant frequencies across the signals, which are then used in a subsequent network that learns the phase shifts across the signals and produces a synchronized representation of the raw multivariate. |
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection - | have explored the transferability of the vanilla ViT pre-trained on mid-sized ImageNet-1k dataset to the more challenging COCO object detection benchmark |
Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers - | MNIST | introduced an extension to the classic DTW algorithm, which relaxes the constraints of matching endpoints of paired sequences and the continuity of the path cost. |
USAD : UnSupervised Anomaly Detection on multivariate time series - | SWaT, WADI, SMD, SMAP, MSL | adversely trained autoencoders |
Regularization for Time Series Trend Filtering - | - | we adopt the Hu- ber loss to suppress outliers, and utilize a combina- tion of the first order and second order difference on the trend component as regularization to cap- ture both slow and abrupt trend changes. Further- more, an efficient method is designed to solve the proposed robust trend filtering based on majoriza- tion minimization (MM) and alternative direction method of multipliers (ADMM). |

Others

Adaptive Conformal Predictions for Time Series - making problems. Conformal prediction is a general and theoretically sound answer. However, it requires exchangeable data, excluding time series. While recent works tackled this issue, we argue that Adaptive Conformal Inference (ACI, Gibbs and Candes` , 2021), developed for distribution-shift time series, is a good procedure for time series with general dependency. We theoretically analyse the impact of the learning rate on its efficiency in the exchangeable and auto-regressive case. We propose a parameter-free method, AgACI, that adaptively builds upon ACI based on online expert aggregation. We lead extensive fair simulations against competing methods that advocate for ACI’s use in time series. We conduct a real case study: electricity price forecasting. The proposed aggregation algorithm provides efficient prediction intervals for day-ahead forecasting. All the code and data to reproduce the experiments is made available.|
Modeling Irregular Time Series with Continuous Recurrent Units - Recurrent-Units) | Pendulum Images, Climate Data (USHCN), Electronic Health Records (Physionet) | In many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) – a neural architecture that can naturally handle irregular intervals between observations. |
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion - spectral fusion to explicitly encode the affinities of abundant time-frequency pairs, and iteratively refines representations in a fusion-and-squeeze manner with Spectrum-to-Time (S2T) and Time-to-Spectrum (T2S) Aggregation modules |
Utilizing Expert Features for Contrastive Learning of Time-Series Representations - series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. |
Neural Predicting Higher-order Patterns in Temporal Networks - COM/Neural_Higher-order_Pattern_Prediction) | Tags-math-sx, Tags-ask-ubuntu, Congress-bills, DAWN, Threads-ask-ubuntu | we proposed the first model HIT to predict higher- order patterns in temporal hypergraphs to answer what type of, when, and why interactions may expand in a node triplet. HIT can be further generalized to predict even higher-order patterns. |
ONBRA: Rigorous Estimation of the Temporal Betweenness Centrality in Temporal Networks - motifs/data-html) | In this work we present ONBRA, the first sampling-based approximation algorithm for estimating the temporal betweenness centrality values of the nodes in a temporal network, providing rigorous probabilistic guar- antees on the quality of its output. |
Knowledge-based Temporal Fusion Network for Interpretable Online Video Popularity Prediction - video dataset and a micro-video dataset from the server logs of Xigua and Douyin | In this paper, we propose a Knowledge-based Temporal Fusion Network (KTFN) that incorporates knowledge graph representation to address the aforementioned challenges in the task of online video popularity prediction. |
STAM: A Spatiotemporal Aggregation Method for Graph Neural Network-based Recommendation - 16/STAM) | MovieLens, Amazon, Taobao | In this work, we propose a spatiotemporal aggregation method STAM to efficiently incorporate temporal information into neighbor embedding learning. |
A Graph Temporal Information Learning Framework for Popularity Prediction
Conditional Loss and Deep Euler Scheme for Time Series Generation - | - | - |
TS2Vec: Towards Universal Representation of Time Series - 10056879.file.myqcloud.com/10056879/test/20180524_78431960010324/KPI%E5%BC%82%E5%B8%B8%E6%A3%80%E6%B5%8B%E5%86%B3%E8%B5%9B%E6%95%B0%E6%8D%AE%E9%9B%86.zip) | performs contrastive learning in a hierarchical way over augmented context views|
Time Masking for Temporal Language Models - |- |
Long Short-Term Temporal Meta-learning in Online Recommendation - | - |- |
Structure Meets Sequences: Predicting Network of Co-evolving Sequences - group/SeeS) | - |- |
FILLING THE GAPS: MULTIVARIATE TIME SERIES IMPUTATION BY GRAPH NEURAL NETWORKS - | Air quality, Traffic, and Smart Grids | - |
