ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques

This paper mainly formulates the problem of predicting context-aware smartphone <i>apps usage</i> based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the <i>user-centric</i> c...

Full description

Bibliographic Details
Main Authors: Iqbal H. Sarker, Yoosef B. Abushark, Asif Irshad Khan
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Symmetry
Subjects:
Online Access:https://www.mdpi.com/2073-8994/12/4/499
id doaj-d66ca2331f9545bcb56ba2212d89c6f2
record_format Article
spelling doaj-d66ca2331f9545bcb56ba2212d89c6f22020-11-25T02:28:44ZengMDPI AGSymmetry2073-89942020-04-011249949910.3390/sym12040499ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning TechniquesIqbal H. Sarker0Yoosef B. Abushark1Asif Irshad Khan2Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne VIC-3122, AustraliaComputer Science Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaComputer Science Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaThis paper mainly formulates the problem of predicting context-aware smartphone <i>apps usage</i> based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the <i>user-centric</i> context and <i>device-centric</i> context. In the area of artificial intelligence and machine learning, <i>decision tree</i> model is one of the most popular approaches for predicting context-aware smartphone usage. However, real-life smartphone apps usage data may contain <i>higher dimensions of contexts</i>, which may cause several issues such as increases model <i>complexity</i>, may arise <i>over-fitting</i> problem, and consequently decreases the <i>prediction accuracy</i> of the context-aware model. In order to address these issues, in this paper, we present an effective <i>principal component analysis (PCA)</i> based context-aware smartphone apps prediction model, <i>“ContextPCA”</i> using decision tree machine learning classification technique. PCA is an <i>unsupervised machine learning</i> technique that can be used to separate symmetric and asymmetric components, and has been adopted in our “ContextPCA” model, in order to reduce the context dimensions of the original data set. The experimental results on smartphone apps usage datasets show that “ContextPCA” model effectively predicts context-aware smartphone apps in terms of precision, recall, f-score and ROC values in various test cases.https://www.mdpi.com/2073-8994/12/4/499mobile data analyticsmachine learningprincipal component analysisclassificationdecision treecontext-aware computing
collection DOAJ
language English
format Article
sources DOAJ
author Iqbal H. Sarker
Yoosef B. Abushark
Asif Irshad Khan
spellingShingle Iqbal H. Sarker
Yoosef B. Abushark
Asif Irshad Khan
ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
Symmetry
mobile data analytics
machine learning
principal component analysis
classification
decision tree
context-aware computing
author_facet Iqbal H. Sarker
Yoosef B. Abushark
Asif Irshad Khan
author_sort Iqbal H. Sarker
title ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
title_short ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
title_full ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
title_fullStr ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
title_full_unstemmed ContextPCA: Predicting Context-Aware Smartphone Apps Usage Based On Machine Learning Techniques
title_sort contextpca: predicting context-aware smartphone apps usage based on machine learning techniques
publisher MDPI AG
series Symmetry
issn 2073-8994
publishDate 2020-04-01
description This paper mainly formulates the problem of predicting context-aware smartphone <i>apps usage</i> based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the <i>user-centric</i> context and <i>device-centric</i> context. In the area of artificial intelligence and machine learning, <i>decision tree</i> model is one of the most popular approaches for predicting context-aware smartphone usage. However, real-life smartphone apps usage data may contain <i>higher dimensions of contexts</i>, which may cause several issues such as increases model <i>complexity</i>, may arise <i>over-fitting</i> problem, and consequently decreases the <i>prediction accuracy</i> of the context-aware model. In order to address these issues, in this paper, we present an effective <i>principal component analysis (PCA)</i> based context-aware smartphone apps prediction model, <i>“ContextPCA”</i> using decision tree machine learning classification technique. PCA is an <i>unsupervised machine learning</i> technique that can be used to separate symmetric and asymmetric components, and has been adopted in our “ContextPCA” model, in order to reduce the context dimensions of the original data set. The experimental results on smartphone apps usage datasets show that “ContextPCA” model effectively predicts context-aware smartphone apps in terms of precision, recall, f-score and ROC values in various test cases.
topic mobile data analytics
machine learning
principal component analysis
classification
decision tree
context-aware computing
url https://www.mdpi.com/2073-8994/12/4/499
work_keys_str_mv AT iqbalhsarker contextpcapredictingcontextawaresmartphoneappsusagebasedonmachinelearningtechniques
AT yoosefbabushark contextpcapredictingcontextawaresmartphoneappsusagebasedonmachinelearningtechniques
AT asifirshadkhan contextpcapredictingcontextawaresmartphoneappsusagebasedonmachinelearningtechniques
_version_ 1724836854225698816