Time Series Classification with Meta Learning

Learning Algorithms ◽

Classification Task ◽

Learning To Learn ◽

Learning Tasks ◽

Task Classification ◽

Meta Learning ◽

Speed Up

Meta-Learning, the ability of learning to learn, helps to train a model to learn very quickly on a variety of learning tasks; adapting to any new environment with a minimal number of examples allows us to speed up the performance and training of the model. It solves the traditional machine learning paradigm problem, where it needed a vast dataset to learn any task to train the model from scratch. Much work has already been done on meta-learning in various learning environments, including reinforcement learning, regression task, classification task with image, and other datasets, but it is yet to be explored with the time-series domain. In this work, we aimed to understand the effectiveness of meta-learning algorithms in time series classification task with multivariate time-series datasets. We present the algorithm’s performance on the time series archive, where the result shows that using meta-learning algorithms leads to faster convergence with fewer iteration over the non-meta-learning equivalent.

Meta-Learning For Few-Shot Time Series Classification

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss39084.2020.9441016 ◽

2020 ◽

Author(s):

Sherrie Wang ◽

Marc Ruswurm ◽

Marco Korner ◽

David B. Lobell

Keyword(s):

Time Series ◽

Meta Learning

A Novel Channel and Temporal-Wise Attention in Convolutional Networks for Multivariate Time Series Classification

IEEE Access ◽

10.1109/access.2020.3040515 ◽

2020 ◽

Vol 8 ◽

pp. 212247-212257

Author(s):

Xu Cheng ◽

Peihua Han ◽

Guoyuan Li ◽

Shengyong Chen ◽

Houxiang Zhang

Keyword(s):

Time Series ◽

Convolutional Networks

2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) ◽

Multivariate Time Series Forecasting Based Cloud Computing For Consumer Price Index Using Deep Learning Algorithms

10.1109/isriti51436.2020.9315465 ◽

2020 ◽

Author(s):

Soffa Zahara ◽

Sugianto

Keyword(s):

Time Series ◽

Cloud Computing ◽

Deep Learning ◽

Price Index ◽

Learning Algorithms ◽

Consumer Price Index ◽

Time Series Forecasting

Difference-Guided Representation Learning Network for Multivariate Time-Series Classification

IEEE Transactions on Cybernetics ◽

10.1109/tcyb.2020.3034755 ◽

2020 ◽

pp. 1-11

Author(s):

Qianli Ma ◽

Zipeng Chen ◽

Shuai Tian ◽

Wing W. Y. Ng

Keyword(s):

Time Series ◽

Representation Learning ◽

Learning Network

Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies ◽

MetaTP

10.1145/3478083 ◽

2021 ◽

Vol 5 (3) ◽

pp. 1-28

Author(s):

Weida Zhong ◽

Qiuling Suo ◽

Abhishek Gupta ◽

Xiaowei Jia ◽

Chunming Qiao ◽

...

Keyword(s):

Time Series ◽

Large Scale ◽

Modern Society ◽

Training Data ◽

Traffic Prediction ◽

Temporal Prediction ◽

Reference Space ◽

Meta Learning ◽

Real World Datasets

With the popularity of smartphones, large-scale road sensing data is being collected to perform traffic prediction, which is an important task in modern society. Due to the nature of the roving sensors on smartphones, the collected traffic data which is in the form of multivariate time series, is often temporally sparse and unevenly distributed across regions. Moreover, different regions can have different traffic patterns, which makes it challenging to adapt models learned from regions with sufficient training data to target regions. Given that many regions may have very sparse data, it is also impossible to build individual models for each region separately. In this paper, we propose a meta-learning based framework named MetaTP to overcome these challenges. MetaTP has two key parts, i.e., basic traffic prediction network (base model) and meta-knowledge transfer. In base model, a two-layer interpolation network is employed to map original time series onto uniformly-spaced reference time points, so that temporal prediction can be effectively performed in the reference space. The meta-learning framework is employed to transfer knowledge from source regions with a large amount of data to target regions with a few data examples via fast adaptation, in order to improve model generalizability on target regions. Moreover, we use two memory networks to capture the global patterns of spatial and temporal information across regions. We evaluate the proposed framework on two real-world datasets, and experimental results show the effectiveness of the proposed framework.

Interpretable Multivariate Time Series Classification Based on Prototype Learning

Green, Pervasive, and Cloud Computing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-64243-3_16 ◽

2020 ◽

pp. 205-216

Author(s):

Dengjuan Ma ◽

Zhu Wang ◽

Jia Xie ◽

Bin Guo ◽

Zhiwen Yu

Keyword(s):

Time Series ◽

Prototype Learning

Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Prediction

10.5194/tc-2021-194 ◽

2021 ◽

Author(s):

Fatemehalsadat Madaeni ◽

Karem Chokmani ◽

Rachid Lhissou ◽

Saeid Homayuni ◽

Yves Gauthier ◽

...

Keyword(s):

Time Series ◽

Short Term Memory ◽

Weather Forecasting ◽

Water Levels ◽

Ice Jams ◽

Ice Jam ◽

Learning Techniques ◽

Long Short Term Memory

Abstract. In cold regions, ice-jam events result in severe flooding due to a rapid rise in water levels upstream of the jam. These floods threaten human safety and damage properties and infrastructures as the floods resulting from ice-jams are sudden. Hence, the ice-jam prediction tools can give an early warning to increase response time and minimize the possible corresponding damages. However, the ice-jam prediction has always been a challenging problem as there is no analytical method available for this purpose. Nonetheless, ice jams form when some hydro-meteorological conditions happen, a few hours to a few days before the event. The ice-jam prediction problem can be considered as a binary multivariate time-series classification. Deep learning techniques have been successfully applied for time-series classification in many fields such as finance, engineering, weather forecasting, and medicine. In this research, we successfully applied CNN, LSTM, and combined CN-LSTM networks for ice-jam prediction for all the rivers in Quebec. The results show that the CN-LSTM model yields the best results in the validation and generalization with F1 scores of 0.82 and 0.91, respectively. This demonstrates that CNN and LSTM models are complementary, and a combination of them further improves classification.