Limits...
VisitSense: Sensing Place Visit Patterns from Ambient Radio on Smartphones for Targeted Mobile Ads in Shopping Malls.

Kim B, Kang S, Ha JY, Song J - Sensors (Basel) (2015)

Bottom Line: For accurate visit detection, we develop a change-based detection method to take into consideration the stability change of ambient radio and the mobility change of users.In addition, we proposed a causality-based visit prediction model to capture the causality in the sequential visit patterns for effective prediction.We have developed a VisitSense prototype system, and a visit-pattern-aware mobile advertising application that is based on it.

View Article: PubMed Central - PubMed

Affiliation: School of Computing, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong, Daejeon 305-338, Korea. bjkim@nclab.kaist.ac.kr.

ABSTRACT
In this paper, we introduce a novel smartphone framework called VisitSense that automatically detects and predicts a smartphone user's place visits from ambient radio to enable behavioral targeting for mobile ads in large shopping malls. VisitSense enables mobile app developers to adopt visit-pattern-aware mobile advertising for shopping mall visitors in their apps. It also benefits mobile users by allowing them to receive highly relevant mobile ads that are aware of their place visit patterns in shopping malls. To achieve the goal, VisitSense employs accurate visit detection and prediction methods. For accurate visit detection, we develop a change-based detection method to take into consideration the stability change of ambient radio and the mobility change of users. It performs well in large shopping malls where ambient radio is quite noisy and causes existing algorithms to easily fail. In addition, we proposed a causality-based visit prediction model to capture the causality in the sequential visit patterns for effective prediction. We have developed a VisitSense prototype system, and a visit-pattern-aware mobile advertising application that is based on it. Furthermore, we deploy the system in the COEX Mall, one of the largest shopping malls in Korea, and conduct diverse experiments to show the effectiveness of VisitSense.

No MeSH data available.


An example of the limitation of Wi-Fi scan similarity-based visit detection: Five adjacent places are visited. The black line represents real visits. The high values (i.e., 1.5) of the black line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The gray line represents the detected visits. The high values (i.e., 2.0) of the gray line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The red line represents the Wi-Fi scan similarity measured by the Tanimoto coefficient. The detected visits are determined by the comparison of the Tanimoto coefficient. The mismatch of the black line and gray line in horizontal axis means that there are many false positives and negatives for detecting the entrance and departure from a place.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541934&req=5

sensors-15-17274-f005: An example of the limitation of Wi-Fi scan similarity-based visit detection: Five adjacent places are visited. The black line represents real visits. The high values (i.e., 1.5) of the black line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The gray line represents the detected visits. The high values (i.e., 2.0) of the gray line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The red line represents the Wi-Fi scan similarity measured by the Tanimoto coefficient. The detected visits are determined by the comparison of the Tanimoto coefficient. The mismatch of the black line and gray line in horizontal axis means that there are many false positives and negatives for detecting the entrance and departure from a place.

Mentions: Wide overlap of Wi-Fi APs between adjacent places: Figure 4c shows the distribution of APs between two adjacent places. The number of commonly scanned APs is 20. This is 80% of all APs seen at place B, and 67% at place A. This problem causes the similarity-based algorithms such as SensLoc [9] to fail. For example, in the COEX Mall, the Tanimoto coefficient (Table 1) is continuously high (i.e., around 0.9) while moving around places. This problem is illustrated in Figure 5. This means that it is not a good measure to determine whether or not it is a visit. As a result, the similarity-based algorithms generate many false positives and negatives.


VisitSense: Sensing Place Visit Patterns from Ambient Radio on Smartphones for Targeted Mobile Ads in Shopping Malls.

Kim B, Kang S, Ha JY, Song J - Sensors (Basel) (2015)

An example of the limitation of Wi-Fi scan similarity-based visit detection: Five adjacent places are visited. The black line represents real visits. The high values (i.e., 1.5) of the black line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The gray line represents the detected visits. The high values (i.e., 2.0) of the gray line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The red line represents the Wi-Fi scan similarity measured by the Tanimoto coefficient. The detected visits are determined by the comparison of the Tanimoto coefficient. The mismatch of the black line and gray line in horizontal axis means that there are many false positives and negatives for detecting the entrance and departure from a place.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541934&req=5

sensors-15-17274-f005: An example of the limitation of Wi-Fi scan similarity-based visit detection: Five adjacent places are visited. The black line represents real visits. The high values (i.e., 1.5) of the black line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The gray line represents the detected visits. The high values (i.e., 2.0) of the gray line indicate staying in a place, and the low values (i.e., 0) indicate moving between places. The red line represents the Wi-Fi scan similarity measured by the Tanimoto coefficient. The detected visits are determined by the comparison of the Tanimoto coefficient. The mismatch of the black line and gray line in horizontal axis means that there are many false positives and negatives for detecting the entrance and departure from a place.
Mentions: Wide overlap of Wi-Fi APs between adjacent places: Figure 4c shows the distribution of APs between two adjacent places. The number of commonly scanned APs is 20. This is 80% of all APs seen at place B, and 67% at place A. This problem causes the similarity-based algorithms such as SensLoc [9] to fail. For example, in the COEX Mall, the Tanimoto coefficient (Table 1) is continuously high (i.e., around 0.9) while moving around places. This problem is illustrated in Figure 5. This means that it is not a good measure to determine whether or not it is a visit. As a result, the similarity-based algorithms generate many false positives and negatives.

Bottom Line: For accurate visit detection, we develop a change-based detection method to take into consideration the stability change of ambient radio and the mobility change of users.In addition, we proposed a causality-based visit prediction model to capture the causality in the sequential visit patterns for effective prediction.We have developed a VisitSense prototype system, and a visit-pattern-aware mobile advertising application that is based on it.

View Article: PubMed Central - PubMed

Affiliation: School of Computing, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong, Daejeon 305-338, Korea. bjkim@nclab.kaist.ac.kr.

ABSTRACT
In this paper, we introduce a novel smartphone framework called VisitSense that automatically detects and predicts a smartphone user's place visits from ambient radio to enable behavioral targeting for mobile ads in large shopping malls. VisitSense enables mobile app developers to adopt visit-pattern-aware mobile advertising for shopping mall visitors in their apps. It also benefits mobile users by allowing them to receive highly relevant mobile ads that are aware of their place visit patterns in shopping malls. To achieve the goal, VisitSense employs accurate visit detection and prediction methods. For accurate visit detection, we develop a change-based detection method to take into consideration the stability change of ambient radio and the mobility change of users. It performs well in large shopping malls where ambient radio is quite noisy and causes existing algorithms to easily fail. In addition, we proposed a causality-based visit prediction model to capture the causality in the sequential visit patterns for effective prediction. We have developed a VisitSense prototype system, and a visit-pattern-aware mobile advertising application that is based on it. Furthermore, we deploy the system in the COEX Mall, one of the largest shopping malls in Korea, and conduct diverse experiments to show the effectiveness of VisitSense.

No MeSH data available.