2018
DOI: 10.1016/j.patcog.2018.04.022
|View full text |Cite
|
Sign up to set email alerts
|

Learning structures of interval-based Bayesian networks in probabilistic generative model for human complex activity recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
32
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 72 publications
(33 citation statements)
references
References 35 publications
1
32
0
Order By: Relevance
“…Allahbakhshi et al state that this makes it easier to understand and interpret compared to other classifier methods [34], a prerequisite for an adjustable algorithm. To discriminate more specific categories of physical activity e.g., cycling or stair walking, a machine learning approach might be more suitable [35,36]. The results of the current work confirm the need for SFP, including target population specific ADLs, in validation procedures in accordance with the recommendation of Lindemann et al [11].…”
Section: Discussionsupporting
confidence: 75%
“…Allahbakhshi et al state that this makes it easier to understand and interpret compared to other classifier methods [34], a prerequisite for an adjustable algorithm. To discriminate more specific categories of physical activity e.g., cycling or stair walking, a machine learning approach might be more suitable [35,36]. The results of the current work confirm the need for SFP, including target population specific ADLs, in validation procedures in accordance with the recommendation of Lindemann et al [11].…”
Section: Discussionsupporting
confidence: 75%
“…Moreover, as in all such studies, the classification results depend on the target activities and study settings; selecting other activities and experimental conditions might lead to different outcomes. Though we accurately detected three major sub-types of postures (i.e., sitting, standing and lying), we did not aim to detect other sub-types of posture activity such as active standing (which occupies significant percentages of human daily activities) or complex activities [44]. In future studies, a wider range of activities should be included to provide more information about health-related daily PAs.…”
Section: Contributions and Limitationsmentioning
confidence: 93%
“…For the proof-of-concept of the use of multimodal sensors, we employed a generic approach using widely-used feature selection and classification algorithms [23]. Minimum redundancy maximum relevance (mRMR), was applied to the standardized feature matrix obtained from Eq (3).…”
Section: Feature Selection and Classificationmentioning
confidence: 99%