Reminisce: Transparent and Contextually-Relevant Retrospection

Autor: Sangsu Lee, Christine Julien, Tomasz Kalbarczyk
Rok vydání: 2019
Předmět:
Zdroj: PerCom Workshops
DOI: 10.1109/percomw.2019.8730847
Popis: Many envisioned applications of pervasive computing, from smart personal assistants to interaction in the IoT, assume the ability to assess the context and provide data and services relevant to that context. As a demonstration of needed practical support for seamless context-based interaction, we present Reminisce, an application that allows users to look back on their memories by prioritizing photographs that were taken in contexts that are similar to the current context. While we focus on the use of context to draw up photographic history, the vision behind Reminisce is more general. We describe how Reminisce is built on a contextual database middleware that provides context storage and context-sensitive queries that determine the similarity between pairs of contexts. Reminisce uses the contextual database to store the contexts of a user's photos, which include location, time, neighboring devices, and weather conditions. Later, the app identifies the photos whose stored contexts are most similar to the user's current context by querying the contextual database; this query uses a context similarity function to compare entries in the database to the user's current context. During the demonstration, visitors will be able to interact with the app on the spot with auto-generated contexts and an on-device context simulation.
Databáze: OpenAIRE