An Efficient Scheme for Prototyping kNN in the Context of Real-Time Human Activity Recognition

Paulo J.S. Ferreira, Ricardo M.C. Magalhães, Kemilly Dearo Garcia, João M.P. Cardoso, João Mendes-Moreira

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

The Classifier kNN is largely used in Human Activity Recognition systems. Research efforts have proposed methods to decrease the high computational costs of the original kNN by focusing, e.g., on approximate kNN solutions such as the ones relying on Locality-sensitive Hashing (LSH). However, embedded kNN implementations need to address the target device memory constraints and power/energy consumption savings. One of the important aspects is the constraint regarding the maximum number of instances stored in the kNN learning process (being it offline or online and incremental). This paper presents simple, energy/computationally efficient and real-time feasible schemes to maintain a maximum number of learning instances stored by kNN. Experiments in the context of HAR show the efficiency of our best approaches, and their capability to avoid the kNN storage runs out of training instances for a given activity, a situation not prevented by typical default schemes.
Original languageEnglish
Title of host publicationIntelligent Data Engineering and Automated Learning – IDEAL 2019
Subtitle of host publication20th International Conference, Manchester, UK, November 14–16, 2019, Proceedings, Part I
EditorsHujun Yin, David Camacho, Peter Tino, Antonio J. Tallón-Ballesteros, Ronaldo Menezes
Place of PublicationCham
PublisherSpringer
Pages486-493
ISBN (Electronic)978-3-030-33607-3
ISBN (Print)978-3-030-33606-6
DOIs
Publication statusPublished - 2019
Event20th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2019 - University of Manchester, Manchester, United Kingdom
Duration: 14 Nov 201916 Nov 2019
Conference number: 20
http://www.confercare.manchester.ac.uk/events/ideal2019/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11871
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameInformation Systems and Applications, incl. Internet/Web, and HCI
PublisherSpringer

Conference

Conference20th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2019
Abbreviated titleIDEAL 2019
CountryUnited Kingdom
CityManchester
Period14/11/1916/11/19
Internet address

Keywords

  • k-Nearest neighbor
  • Classification
  • kNN prototyping
  • LSH
  • Human Activity Recognition (HAR)

Fingerprint Dive into the research topics of 'An Efficient Scheme for Prototyping kNN in the Context of Real-Time Human Activity Recognition'. Together they form a unique fingerprint.

Cite this