Mobile User Behavior Research Articles

Analysis of Trip Distributions of Human Mobility Patterns and Their Transit Behaviors Using Mobile Call Detail Records

Rapid urbanization and modernization are increasing worldwide, including in Myanmar. Mobile call detail records (CDRs) provide new opportunities for measuring transport demands and problems in transportation planning. This research aims to analyze trip distributions and transit behaviors of mobile phone users based on their call activities. Origin-Destination (O-D) pairs were computed for the entire city, and the trip distributions help understand human mobility. It was found that zone-to-zone flow has the highest flow in commercial and industrial areas. Moreover, the logical assumptions were specified to extract the transit behaviors of users. The results indicate the degree of mode-to-mode transfer behaviors of users. Among the four categories of transit usage, only rail users do not transfer to other modes, having the lowest proportion, with other mode-to-other mode transfers having the highest proportion. The results were validated with the Person Trip Survey for Comprehensive Urban Transport Plan of the Greater Yangon. This study contributes significantly to the expansion of current and potential future transit systems, which can provide a new and improved transport system for Yangon City to meet its demands. This information is helpful in conducting disaster management and emergency preparedness in terms of trip distributions of human mobility patterns changing over space and time and the transit behaviors of the transferring mode in daily trips.

Tracking area list allocation scheme based on overlapping community algorithm

Reducing the singling overhead for tracking and mobile paging devices is a challenging issue in the study of location management of cellular networks. Cellular networks have become massive generators of data, and in the forthcoming years, this data is expected to increase drastically. Big data-based intelligence and analytics can improve network operational efficiency and user service quality. This work proposes to exploit massive handover and paging data from cellular networks to minimize singling due to user mobility. In this paper, we offer a new holistic tracking area lists (TAL) management methodology, considering group user mobility behavior and paging characteristics. Firstly, a series of graphs showing the evolution of user mobility and traffic is built from handover and paging statistics in the network management system (NMS). Then, the TAL allocation problem is formulated as a classical graph partitioning problem, which is then solved by detecting overlapping communities algorithm based on game theory. Results show that the proposed method can effectively reduce the location management singling overhead and improve the TAL configuration efficiency.

Mobile Privacy: Scalable Ensemble Matching for User Identification Attacks

Mobile privacy is broadly concerning in the mobile big data era, as user mobility behaviors are privacy-sensitive and unique. User identification attacks consist of one of the most critical privacy concerns on mobile big data. In this paper, we study mobile privacy in terms of user identifiability from the perspective of privacy adversaries. User identification in two datasets from the same data source or two different data sources is generally formulated as a linear assignment problem (LAP), in which the cost matrix of users is generated by a single distance measure. However, user identification via one single distance measure may lead to a large portion of false matches, especially when only a few users coexist across these two datasets. In addition, the cubic computational complexity of LAP limits the scale of user identification analysis. In this paper, we propose a multi-feature ensemble matching framework to improve the user identification precision based on a majority voting rule, by integrating multiple distance measures. The computational complexity of the proposed ensemble matching algorithm is an order of magnitude less than that of the single-distance based approach, which results from solving an LAP on a highly sparse matrix rather than a dense matrix. Experiments demonstrate the superior performance of our proposed scalable ensemble matching framework with respect to matching precision as well as the vulnerability of mobile network subscribers' privacy.

A mixed attributes oriented dynamic SOM fuzzy cluster algorithm for mobile user classification

In the field of mobile user behavior analysis, clustering algorithm is used to do the user classification. Usually the mobile user’s dataset is mixed, which contains both numerical and categorical type of data. It leads to inaccurate results when doing the user classification using traditional algorithms like K-Means and which are affected by the initialization process extremely. On the other hand, K-Prototypes algorithm is used to process the mixed data. It is difficult to ascertain the coefficient of classification attribute weight. Based on the above problems, this paper proposes a mixed attributes oriented dynamic SOM fuzzy cluster algorithm (D-SOMFCM-OMA) for mobile user classification. Firstly, the algorithm proposed in this paper gives the primary clustering using Self-Organizing feature Map (SOM) to get the initial clustering parameters. As the preprocessing of clustering, this step reduces effects caused by inappropriate initialization. Then, the algorithm utilizes the improved dynamic fuzzy K-Prototypes cluster method in the second-time clustering to classify users dynamically. It calculates weight of all kinds of attributes according to the proportion of the attribute and uses fine-tuned coefficient to adjust the attribute weight. For improving the clustering effect, the algorithm uses Jaccard distance to calculate the distance in the mixed attribute variables. Further, this paper defines the user mean membership threshold which is an indicator to determine whether different groups need to be added. Finally, some comparison experiments are conducted on the UCI standard datasets to show the advantage of the improved fuzzy clustering algorithm oriented the mixed attributes (IFCM-OMA). Also the other experiment using dataset of UCI verify the validity of the algorithm of D-SOMFCM-OMA.

