Mobile Traffic Data Decomposition for Understanding Human Urban Activities

Abstract

The goal of this paper is to understand the patterns of mobile traffic consumption and reveal the correlations between human activities and mobile traffic patterns in the urban environment. This task is nontrivial in terms of three challenges: the complexity of mobile traffic consumption in large urban scale, the disturbance of abnormal events, and lack of prior knowledge about urban traffic patterns. We propose a novel approach and design a powerful system that consists of three parts: time series decomposing of mobile traffic data, extracting patterns from different components of the original traffic, and detecting anomalous events from noises. Our investigation reveals three important observations. Firstly, among all the 6,400 cellular towers we identify five daily patterns corresponding to different human daily activity patterns. Secondly, we find out that two natural patterns can be extracted from the weekly trend of mobile traffic consumption, which reflects modes of human activities from a different perspective. Last but not least, besides the regular patterns, we investigate how do irregular activities affect mobile traffic consumption, and exploit this knowledge to successfully detect unusual events like concerts and soccer matches. We believe our proposed methodology will lead to a comprehensive understanding of large-scale mobile traffic consumption in the urban areas.

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.