Analytic Strategies of Streaming Data for eHealth

Area of Science:

• eHealth and Big Data Analytics
• Computational Social Science

Background:

• Traditional data processing struggles with the high volume and velocity of streaming big data from sources like wearable devices and social media.
• Extracting meaningful patterns from large, complex datasets presents significant challenges for researchers in eHealth.

Purpose of the Study:

• To provide hands-on instruction on advanced analytics techniques for streaming big data.
• To equip researchers with practical strategies for dimensionality reduction in big data analysis.
• To highlight the importance of domain expertise and a comprehensive approach for analyzing streaming social media data.

Main Methods:

• Tutorial format offering practical, hands-on instruction.
• Focus on analytics techniques such as topic modeling and social network analysis.
• Demonstration of dimensionality reduction strategies using real-world big data examples.

Main Results:

• Participants will gain practical skills in analyzing streaming big data.
• Understanding of effective methods for reducing data complexity.
• Strategies for integrating domain knowledge into data analysis.

Conclusions:

• New analytic strategies are crucial for leveraging big data in eHealth.
• Hands-on tutorials are effective for teaching complex data analysis techniques.
• A comprehensive approach, including domain expertise, enhances the value of streaming data analytics.