PSA-GAN: PROGRESSIVE SELF ATTENTION GANS FOR SYNTHETIC TIME SERIES - gan), Code on glueonts | Electricty, M4, Solar energy, Traffic | - |
Generative Semi-Supervised Learning for Multivariate Time Series Imputation - | - | - |
Temporal Cross-Effects in Knowledge Tracing - | - |- |
Learning Dynamic Embeddings for Temporal Knowledge Graphs - | - |- |
Temporal Meta-path Guided Explainable Recommendation - | - |- |
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation - |- |
Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning - codes/HTGN-KDD21) | - |- |
Time-series Generation by Contrastive Imitation - | - |- |
Adjusting for Autocorrelated Errors in Neural Networks for Time Series - Sun/AdjustAutocorrelation) | - |- |
Spikelet: An Adaptive Symbolic Approximation for Finding Higher-Level Structure in Time Series - | - | - |
STING: Self-attention based Time-series Imputation Networks using GAN - | - |
SMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Series - | - |
TCube: Domain-Agnostic Neural Time-series Narration - | - |
Towards Interpretability and Personalization: A Predictive Framework for Clinical Time-series Analysis - | - |
Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions - | - |
CASPITA: Mining Statistically Significant Paths in Time Series Data from an Unknown Network - | - |
Multi-way Time Series Join on Multi-length Patterns - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Time-Aware Multi-Scale RNNs for Time Series Modeling - | - |
Deep reconstruction of strange attractors from time series - | - |
One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework - | - |
High-recall causal discovery for autocorrelated time series with latent confounders - | - |
Learning Long-Term Dependencies in Irregularly-Sampled Time Series - lstms) | - | - |
ARMA Nets: Expanding Receptive Field for Dense Prediction - huang-lab/ARMA-Networks) | - | - |
Learnable Group Transform For Time-Series - TimeSeries) | - | - |
Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns - | - | - |
Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data - | - |
Order-Preserving Metric Learning for Mining Multivariate Time Series - | - |
Fast Automatic Feature Selection for Multi-period Sliding Window Aggregate in Time Series - | Tianchi, PLAsTiCC, NFL, MotionSense, Gas Sensors | a framework to fill the gap of the end-to-end automatic sliding window aggregate feature selection for time series |
Matrix Profile XXII: Exact Discovery of Time Series Motifs Under DTW - | - |
Inductive Granger Causal Modeling for Multivariate Time Series - | Finance, FMRI, Synthetic data | - |
Mining Recurring Patterns in Real-Valued Time Series using the Radius Profile - | - | - |
FilCorr: Filtered and Lagged Correlation on Streaming Time Series - | - | - |
Unsupervised Scalable Representation Learning for Multivariate Time Series - |
Latent Ordinary Differential Equations for Irregularly-Sampled Time Series - | Human Activity dataset | We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. |
GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series - |
Interpolation-Prediction Networks for Irregularly Sampled Time Series - lab/interp-net) | MIMIC-III, UWaveGestureLibraryAll | In this paper, we have presented a new framework for dealing with the problem of supervised learn- ing in the presence of sparse and irregularly sampled time series. The proposed framework is fully modular.|
SOM-VAE: Interpretable Discrete Representation Learning on Time Series - | - | The SOM-VAE can recover topologically interpretable state representations on time series and static data. It provides an improvement to standard methods in terms of clustering performance and offers a way to learn discrete two-dimensional representations of the data manifold in concurrence with the reconstruction task. |
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging - |
Monash Time Series Forecasting Repository - ) |There have been many deep time series evaluated on the same datasets in recent years. Even though this works for basic benchmarking, it may not hold up when applied to a variety of temporal tasks. Its goal is to create a "master list" of different time series datasets and serve as an authoritative benchmark. Over 20 different datasets are included in the repository, spanning industries as diverse as health, retail, ride-share, and demographics.
Revisiting Time Series Outlier Detection: Definitions and Benchmarks - new synthetic datasets and 4 real-world datasets for benchmarking purposes.
Subseasonal Forecasting Microsoft - us/research/project/subseasonal-climate-forecasting/downloads/) |Microsoft has released a dataset to facilitate machine learning for improving subseasonal forecasting (e.g. two to six weeks in the future). Forecasting subseasonally helps government agencies and farmers prepare for weather events. In general, deep learning models performed quite poorly compared to other methods in Microsoft's benchmark. A simple feed-forward model proved to be the most accurate DL model, while the Informer performed poorly.
