Claire Chang

Claire Chang


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 April 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CCClaire Chang
Claire Chang
TSThaxter B Shaw
Thaxter B Shaw
AGArya Goutam
Arya Goutam
CLChristina Lau
Christina Lau
MSMengyi Shan
Mengyi Shan
TTTJ Tsai
TJ Tsai
This paper investigates an ordered partial matching alignment problem, in which the goal is to align two sequences in the presence of potentially non-matching regions. We propose a novel parameter-free dynamic programming alignment method called hidden state time warping that allows an alignment path to switch between two different planes: a “visible” plane corresponding to matching sections and a “hidden” plane corresponding to non-matching sections. By defining two distinct planes, we can allow different types of time warping in each plane (e.g., imposing a maximum warping factor in matching regions while allowing completely unconstrained movements in non-matching regions). The resulting algorithm can determine the optimal continuous alignment path via dynamic programming, and the visible plane induces a (possibly) discontinuous alignment path containing matching regions. We show that this approach outperforms existing parameter-free methods on two different partial matching alignment problems involving speech and music.

16 April 2024 in Mathematics in Industry Repository
Verified
Preprint
Open access
PDF file
Jamiree HarrisonJamiree Harrison
Jamiree Harrison
MAManuchehr Aminian
Manuchehr Aminian
ABAnna Berryman
Anna Berryman
GBGeorgia Brennan
Georgia Brennan
ZCZaoshu Cao
Zaoshu Cao
Olaniyi Samuel IyiolaOlaniyi Samuel Iyiola
Olaniyi Samuel Iyiola
Chronic Kidney Disease (CKD) is a progressive condition during which the kidneys fail to filter blood properly. Many moderate to late-stage symptoms exist for CKD but no prominent symptoms exist for early CKD, making it historically difficult to diagnose and treat. CKD can be triggered by infections, certain medications, dehydration, drug abuse, as well as spiraling blood pressure and blood sugar levels. Still, CKD is oftentimes overlooked when these triggers are present. For these combined reasons, we provide methodologies for cleaning pertinent data sets to conduct an exploratory analysis of patient profiles. Once we analyze how patient features correlate with CKD and identify important features for diagnosis, we train various machine learning classifiers to predict what stage of CKD a patient is in without invoking the features that are explicitly indicative of CKD. We then validate our models using out-of-sample test data.