Mobile Big Data Research Articles

Mobile Big Data Based Network Intelligence

The mobile network is at a critical tipping point. On the one hand, it is heavily stressed by the explosive increase of traffic, and the steep transition from a smartphone-dominated market to one that is dazzling diverse, all subject to the same electromagnetic theory-ruled physical world. On the other hand, it is hopefully excited by the rapid development of data science, more powerful and versatile computing, and increasingly affordable hardware. It seems that we have come to the point at which in order to make the ends meet, one would need to put all the pieces together. In this paper, we aspire to establish a holistic framework for mobile big data (MBD) based network intelligence. Combining the top-down and bottom-up approaches, we put in context the recent development in the mobile network architecture, resource-based management theory, MBD orchestration, and data analytics, and establish a hierarchical network intelligence architecture fueled by MBD analytics. This architecture nurtures holistic understanding on how the multidimensional, multilateral, and multigranular MBD, together with its processing, can be plugged into the network architecture.

Big Data Driven Mobile Cellular Networks: Modelling, Experiments, and Applications

The proliferation and pervasive use of mobile devices results in the accumulation of massive amounts of wireless data. Mobile big data can be profitable only if suitable analytics and learning methods are utilized to extract meaningful knowledge and hidden patterns. In this article, we propose a novel mobile big data architecture consisting of five layers: the data storage layer, the data fusion layer, the data security layer, the data analysis layer and the data application layer. The functionality of each layer is presented. We consider one illustrative cases under this architecture, namely, user experience prediction by leveraging machine learning techniques. In practice, mobile big data analytics can be used for network planning and parameter dimensioning to facilitate network design, deployment and operation.

A Study on Improving the Location of CCTV Cameras for Crime Prevention through an Analysis of Population Movement Patterns using Mobile Big Data

As Koreans’ interest in safety and security increases and the desire to live a life without fear of crime grows, the building of safe cities has become a national priority. To effectively prevent urban crime, it is necessary to comprehensively consider the daily living patterns of urban residents and the geographic characteristics of each area. However, Korea’s crime prevention policies have often been determined based on the preferences of policy makers and the demands of residents, without consideration of accurate data. In addition, most preceding research on crime has focused on the distribution of crime based on administrative neighborhoods. There have been few studies that linked analysis on population flow patterns using mobile big data and safety vulnerable zones. Therefore, this study intends to investigate the problems with the location of Closed Circuit Television (CCTV) cameras, a representative defense mechanism in the CPTED (Crime Prevention Through Environmental Design) strategy, and suggests improvement measures based on the findings of analyses on the relationship between mobile big data-based population flow patterns and safety vulnerable zones. It also aims to suggest directions for building successful smart safe cities in the future based on the study results.

Mobile Big Data for Urban Analytics

The rapid progress of urbanization not only enables higher populations living in modern cities, but also engenders many “urban diseases,” such as air pollution, traffic congestion, and increased energy consumption. Mobile big data, with advanced communication and information technologies, can be collected through a variety of data sources, including cellular networks, the Internet of Things (IoT), social networks, and so on. This allows detailed analysis on the moving patterns of citizens and behaviors of devices deployed in urban areas, which helps grasp the outlines and the inner flows of cities. Based on those observations, prediction of events and their involved crowds and departments in cities can lead the city to become more intelligent and greener. The articles in this special section offer a comprehensive overview of the state-of-the-art developments in technology, application, and theory for mobile big data for urban analytics.

Environment Classification for Urban Big Data Using Deep Learning

With the increased population in urban areas, it has become a challenge to a service provider to manage big data coming from various users and devices. One of the fastest growing devices used by the citizens of urban areas is the smartphone. Today we can find almost nobody without at least one smartphone in their possession. While talking through a smartphone, surrounding environmental noises are added to the speech of the talker. Sometimes these noises are very annoying to the listeners. In this article, we propose a communication framework for urban mobile big data integrating an urban environment classification system. The proposed system utilizes a deep learning approach to classify environmental noises so that an appropriate noise cancellation algorithm can be used to reduce the effect of noise while having a conversation through smartphones. The proposed framework uses mobile edge computing technology to provide low-latency and efficient transmission. Experimental results demonstrate that the proposed system is very efficient in classifying environmental noises.

