Please use this identifier to cite or link to this item:
Author(s): João Mendes Moreira
Hugo Cardoso
Title: Improving human activity classification through online semi-supervised learning
Issue Date: 2016-09-23
Abstract: Built-in sensors in most modern smartphones open multipleopportunities for novel context-aware applications. Although the HumanActivity Recognition field seized such opportunity, many challengesare yet to be addressed, such as the differences in movement by peopledoing the same activities. This paper exposes empirical research onOnline Semi-supervised Learning (OSSL), an under-explored incrementalapproach capable of adapting the classification model to the userby continuously updating it as data from the users own input signalsarrives. Ultimately, we achieved an average accuracy increase of 0.18percentage points (PP) resulting in a 82.76% accuracy model with NaiveBayes, 0.14 PP accuracy increase resulting in a 83.03% accuracy modelwith a Democratic Ensemble, and 0.08 PP accuracy increase resultingin a 84.63% accuracy model with a Confidence Ensemble. These modelscould detect 3 stationary activities, 3 active activities, and all transitionsbetween the stationary activities, totaling 12 distinct activities
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: openAccess
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
162606.pdf658.32 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.