Limits...
Robust Indoor Human Activity Recognition Using Wireless Signals.

Wang Y, Jiang X, Cao R, Wang X - Sensors (Basel) (2015)

Bottom Line: Then, an online filtering method is designed to make actions' CSI curves smooth and allow them to contain enough pattern information.Each primitive action pattern can be segmented from the outliers of its multi-input multi-output (MIMO) signals by a proposed segmentation method.Lastly, in online activities recognition, by selecting proper features and Support Vector Machine (SVM) based multi-classification, activities constituted by primitive actions can be recognized insensitive to the locations, orientations, and speeds.

View Article: PubMed Central - PubMed

Affiliation: School of Software, Dalian University of Technology, Dalian 116620, China. dlutwangyi@dlut.edu.cn.

ABSTRACT
Wireless signals-based activity detection and recognition technology may be complementary to the existing vision-based methods, especially under the circumstance of occlusions, viewpoint change, complex background, lighting condition change, and so on. This paper explores the properties of the channel state information (CSI) of Wi-Fi signals, and presents a robust indoor daily human activity recognition framework with only one pair of transmission points (TP) and access points (AP). First of all, some indoor human actions are selected as primitive actions forming a training set. Then, an online filtering method is designed to make actions' CSI curves smooth and allow them to contain enough pattern information. Each primitive action pattern can be segmented from the outliers of its multi-input multi-output (MIMO) signals by a proposed segmentation method. Lastly, in online activities recognition, by selecting proper features and Support Vector Machine (SVM) based multi-classification, activities constituted by primitive actions can be recognized insensitive to the locations, orientations, and speeds.

Show MeSH

Related in: MedlinePlus

The MIMOs subplots for an action (e.g., squatting down to pick up something from the standing state) performed in three different orientations (a–c).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541929&req=5

sensors-15-17195-f004: The MIMOs subplots for an action (e.g., squatting down to pick up something from the standing state) performed in three different orientations (a–c).

Mentions: Performing the same action in different orientations will cause the reflection area to be varied. However, using the MIMO mechanism, this affect is not very obvious; e.g., in Figure 4, where a tester performed the same action in three directions: facing the transmission point (TP), perpendicular to the line-of-sight, and facing the access point (AP). The action patterns are similar, except for the relationship of the MIMOs, so we tried to avoid putting this into the features by generating the features of three MIMOs respectively.


Robust Indoor Human Activity Recognition Using Wireless Signals.

Wang Y, Jiang X, Cao R, Wang X - Sensors (Basel) (2015)

The MIMOs subplots for an action (e.g., squatting down to pick up something from the standing state) performed in three different orientations (a–c).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541929&req=5

sensors-15-17195-f004: The MIMOs subplots for an action (e.g., squatting down to pick up something from the standing state) performed in three different orientations (a–c).
Mentions: Performing the same action in different orientations will cause the reflection area to be varied. However, using the MIMO mechanism, this affect is not very obvious; e.g., in Figure 4, where a tester performed the same action in three directions: facing the transmission point (TP), perpendicular to the line-of-sight, and facing the access point (AP). The action patterns are similar, except for the relationship of the MIMOs, so we tried to avoid putting this into the features by generating the features of three MIMOs respectively.

Bottom Line: Then, an online filtering method is designed to make actions' CSI curves smooth and allow them to contain enough pattern information.Each primitive action pattern can be segmented from the outliers of its multi-input multi-output (MIMO) signals by a proposed segmentation method.Lastly, in online activities recognition, by selecting proper features and Support Vector Machine (SVM) based multi-classification, activities constituted by primitive actions can be recognized insensitive to the locations, orientations, and speeds.

View Article: PubMed Central - PubMed

Affiliation: School of Software, Dalian University of Technology, Dalian 116620, China. dlutwangyi@dlut.edu.cn.

ABSTRACT
Wireless signals-based activity detection and recognition technology may be complementary to the existing vision-based methods, especially under the circumstance of occlusions, viewpoint change, complex background, lighting condition change, and so on. This paper explores the properties of the channel state information (CSI) of Wi-Fi signals, and presents a robust indoor daily human activity recognition framework with only one pair of transmission points (TP) and access points (AP). First of all, some indoor human actions are selected as primitive actions forming a training set. Then, an online filtering method is designed to make actions' CSI curves smooth and allow them to contain enough pattern information. Each primitive action pattern can be segmented from the outliers of its multi-input multi-output (MIMO) signals by a proposed segmentation method. Lastly, in online activities recognition, by selecting proper features and Support Vector Machine (SVM) based multi-classification, activities constituted by primitive actions can be recognized insensitive to the locations, orientations, and speeds.

Show MeSH
Related in: MedlinePlus