Towards an efficient and Energy-Aware mobile big health data architecture

Background and objectivesMobile and ubiquitous devices are everywhere, generating an exorbitant amount of data. New generations of healthcare systems are using mobile devices to continuously collect large amounts of different types of data from patients with chronic diseases. The challenge with such Mobile Big Data in general, is how to meet the growing performance demands of the mobile resources handling these tasks, while simultaneously minimizing their consumption. MethodsThis research proposes a scalable architecture for processing Mobile Big Data. The architecture is developed around three new algorithms for the effective use of resources in performing mobile data processing and analytics: mobile resources optimization, mobile analytics customization, and mobile offloading. The mobile resources optimization algorithm monitors resources and automatically switches off unused network connections and application services whenever resources are limited. The mobile analytics customization algorithm attempts to save energy by customizing the analytics processes through the implementation of some data-aware schemes. Finally, the mobile offloading algorithm uses some heuristics to intelligently decide whether to process data locally, or delegate it to a cloud back-end server. ResultsThe three algorithms mentioned above are tested using Android-based mobile devices on real Electroencephalography (EEG) data streams retrieved from sensors and an online data bank. Results show that the three combined algorithms proved their effectiveness in optimizing the resources of mobile devices in handling, processing, and analyzing EEG data. ConclusionWe developed an energy-efficient model for Mobile Big Data which addressed key limitations in mobile device processing and analytics and reduced execution time and limited battery resources. This was supported with the development of three new algorithms for the effective use of resources, energy saving, parallel processing and analytics customization.

Location Privacy in Mobile Big Data: User Identifiability via Habitat Region Representation

Mobile big data collected by mobile network operators is of interest to many research communities and industries for its remarkable values. However, such spatiotemporal information may lead to a harsh threat to subscribers’ privacy. This work focuses on subscriber privacy vulnerability assessment in terms of user identifiability across two datasets with significant detail reduced mobility representation. In this paper, we propose an innovative semantic spatiotemporal representation for each subscriber based on the geographic information, termed as daily habitat region, to approximate the subscriber’s daily mobility coverage with far lesser information compared with original mobility traces. The daily habitat region is realized via convex hull extraction on the user’s daily spatiotemporal traces. As a result, user identification can be formulated to match two records with the maximum similarity score between two convex hull sets, obtained by our proposed similarity measures based on cosine distance and permutation hypothesis test. Experiments are conducted to evaluate our proposed innovative mobility representation and user identification algorithms, which also demonstrate that the subscriber’s mobile privacy is under a severe threat even with significantly reduced spatiotemporal information.

Design of Prevention Method Against Infectious Diseases based on Mobile Big Data and Rule to Select Subjects Using Artificial Intelligence Concept

The rapid evolution of transportation has enabled us to travel to any part of the world. At the same time, infectious diseases are now able to reach anywhere in the world via this same ease of travel. In 2015, a MERS epidemic broke out in Korea. The MERS virus infected 186 people with 38 dead and caused economic damage worth 6 billion dollars. In this paper, we investigate a joint project of KT and KCDC (Korea Centers for Disease Control and Prevention) to prevent infectious diseases through the use of mobile roaming Big Data. KT developed a monitoring system that uses telephone roaming data to identify subscribers who traveled to a country affected with an infectious disease. Upon returning to Korea, a subscriber receives a notice that he/she is required to report for potential quarantine in accordance with the regulations and gets guided on the measures to take in case symptoms of the infectious disease occur. The travel information is also provided to healthcare facilities throughout the country for reference when symptomatic individuals visit them. Laws and regulations are enacted to allow personal information to be used to prevent and control infectious diseases. By providing a solution for monitoring individuals with potential risk of having been infected, loss of life and financial loss caused by the spread of panic of infectious disease have been minimized. This study is an example of the significant social contribution of Big Data. The global propagation of this system can reduce the threat of the spread of infection significantly.

