Human activity mining in multi-occupancy contexts based on nearby interaction under a fuzzy approach

Aurora Polo-Rodriguez; Filippo Cavallo; CD Nugent; Javier Medina Quero

doi:10.1016/j.iot.2023.101018

Human activity mining in multi-occupancy contexts based on nearby interaction under a fuzzy approach

Aurora Polo-Rodriguez, Filippo Cavallo, CD Nugent, Javier Medina Quero

Faculty Of Computing, Eng. & Built Env.

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

19 Downloads (Pure)

Abstract

Multioccupation encompasses real-life environments in which people interact in the same common space. Recognizing activities in this context for each inhabitant has been challenging and complex. This work presents a fuzzy knowledge-based system for mining human activities in multi-occupancy contexts based on nearby interaction based on the Ultra-wideband. First, interest zone spatial location is modelled using a straightforward fuzzy logic approach, enabling discriminating short-term event interactions. Second, linguistic protoforms use fuzzy rules to describe long-term events for mining human activities in a multi-occupancy context. A data set with multimodal sensors has been collected and labelled to exhibit the application of the approach. The results show an encouraging performance (0.9 precision) in the discrimination of multiple occupations.

Original language	English
Article number	101018
Journal	IEEE Internet of Things
Volume	25
Early online date	1 Dec 2023
DOIs	https://doi.org/10.1016/j.iot.2023.101018
Publication status	Published (in print/issue) - 5 Dec 2023

Keywords

Multi-occupancy
Human activity recognition
Nearby interaction

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.iot.2023.101018

Final published versionFinal published version, 2.15 MBLicence: CC BY

Cite this

@article{b5aced8c853c4de5aca8446823f23642,

title = "Human activity mining in multi-occupancy contexts based on nearby interaction under a fuzzy approach",

abstract = "Multioccupation encompasses real-life environments in which people interact in the same common space. Recognizing activities in this context for each inhabitant has been challenging and complex. This work presents a fuzzy knowledge-based system for mining human activities in multi-occupancy contexts based on nearby interaction based on the Ultra-wideband. First, interest zone spatial location is modelled using a straightforward fuzzy logic approach, enabling discriminating short-term event interactions. Second, linguistic protoforms use fuzzy rules to describe long-term events for mining human activities in a multi-occupancy context. A data set with multimodal sensors has been collected and labelled to exhibit the application of the approach. The results show an encouraging performance (0.9 precision) in the discrimination of multiple occupations.",

keywords = "Multi-occupancy, Human activity recognition, Nearby interaction",

author = "Aurora Polo-Rodriguez and Filippo Cavallo and CD Nugent and Quero, {Javier Medina}",

year = "2023",

month = dec,

day = "5",

doi = "10.1016/j.iot.2023.101018",

language = "English",

volume = "25",

journal = "IEEE Internet of Things",

issn = "2327-4662",

publisher = "IEEE",

}

TY - JOUR

T1 - Human activity mining in multi-occupancy contexts based on nearby interaction under a fuzzy approach

AU - Polo-Rodriguez, Aurora

AU - Cavallo, Filippo

AU - Nugent, CD

AU - Quero, Javier Medina

PY - 2023/12/5

Y1 - 2023/12/5

N2 - Multioccupation encompasses real-life environments in which people interact in the same common space. Recognizing activities in this context for each inhabitant has been challenging and complex. This work presents a fuzzy knowledge-based system for mining human activities in multi-occupancy contexts based on nearby interaction based on the Ultra-wideband. First, interest zone spatial location is modelled using a straightforward fuzzy logic approach, enabling discriminating short-term event interactions. Second, linguistic protoforms use fuzzy rules to describe long-term events for mining human activities in a multi-occupancy context. A data set with multimodal sensors has been collected and labelled to exhibit the application of the approach. The results show an encouraging performance (0.9 precision) in the discrimination of multiple occupations.

AB - Multioccupation encompasses real-life environments in which people interact in the same common space. Recognizing activities in this context for each inhabitant has been challenging and complex. This work presents a fuzzy knowledge-based system for mining human activities in multi-occupancy contexts based on nearby interaction based on the Ultra-wideband. First, interest zone spatial location is modelled using a straightforward fuzzy logic approach, enabling discriminating short-term event interactions. Second, linguistic protoforms use fuzzy rules to describe long-term events for mining human activities in a multi-occupancy context. A data set with multimodal sensors has been collected and labelled to exhibit the application of the approach. The results show an encouraging performance (0.9 precision) in the discrimination of multiple occupations.

KW - Multi-occupancy

KW - Human activity recognition

KW - Nearby interaction

UR - https://www.sciencedirect.com/science/article/pii/S2542660523003414?via%3Dihub

U2 - 10.1016/j.iot.2023.101018

DO - 10.1016/j.iot.2023.101018

M3 - Article

SN - 2327-4662

VL - 25

JO - IEEE Internet of Things

JF - IEEE Internet of Things

M1 - 101018

ER -

Human activity mining in multi-occupancy contexts based on nearby interaction under a fuzzy approach

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this