Danger Detection based on Fusion Analysis of Multimodal Data from a Smartphone and Smartwatch

Park, Soo Young; Kwon, Eunjung; Byon, Sungwon; Shin, Wonjae; Jung, Eui-Suk; Lee, Yong-Tae

doi:10.1109/ictc46691.2019.8939724

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sequential analysis is used to assess whether specific activities repeat over a certain duration (for example, one minute). Park et al of a previous study [23] classified activity types into Still (that is, staying still without large movements), Walk, Run, Defensive Arm (that is, an action of an arm for defending oneself), Offensive Arm (that is, an action of an arm for attacking someone), Offensive Leg (that is, an action of a leg for attacking someone), Collision (that is, an action of an arm or leg when someone is hit), and Fall. If the activities of Defensive Arm, Offensive Arm, Offensive Leg, and Collision are repeated over a certain duration, we can conclude that those activities indicate dangerous situations.…”

Section: Hla Processmentioning

confidence: 89%

Danger detection technology based on multimodal and multilog data for public safety services

et al. 2021

Self Cite

View full text Add to dashboard Cite

Recently, public safety services have attracted significant attention for their ability to protect people from crimes. Rapid detection of dangerous situations (that is, abnormal situations where someone may be harmed or killed) is required in public safety services to reduce the time required to respond to such situations.This study proposes a novel danger detection technology based on multimodal data, which includes data from multiple sensors (for example, accelerometer, gyroscope, heart rate, air pressure, and global positioning system sensors), and multilog data, which includes contextual logs of humans and places (for example, contextual logs of human activities and crime-ridden districts) over time. To recognize human activity (for example, walk, sit, and punch), the proposed technology uses multimodal data analysis with an attitude heading reference system and long short-term memory. The proposed technology also includes multilog data analysis for detecting whether recognized activities of humans are dangerous. The proposed danger detection technology will benefit public safety services by improving danger detection capabilities.

show abstract

Section: Hla Processmentioning

confidence: 89%