SPARTAN: Semantic integration of big spatio-temporal data from streaming and archival sources

An ever-increasing number of applications in critical domains, such as maritime and aviation, generate, collect, manage and process spatio-temporal data related to the mobility of entities. This wealth of data can be exploited for various purposes, towards improving the safety of operations, reducing economical costs, and increasing dependability: The major issue to achieve these objectives is increasing predictability of moving objects’ trajectories and events. To achieve this purpose in a data-driven way we need to exploit in integrated manners data from a variety of disparate and heterogeneous data sources, both streaming and archival, regarding – among other – surveillance, weather, and contextual data. Motivated by this fact, in this paper, we propose a framework for semantic integration of big mobility data with other data sources that are necessary to data analytics tasks, providing a unified representation of such data. Notable features of our framework include the real-time generation of data synopses of moving entities’ trajectories, the efficient and flexible transformation of data from heterogeneous and big data sources in RDF, and the spatio-temporal link discovery between spatio-temporal entities in diverse data sources. The design and implementation of our framework uses big data technologies (Apache Flink and Kafka), and our experimental evaluation demonstrates the efficiency and scalability of the proposed framework using large, real-life datasets.

China Digital Governance Development Review Over the Past Two Decades

This article describes how with the emergence of ubiquitous technology, intelligence, and the rise of social networks facilitated by mobile Internet, big data, cloud computing and other emerging technologies, it has become a global trend that digital governance has been employed in the executive branches of many countries in the world. This article explores the data of quantity of published articles, researchers, research institutes, high-frequency key words, etc., obtained through CiteSpaceIII. The analysis of the articles related to digital governance for the recent 20 years are used to perform content analysis on the research topic and evolution. The development situations and problems of digital governance research in China are analyzed based on the literature review. The future study direction is prospected.

Temporal-Spatial Mobile Application Usage Understanding and Popularity Prediction for Edge Caching

The explosive growth of smart devices and expansion of network services drives the flourish of mobile applications. Caching popular application services at the edge, BSs, or APs, which are closer to end users, could significantly improve the user experience and network capacity. To exploit this potential, it is critical to understand the traffic consumption and app usage pattern under BSs in the metropolitan area. Mobile big data collected from network interfaces facilitates the data-driven approach in characterizing these features. This article aims to design an edge caching strategy for app services based on the observed characteristics of BSs in terms of points of interest (POIs), logs, and traffic generated by various categories of apps. We first analyze the temporal characteristics of different categories of apps, and then further investigate the logs and traffic generated by app types under different BSs clustered by POIs. The top N popular app types in a given period of time under different BS clusters are predicted, which is helpful for network operators to know the traffic distribution of different app services over all BSs and design the edge caching scheme.

CoPFun: an urban co-occurrence pattern mining scheme based on regional function discovery

Analysis of mobile big data enables smart cities from aspects of traffic pattern, human mobility, air quality, and so on. Co-occurrence pattern in human mobility has been proposed in recent years and sparked high attentions of academia and industry. Co-occurrence pattern has shown enormous values in aspects of urban planning, business, and social applications, such as shopping mall promotion strategy making, and contagious disease spreading. What’s more, human mobility has strong relation with regional functions, because each urban region owns a major function to offer specialized services for city’s operations and such location-based services attract massive passenger flow, which is exactly the essence of urban human mobility pattern. Therefore, in this paper, we put forward a co-occurrence pattern mining scheme (CoPFun) based on regional function discovery utilizing various mobile data. First, we do traffic modeling to map trajectory data into population groups, which include temporal partition and map segmentation. Then we employ a frequent pattern mining algorithm to mine co-occurrence event data. Meanwhile, we exploit TF-IDF method to process POI data and LDA algorithm to process trajectory data to discover urban regional functions. We apply CoPFun to real mobile data to extract co-occurrence event data and compare it with OD data to analyze urban co-occurrence pattern from a perspective of regional functions. The experiment results verify the effectiveness of CoPFun.

