PRIMORIS      Contacts      FAQs      INSTICC Portal
 

Tutorials

The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.



Wireless Sensors and Big Data Analytics in Health Monitoring Applications


Lecturer

Hesham Ali
University of Nebraska at Omaha
United States
 
Brief Bio
Hesham H. Ali is a Professor of Computer Science and the Lee and Wilma Seaman Distinguished Dean of the College of Information Science and Technology (IS&T), at the University of Nebraska at Omaha (UNO). He currently serves as the director of the UNO Bioinformatics Core Facility that supports a large number of biomedical research projects in Nebraska. He has published numerous articles in various IT areas including scheduling, distributed systems, data analytics, wireless networks, and Bioinformatics. He has also published two books in scheduling and graph algorithms, and several book chapters in Bioinformatics. He is currently serving as the PI or Co-PI of several projects funded by NSF, NIH and Nebraska Research Initiative (NRI) in the areas of data analytics, wireless networks and Bioinformatics. He has been leading a Research Group at UNO that focuses on developing innovative computational approaches to classify biological organisms and analyze big bioinformatics data. The research group is currently developing several next generation data analysis tools for mining various types of large-scale biological data. This includes the development of new graph theoretic models for assembling short reads obtained from high throughput instruments, as well as employing a novel correlation networks approach for analyzing large heterogeneous biological data associated with various biomedical research areas, particularly projects associated with aging and infectious diseases. He has also been leading two funded projects for developing secure and energy-aware wireless infrastructure to address tracking and monitoring problems in medical environments, particularly to study mobility profiling for healthcare research.
Abstract

Abstract
The last several years have witnessed the development of multiple technologies with the goal of collecting mobility related information and monitor health related activities. Based on such technologies, many wireless devices have swamped the market and found their way on the wrists of many users. Although these developments are certainly welcomed in the domain of health monitoring, there are so much left to be done to take full-advantage of the data gathered by such devices. The most important missing component is the lack of advanced data analytics. Like many aspects of healthcare, the focus has been primarily on producing devices with data collection capabilities rather than developing advanced models for analyzing the available data. There is much needed balance between data gathering and data analysis. In this tutorial, we attempt to fill this gap by proposing various data integration and analysis models. We are interested in gathering mobility data that can be used to classify the daily activities of each individual, which in turn can be used to build a mobility pattern associated with that individual for a given time period. We also propose a graph-theoretic model based on building correlation networks among the various mobility patterns to develop a big data analytics tool for analyzing the collected mobility data. The concept of correlation networks is used to establish a comprehensive large-granularity approach for monitoring health activities and classifying health levels for each individual. We also utilize a graph-theoretic mechanism to zoom in and out of the networks and extract different types of information at various granularity levels. The proposed approach can potentially be used to predict health hazards before they take place and allow for preventive care rather the traditional reactive approach used in today’s healthcare. It can also serve as the core of a decision support system to help healthcare professional provide more advanced healthcare support.


Keywords
Wireless Sensors, Mobility Data, Mobility Devices, Correlation Networks, Predictive Models, Preventative Healthcare.

Aims and Learning Objectives
The field of Biomedical Informatics has been attracting a lot of attention in recent years. The use of wireless devices to collect mobility data continue to grow both in the commercial world as well as in the research domain. The impact of such devices remain limited though, primarily due to the lack of sophisticated data analytics tools to extract useful information out of the collected data. The proposed tutorial will address these issues with a particular focus on the following objectives:
1- Provide an overview of the current commercial devices and research studies associate with the use of wireless sensors in the domain of healthcare, with a focus on the advantages and disadvantages of each device and approach.
2- Introduce the main ideas associated with obtaining a mobility pattern or signature using raw data collected from wireless sensors. The goal of such pattern is to fully characterize the mobility parameters and to some degree the health level of each individual for a given time period.
3- Introduce the audience to how graph models and correlation networks can be developed using the mobility patterns and used to estimate health levels of various user groups. The goal of the proposed model is to classify health levels of individuals and track their health variability pattern, which may to the ability to predict potential health hazards and allow for the much needed objective of predictive and preventive healthcare.
Target Audience
The tutorial is intended primarily for computational scientists who are interested in Biomedical Research. In particular, those interested in how wireless and network technologies can used to support the new direction of health care that focused on predictive and preventative health care. Biomedical scientists with some background in computational concepts who are interested in how new technologies can support health care research represent another group of intended audience.

