Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks

Huan Li, Hua Lu, Muhammad Aamir Cheema, Lidan Shou, Gang Chen

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Resumé

Indoor mobility semantics analytics can greatly benefit many pertinent applications. Existing semantic annotation methods mainly focus on outdoor space and require extra knowledge such as POI category or human activity regularity. However, these conditions are difficult to meet in indoor venues with relatively small extents but complex topology. This work studies the annotation of indoor mobility semantics that describe an object’s mobility event (what) at a semantic indoor region (where) during a time period (when). A coupled conditional Markov network (C2MN) is proposed with a set of feature functions carefully designed by incorporating indoor topology and mobility behaviors. C2MN is able to capture probabilistic dependencies among positioning records, semantic regions, and mobility events jointly. Nevertheless, the correlation of regions and events hinders the parameters learning. Therefore, we devise an alternate learning algorithm to enable the parameter learning over correlated variables. The extensive experiments demonstrate that our C2MN-based semantic annotation is efficient and effective on both real and synthetic indoor mobility data.
OriginalsprogEngelsk
TitelThe 36th IEEE International Conference on Data Engineering (ICDE 2020)
Antal sider12
ForlagIEEE
StatusAccepteret/In press - jan. 2020

Fingerprint

Semantics
Topology
Learning algorithms
Experiments

Citer dette

Li, H., Lu, H., Cheema, M. A., Shou, L., & Chen, G. (Accepteret/In press). Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks. I The 36th IEEE International Conference on Data Engineering (ICDE 2020) IEEE.
Li, Huan ; Lu, Hua ; Cheema, Muhammad Aamir ; Shou, Lidan ; Chen, Gang. / Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks. The 36th IEEE International Conference on Data Engineering (ICDE 2020). IEEE, 2020.
@inproceedings{0fb7863caac7419da278e653cc52dae7,
title = "Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks",
abstract = "Indoor mobility semantics analytics can greatly benefit many pertinent applications. Existing semantic annotation methods mainly focus on outdoor space and require extra knowledge such as POI category or human activity regularity. However, these conditions are difficult to meet in indoor venues with relatively small extents but complex topology. This work studies the annotation of indoor mobility semantics that describe an object’s mobility event (what) at a semantic indoor region (where) during a time period (when). A coupled conditional Markov network (C2MN) is proposed with a set of feature functions carefully designed by incorporating indoor topology and mobility behaviors. C2MN is able to capture probabilistic dependencies among positioning records, semantic regions, and mobility events jointly. Nevertheless, the correlation of regions and events hinders the parameters learning. Therefore, we devise an alternate learning algorithm to enable the parameter learning over correlated variables. The extensive experiments demonstrate that our C2MN-based semantic annotation is efficient and effective on both real and synthetic indoor mobility data.",
keywords = "Semantic annotation, Indoor mobility data, Markov random fields",
author = "Huan Li and Hua Lu and Cheema, {Muhammad Aamir} and Lidan Shou and Gang Chen",
year = "2020",
month = "1",
language = "English",
booktitle = "The 36th IEEE International Conference on Data Engineering (ICDE 2020)",
publisher = "IEEE",
address = "United States",

}

Li, H, Lu, H, Cheema, MA, Shou, L & Chen, G 2020, Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks. i The 36th IEEE International Conference on Data Engineering (ICDE 2020). IEEE.

Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks. / Li, Huan; Lu, Hua; Cheema, Muhammad Aamir; Shou, Lidan; Chen, Gang.

The 36th IEEE International Conference on Data Engineering (ICDE 2020). IEEE, 2020.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks

AU - Li, Huan

AU - Lu, Hua

AU - Cheema, Muhammad Aamir

AU - Shou, Lidan

AU - Chen, Gang

PY - 2020/1

Y1 - 2020/1

N2 - Indoor mobility semantics analytics can greatly benefit many pertinent applications. Existing semantic annotation methods mainly focus on outdoor space and require extra knowledge such as POI category or human activity regularity. However, these conditions are difficult to meet in indoor venues with relatively small extents but complex topology. This work studies the annotation of indoor mobility semantics that describe an object’s mobility event (what) at a semantic indoor region (where) during a time period (when). A coupled conditional Markov network (C2MN) is proposed with a set of feature functions carefully designed by incorporating indoor topology and mobility behaviors. C2MN is able to capture probabilistic dependencies among positioning records, semantic regions, and mobility events jointly. Nevertheless, the correlation of regions and events hinders the parameters learning. Therefore, we devise an alternate learning algorithm to enable the parameter learning over correlated variables. The extensive experiments demonstrate that our C2MN-based semantic annotation is efficient and effective on both real and synthetic indoor mobility data.

AB - Indoor mobility semantics analytics can greatly benefit many pertinent applications. Existing semantic annotation methods mainly focus on outdoor space and require extra knowledge such as POI category or human activity regularity. However, these conditions are difficult to meet in indoor venues with relatively small extents but complex topology. This work studies the annotation of indoor mobility semantics that describe an object’s mobility event (what) at a semantic indoor region (where) during a time period (when). A coupled conditional Markov network (C2MN) is proposed with a set of feature functions carefully designed by incorporating indoor topology and mobility behaviors. C2MN is able to capture probabilistic dependencies among positioning records, semantic regions, and mobility events jointly. Nevertheless, the correlation of regions and events hinders the parameters learning. Therefore, we devise an alternate learning algorithm to enable the parameter learning over correlated variables. The extensive experiments demonstrate that our C2MN-based semantic annotation is efficient and effective on both real and synthetic indoor mobility data.

KW - Semantic annotation

KW - Indoor mobility data

KW - Markov random fields

M3 - Article in proceeding

BT - The 36th IEEE International Conference on Data Engineering (ICDE 2020)

PB - IEEE

ER -

Li H, Lu H, Cheema MA, Shou L, Chen G. Indoor Mobility Semantics Annotation Using Coupled Conditional Markov Networks. I The 36th IEEE International Conference on Data Engineering (ICDE 2020). IEEE. 2020