Characterizing Flow, Application, and User Behavior in Mobile Networks: A Framework for Mobile Big Data

The recent explosion of data traffic calls for specialized systems to monitor the status of networks. Traditionally, Internet service providers collect and analyze IP flow data as they present an aggregated view of traffic. In the era of mobile big data, new approaches are required to address new challenges regarding the flow characterization in the next generation wireless networks. In this article, we propose a framework for mobile big data, referred to as FMBD, which provides massive data traffic collection, storage, processing, analysis, and management functions, to cope with the tremendous amount of data traffic. In particular, by analyzing the specific characteristics of the mobile big data from flow, application, and user behavior, such as high volume, diversity of applications, and spatio-temporal distribution, our proposed FMBD demonstrates its capability to offer real data-based advice to address new challenges for future wireless networks from the viewpoints of both operators and individuals. Tested by real mobile big data, FMBD has been operational for more than five years, and can be generalized to other environments with massive data traffic or big data. Introduction

Recent Advances and Challenges in Mobile Big Data

The unabated flurry of research activities dedicated to gaining business insights from a flood of data generated by heterogeneous mobile sources, such as the Internet of Vehicles, sensors, and smartphones, has instigated a new research domain called MBD. At the core of this mobile environment, scalability, cost effectiveness, reliability, analytics, and security are important concerns. Coping with these issues in handling MBD requires understanding the challenges associated with it. Mobile computing and big data have been widely studied separately; however, very few studies have explored the convergence of these two domains. In this article, we critically review recent research efforts directed at MBD. We also classify the MBD by devising a thematic taxonomy that is based on source, analytics, applications, characteristics, security, and data type. Furthermore, we discuss the opportunities offered by MBD in terms of analytics. Some potential uses of MBD in healthcare, telecommunication, digital advertising, and transportation are also presented. Several open research challenges are discussed as future research directions.

A Mobility-Aware Optimal Resource Allocation Architecture for Big Data Task Execution on Mobile Cloud in Smart Cities

In recent years, the smart city concept, which involves multiple disciplines, for example, smart healthcare, smart transportation, and smart community, has become popular because of its ability to improve urban citizens' quality of life. However, most services in these areas of smart cities have become data-driven, thus generating big data that require seamless real-time access, sharing, storing, processing, and analysis anywhere at any time for intelligent decision making to improve living standards. In this scenario, MCC can play a vital role by allowing a mobile device to access and offload big-data-related tasks to powerful cloudlet servers attached to many wireless APs, thus ensuring that the QoS demands of end users are met. However, the connectivity of mobile devices with a given AP is not continuous, but rather sporadic with varying signal strengths. Furthermore, the heterogeneity of the cloudlet resources and the big data application requests place additional challenges in making optimal code execution decision. To cope with this problem, this article proposes a mobility- aware optimal resource allocation architecture, namely Mobi-Het, for remote big data task execution in MCC that offers higher efficiency in timeliness and reliability. The system architecture and key components of the proposed resource allocation service are presented and evaluated. The results of experiments and simulations have demonstrated the effectiveness and efficiency of the proposed Mobi-Het architecture for mobile big data applications.

A Survey on Machine Learning‐Based Mobile Big Data Analysis: Challenges and Applications

This paper attempts to identify the requirement and the development of machine learning‐based mobile big data (MBD) analysis through discussing the insights of challenges in the mobile big data. Furthermore, it reviews the state‐of‐the‐art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently applied data analysis methods are reviewed. Three typical applications of MBD analysis, namely, wireless channel modeling, human online and offline behavior analysis, and speech recognition in the Internet of Vehicles, are introduced, respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.