Resource Allocation in Heterogeneous Network With Visible Light Communication and D2D: A Hierarchical Game Approach

Utilizing the illuminating light-emitting diode (LED) for signal transmission, the visible light communication (VLC) offloads the congested traffic in licensed spectrum while providing users with high quality of service. However, in shaded areas, the performance of VLC is affected. In this paper, we apply Device-to-Device (D2D) technology on the VLC network, where some mobile users are able to relay the data transmission to nearby end mobile users. Considering the autonomous behaviors of mobile users as relays (RUs), cellular service provider (CSP) and VLC service provider (VLCSP), we propose a hierarchical game framework and analyze the distributive strategies for each individual. In the game, the data packet size, the price of licensed spectrum and data rates in possible data transmission routes are sequentially determined with equilibrium solutions, and each VLC transmitter (VLCT) determines the optimal data transmission route with stable matching. Simulations depict the high performance when combining VLC and D2D with the proposed strategies.

Feature intersection for agent-based customer churn prediction

Purpose Telecommunication has a decisive role in the development of technology in the current era. The number of mobile users with multiple SIM cards is increasing every second. Hence, telecommunication is a significant area in which big data technologies are needed. Competition among the telecommunication companies is high due to customer churn. Customer retention in telecom companies is one of the major problems. The paper aims to discuss this issue. Design/methodology/approach The authors recommend an Intersection-Randomized Algorithm (IRA) using MapReduce functions to avoid data duplication in the mobile user call data of telecommunication service providers. The authors use the agent-based model (ABM) to predict the complex mobile user behaviour to prevent customer churn with a particular telecommunication service provider. Findings The agent-based model increases the prediction accuracy due to the dynamic nature of agents. ABM suggests rules based on mobile user variable features using multiple agents. Research limitations/implications The authors have not considered the microscopic behaviour of the customer churn based on complex user behaviour. Practical implications This paper shows the effectiveness of the IRA along with the agent-based model to predict the mobile user churn behaviour. The advantage of this proposed model is as follows: the user churn prediction system is straightforward, cost-effective, flexible and distributed with good business profit. Originality/value This paper shows the customer churn prediction of complex human behaviour in an effective and flexible manner in a distributed environment using Intersection-Randomized MapReduce Algorithm using agent-based model.

Predicting the sequential behavior of mobile Internet users based on MSM model

The behavior of users concerning mobile Internet varies significantly throughout the day. Results from existing studies—which generally simply segment one day into morning, afternoon, and evening—often provide inaccurate predictions of the behavior of users. To improve prediction accuracy, we propose a segment-based multi-state Markov (SBMSM) model for the dynamic time interval segmentation of the sequential behavior of users. The specific procedure of this proposed model can be described as follows: first, we divide each user’s behaviors into minimum unit according to time dimension; then, we merge adjacent time intervals or ensure they are constant according to the similarities in behavior; and finally, a multi-state Markov (MSM) model is trained using the newly constructed data individually. The experimental results illustrate that for 95.78% of users, an SBMSM model performs much better than a naive MSM model and hidden Markov model.

Determinants of Continuous Use of Mobile Money Payment Systems in Ghana.

This study examines the effect of user’s satisfaction on post-acceptance behaviour of mobile money users. Specifically, the paper identifies satisfactory factors and further examines the relationship between satisfaction and continuous use of mobile money application at the post-acceptance phase. Data was collected from 696 mobile phone users who had subscribed to mobile money services. Partial least squares (PLS) (Smart PLS 3.0) were used to analyse the collected data to test proposed hypotheses. This study revealed that users’ satisfaction is a significant factor that influences their intentions to continue to use mobile money services. The results indicated that users’ satisfaction is strongly influenced by confirmation and perceived usefulness which in turn significantly impact on continuous use of mobile money applications. Also, perceived security and privacy exert significant impact on users satisfaction. It was noted that charges and fees were insignificant but positively related to users’ intentions to continue to use mobile money applications. The findings have implications on both telecommunication firms and policy makers as they offer practical guidelines in developing strategies to ensure continuous use of mobile money applications/ services as we improve upon financial inclusion in Ghana in particular and Africa in general. This study therefore fills the gap in the post-adoption stage of mobile money usage and further use in Ghana.