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Adaptive Conformal Predictions for Time Series - making problems. Conformal prediction is a general and theoretically sound answer. However, it requires exchangeable data, excluding time series. While recent works tackled this issue, we argue that Adaptive Conformal Inference (ACI, Gibbs and Candes` , 2021), developed for distribution-shift time series, is a good procedure for time series with general dependency. We theoretically analyse the impact of the learning rate on its efficiency in the exchangeable and auto-regressive case. We propose a parameter-free method, AgACI, that adaptively builds upon ACI based on online expert aggregation. We lead extensive fair simulations against competing methods that advocate for ACI’s use in time series. We conduct a real case study: electricity price forecasting. The proposed aggregation algorithm provides efficient prediction intervals for day-ahead forecasting. All the code and data to reproduce the experiments is made available.|
Modeling Irregular Time Series with Continuous Recurrent Units - Recurrent-Units) | Pendulum Images, Climate Data (USHCN), Electronic Health Records (Physionet) | In many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) – a neural architecture that can naturally handle irregular intervals between observations. |
Temporal Meta-path Guided Explainable Recommendation - | - |- |
Adjusting for Autocorrelated Errors in Neural Networks for Time Series - Sun/AdjustAutocorrelation) | - |- |
SMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Series - | - |
Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Fast Automatic Feature Selection for Multi-period Sliding Window Aggregate in Time Series - | Tianchi, PLAsTiCC, NFL, MotionSense, Gas Sensors | a framework to fill the gap of the end-to-end automatic sliding window aggregate feature selection for time series |
Inductive Granger Causal Modeling for Multivariate Time Series - | Finance, FMRI, Synthetic data | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
E^2GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation - | - | - |
📚 Darts - friendly forecasting and anomaly detection on time series. It contains a variety of models, from classics such as ARIMA to deep neural networks. The forecasting models can all be used in the same way, using fit() and predict() functions, similar to scikit-learn. The library also makes it easy to backtest models, combine the predictions of several models, and take external data into account. Darts supports both univariate and multivariate time series and models. The ML-based models can be trained on potentially large datasets containing multiple time series, and some of the models offer a rich support for probabilistic forecasting.
📚 Prophet - linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well.
📚 Neural Prophet - | ⭐️ 2.8K | A Neural Network based Time-Series model, inspired by Facebook Prophet and AR-Net, built on PyTorch.
📚 GluonTS
📚 stumpy - neighbor". What's important is that once you've computed your matrix profile (middle panel above) it can then be used for a variety of time series data mining tasks.
📚 tsfresh - series feature extraction by combining established algorithms from statistics, time-series analysis, signal processing, and nonlinear dynamics with a robust feature selection algorithm. In this context, the term time-series is interpreted in the broadest possible sense, such that any types of sampled data or even event sequences can be characterised.
📚 SKTIME - | ⭐️ 6.1K | sktime is a library for time series analysis in Python. It provides a unified interface for multiple time series learning tasks. Currently, this includes time series classification, regression, clustering, annotation and forecasting. It comes with time series algorithms and scikit-learn compatible tools to build, tune and validate time series models.
📚 pmdarima - | ⭐️ 1.3K | Pmdarima (originally pyramid-arima, for the anagram of 'py' + 'arima') is a statistical library designed to fill the void in Python's time series analysis capabilities.
📚 tslearn - | ⭐️ 2.4K | The machine learning toolkit for time series analysis in Python.
📚 StatsForecast - | ⭐️ 2.2K | StatsForecast offers a collection of widely used univariate time series forecasting models, including automatic ARIMA, ETS, CES, and Theta modeling optimized for high performance using numba. It also includes a large battery of benchmarking models.
📚 Streamz - | ⭐️ 1.1K | Streamz helps you build pipelines to manage continuous streams of data. It is simple to use in simple cases, but also supports complex pipelines that involve branching, joining, flow control, feedback, back pressure, and so on.
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
TCube: Domain-Agnostic Neural Time-series Narration - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework - | - |
Matrix Profile XXI: A Geometric Approach to Time Series Chains Improves Robustness - | - |
Personalized Imputation on Wearable-Sensory Time Series via Knowledge Transfer - | - |
Hybrid Sequential Recommender via Time-aware Attentive Memory Network - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |
Temporal Event Profiling based on Multivariate Time Series Analysis over Long-term Document Archives - | - |

