Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Medicine and Health Sciences
Session 12: Active Learning To Minimize The Possible Risk From Future Epidemics, Kc Santosh
Session 12: Active Learning To Minimize The Possible Risk From Future Epidemics, Kc Santosh
SDSU Data Science Symposium
In medical imaging informatics, for any future epidemics (e.g., Covid-19), deep learning (DL) models are of no use as they require a large dataset as they take months and even years to collect enough data (with annotations). In such a context, active learning (or human/expert-in-the-loop) is the must, where a machine can learn from the first day with minimum possible labeled data. In unsupervised learning, we propose to build pre-trained DL models that iteratively learn independently over time, where human/expert intervenes only when it makes mistakes and for only a limited data. In our work, deep features are used to …
Generalized Estimating Equations (Gee) Approach For Clustered Binary Data With Application To Covid-19 Treatment., Sadixa Sanjel
Generalized Estimating Equations (Gee) Approach For Clustered Binary Data With Application To Covid-19 Treatment., Sadixa Sanjel
SDSU Data Science Symposium
Clustered binary data frequently occur in epidemiology and other applied fields such as clinical trial studies, where observations within the respective samples are correlated. In such situations, the standard logistic regression method is not valid as logistic regression requires the observations to be independent of one other. This situation arises when treating COVD-19 patients. Patients from certain clusters, such as geographic areas or the same family, are highly correlated, and we need to fit the model using the GEE approach. In this paper, Standard Logistic Regression (LS), Generalized Linear Models (GENMOD), and GEE procedures have been utilized for comparison purposes. …
A Comparative Study Of Machine Learning Approaches For Human Activity Recognition, Loknath Ambati, Omar El-Gayar
A Comparative Study Of Machine Learning Approaches For Human Activity Recognition, Loknath Ambati, Omar El-Gayar
SDSU Data Science Symposium
The goal of this project is to study the performance of Machine Learning (ML) techniques used in Human Activity Recognition (HAR). Specifically, we aim to 1) evaluate and benchmark the performance of various ML techniques used for HAR against established ML performance metrics using multiple datasets, and 2) map the characteristics of various HAR datasets to appropriate ML techniques. From a theoretical perspective, the research will shed light into the strengths and weaknesses of various ML techniques that can provide insights into future research aimed at improving these techniques for HAR. From a practical perspective, the research provides guidance into …