Pattern Recognition of Canine Duodenal Contractile Activity

S. NARASIMHA REDDY, SURYA RAO DUMPALA, SUSHIL K. SARNA, PETER G. NORTHCOTT

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Abstract An application of statistical pattern recognition technique to the classification of canine duodenal contractile activity resulting from the ingestion of three different test meals, viz. water, acid, and solid, is described. Feature vectors were extracted from the contractile activities recorded by means of strain gauges, and were based on average duration, number, and intensities of contractions, as well as their frequency and propagational characteristics. Pattern training and classification were performed via the Bayes decision rule. The results indicate that the three different meals give rise to three different kinds of contractile activities. An improvement in the classifier's performance was observed when it was updated with correctly classified patterns. The results appear to suggest that pattern analysis techniques add a new dimension to the study of gastrointestinal motility in health and disease. For example, pattern recognition techniques can also be extended to identify contractile patterns altered due to such pathological conditions as irritable bowel syndrome and postoperative diarrhea and, hence, elucidate the underlying relationship between contractile activity and distal propulsion of contents.

Original languageEnglish (US)
Pages (from-to)696-701
Number of pages6
JournalIEEE Transactions on Biomedical Engineering
VolumeBME-28
Issue number10
DOIs
StatePublished - Oct 1 1981
Externally publishedYes

Fingerprint

Pattern recognition
Strain gages
Propulsion
Classifiers
Health
Acids
Water

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

REDDY, S. NARASIMHA., DUMPALA, SURYA. RAO., SARNA, SUSHIL. K., & NORTHCOTT, PETER. G. (1981). Pattern Recognition of Canine Duodenal Contractile Activity. IEEE Transactions on Biomedical Engineering, BME-28(10), 696-701. https://doi.org/10.1109/TBME.1981.324663

Pattern Recognition of Canine Duodenal Contractile Activity. / REDDY, S. NARASIMHA; DUMPALA, SURYA RAO; SARNA, SUSHIL K.; NORTHCOTT, PETER G.

In: IEEE Transactions on Biomedical Engineering, Vol. BME-28, No. 10, 01.10.1981, p. 696-701.

Research output: Contribution to journalArticle

REDDY, SNARASIMHA, DUMPALA, SURYARAO, SARNA, SUSHILK & NORTHCOTT, PETERG 1981, 'Pattern Recognition of Canine Duodenal Contractile Activity', IEEE Transactions on Biomedical Engineering, vol. BME-28, no. 10, pp. 696-701. https://doi.org/10.1109/TBME.1981.324663
REDDY SNARASIMHA, DUMPALA SURYARAO, SARNA SUSHILK, NORTHCOTT PETERG. Pattern Recognition of Canine Duodenal Contractile Activity. IEEE Transactions on Biomedical Engineering. 1981 Oct 1;BME-28(10):696-701. https://doi.org/10.1109/TBME.1981.324663
REDDY, S. NARASIMHA ; DUMPALA, SURYA RAO ; SARNA, SUSHIL K. ; NORTHCOTT, PETER G. / Pattern Recognition of Canine Duodenal Contractile Activity. In: IEEE Transactions on Biomedical Engineering. 1981 ; Vol. BME-28, No. 10. pp. 696-701.
@article{724be6c87a344a9a904f76d6a368b062,
title = "Pattern Recognition of Canine Duodenal Contractile Activity",
abstract = "Abstract An application of statistical pattern recognition technique to the classification of canine duodenal contractile activity resulting from the ingestion of three different test meals, viz. water, acid, and solid, is described. Feature vectors were extracted from the contractile activities recorded by means of strain gauges, and were based on average duration, number, and intensities of contractions, as well as their frequency and propagational characteristics. Pattern training and classification were performed via the Bayes decision rule. The results indicate that the three different meals give rise to three different kinds of contractile activities. An improvement in the classifier's performance was observed when it was updated with correctly classified patterns. The results appear to suggest that pattern analysis techniques add a new dimension to the study of gastrointestinal motility in health and disease. For example, pattern recognition techniques can also be extended to identify contractile patterns altered due to such pathological conditions as irritable bowel syndrome and postoperative diarrhea and, hence, elucidate the underlying relationship between contractile activity and distal propulsion of contents.",
author = "REDDY, {S. NARASIMHA} and DUMPALA, {SURYA RAO} and SARNA, {SUSHIL K.} and NORTHCOTT, {PETER G.}",
year = "1981",
month = "10",
day = "1",
doi = "10.1109/TBME.1981.324663",
language = "English (US)",
volume = "BME-28",
pages = "696--701",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - Pattern Recognition of Canine Duodenal Contractile Activity

AU - REDDY, S. NARASIMHA

AU - DUMPALA, SURYA RAO

AU - SARNA, SUSHIL K.

AU - NORTHCOTT, PETER G.

PY - 1981/10/1

Y1 - 1981/10/1

N2 - Abstract An application of statistical pattern recognition technique to the classification of canine duodenal contractile activity resulting from the ingestion of three different test meals, viz. water, acid, and solid, is described. Feature vectors were extracted from the contractile activities recorded by means of strain gauges, and were based on average duration, number, and intensities of contractions, as well as their frequency and propagational characteristics. Pattern training and classification were performed via the Bayes decision rule. The results indicate that the three different meals give rise to three different kinds of contractile activities. An improvement in the classifier's performance was observed when it was updated with correctly classified patterns. The results appear to suggest that pattern analysis techniques add a new dimension to the study of gastrointestinal motility in health and disease. For example, pattern recognition techniques can also be extended to identify contractile patterns altered due to such pathological conditions as irritable bowel syndrome and postoperative diarrhea and, hence, elucidate the underlying relationship between contractile activity and distal propulsion of contents.

AB - Abstract An application of statistical pattern recognition technique to the classification of canine duodenal contractile activity resulting from the ingestion of three different test meals, viz. water, acid, and solid, is described. Feature vectors were extracted from the contractile activities recorded by means of strain gauges, and were based on average duration, number, and intensities of contractions, as well as their frequency and propagational characteristics. Pattern training and classification were performed via the Bayes decision rule. The results indicate that the three different meals give rise to three different kinds of contractile activities. An improvement in the classifier's performance was observed when it was updated with correctly classified patterns. The results appear to suggest that pattern analysis techniques add a new dimension to the study of gastrointestinal motility in health and disease. For example, pattern recognition techniques can also be extended to identify contractile patterns altered due to such pathological conditions as irritable bowel syndrome and postoperative diarrhea and, hence, elucidate the underlying relationship between contractile activity and distal propulsion of contents.

UR - http://www.scopus.com/inward/record.url?scp=0019728679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0019728679&partnerID=8YFLogxK

U2 - 10.1109/TBME.1981.324663

DO - 10.1109/TBME.1981.324663

M3 - Article

VL - BME-28

SP - 696

EP - 701

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

ER -