Survey

Time series data augmentation for deep learning: a survey - | 1. This work systematically reviews and empirically compares different data augmentation methods for time series. 2. They discuss and highlight five future directions to provide useful research guidance.
Neural temporal point processes: a review - | 1. They focus on important design choices and general principles for defining neural TPP models. 2. They provide an overview of common application areas. 3. They conclude many open challenges and important directions.
Time-series forecasting with deep learning: a survey - |1. They survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time series forecasting– describing how temporal information is incorporated into predictions by each model. 2. They highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. 3. They outline some ways in which deep learning can also facilitate decision support with time series data.
Deep learning for time series forecasting: a survey - | 1. They formulate the time series forecasting problem along with its mathematical fundamentals. 2. They discuss the advantages and limitations in the feed forward networks, recurrent neural networks (including Elman, long-short term memory, gated recurrent units, and bidirectional networks), and convolutional neural networks.
DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction - data](https://github.com/deepkashiwa20/DL-Traff-Graph), grid-data |They synthetically review the deep traffic models and the widely used datasets, then build a standard benchmark to comprehensively evaluate their performances with the same settings and metrics.
Graph Neural Network for Traffic Forecasting: A Survey - | 2021 | - |The first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems (e.g. road traffic flow and speed forecasting, passenger flow forecasting in urban rail transit systems, and demand forecasting in ride-hailing platforms).
Deep learning for anomaly detection in time-series data: review, analysis, and guidelines - | 1. This review provides a background on anomaly detection in time-series data and reviews the latest applications in the real world. 2. They comparatively analyze state-of-the-art deep-anomaly-detection models with several benchmark datasets. 3. They offer guidelines for appropriate model selection and training strategy for deep learning-based time series anomaly detection.
A review on outlier/anomaly detection in time series data - |1. This review provides a structured and comprehensive state-of-the-art on outlier detection techniques in the context of time series. 2. a taxonomy is presented based on the main aspects that characterize an outlier detection technique.
A unifying review of deep and shallow anomaly detection - |1. This work draws connections between classic ‘shallow’ and novel deep approaches and show how this relation might cross-fertilize or extend both directions. 2. They outline some critical open challenges.
Big Data for Traffic Estimation and Prediction: A Survey of Data and Tools - |This study presents an up-to-date survey of open data and big data tools used for traffic estimation and prediction.
Fusion in stock market prediction: A decade survey on the necessity, recent developments, and potential future directions - | 1. Survey information, feature, model fusion from 2011–2020. 2. Discuss their limitations and future directions are explored for various stock applications.
Applications of deep learning in stock market prediction: Recent progress - | 1. Give a latest review of recent works on deep learning models for stock market prediction. 2. Discuss data sources, models, metrics and the implementation and reproducibility.
Deep Learning for Spatio-Temporal Data Mining: A Survey - | 1. A review of recent progress in applying deep learning techniques for STDM. 2. They classify existing literature based on the types of spatio-temporal data, the data mining tasks, and the deep learning models.
Urban flow prediction from spatiotemporal data using machine learning: A survey - | 1. Urban flow prediction from spatiotemporal data. 2. methods based on machine learning. 3. The difficulties and some ideas.
An empirical survey of data augmentation for time series classification with neural networks - | 2020 | link |1. a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. 2. empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. 3. analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method.
Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions - | 2020 | - | 1. They summarize the existing traffic prediction methods, widely used public datasets, give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset.
Neural forecasting: Introduction and literature overview - | 2020 | - | An introduction and an overview of some of the advances of neural networks in machine learning.
Financial time series forecasting with deep learning : A systematic literature review: 2005–2019 - | 1. They categorized the studies according to their intended forecasting implementation areas, such as index, forex, commodity forecasting. 2. They grouped DL model, such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), Long-Short Term Memory (LSTM).
Deep learning for time series classification: a review - 4-tsc) | They implemented existing approaches by training 8,730 deep learning models on 97 time series datasets.
Natural language based financial forecasting: a survey - | They show scopes, progress and hotspots in natural language based financial forecasting (NLFF).
Neural temporal point processes: a review - | 1. They focus on important design choices and general principles for defining neural TPP models. 2. They provide an overview of common application areas. 3. They conclude many open challenges and important directions.
DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction - data](https://github.com/deepkashiwa20/DL-Traff-Graph), grid-data |They synthetically review the deep traffic models and the widely used datasets, then build a standard benchmark to comprehensively evaluate their performances with the same settings and metrics.
Graph Neural Network for Traffic Forecasting: A Survey - | 2021 | - |The first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems (e.g. road traffic flow and speed forecasting, passenger flow forecasting in urban rail transit systems, and demand forecasting in ride-hailing platforms).
A review on outlier/anomaly detection in time series data - |1. This review provides a structured and comprehensive state-of-the-art on outlier detection techniques in the context of time series. 2. a taxonomy is presented based on the main aspects that characterize an outlier detection technique.
An empirical survey of data augmentation for time series classification with neural networks - | 2020 | link |1. a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. 2. empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. 3. analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method.
Financial time series forecasting with deep learning : A systematic literature review: 2005–2019 - | 1. They categorized the studies according to their intended forecasting implementation areas, such as index, forex, commodity forecasting. 2. They grouped DL model, such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), Long-Short Term Memory (LSTM).
Deep learning for time series classification: a review - 4-tsc) | They implemented existing approaches by training 8,730 deep learning models on 97 time series datasets.
Natural language based financial forecasting: a survey - | They show scopes, progress and hotspots in natural language based financial forecasting (NLFF).
Transformers in Time Series: A Survey - | 2022 | link |1. This work summarizes the network structures from adaptations and modification. 2. This work categorizes these methods into three tasks, e.g., forecasting, anomaly detection, and classification.
Time series data augmentation for deep learning: a survey - | 1. This work systematically reviews and empirically compares different data augmentation methods for time series. 2. They discuss and highlight five future directions to provide useful research guidance.
Time-series forecasting with deep learning: a survey - |1. They survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time series forecasting– describing how temporal information is incorporated into predictions by each model. 2. They highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. 3. They outline some ways in which deep learning can also facilitate decision support with time series data.
Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions - | 2020 | - | 1. They summarize the existing traffic prediction methods, widely used public datasets, give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset.
Neural forecasting: Introduction and literature overview - | 2020 | - | An introduction and an overview of some of the advances of neural networks in machine learning.
Applications of deep learning in stock market prediction: Recent progress - | 1. Give a latest review of recent works on deep learning models for stock market prediction. 2. Discuss data sources, models, metrics and the implementation and reproducibility.

