Designing Robust Models for Behaviour Prediction Using Sparse Data from Mobile Sensing

Date

2021-07-01

Author

ÇAVDAR, ŞEYMA
Taşkaya Temizel, Tuğba
MEHROTRA, Abhinav
Mirco, Musolesi
Tino, Peter

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

143
views

0
downloads

Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related conditions. In this article, we propose a hybrid personalised model involving a kernel density estimation model and a generalised linear mixed model to model office workers’ available moments for rest breaks during working hours. We adopt the experience-based sampling method through which we collected office workers’ responses regarding their availability through a mobile application with contextual information extracted by means of the mobile phone sensors. The experiment lasted 10 workdays and involved 19 office workers with a total of 528 responses. Our results show that time, location, ringer mode, and activity are effective features for predicting office workers’ availability. Our method can address sparse sample issues for building individual predictive behavioural models based on limited and unbalanced data. In particular, the proposed method can be considered as a potential solution to the “cold-start problem,” i.e., the negative impact of the lack of individual data when a new application is installed.

URI

https://doi.org/10.1145/3458753
https://hdl.handle.net/11511/91958

Journal

ACM Transactions on Computing for Healthcare

DOI

https://doi.org/10.1145/3458753

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

A Multi-perspective Analysis of Social Context and Personal Factors in Office Settings for the Design of an Effective Mobile Notification System ÇAVDAR, ŞEYMA; Taşkaya Temizel, Tuğba; Musolesi, Mirco; Tino, Peter (2020-03-01) In this study, we investigate the effects of social context, personal and mobile phone usage on the inference of work engagement/challenge levels of knowledge workers and their responsiveness to well-being related notifications. Our results show that mobile application usage is associated to the responsiveness and work engagement/challenge levels of knowledge workers. We also developed multi-level (within- and between-subjects) models for the inference of attentional states and engagement/challenge levels w...
The Role of Gender and Relative Skills in Task Juggling Büyükboyacı Hanay, Mürüvvet İlknur (2018-01-01) In this article, we examine individuals’ multitasking behaviors and how multitasking affects their performance when they are faced with two different tasks and the tasks are complementary, i.e., multitasking is compulsory. First, we find that when individuals are switching between tasks in such an environment, the process of switching is affected by their gender as well as their relative skill in the tasks. In particular, whereas the frequency with which men and women switch between tasks is relatively simi...
Linear programming based approaches for the discrete time/cost trade-off problem in project networks Hafizoglu, A. B.; Azizoğlu, Meral (Informa UK Limited, 2010-04-01) In project management, the activity durations can often be reduced by dedicating additional resources. The Time/Cost Trade-off Problem considers the compromise between the total cost and the project duration. The discrete version of the problem assumes a number of time/cost pairs, called modes, and selects a mode for each activity. In this paper, we consider the Discrete Time/Cost Trade-off Problem. We study the Deadline Problem, that is, the problem of minimizing total cost subject to a deadline on the pro...
The antecedents and consequences of burnout, work engagement and workaholism Metin, Ümit Baran; Bilgiç, Reyhan; Department of Industrial and Organizational Psychology (2010) The purpose of the present study is to find the relationship between characteristics of working life such as job demands (e.g. workload), and job resources (e.g. colleague support) and job attachments of employees, such as burnout, work engagement, and workaholism. Moreover, the effects of work characteristics on physical health, organizational commitment and work-family balance are investigated. Additionally, the relationship between three major employee attachment styles to work, namely, burnout, workahol...
Identifying the barriers of implementing lean construction principals in developing countries Markazi Movaghar, Ehsan; Elias Özkan, Soofia Tahira; Department of Building Science in Architecture (2016) The construction industry is congested with many types of project management systems to control and manage construction projects but none of them really look in-depth to maximize the efficiency of the work flow and minimizing waste. The implementation of the lean construction principles into the local construction scene can improve the problems. However, lean construction is complex and can be risky if not properly managed. Lean construction efforts in some other countries have not been successful due to th...

Citation Formats

Ş. ÇAVDAR, T. Taşkaya Temizel, A. MEHROTRA, M. Mirco, and P. Tino, “Designing Robust Models for Behaviour Prediction Using Sparse Data from Mobile Sensing,” ACM Transactions on Computing for Healthcare, vol. 2, no. 4, pp. 1–33, 2021, Accessed: 00, 2021. [Online]. Available: https://doi.org/10.1145/3458753.