(found 2 matches in 0.000779s)
-
A Topological Data Analysis Based Classification Method for Multiple Measurements
(2019)
Henri Riihimäki, Wojciech Chachólski, Jakob Theorell, Jan Hillert, Ryan Ramanujam
Abstract
\textlessh3\textgreaterAbstract\textless/h3\textgreater \textlessh3\textgreaterBackground\textless/h3\textgreater \textlessp\textgreaterMachine learning models for repeated measurements are limited. Using topological data analysis (TDA), we present a classifier for repeated measurements which samples from the data space and builds a network graph based on the data topology. When applying this to two case studies, accuracy exceeds alternative models with additional benefits such as reporting data subsets with high purity along with feature values.\textless/p\textgreater\textlessh3\textgreaterResults\textless/h3\textgreater \textlessp\textgreaterFor 300 examples of 3 tree species, the accuracy reached 80% after 30 datapoints, which was improved to 90% after increased sampling to 400 datapoints. Using data from 100 examples of each of 6 point processes, the classifier achieved 96.8% accuracy. In both datasets, the TDA classifier outperformed an alternative model.\textless/p\textgreater\textlessh3\textgreaterConclusions\textless/h3\textgreater \textlessp\textgreaterThis algorithm and software can be beneficial for repeated measurement data common in biological sciences, as both an accurate classifier and a feature selection tool.\textless/p\textgreater
-
Topology-Driven Trajectory Synthesis With an Example on Retinal Cell Motions
(2014)
Chen Gu, Leonidas Guibas, Michael Kerber
Abstract
We design a probabilistic trajectory synthesis algorithm for generating time-varying sequences of geometric configuration data. The algorithm takes a set of observed samples (each may come from a different trajectory) and simulates the dynamic evolution of the patterns in O(n2 logn) time. To synthesize geometric configurations with indistinct identities, we use the pair correlation function to summarize point distribution, and α-shapes to maintain topological shape features based on a fast persistence matching approach. We apply our method to build a computational model for the geometric transformation of the cone mosaic in retinitis pigmentosa — an inherited and currently untreatable retinal degeneration.