Difference between revisions of "SOCR News SpacekimeAnalytics Fall2019"
(→References) |
(→Logistics) |
||
| Line 4: | Line 4: | ||
[[Image:SOCR_Hat_2019.png|150px|thumbnail|right| [http://socr.umich.edu SOCR Resource] ]] | [[Image:SOCR_Hat_2019.png|150px|thumbnail|right| [http://socr.umich.edu SOCR Resource] ]] | ||
* '''School of Public Health''': [https://sph.umich.edu/biostat/events.php Biostatistics Seminar] | * '''School of Public Health''': [https://sph.umich.edu/biostat/events.php Biostatistics Seminar] | ||
| − | * '''Date/Times''': Thursday, September 26, 2019, 3:30 PM | + | * '''Date/Times''': Thursday, September 26, 2019, 3:30 PM |
| − | * '''Place/Time''': [https://maps.studentlife.umich.edu/building/henry-frieze-vaughan-public-health-building 3755 SPH-I], University of Michigan, Ann Arbor | + | * '''Place/Time''': [https://maps.studentlife.umich.edu/building/henry-frieze-vaughan-public-health-building 3755 SPH-I], University of Michigan, Ann Arbor |
| − | * '''Presenter''': [http://www.socr.umich.edu/people/dinov/ Ivo Dinov], joint work with [ Milen Velev] | + | * '''Presenter''': [http://www.socr.umich.edu/people/dinov/ Ivo Dinov], joint work with [http://www.socr.umich.edu/people/Milen_Velev.html Milen Velev] |
* '''Flyer''': [http://wiki.socr.umich.edu/images/0/06/Dinov_SPH_Biostats_Spacekime_TalkFlyer_092619.pdf Seminar Flyer] | * '''Flyer''': [http://wiki.socr.umich.edu/images/0/06/Dinov_SPH_Biostats_Spacekime_TalkFlyer_092619.pdf Seminar Flyer] | ||
Revision as of 11:29, 23 September 2019
Contents
SOCR News & Events: Longitudinal Spacekime Analytics: Time Complexity & Inferential Uncertainty
Logistics
- School of Public Health: Biostatistics Seminar
- Date/Times: Thursday, September 26, 2019, 3:30 PM
- Place/Time: 3755 SPH-I, University of Michigan, Ann Arbor
- Presenter: Ivo Dinov, joint work with Milen Velev
- Flyer: Seminar Flyer
Title
Longitudinal Spacekime Analytics: Time Complexity & Inferential Uncertainty
Abstract
As Big biomedical and health data becomes more ubiquitous, the corresponding analytical challenges require novel techniques for data management, aggregation, harmonization, processing, and analytics. This talk will present a new technique for modeling high-dimensional and time-varying data. The Longitudinal Spacekime Analytics approach relies on extending the notions of time and event to complex-time (kime) and complex-event (kevent). We will illustrate how the kime-order (time) and kime-direction (phase) affect the subsequent predictive analytics and the induced scientific inference. We will present some of the mathematical foundations and reveal various statistical implications including inferential uncertainty and Bayesian formulation of spacekime analytics. Simulated data, clinical observations (e.g., fMRI, UK Biobank), and air quality data will be used to demonstrate applications of spacekime analytics.
Slidedeck
SOCR Resources
- SOCR News & Events
- SOCR Global Users
- SOCR Navigators
- SOCR Datasets and Challenging Case-studies
- Electronic Textbooks:
SOCR Demos
- General SOCR Webapps
- SOCR BrainViewer
- Hands-on interactive visualization of extremely high-dimensional data (learning module and webapp)
References
- Spacekime Analytics
- Special thanks to Yongkai Qiu, Yufei Yang, and Zhe Yin for their substantial efforts in developing, packaging, documenting, and validating the TCIU R source code.
- SOCR is sponsored in part by NIH Grants P30 DK089503, P20 NR015331, U54 EB020406, P50 NS091856, UL1TR002240, R01CA233487, as well as, NSF Grants 1916425, 1734853 and 1636840.
- SOCR Home page: http://www.socr.umich.edu
Translate this page:
