A hybrid system approach to multivariate analysis of flow cytometry data

Author

Fu, LiMin ; Yang, Mark ; Braylan, Raul ; Benson, Neal

Author_Institution

Florida Univ., Gainesville, FL, USA

fYear

1992

fDate

14-17 Jun 1992

Firstpage

315

Lastpage

324

Abstract

In dealing with massive flow cytometric data, an adaptive data analysis scheme has been developed. The problem solving structure is configured as a connectionist network. Information is encoded in the form of connection weights. The structure evolves as more data are seen by adjusting its weights, governed by a learning equation. The knowledge embedded in the network can be further decoded in symbolic form. The results are reported from the domain of measuring the antigenic properties of blood samples. The technique has been validated statistically with respect to its self-consistency and determinacy

Keywords

biological techniques and instruments; blood; cellular transport and dynamics; data analysis; learning (artificial intelligence); medical computing; neural nets; adaptive data analysis scheme; antigenic properties; blood samples; connection weights; connectionist network; determinacy; flow cytometry data; knowledge decoding; learning equation; multivariate analysis; problem solving structure; self-consistency; statistical validation; symbolic form; Blood; Cells (biology); Data analysis; Decoding; Fluorescence; Instruments; Light scattering; Neural networks; Particle measurements; Pattern analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 1992. Proceedings., Fifth Annual IEEE Symposium on

Conference_Location

Durham, NC

Print_ISBN

0-8186-2742-5

Type

conf

DOI

10.1109/CBMS.1992.244933

Filename

244933