Detailed Outline
The proposed tutorial is designed for a 1.5 hour session that could potentially be extended to a three hour session if needed. The shorter version of the tutorial focuses on four points; providing a brief background of current technologies associated with the use of wireless sensors in health monitoring, introducing the new concept of mobility signatures developed using data collected from wireless sensors, using correlation networks and graph theoretic tools to properly analyze mobility data and extract critical health information, and finally studying how correlation networks can link mobility studies with bioinformatics research linking the two main aspects of the emerging field of biomedical informatics.
1. Survey of current wireless technologies in healthcare - Brief discussion on the various research studies and commercial wireless devises developed with the goal of monitor health activities and measure various mobility parameters such as number of steps, distance covered, and active periods while emphasizing the ease of use and level of trustworthiness associated with collected data.
2. How to obtain mobility signatures using raw mobility data – Algorithms for classifying various daily activities using mobility data will be introduced and used to build the characterizing models of mobility signature. Such characterizing patterns can be used to accurately measure the level of mobility associated with each individual.
3. Big data analytics using correlation networks – New techniques for building mobility networks from correlation mobility data calculated for multiple individuals at different times will be presented. Big Data analysis tools will be introduced to analyze the developed correlation networks and predict health levels of various groups with a focus on how to use such tools in predicting potential health problems.
4. Data integration tools using mobility and genomic data – Correlation Networks for modeling mobility data and bioinformatics data will be presented. The integration model represents potential next steps in healthcare in which various types of data will be used to establish an accurate picture associated with each person’s health and the ability to track progress of recovery from injuries or medical procedures.

Duration
1.5 hours


Keywords

wireless sensors, mobility data, mobility devices, correlation networks, predictive models, preventative healthcare.

Target Audience

The tutorial is intended primarily for computational scientists who are interested in Biomedical Research. In particular, those interested in how wireless and network technologies can used to support the new direction of health care that focused on predictive and preventative health care. Biomedical scientists with some background in computational concepts who are interested in how new technologies can support health care research represent another group of intended audience.

Detailed Outline

The proposed tutorial is designed for a 1.5 hour session that could potentially be extended to a three hour session if needed. The shorter version of the tutorial focuses on four points; providing a brief background of current technologies associated with the use of wireless sensors in health monitoring, introducing the new concept of mobility signatures developed using data collected from wireless sensors, using correlation networks and graph theoretic tools to properly analyze mobility data and extract critical health information, and finally studying how correlation networks can link mobility studies with bioinformatics research linking the two main aspects of the emerging field of biomedical informatics.
1. Survey of current wireless technologies in healthcare - Brief discussion on the various research studies and commercial wireless devises developed with the goal of monitor health activities and measure various mobility parameters such as number of steps, distance covered, and active periods while emphasizing the ease of use and level of trustworthiness associated with collected data.
2. How to obtain mobility signatures using raw mobility data – Algorithms for classifying various daily activities using mobility data will be introduced and used to build the characterizing models of mobility signature. Such characterizing patterns can be used to accurately measure the level of mobility associated with each individual.
3. Big data analytics using correlation networks – New techniques for building mobility networks from correlation mobility data calculated for multiple individuals at different times will be presented. Big Data analysis tools will be introduced to analyze the developed correlation networks and predict health levels of various groups with a focus on how to use such tools in predicting potential health problems.
4. Data integration tools using mobility and genomic data – Correlation Networks for modeling mobility data and bioinformatics data will be presented. The integration model represents potential next steps in healthcare in which various types of data will be used to establish an accurate picture associated with each person’s health and the ability to track progress of recovery from injuries or medical procedures.

Secretariat Contacts
e-mail: sensornets.secretariat@insticc.org

footer