Factors Affecting Switching Behavior of Mobile Set Users: The Case of Khulna City, Bangladesh

This study leads to explore the important factors affecting the behaviors of switching mobile sets and people's attitudes toward particular features. The questionnaire which is provided to gather data regarding the study contains 16 items measured on a five-point Likert scale. The data were analyzed by using frequency analysis and descriptive statistics. The results indicate that problem with network, design, price consideration and problem in power supply, etc. has greater impact on switching behavior of mobile set users. And it also shows the factors which are less considered by the mobile handset users that includes: using new one as well as making a profit by selling it and gift from others. It is assumed that this research will enable the future researchers to work in an expanded field.

Empirical assessment of mobile device users’ information security behavior towards data breach

Purpose The purpose of this paper is to investigate the information security behavior of mobile device users in the context of data breach. Much of the previous research done in user information security behavior have been in broad contexts, therefore creating needs of research that focuses on specific emerging technologies and trends such as mobile technology. Design/methodology/approach This study was an empirical study that gathered survey data from 390 mobile users. Delphi study and pilot study were conducted prior to the main survey study. Partial Least Square Structural Equation Modeling was used to analyze the survey data after conducting pre-analysis data screening. Findings This study shows that information security training programs must be designed by practitioners to target the mobile self-efficacy (MSE) of device users. It also reveals that practitioners must design mobile device management systems along with processes and procedures that guides users to take practical steps at protecting their devices. This study shows the high impact of MSE on users’ protection motivation (PM) to protect their mobile devices. Additionally, this study reveals that the PM of users influences their usage of mobile device security. Originality/value This study makes theoretical contributions to the existing information security literature. It confirms PM theory’s power to predict user behavior within the context of mobile device security usage. Additionally, this study investigates mobile users’ actual security usage. Thus, it goes beyond users’ intention.

Derivation of scaled design premises for future vehicle concepts based on a forecast of travel demand using the example of a commercial fully automated on-demand fleet

This paper presents an approach for linking the vehicle concept design in the early phase of development with findings from the forecast of mobility behavior under the boundary conditions of a future scenario for Germany. The focus is on an objective and data-based methodology for the derivation of design premises for vehicle concepts, illustrated by using the example of a commercial fully automated on-demand fleet. Today, vehicle concepts are designed on the basis of technical premises derived from the customer requirements of the relevant target group determined by market research and the competitive comparison. Technological trends (e.g., fully automated driving) and business model innovations (e.g., mobility as a service) have the potential to change the individual mobility behavior of users significantly so that today’s vehicle concepts will no longer meet the future requirements. Thus, the conventional approach of determining design premises for vehicle concepts alone may no longer be appropriate. Therefore, as the starting point of the overall methodology, the future mobility behavior is simulated in an aspatial travel demand model. By converting the simulated mobility behavior into relevant design premises and using a cluster analysis adapted for the specific application case, total vehicle concepts are objectively derived and optimized regarding the coverage of mobility needs. The concepts are scaled taking technical concept leaps into account. This application example shows that almost 85% of urban autonomous car sharing trips can be covered using a vehicle concept with significantly reduced requirements. Based on the scaled vehicle portfolio and the respective relevance of covering mobility needs, a recommendation for an efficient fleet design can be made.

Easy come or easy go? Empirical evidence on switching behaviors in mobile payment applications

Switching behaviors of mobile payment application received scarce attention. This study investigates the key factors influencing the switching behaviors of mobile payment application through the perspective of the push–pull–mooring framework. Privacy concerns, alternative rewards, and inertia are identified as push, pull, and mooring factors, respectively. The model was tested with 3785 valid responses among Alipay users. Inertia was found to attenuate the relationship between alternative rewards and switching behavior. This study sheds new light on the switching behavior of mobile payment application users. Our findings inform service providers to retain existing users as well as attract potential users.

