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

Iqbal H Sarker,Yoosef B Abushark,Asif Irshad Khan

doi:10.3390/sym12040499

Abstract

This paper mainly formulates the problem of predicting context-aware smartphone apps usage based on machine learning techniques. In the real world, people use various kinds of smartphone apps differently in different contexts that include both the user-centric context and device-centric context. In the area of artificial intelligence and machine learning, decision tree model is one of the most popular approaches for predicting context-aware smartphone usage. However, real-life smartphone apps usage data may contain higher dimensions of contexts, which may cause several issues such as increases model complexity, may arise over-fitting problem, and consequently decreases the prediction accuracy of the context-aware model. In order to address these issues, in this paper, we present an effective principal component analysis (PCA) based context-aware smartphone apps prediction model, “ContextPCA” using decision tree machine learning classification technique. PCA is an unsupervised machine learning 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.

Highlights

Context-awareness is a popular term in the context of computing, because of the popularity of Internet of Things (IoT), the recent advanced features in the most popular IoT device, i.e., smartphones
The goal of classification typically is to accurately classify or predict the given class labels of instances, whose contextual features or attribute values are known, but class values are unknown [6]. Association learning is another popular approach in the area of machine learning and data science and can be used for user behavioural analytics [7,8,9,10,11], we focus on classification approach for the purpose of building a prediction model in this work
We aim to focus on reducing higher dimensions of contexts for building an effective context-aware smartphone apps usage predictive model based on machine learning techniques

Summary

Introduction

Context-awareness is a popular term in the context of computing, because of the popularity of Internet of Things (IoT), the recent advanced features in the most popular IoT device, i.e., smartphones. Users’ behaviour with these apps may vary from user to user according to their contextual information in different dimensions such as temporal context, work status in workday or holiday, spatial context, their emotional state, Wifi status, or device related status etc. To build the prediction model in the area of mobile environment, ZeroR as base classifier, probability based naive Bayes classifier, support vector machines, instance based k-nearest neighbours, logistic regression, artificial neural network or deep learning, rule-based learning like decision trees, ensemble learning like random forest have been used [6,12] These machine learning classifiers are frequently used in context-aware mobile analytics [12]

Objectives

Methods

Conclusion