Sorry, you need to enable JavaScript to visit this website.

INSTANT ADAPTIVE LEARNING: AN ADAPTIVE FILTER BASED FAST LEARNING MODEL CONSTRUCTION FOR SENSOR SIGNAL TIME SERIES CLASSIFICATION ON EDGE DEVICES

Citation Author(s):
Arpan Pal, Arijit Ukil, Trisrota Deb, Ishan Sahu, Angshul Majumdar
Submitted by:
Arijit Ukil
Last updated:
14 May 2020 - 12:56pm
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
Arijit Ukil
Paper Code:
3324

Abstract 

Abstract: 

Construction of learning model under computational and energy constraints, particularly in highly limited training time requirement is a critical as well as unique necessity of many practical IoT applications that use time series sensor signal analytics for edge devices. Yet, majority of the state-of-the-art algorithms and solutions attempt to achieve high performance objective (like test accuracy) irrespective of the computational constraints of real-life applications. In this paper, we propose Instant Adaptive Learning that characterizes the intrinsic signal processing properties of time series sensor signals using linear adaptive filtering and derivative spectrum to efficiently construct a low-cost learning model followed by standard classification algorithms. Our empirical studies on a number of time series sensor signals from publicly available time series database (UCR) demonstrate that with slight trade-off in performance, the proposed method achieves very fast learning capability.

up
1 user has voted: Arijit Ukil

Dataset Files

ICASSP_2020_presentation_Arijit.pdf

(95)