Discovering People's Life Patterns from Anonymized WiFi Scanlists

Abstract

The prevalence of smart phones equipped with various sensors enables pervasive capturing users' mobility data (GPS, GSM network, WiFi, etc.), which contains approximate whereabouts of users. In order to protect users' privacy some mobility data is anonymized, which is challenging for discovering individual information implicated in the data. In this study, we are attempting to discover people's life patterns, which capture individual's life regularity and living style, from the anonymized WiFi scan lists. We transform the life pattern discovery problem into an unsupervised problem by extracting stay place, discovering trajectory patterns, etc. Particularly, we design a user feature space in which we use frequent trajectory patterns to represent each user as a feature vector. Thus, the life pattern discovery problem can be solved by finding clusters of users in the user feature space. The proposed approach is verified using the Device Analyzer data, which contains records of smart phone usage of more than 17,000 volunteering participants. Our work is a promising step towards automatically mining people's life patterns from anonymized mobility data of smart phones.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 5 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.