A MapReduce-Based Parallel Frequent Pattern Growth Algorithm for Spatiotemporal Association Analysis of Mobile Trajectory Big Data

Frequent pattern mining is an effective approach for spatiotemporal association analysis of mobile trajectory big data in data-driven intelligent transportation systems. While existing parallel algorithms have been successfully applied to frequent pattern mining of large-scale trajectory data, two major challenges are how to overcome the inherent defects of Hadoop to cope with taxi trajectory big data including massive small files and how to discover the implicitly spatiotemporal frequent patterns with MapReduce. To conquer these challenges, this paper presents a MapReduce-based Parallel Frequent Pattern growth (MR-PFP) algorithm to analyze the spatiotemporal characteristics of taxi operating using large-scale taxi trajectories with massive small file processing strategies on a Hadoop platform. More specifically, we first implement three methods, that is, Hadoop Archives (HAR), CombineFileInputFormat (CFIF), and Sequence Files (SF), to overcome the existing defects of Hadoop and then propose two strategies based on their performance evaluations. Next, we incorporate SF into Frequent Pattern growth (FP-growth) algorithm and then implement the optimized FP-growth algorithm on a MapReduce framework. Finally, we analyze the characteristics of taxi operating in both spatial and temporal dimensions by MR-PFP in parallel. The results demonstrate that MR-PFP is superior to existing Parallel FP-growth (PFP) algorithm in efficiency and scalability.

Measuring economic activity in China with mobile big data

Emerging trends in the use of smartphones, online mapping applications, and social media, in addition to the geo-located data they generate, provide opportunities to trace users’ socio-economic activities in an unprecedentedly granular and direct fashion and have triggered a revolution in empirical research. These vast mobile data offer new perspectives and approaches to measure economic dynamics, and they are broadening the social science and economics fields. In this paper, we explore the potential for using mobile data to measure economic activity in China from a bottom-up view. First, we build indices for gauging employment and consumer trends based on billions of geo-positioning data. Second, we advance the estimation of offline store foot traffic via location search data derived from Baidu Maps, which is then applied to predict Apple’s revenues in China and to accurately detect box-office fraud. Third, we construct consumption indicators to track trends in various service sector industries and verify them with several existing indicators. To the best of our knowledge, this is the first study to measure the world’s second-largest economy by mining such unprecedentedly large-scale and fine-granular spatial-temporal data. In this way, our research provides new approaches and insights into measuring economic activity.

Scalable Structural Modal Identification Using Dynamic Sensor Network Data with STRIDEX

AbstractThis article uses the formulation of the structural identification using expectation maximization (STRIDE) algorithm for compatibility with the truncated physical model (TPM) to enable scalable, output‐only modal identification using dynamic sensor network (DSN) data. The DSN data class is an adaptable and efficient technique for storing measurements from a very large number of sensing nodes, which is the case in mobile sensor networks and BIGDATA problems. In this article, the STRIDEX output‐only identification algorithm is proposed for the stochastic TPM to estimate structural modal properties (frequencies, damping ratios, and mode shapes) directly from DSN data. The spatial information produced by this novel algorithm, called STRIDEX (“X” for extended), is scalable, as demonstrated in a strategy to construct high‐resolution mode shapes from a single DSN data set using a series of independent identification runs. The ability to extract detailed structural system information from DSN data in a computationally scalable framework is a step toward mobile infrastructure informatics in a large urban setting. The performance of the STRIDEX algorithm is demonstrated, using the simulated response of a 5,000 DOF structure, and experimentally, using measurements from two mobile sensor cars, which scanned about 8,000 points on a beam specimen in the laboratory. In the experimental results, a mobile sensor is shown to provide over 120 times more mode shape points than a fixed sensor.

Mobile Big Data: The Fuel for Data-Driven Wireless

In the past decade, the smart phone evolution has accelerated the proliferation of the mobile Internet and spurred a new wave of mobile applications, leading to an unprecedented mobile data volume generated from the mobile devices, content servers, and network operators, which are mainly nonstructured. In this big data era, such nonstructured data fragments are pieced together such that, drastically differing from the traditional practice where services determine and define the data, data is becoming a proactive entity that may drive and even create new services. Compared with the so-termed 5V characteristics of generic big data, namely volume, variety, velocity, veracity, and value, mobile big data is distinct in its unique multidimensional, personalized, multisensory, and real-time features. In this survey, we provide in-depth and comprehensive coverage on the features, sources and applications of mobile big data, as well as the current state-of-the-art, challenges and opportunities for research and development in this field, with an emphasis on the user modeling, infrastructure supporting, data management, and knowledge discovery aspects.