VLC and D2D Heterogeneous Network Optimization: A Reinforcement Learning Approach Based on Equilibrium Problems With Equilibrium Constraints

The radio frequency spectrum crunch has triggered the harnessing of other sources of bandwidth, for which visible light is a promising candidate. Even though visible light communication (VLC) ensures high capacity, coverage is limited. This necessitates the integration of VLC and device-to-device (D2D) technologies into heterogeneous networks. In particular, mobile users which are accessible by the VLC transmitters can relay data to mobile users which are not, by means of D2D communication. However, due to the distributed behaviors of mobile users, determining optimal data transmission routes from VLC transmitters to end mobile devices is a major challenge. In this paper, we propose a reinforcement learning (RL)-based approach to determine multi-hop data transmission routes in an indoor VLC-D2D heterogeneous network. We obtain the rewards for the RL-based method dynamically, by formulating the interactions between the mobile users relaying the data as an equilibrium problem with equilibrium constraints and using alternating direction method of multipliers to solve it. The proposed technique can achieve optimal data transmission routes in a distributed manner. The simulation results demonstrate the effectiveness of the proposed approach, showing that transmission routes with low delays and high capacities can be achieved through the learning algorithm.

Research on the Adoption Behavior of Domestic Mobile Health Users: Present Situation and Direction

In recent years, the government has vigorously promoted mobile health services, and the related fields of mobile health are also developing rapidly. The research on mobile health at home and abroad mainly focuses on the present situation, problems and prospects. Users are the experience and consumers of mobile health. As an important part of Internet + Mobile Health, the adoption behavior research of mobile health users is still relatively lacking, most of the research is stuck in qualitative research, and theoretical innovation is also less. By combing the theoretical and practical research on the adoption behavior of mobile health users, this paper looks forward to the future research direction of the adoption behavior of mobile health users, in order to provide reference for future research and industry development.

Computation Offloading Optimization Based on Probabilistic SFC for Mobile Online Gaming in Heterogeneous Network

To support new services targeted by 5G, great efforts have been taken not only on the research work of new waveform design and air interface but also on cloudification and softwarization for future heterogeneous network. As one of the most popular services toward 5G, cloud gaming offloads computation-intensive tasks to the cloud in order to alleviate the computation burden of mobile devices, but it introduces latency which deteriorates user experience especially for the delay-sensitive online game. In order to solve the optimization problem of resource allocation with the quality of experience guarantees and reduce the operational expenditures and capital expenditures of mobile operators for deploying online game, fog computing and network function virtualization are deemed as promising solutions. In this paper, a component-based approach is proposed to model online game based on the probabilistic service function chain. In order to obtain the optimal virtual function placement in the fog-enabled heterogeneous radio access network, the cost minimization of computation offloading on the data plane is formulated as an integer linear programming problem considering the constraints of application maximum tolerable latency, resource limitation, and user behavior. The optimization problem is NP-hard. To solve the problem with low complexity, the heuristic algorithm is proposed called Probabilistic Service function chain Embedding based on Cost Optimization(PSECO). The performances of the two algorithms are evaluated. The simulation results show that the costs are affected mainly by the number of components, the arrival rate of user requests, mobile user behavior, as well as the physical network topology and the number of users. The heuristic algorithm PSECO has optimal results with low complexity and it is suitable for large scale networks.

Determinants of Mobile Digital Information Usage among Senior Consumers: Focusing on secondary digital divide

This study analyzes factors that determine the usage of digital information by senior consumers in the mobile environment. Senior consumers are alienated from digital information in South Korea; therefore, there have been increasing attempts to resolve this digital divide and reduce the digital information usage gap between young adults and senior consumers. The study used panel data from the National Information Society Agency (2017); there were 1,463 participants, aged 50-79 years. SPSS 19.0 was used to conduct the statistical analyses for frequency, factor analysis, Cronbach’ α analysis, descriptive analysis and hierarchical multiple-regression analysis. The results are as follows. First, negative attitude toward information society negatively influenced the mobile digital information usage in diversity context. Second, average monthly income, degree of digital device usage motivation, positive attitude toward digital device usage, digital literacy of PC & Mobile, and family support positively influenced the mobile digital information usage in diversity context. Third, negative attitudes toward information society negatively influenced the mobile digital information usage in quality context. Forth, average monthly income, degree of digital device usage motivation, positive attitude toward digital device usage, digital literacy of PC & mobile, and family support positively influenced the mobile digital information usage in quality context. The study results can help further understand mobile usage behaviors among senior citizens and the implications on their quality of life in the digital information era. Keywords: second digital divide, digital information usage, attitude, digital literacy, mobile usage

