2015
DOI: 10.3390/e17031358
|View full text |Cite
|
Sign up to set email alerts
|

Hidden State Conditional Random Field for Abnormal Activity Recognition in Smart Homes

Abstract: Abstract:As the number of elderly people has increased worldwide, there has been a surge of research into assistive technologies to provide them with better care by recognizing their normal and abnormal activities. However, existing abnormal activity recognition (AAR) algorithms rarely consider sub-activity relations when recognizing abnormal activities. This paper presents an application of the Hidden State Conditional Random Field (HCRF) method to detect and assess abnormal activities that often occur in eld… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2015
2015
2019
2019

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 19 publications
(14 citation statements)
references
References 34 publications
0
14
0
Order By: Relevance
“…In-home automatic assessment of cognitive decline has been the subject of many studies [16,17,6,7,18,19,20]. Many machine learning approaches such as SVMs and Naïve Bayes methods [21,22], Restricted Boltzmann Machines (RBMs) [19] and Markov Logic Networks [7,18,20], Hidden Markov Models (HMMs) [14], Random Forest methods [15], and Hidden Conditional Random Fields [23] have been exploited.…”
Section: Literature Reviewmentioning
confidence: 99%
“…In-home automatic assessment of cognitive decline has been the subject of many studies [16,17,6,7,18,19,20]. Many machine learning approaches such as SVMs and Naïve Bayes methods [21,22], Restricted Boltzmann Machines (RBMs) [19] and Markov Logic Networks [7,18,20], Hidden Markov Models (HMMs) [14], Random Forest methods [15], and Hidden Conditional Random Fields [23] have been exploited.…”
Section: Literature Reviewmentioning
confidence: 99%
“…A secure smart home can detect such a situation and alert the resident in order to ensure that the home is safe and to assist the resident if needed in completing a task. Tong et al [120] tackle this problem using hidden state conditional random fields (HCRF). A HCRF can be used to compare an observed activity with a database of activities performed normally.…”
Section: Detecting and Assessing Threatsmentioning
confidence: 99%
“…The approaches to activity recognition that have been developed over the last ten years range from logic-based approaches to probabilistic machine learning approaches [1], [2], [3], [4], [5], [6], [7], [8], [9], [10]. Although the reported successes are promising, determining the correct activity from sensor data alone is often impossible, since sensors can only provide very limited information and human behaviours are inherently complex.…”
Section: Introductionmentioning
confidence: 99%