2020
DOI: 10.1016/j.inffus.2019.08.004
|View full text |Cite
|
Sign up to set email alerts
|

A body sensor data fusion and deep recurrent neural network-based behavior recognition approach for robust healthcare

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
64
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 160 publications
(71 citation statements)
references
References 18 publications
0
64
0
Order By: Relevance
“…Xu et al combined the CNN and the gated recurrent unit (GRU) to identify human activities, and verified the effectiveness of the proposed method on three public datasets [17]. Uddin et al proposed a multi-sensors data fusion network based on recurrent neural network (RNN) [18]. Firstly, the timefrequency domain features were extracted from the original sensor data.…”
Section: Introductionmentioning
confidence: 99%
“…Xu et al combined the CNN and the gated recurrent unit (GRU) to identify human activities, and verified the effectiveness of the proposed method on three public datasets [17]. Uddin et al proposed a multi-sensors data fusion network based on recurrent neural network (RNN) [18]. Firstly, the timefrequency domain features were extracted from the original sensor data.…”
Section: Introductionmentioning
confidence: 99%
“…In modern platforms like CIoTVID, this is done taking care of ownership, security, and privacy. The reasons why these platforms give a large marginal value to society is because the proliferation of IoT devices in smart environments is happening in the form of smartphones, smart speakers, security sensors (as part of home alarms), comfort sensors, wearable devices for recognizing and monitoring behavior [ 7 ] and so forth. This implies the generation of a variety of methodologies and tools taking the form of integrated IoT platforms in more mature fields such as energy management, home security, or smart entertainment or healthcare.…”
Section: Related Workmentioning
confidence: 99%
“…Activity recognition using a smartphone aims to recognize a user’s behavior using the built-in inertial sensor. The target activities range from work that recognizes daily movements, such as walking and running, to work that recognizes focused movements, such as falling movements [ 10 , 11 , 12 ]. However, activity recognition has the problem that recognition accuracy decreases, depending on the position of the smartphone on the body [ 13 ].…”
Section: Related Workmentioning
confidence: 99%