Data Science involves the blending of techniques and theories from various disciplines including mathematics, statistics, engineering, and computer science, to conduct data mining, in order to elicit substantial information from datasets. The interdisciplinary nature of data science provides a wide platform for the utilization and development of powerful computational tools to tackle an array of real world data sets. In this talk, I will discuss my data science based approach in processing human polysomnograms (psgs), sleep records.
The human psg consists of a collection of bio-physiological events recorded simultaneously over many hours. Multiple non-invasive electrodes, located on different body regions, are used to obtain information regarding physiological state fluctuations of the subject in order to access sleep health. Although, information regarding healthy adult sleep is well characterized the establishment of robust models for sleep in patients suffering from certain sleep disorders and neurological pathologies are still being demystified. The delay in understanding the sleep patterns of these patients can be contributed to the need for efficient approaches to analyze the large, complex, and at times noisy records generated from sleep studies.
In order to meet this need, I have used a combination of signal processing, machine learning, and statistical modeling techniques to probe psgs and obtain information regarding the human sleep cycle of patients with sleep disorders and neurological pathologies. More specifically, I focus on pre-processing, data characterization, and post-processing challenges. My investigations indicate that Data Science offers many robust tools to hasten understanding of the human sleep cycle with respect to pathological conditions.
Dr. Jacqueline A. Fairley is a postdoctoral fellow at Emory University in the Neurology Department, Sleep Medicine Division. She received her B.S. in Electrical Engineering (Honors Graduate) from the University of Missouri-Columbia. Her graduate work, M.S. and Ph.D. in Electrical and Computer Engineering (ECE), was completed at the Georgia Institute of Technology (GaTech) and funded through the GEM and IBM Doctoral Fellowships.
Dr. Fairley’s dissertation, entitled “Statistical Modeling of the Human Sleep Process via Physiological Recordings” was nominated by GaTech for the 2009 ACM Dissertation of the Year Award. Her doctoral work in statistical modeling was further explored during her postdoctoral appointment by using data science schemes incorporating signal processing, machine learning, and statistical modeling techniques for developing computerized clinical decision support systems for diagnosis and prognosis of neurological pathologies and sleep disorders in humans. Her future research will extend upon this work by developing novel data science schemes to aid clinicians in formulating personalized medicine approaches for mental illness therapies.
Jacqueline’s teaching experience includes a one year NSF K-12 Outreach Mathematics Teaching Practicum at Tri-Cities High School in East Point, Georgia. She has also held various higher education teaching appointments at GaTech and was awarded the 2008 Outstanding ECE Teaching Assistant Award for the graduate course Statistical Digital Signal Processing. During her faculty appointment she intends to teach: Digital Signal Processing, Circuit Analysis, Machine Learning, Linear Systems, and a special topics course in Data Science.
Her industry experience consists of working as a Summer Manager at AT&T Bell Laboratories optimizing Bluetooth and Wireless Local Area Networks and non-destructive testing of high frequency flip-chips at the Motorola Advanced Technology Center.
Sponsorship of Dr.Fairley’s postdoctoral training have included various domestic and international travel awards and grants from NIH NINDS (F32 Training Grant No. 1F32NS070572-01A1), and NSF (FACES Career Initiation Grant No. 0450303).