Amazing technological breakthrough possible @S-Logix

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • +91- 81240 01111

Social List

A Deep Reinforcement Learning Approach for Early Classification of Time Series - 2018

A Deep Reinforcement Learning Approach For Early Classification Of Time Series

Research Paper on A Deep Reinforcement Learning Approach For Early Classification Of Time Series

Research Area:  Machine Learning


In many real-world applications, ranging from predictive maintenance to personalized medicine, early classification of time series data is of paramount importance for supporting decision makers. In this article, we address this challenging task with a novel approach based on reinforcement learning. We introduce an early classifier agent, an end-to-end reinforcement learning agent (deep Q-network, DQN) [1] able to perform early classification in an efficient way. We formulate the early classification problem in a reinforcement learning framework: we introduce a suitable set of states and actions but we also define a specific reward function which aims at finding a compromise between earliness and classification accuracy. While most of the existing solutions do not explicitly take time into account in the final decision, this solution allows the user to set this trade-off in a more flexible way. In particular, we show experimentally on datasets from the UCR time series archive [2] that this agent is able to continually adapt its behavior without human intervention and progressively learn to compromise between accurate and fast predictions.

Deep Reinforcement Learning
Early Classification
Time Series
Deep Q-Network
time sensitive applications
Machine Learning
Deep Learning

Author(s) Name:  C. Martinez; G. Perrin; E. Ramasso; M. Rombaut

Journal name:  2018 26th European Signal Processing Conference

Conferrence name:  

Publisher name:  IEEE

DOI:  10.23919/EUSIPCO.2018.8553544

Volume Information: