LineKing: Crowdsourced Line Wait-Time Estimation Using Smartphones

Abstract

Abstract. This paper describes the design, implementation and deployment of LineKing (LK), a crowdsourced line wait-time monitoring service. LK consists of a smartphone component (that provides automatic, energy-efficient, and accurate wait-time detection), and a cloud backend (that uses the collected data to provide accurate wait-time estimation). LK is used on a daily basis by hundreds of users to monitor the wait-times of a coffee shop in our university campus. The novel wait-time estimation algorithms deployed at the cloud backend provide mean absolute errors of less than 2-3 minutes.

Eywa: Crowdsourced and cloudsourced omniscience

“…At some point in the day, based on the availability of friends nearby (whose mobile positions are learned from Eywa), CuratedLiving may arrange a joint lunch. Alternatively based on the interests of the friends, this is converted to an art gallery visit followed by snack at a cafe (whose line-wait times are input to Eywa via LineKing [7]). Finally, based on customized/bargained deals, CuratedLiving may guide the user to buy the dresses and groceries.…”

“…Indeed we have observed a quick proliferation of location-based services and location-aware services, which are tell signs of the pendulum swinging back to physical; this time empowered with a very strong cyber component. As a result, we are seeing innovative location-based services such as cab hailing [6], line wait-time monitoring [7] 2 , and suggest-nearby services by search engines [8].…”

Energy efficient proximity alert on Android

“…In the last couple of years, the number of smartphone users in US alone has proliferated to 100 million 1 . Equipped with a touch screen, built-in sensors, one hop access to web, and supreme portability, smartphones position themselves as an alternative to personal computers.…”

“…Recently, in our LineKing [1] work, we have utilized proximity alert on the participants' smartphones to detect the time spent at the coffee shop in our campus. Then using the aggregated crowdsourced data and by leveraging on the computational power of the cloud, our system is able to forecast future wait times with less than 3 mins mean absolute error.…”

“…Then using the aggregated crowdsourced data and by leveraging on the computational power of the cloud, our system is able to forecast future wait times with less than 3 mins mean absolute error. 1 Android smartphones constitute 50% of the US market and 75% of the global market for smartphones.…”