Asynchronous data-driven classification of weapon systems

Xin Jin, Kushal Mukherjee, Shalabh Gupta, Asok Ray, Shashi Phoha, Thyagaraju Damarla

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This communication addresses real-time weapon classification by analysis of asynchronous acoustic data, collected from microphones on a sensor network. The weapon classification algorithm consists of two parts: (i) feature extraction from time-series data using symbolic dynamic filtering (SDF), and (ii) pattern classification based on the extracted features using the language measure (LM) and support vector machine (SVM). The proposed algorithm has been tested on field data, generated by firing of two types of rifles. The results of analysis demonstrate high accuracy and fast execution of the pattern classification algorithm with low memory requirements. Potential applications include simultaneous shooter localization and weapon classification with soldier-wearable networked sensors.

Original languageEnglish (US)
Article number123001
JournalMeasurement Science and Technology
Volume20
Issue number12
DOIs
StatePublished - Dec 22 2009

Fingerprint

weapon systems
Pattern Classification
Classification Algorithm
Data-driven
weapons
Pattern recognition
Symbolic Dynamics
Time Series Data
Feature Extraction
Sensor Networks
Support Vector Machine
Acoustics
High Accuracy
Filtering
Microphones
Real-time
Sensor
rifles
Sensor networks
Support vector machines

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Applied Mathematics

Cite this

Jin, Xin ; Mukherjee, Kushal ; Gupta, Shalabh ; Ray, Asok ; Phoha, Shashi ; Damarla, Thyagaraju. / Asynchronous data-driven classification of weapon systems. In: Measurement Science and Technology. 2009 ; Vol. 20, No. 12.
@article{e917fe15d02046bfa350e68a1bf5e8e6,
title = "Asynchronous data-driven classification of weapon systems",
abstract = "This communication addresses real-time weapon classification by analysis of asynchronous acoustic data, collected from microphones on a sensor network. The weapon classification algorithm consists of two parts: (i) feature extraction from time-series data using symbolic dynamic filtering (SDF), and (ii) pattern classification based on the extracted features using the language measure (LM) and support vector machine (SVM). The proposed algorithm has been tested on field data, generated by firing of two types of rifles. The results of analysis demonstrate high accuracy and fast execution of the pattern classification algorithm with low memory requirements. Potential applications include simultaneous shooter localization and weapon classification with soldier-wearable networked sensors.",
author = "Xin Jin and Kushal Mukherjee and Shalabh Gupta and Asok Ray and Shashi Phoha and Thyagaraju Damarla",
year = "2009",
month = "12",
day = "22",
doi = "10.1088/0957-0233/20/12/123001",
language = "English (US)",
volume = "20",
journal = "Measurement Science and Technology",
issn = "0957-0233",
publisher = "IOP Publishing Ltd.",
number = "12",

}

Asynchronous data-driven classification of weapon systems. / Jin, Xin; Mukherjee, Kushal; Gupta, Shalabh; Ray, Asok; Phoha, Shashi; Damarla, Thyagaraju.

In: Measurement Science and Technology, Vol. 20, No. 12, 123001, 22.12.2009.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Asynchronous data-driven classification of weapon systems

AU - Jin, Xin

AU - Mukherjee, Kushal

AU - Gupta, Shalabh

AU - Ray, Asok

AU - Phoha, Shashi

AU - Damarla, Thyagaraju

PY - 2009/12/22

Y1 - 2009/12/22

N2 - This communication addresses real-time weapon classification by analysis of asynchronous acoustic data, collected from microphones on a sensor network. The weapon classification algorithm consists of two parts: (i) feature extraction from time-series data using symbolic dynamic filtering (SDF), and (ii) pattern classification based on the extracted features using the language measure (LM) and support vector machine (SVM). The proposed algorithm has been tested on field data, generated by firing of two types of rifles. The results of analysis demonstrate high accuracy and fast execution of the pattern classification algorithm with low memory requirements. Potential applications include simultaneous shooter localization and weapon classification with soldier-wearable networked sensors.

AB - This communication addresses real-time weapon classification by analysis of asynchronous acoustic data, collected from microphones on a sensor network. The weapon classification algorithm consists of two parts: (i) feature extraction from time-series data using symbolic dynamic filtering (SDF), and (ii) pattern classification based on the extracted features using the language measure (LM) and support vector machine (SVM). The proposed algorithm has been tested on field data, generated by firing of two types of rifles. The results of analysis demonstrate high accuracy and fast execution of the pattern classification algorithm with low memory requirements. Potential applications include simultaneous shooter localization and weapon classification with soldier-wearable networked sensors.

UR - http://www.scopus.com/inward/record.url?scp=72149103291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72149103291&partnerID=8YFLogxK

U2 - 10.1088/0957-0233/20/12/123001

DO - 10.1088/0957-0233/20/12/123001

M3 - Article

VL - 20

JO - Measurement Science and Technology

JF - Measurement Science and Technology

SN - 0957-0233

IS - 12

M1 - 123001

ER -