Vol.:(0123456789)
SN Computer Science (2021) 2:146
https://doi.org/10.1007/s42979-021-00548-1
SN Computer Science
ORIGINAL RESEARCH
Mobile Deep Learning: Exploring Deep Neural Network for Predicting
Context‑Aware Smartphone Usage
Iqbal H. Sarker
1,2
· Yoosef B. Abushark
3
· Asif Irshad Khan
3
· Md Mottahir Alam
4
· Raza Nowrozy
5
Received: 14 February 2021 / Accepted: 25 February 2021 / Published online: 17 March 2021
© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature 2021
Abstract
In this paper, we mainly formulate the problem of predicting smartphone usage based on contextual information, which
involves both the user-centric and device-centric contexts. In the area of mobile analytics, traditional machine learning
techniques, such as Decision Trees, Random Forests, Support Vector Machines, etc. are popular for building context-aware
prediction models. However, real-life smartphone usage data may contain higher dimensions of contexts and can be huge in
size considering the daily behavioral data of the users. Thus, the traditional machine learning models may not be efective
to build the context-aware model. In this paper, we explore “Mobile Deep Learning”, an artificial neural network learning-
based model considering multiple hidden layers for predicting context-aware smartphone usage. Our model frst takes into
account context correlation analysis to reduce the neurons as well as to simplify the network model through fltering the
irrelevant or less signifcant contexts, and then build the deep learning model with the selected contexts. The experimental
results on smartphone usage datasets show the efectiveness of the model.
Keywords Mobile data analytics · Deep learning · Artifcial neural network · Context-aware computing · User behavior
modeling · Predictive analytics · Personalization · Intelligent applications
Introduction
Due to the extreme popularity of the Internet of Things
(IoT), context-awareness is a commonly used term in the
context of computing, particularly the recent advanced fea-
tures in the most popular IoT devices, i.e., smartphones. In
the real world, users’ interest in “Mobile Phones” is more
and more than other platforms like “Tablet Computer”,
“Desktop Computer”, “Laptop Computer” overtime [18].
In addition to voice contact, smartphones are used by people
in diferent types of applications such as social networking
systems, tour guides, recommendation systems, shopping
suggestions, transportation, messaging, medical appoint-
ment, etc. [22]. The behavioral activities of users with these
apps may vary from user to user in diferent contexts, such
as temporal context, workday or vacation status, spatial con-
text, user emotional state, WiFi status, device-related status,
etc. These contextual circumstances may afect the actions
of individuals using such apps. In this paper, we formulate
the problem of predicting smartphone usage based on the
contextual information and aim to build an efective context-
aware prediction model.
This article is part of the topical collection “Advances in
Computational Approaches for Artifcial Intelligence, Image
Processing, IoT and Cloud Applications” guest edited by Bhanu
Prakash K N and M. Shivakumar.
* Iqbal H. Sarker
iqbal.sarker.cse@gmail.com
1
Swinburne University of Technology, Melbourne, VIC 3122,
Australia
2
Department of Computer Science and Engineering,
Chittagong University of Engineering & Technology,
Chittagong 4349, Bangladesh
3
Department of Computer Science, Faculty of Computing
and Information Technology, King Abdulaziz University,
Jeddah 21589, Saudi Arabia
4
Department of Electrical and Computer Engineering, Faculty
of Engineering, King Abdulaziz University, Jeddah 21589,
Saudi Arabia
5
Victoria University, Footscray, VIC 3011, Australia