Adaptive mobile activity recognition system with evolving data streams

Mobile activity recognition focuses on inferring current user activities by leveraging sensory data available on today׳s sensor rich mobile phones. Supervised learning with static models has been applied pervasively for mobile activity recognition. In this paper, we propose a novel phone-based dynam...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 150; pp. 304 - 317
Main Authors: Abdallah, Zahraa Said, Gaber, Mohamed Medhat, Srinivasan, Bala, Krishnaswamy, Shonali
Format: Journal Article
Language:English
Published: Elsevier B.V 20.02.2015
Subjects:
Active learning
Activity recognition
Data transmission
Dynamical systems
Dynamics
Evolution
Incremental learning
Learning
Mobile application
Real time
Recognition
Stream mining
Streams
Ubiquitous computing
Activity recognition
Ubiquitous computing
Incremental learning
Mobile application
Stream mining
Active learning
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mobile activity recognition focuses on inferring current user activities by leveraging sensory data available on today׳s sensor rich mobile phones. Supervised learning with static models has been applied pervasively for mobile activity recognition. In this paper, we propose a novel phone-based dynamic recognition framework with evolving data streams for activity recognition. The novel framework incorporates incremental and active learning for real-time recognition and adaptation in streaming settings. While stream evolves, we refine, enhance and personalise the learning model in order to accommodate the natural drift in a given data stream. Extensive experimental results using real activity recognition data have evidenced that the novel dynamic approach shows improved performance of recognising activities especially across different users.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2014.09.074