Estimating Human Predictability From Mobile Sensor Data

Bjørn Sand Jensen; Jakob Eg Larsen; Kristian Jensen; Jan Larsen; Lars Kai Hansen

doi:10.1109/MLSP.2010.5588997

Estimating Human Predictability From Mobile Sensor Data

Bjørn Sand Jensen, Jakob Eg Larsen, Kristian Jensen, Jan Larsen, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Quantification of human behavior is of prime interest in many applications ranging from behavioral science to practical applications like GSM resource planning and context-aware services. As proxies for humans, we apply multiple mobile phone sensors all conveying information about human behavior. Using a recent, information theoretic approach it is demonstrated that the trajectories of individual sensors are highly predictable given complete knowledge of the infinite past. We suggest using a new approach to time scale selection which demonstrates that participants have even higher predictability of non-trivial behavior on smaller timer scale than previously considered.

Original language	English
Title of host publication	IEEE International Workshop on Machine Learning for Signal Processing
Publisher	IEEE
Publication date	2010
ISBN (Print)	978-1-4244-7875-0
DOIs	https://doi.org/10.1109/MLSP.2010.5588997
Publication status	Published - 2010
Event	2010 IEEE International Workshop on Machine Learning for Signal Processing - Kittilä, Finland Duration: 29 Aug 2010 → 1 Sept 2010 Conference number: 20 https://ieeexplore.ieee.org/xpl/conhome/5576742/proceeding

Workshop

Workshop	2010 IEEE International Workshop on Machine Learning for Signal Processing
Number	20
Country/Territory	Finland
City	Kittilä
Period	29/08/2010 → 01/09/2010
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5576742/proceeding

Access to Document

10.1109/MLSP.2010.5588997

OpenUrl availability

Full text

Cite this

@inproceedings{dfebd124a2204a08947ce6b3eb66a319,

title = "Estimating Human Predictability From Mobile Sensor Data",

abstract = "Quantification of human behavior is of prime interest in many applications ranging from behavioral science to practical applications like GSM resource planning and context-aware services. As proxies for humans, we apply multiple mobile phone sensors all conveying information about human behavior. Using a recent, information theoretic approach it is demonstrated that the trajectories of individual sensors are highly predictable given complete knowledge of the infinite past. We suggest using a new approach to time scale selection which demonstrates that participants have even higher predictability of non-trivial behavior on smaller timer scale than previously considered.",

author = "Jensen, \{Bj{\o}rn Sand\} and Larsen, \{Jakob Eg\} and Kristian Jensen and Jan Larsen and Hansen, \{Lars Kai\}",

year = "2010",

doi = "10.1109/MLSP.2010.5588997",

language = "English",

isbn = "978-1-4244-7875-0",

booktitle = "IEEE International Workshop on Machine Learning for Signal Processing",

publisher = "IEEE",

address = "United States",

note = "2010 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2010 ; Conference date: 29-08-2010 Through 01-09-2010",

url = "https://ieeexplore.ieee.org/xpl/conhome/5576742/proceeding",

}

TY - GEN

T1 - Estimating Human Predictability From Mobile Sensor Data

AU - Jensen, Bjørn Sand

AU - Larsen, Jakob Eg

AU - Jensen, Kristian

AU - Larsen, Jan

AU - Hansen, Lars Kai

N1 - Conference code: 20

PY - 2010

Y1 - 2010

N2 - Quantification of human behavior is of prime interest in many applications ranging from behavioral science to practical applications like GSM resource planning and context-aware services. As proxies for humans, we apply multiple mobile phone sensors all conveying information about human behavior. Using a recent, information theoretic approach it is demonstrated that the trajectories of individual sensors are highly predictable given complete knowledge of the infinite past. We suggest using a new approach to time scale selection which demonstrates that participants have even higher predictability of non-trivial behavior on smaller timer scale than previously considered.

AB - Quantification of human behavior is of prime interest in many applications ranging from behavioral science to practical applications like GSM resource planning and context-aware services. As proxies for humans, we apply multiple mobile phone sensors all conveying information about human behavior. Using a recent, information theoretic approach it is demonstrated that the trajectories of individual sensors are highly predictable given complete knowledge of the infinite past. We suggest using a new approach to time scale selection which demonstrates that participants have even higher predictability of non-trivial behavior on smaller timer scale than previously considered.

U2 - 10.1109/MLSP.2010.5588997

DO - 10.1109/MLSP.2010.5588997

M3 - Article in proceedings

SN - 978-1-4244-7875-0

BT - IEEE International Workshop on Machine Learning for Signal Processing

PB - IEEE

T2 - 2010 IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 29 August 2010 through 1 September 2010

ER -

Estimating Human Predictability From Mobile Sensor Data

Abstract

Workshop

Access to Document

OpenUrl availability

Fingerprint

Cite this