Time Series Classification

Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting - jhin/ANCDE) | - | a novel NCDE architecture that incorporates the concept of attention. |
OMNI-SCALE CNNS: A SIMPLE AND EFFECTIVE KERNEL SIZE CONFIGURATION FOR TIME SERIES CLASSIFICATION - Tang/OS-CNN) | MEG-TLE, UEA 30 archive, UCR 85 archive, UCR 128 archive | presents a simple 1D-CNN block, namely OS-block. |
Correlative Channel-Aware Fusion for Multi-View Time Series Classification - | EV-Action, NTU RGB+D, UCI Daily and Sports Activities | The global-local temporal encoders are developed to extract robust temporal representations for each view, and a learnable fusion mechanism is proposed to boost the multi-view label information. |
Learnable Dynamic Temporal Pooling for Time Series Classification - | UCR/UEA |proposes a dynamic temporal pooling + a learning framework to simultaneously optimize the network parameters of a CNN classifier and the prototypical hidden series that encodes the latent semantic of the segments. |
ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification - CNN to learn time series subsequences of various lengths into unified space and propose a cluster-wise triplet loss to train the network in an unsupervised fashion. We adopt MST to obtain the MST representation of time series. |
Joint-Label Learning by Dual Augmentation for Time Series Classification - series data augmentation method. |

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

Awesome-time-series

Anomaly Detection

Others

Survey

Time Series Classification