Application of CNN auto-encoder in Spatial Dimentionality Reduction of Mass Spectrometry Imaging Data

Liu, Liyu

Permalink

https://hdl.handle.net/2142/125124 Copy

Description

Title

Application of CNN auto-encoder in Spatial Dimentionality Reduction of Mass Spectrometry Imaging Data

Author(s)

Liu, Liyu

Issue Date

2020-12-01

Keyword(s)

dimension reduction, CNN layers based auto-encoder

Date of Ingest

2024-11-14T10:32:21-06:00

Abstract

Methods to reduce data spatial dimension so as to reduce the computational cost while preserving the original spatial information is an important research field in machine learning. Methods such as PCA (Principal Component Analysis) and NMF (non-negative matrix factorization) are widely used for dimension reduction. There are also works on using auto-encoder based on fully connected layers for dimension reduction. However fully connected layers have extremely high computational cost therefore are time consuming. In this work, we proposed a CNN layers based auto-encoder to reduce the dimension of data input. We applied our network on Mouse Urinary Bladder Data-set with a fix dimension of 5180* 38440. We compared the performance regarding execution time, MSE and spatial variance with those of PCA, NMF and FC auto-encoder. Our result shows that although we sacrificed MSE accuracy compared with PCA, NMF and FC auto-encoder, however we preserved the most spatial information compared with raw input. Also, our CNN layers based auto-encoder increase the computational speed by almost 4x to that of FC auto-encoder. Our result promote the potential of using the reduced feature for further calculation.

Type of Resource

text

Genre of Resource

dissertation/thesis

Language

eng

Owning Collections