A Clickstream Data Analysis of the Differences between Visiting Behaviors of Desktop and Mobile Users

Mobile devices are gaining popularity among online shoppers whose behavior has been reshaped by the changes in screen size, interface, functionality, and context of use. This study, based on a log file from a cross-border E-commerce platform, conducted a clickstream data analysis to compare desktop and mobile users' visiting behavior. The original 2,827,449 clickstream records generated over a 4-day period were cleaned and analyzed according to an established analysis framework at the footprint level. Differences are found between desktop and mobile users in the distribution of footprints, core footprints, and footprint depth. As the results show, online shoppers preferred to explore various products on mobile devices and read product details on desktops. The E-commerce mobile application (app) presented higher interactivity than the desktop and mobile websites, thus increasing both user involvement and product visibility. It enabled users to engage in the intended activities more effectively on the corresponding pages. Mobile users were further divided into iOS and Android users whose visiting behaviors were basically similar to each other, though the latter might experience slower response speed.

Mobile user behavior based topology formation and optimization in ad hoc mobile cloud

As more and more mobile users use social networks to interact with other people currently, the resource limitation of mobile devices becomes an urgent problem to be solved. However, being a novel type of mobile cloud, the ad hoc mobile cloud allows participating mobile devices to share resources with other neighboring mobile devices, which can help the mobile device process a large amount of compute-intensive applications and conserve energy. In this paper, a mobile user behavior based topology formation and optimization in ad hoc mobile cloud is proposed. The mobile device nodes having similar behavioral features are grouped and formed as an ad hoc mobile cloud, which can reduce network delay and improve efficiency of node interaction. Subsequently, a flower pollination based offloading strategy is presented to reduce response time and save energy consumption. The experiment results show that our proposed ad hoc mobile cloud topology outperforms in scalability, while the offloading algorithm can reduce approximately 25%–50% response time and energy consumption as compared with that of other benchmark algorithms.

A statistical comparative performance analysis of mobile network operators

Mobile telephony is one of the most widely utilized technologies in the modern world. Records of the usage behaviour of mobile users can provide valuable information for understanding the behaviour of networks for Mobile Network Operators (MNOs). For different reasons, MNOs are interested in knowing how their competitors’ performance varies based on location, phone category, phone Operating System (OS) for various cellular network technology (CNT). This can help MNOs to invest intelligently in locations where they operate with inferior performance. Therefore, Key Performance Indicator (KPI) comparisons among MNOs are of interest for all MNOs. In this article, we investigate cellular network performance statistical comparisons of major Mobile Network Operators (MNOs) in Turkey using a large scale real-world proprietary mobile traffic dataset over a period of 18 months. Focusing our approach on different dimensions of crowd-sourced dataset allows us: (i) to know end-to-end nationwide network performance comparisons of MNOs using real-world measurement data, (ii) to calculate Confidence Intervals (CIs) for the mean difference of KPIs (such as downlink speed, latency, jitter and packet loss) for obtaining useful comparative statistical information of MNO performances and (iii) to observe the existence of significant performance differences between MNOs depending on the region which they are operating, phone category, phone OS as well as CNTs.

Using Autoencoders to Automatically Extract Mobility Features for Predicting Depressive States

Recent studies have shown the potential of exploiting GPS data for passively inferring people's mental health conditions. However, feature extraction for characterizing human mobility remains a heuristic process that relies on the domain knowledge of the condition under consideration. Moreover, we do not have guarantees that these "hand-crafted" metrics are able to effectively capture mobility behavior of users. Indeed, informative emerging patterns in the data might not be characterized by them. This is also a complex and often time-consuming task, since it usually consists of a lengthy trial-and-error process. In this paper, we investigate the potential of using autoencoders for automatically extracting features from the raw input data. Through a series of experiments we show the effectiveness of autoencoder-based features for predicting depressive states of individuals compared to "hand-crafted" ones. Our results show that automatically extracted features lead to an improvement of the performance of the prediction models, while, at the same time, reducing the complexity of the feature design task. Moreover, through an extensive experimental performance analysis, we demonstrate the optimal configuration of the key parameters at the basis of the proposed approach.