04-637   Mobile Big Data Analytics and Management

Location: Africa

Units: 12

Semester Offered: Spring

Course discipline


Course concentration

Applied machine learning

Course description

The developments in Internet of Things (IoT), mobile computing, and data storage technologies have led to the abundance of Mobile Big Data (MBD). MBD has unique characteristics that distinguish it from classical Big Data: it has multi-dimensional, personalized, multi-sensory, spatiotemporal, and real-time characteristics. These characteristics lead to challenges related to data management, analytics, privacy, and security. The course will provide students with the knowledge and skills to source, process, manage, and analyze MBD. In addition, the course will provide students with practical skills to apply appropriate visualization techniques to communicate the results of analytics in the MBD context.

Learning objectives

The course aims to prepare learners to build next-generation analytics applications that exploit IoT big data and other data sources, collectively called mobile big data, for a wide range of application areas.


At the end of the course, the learners should be able to:

  • Distinguish different types of mobile big data and their sources.
  • Select and apply appropriate data management techniques to source, prepare, and store mobile big data for analysis.
  • Build analytics and visualization models based on various types of mobile big data.
  • Apply analytics techniques for user modeling and context awareness.
  • Build practical mobile big data applications for different application domains.
  • Select and apply appropriate techniques to mitigate privacy and security challenges associated with mobile big data analytics.

Content details

The course covers:

  • Overview of Mobile big data (MBD)
  • MBD data sources: IoT sensors and devices, crowdsensing/crowdsourcing, mobile devices, social media, etc.
  • Types of MBD data: structured, unstructured, and semi-structured data
  • MBD management processes: pre-processing, cleaning, redundancy management, and data storage. This coverage will extend to the types of SQL and NoSQL databases and their support for analytics processing.
  • MBD analysis approaches: statistical analysis, knowledge discovery and data mining, and visualization, among others
  • Real-time and streaming analytics
  • High-performance analytics techniques
  • Context-awareness and user modeling in MBD context
  • MBD analytics tools and infrastructures including cloud-based infrastructures
  • Privacy and security challenges in MBD analytics
  • Applications of MBD analytics: smart city, agriculture, health, financial inclusion, and climate resilience, among others




George Okeyo