Machine learning for multimodality genomic signal processing

Sun Yuan Kung, Man Wai Mak

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Multiple modalities can be generated in various ways. One possiblity is via sensor diversity, and the other is feature diversity. In terms of sensor diversity, both the motif and gene expression modalities can be considered. Motifs are short sequences of DNA responsible for regulating gene networks and the expression of genes, whereas gene expression is the processing of producing proteins from information coded in genes. To further facilitate multi-modality fusion, a diversity of features may be extracted from each sensor by computational means. This is called feature diversity.

Original languageEnglish (US)
Pages (from-to)117-121
Number of pages5
JournalIEEE Signal Processing Magazine
Volume23
Issue number3
DOIs
StatePublished - May 2006

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Machine learning for multimodality genomic signal processing'. Together they form a unique fingerprint.

Cite this