Context-Aware Urban Computing and Services
Scalable Activity-Travel Pattern Monitoring Framework for Large-scale City Environment
In this work, we introduce Activity Travel Pattern (ATP) monitoring in a large-scale city environment. ATP represents where city residents and vehicles stay and how they travel around in a complex megacity. Monitoring ATP will incubate new types of value-added services such as predictive mobile advertisement, demand forecasting for urban stores, and adaptive transportation scheduling. To enable ATP monitoring, we develop ActraMon, a high-performance ATP monitoring framework. As a first step, ActraMon provides a simple but effective computational model of ATP and a declarative query language facilitating effective specification of various ATP monitoring queries. More important, ActraMon employs the shared staging architecture and highly efficient processing techniques, which address the scalability challenges caused by massive location updates, a number of ATP monitoring queries and processing complexity of ATP monitoring. Finally, we demonstrate the extensive performance study of ActraMon using realistic city-wide ATP workloads.
Visit-Pattern-Aware Mobile Advertising System for Urban Commercial Complexes
As smartphones have become prevalent, mobile advertising is getting significant attention as being not only a killer application in future mobile commerce, but also as an important business model of emerging mobile applications to monetize them. In this paper, we present AdNext, a visit-pattern-aware mobile advertising system for urban commercial complexes. AdNext can provide highly relevant ads to users by predicting places that the users will next visit. AdNext predicts the next visit place by learning the sequential visit patterns of commercial complex users in a collective manner. As one of the key enabling techniques for AdNext, we develop a probabilistic prediction model that predicts users’ next visit place from their place visit history. To automatically collect the users’ place visit history by smartphones, we utilize Wi-Fi-based indoor localization. We demonstrate the feasibility of AdNext by evaluating the accuracy of the prediction model. For the evaluation, we used a dataset collected from COEX Mall, the largest commercial complex in South Korea. Also, we implemented an initial prototype of AdNext with the latest smartphones, and deployed it in COEX Mall.
Students: Youngki Lee, SangJeong Lee, Byoungjip Kim, and Jungwoo Kim
Professors: Junehwa Song, Jin-Young Ha, and Yunseok Rhee
Alumni: Seungwoo Kang
Youngki Lee, SangJeong Lee, Byoungjip Kim, Jungwoo Kim, Yunseok Rhee, and Junehwa Song, “Scalable Activity-Travel Pattern Monitoring Framework for Large-scale City Environment”, to appear in IEEE Transactions on Mobile Computing 2011.
Byoungjip Kim, Jin-Young Ha, SangJeong Lee, Seongwoo Kang, Youngki Lee, Yunseok Lee, and Junehwa Song, “AdNext: A Visit-Pattern-Aware Mobile Advertising System for Urban Commercial Complexes”, to appear in ACM HotMobile 2011.