Hidden Markov Mined Activity Model for Human Activity Recognition

Object-usage-based human activity recognition systems require activity data for learning. Acquiring such data from the real world is expensive and time consuming. To overcome such difficulties, the exploitation of web activity data is gaining popularity. However, due to a lack of much real-world inf...

Full description

Saved in:
Bibliographic Details
Main Author: A. M. Jehad Sarkar
Format: Article
Language:English
Published: Wiley 2014-03-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2014/949175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849473033392095232
author A. M. Jehad Sarkar
author_facet A. M. Jehad Sarkar
author_sort A. M. Jehad Sarkar
collection DOAJ
description Object-usage-based human activity recognition systems require activity data for learning. Acquiring such data from the real world is expensive and time consuming. To overcome such difficulties, the exploitation of web activity data is gaining popularity. However, due to a lack of much real-world information in such data, existing activity models are not suitable for web data. In this paper, we propose a hidden Markov model- (HMM-) based activity model specially designed to use web activity data for activity recognition. It utilizes a sequence of object-usage information for activity recognition. We also propose a web activity data mining algorithm for this model. It is extremely fast and efficient in comparison with the existing algorithms. We perform three experiments to validate the proposed model. We show that the model can be effectively utilized by an activity recognition system.
format Article
id doaj-art-d9637a9c012e46d38716d30871bc8fd8
institution Kabale University
issn 1550-1477
language English
publishDate 2014-03-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-d9637a9c012e46d38716d30871bc8fd82025-08-20T03:24:17ZengWileyInternational Journal of Distributed Sensor Networks1550-14772014-03-011010.1155/2014/949175949175Hidden Markov Mined Activity Model for Human Activity RecognitionA. M. Jehad SarkarObject-usage-based human activity recognition systems require activity data for learning. Acquiring such data from the real world is expensive and time consuming. To overcome such difficulties, the exploitation of web activity data is gaining popularity. However, due to a lack of much real-world information in such data, existing activity models are not suitable for web data. In this paper, we propose a hidden Markov model- (HMM-) based activity model specially designed to use web activity data for activity recognition. It utilizes a sequence of object-usage information for activity recognition. We also propose a web activity data mining algorithm for this model. It is extremely fast and efficient in comparison with the existing algorithms. We perform three experiments to validate the proposed model. We show that the model can be effectively utilized by an activity recognition system.https://doi.org/10.1155/2014/949175
spellingShingle A. M. Jehad Sarkar
Hidden Markov Mined Activity Model for Human Activity Recognition
International Journal of Distributed Sensor Networks
title Hidden Markov Mined Activity Model for Human Activity Recognition
title_full Hidden Markov Mined Activity Model for Human Activity Recognition
title_fullStr Hidden Markov Mined Activity Model for Human Activity Recognition
title_full_unstemmed Hidden Markov Mined Activity Model for Human Activity Recognition
title_short Hidden Markov Mined Activity Model for Human Activity Recognition
title_sort hidden markov mined activity model for human activity recognition
url https://doi.org/10.1155/2014/949175
work_keys_str_mv AT amjehadsarkar hiddenmarkovminedactivitymodelforhumanactivityrecognition