End-to-end signal classification in signed cumulative distribution transform space

AHM Rubaiyat, S Li, X Yin… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
This paper presents a new end-to-end signal classification method using the signed
cumulative distribution transform (SCDT). We adopt a transport generative model to define …

Data representation with optimal transport

RD Martín, IV Medri, GK Rohde - arXiv preprint arXiv:2406.15503, 2024 - arxiv.org
arXiv:2406.15503v1 [math.OC] 19 Jun 2024 Page 1 Data representation with optimal
transport Rocıo Dıaz Martın[0000−0002−3732−6296] and Ivan Vladimir Medri[0000−0003−2419−2193] …

Data-driven identification of parametric governing equations of dynamical systems using the signed cumulative distribution transform

AHM Rubaiyat, DH Thai, JM Nichols… - Computer Methods in …, 2024 - Elsevier
This paper presents a novel data-driven approach to identify partial differential equation
(PDE) parameters of a dynamical system. Specifically, we adopt a mathematical “transport” …

Transport-based morphometry of nuclear structures of digital pathology images in cancers

MSE Rabbi, N Ironside, JA Ozolek, R Singh… - arXiv preprint arXiv …, 2023 - arxiv.org
Alterations in nuclear morphology are useful adjuncts and even diagnostic tools used by
pathologists in the diagnosis and grading of many tumors, particularly malignant tumors …

System Identification Using the Signed Cumulative Distribution Transform In Structural Health Monitoring Applications

AHM Rubaiyat, DH Thai, JM Nichols… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper presents a novel, data-driven approach to identifying partial differential equation
(PDE) parameters of a dynamical system in structural health monitoring applications …

[HTML][HTML] Linear optimal transport subspaces for point set classification

M Shifat-E-Rabbi, NS Pathan, S Li, Y Zhuang… - Research …, 2024 - ncbi.nlm.nih.gov
Learning from point sets is an essential component in many computer vision and machine
learning applications. Native, unordered, and permutation invariant set structure space is …

Invariance encoding in sliced-Wasserstein space for image classification with limited training data

MSE Rabbi, Y Zhuang, S Li, AHM Rubaiyat… - arXiv preprint arXiv …, 2022 - arxiv.org
Deep convolutional neural networks (CNNs) are broadly considered to be state-of-the-art
generic end-to-end image classification systems. However, they are known to underperform …

Geodesic Properties of a Generalized Wasserstein Embedding for Time Series Aanalysis

S Li, A Hasnat, M Rubaiyat… - … Algebraic and Geometric …, 2022 - proceedings.mlr.press
Transport-based metrics and related embeddings (transforms) have recently been used to
model signal classes where nonlinear structures or variations are present. In this paper, we …

Linear optimal transport subspaces for point set classification

M Shifat-E-Rabbi, NS Pathan, S Li, Y Zhuang… - europepmc.org
Learning from point sets is an essential component in many computer vision and machine
learning applications. Native, unordered, and permutation invariant set structure space is …