Video OCR for digital news archive

T Sato, T Kanade, EK Hughes… - Proceedings 1998 IEEE …, 1998 - ieeexplore.ieee.org
Video OCR is a technique that can greatly help to locate topics of interest in a large digital
news video archive via the automatic extraction and reading of captions and annotations …

[HTML][HTML] Added value from secondary use of person generated health data in consumer health informatics

PY Hsueh, YK Cheung, S Dey, KK Kim… - Yearbook of Medical …, 2017 - thieme-connect.com
Introduction: Various health-related data, subsequently called Person Generated Health
Data (PGHD), is being collected by patients or presumably healthy individuals as well as …

Uncertainty propagation in long-term structured regression on evolving networks

D Gligorijevic, J Stojanovic, Z Obradovic - Proceedings of the AAAI …, 2016 - ojs.aaai.org
In long-term forecasting it is important to estimate the confidence of predictions, as they are
often affected by errors that are accumulated over the prediction horizon. To address this …

Analyzing dynamical activities of Co-occurrence patterns for cooking ingredients

Y Kikuchi, M Kumano, M Kimura - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
Due to the increasing popularity of cooking-recipe sharing sites and the success of complex
network science, attention has recently been devoted to develo** an effective network …

Improving confidence while predicting trends in temporal disease networks

D Gligorijevic, J Stojanovic, Z Obradovic - arxiv preprint arxiv:1803.11462, 2018 - arxiv.org
For highly sensitive real-world predictive analytic applications such as healthcare and
medicine, having good prediction accuracy alone is often not enough. These kinds of …

Making sense of patient-generated health data for interpretable patient-centered care: the transition from “more” to “better”

PYS Hsueh, S Dey, S Das… - MEDINFO 2017: Precision …, 2017 - ebooks.iospress.nl
The rise of health consumers and the accumulation of patient-generated health data (PGHD)
have brought the patient to the centerstage of precision health and behavioral science. In …

[HTML][HTML] An exploration of ontology-based EMR data abstraction for diabetic kidney disease prediction

X Song, LR Waitman, Y Hu, SL Alan… - AMIA Summits on …, 2019 - ncbi.nlm.nih.gov
Abstract Diabetic Kidney Disease (DKD) is a critical and morbid complication of diabetes
and the leading cause of chronic kidney disease in the developed world. Electronic medical …

PerDREP: Personalized drug effectiveness prediction from longitudinal observational data

S Dey, P Zhang, D Sow, K Ng - Proceedings of the 25th ACM SIGKDD …, 2019 - dl.acm.org
In contrast to the one-size-fits-all approach to medicine, precision medicine will allow
targeted prescriptions based on the specific profile of the patient thereby avoiding adverse …

Comorbidity patterns and its impact on health outcomes: two-way clustering analysis

D Ghosh, J Cabrera, TN Adam… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
Comorbidity greatly increases the complexity of managing disease in patients.
Approximately 27 percent of the US population have two or more concurrent comorbid …

[BOOK][B] Predictive Uncertainty Quantification and Explainable Machine Learning in Healthcare

D Gligorijevic - 2018 - search.proquest.com
Predictive modeling is an ever-increasingly important part of decision making. The advances
in Machine Learning predictive modeling have spread across many domains bringing …