View The Document

Accession Number:

AD1155763

Title:

Enhanced Detection Algorithm for Navy Relevant Chemical Sensing

Author(s):

• Malanoski, Anthony P.
• Dean, Scott N.
• Alvarez, Jerome E.
• White, Brandy J.
• Zabetakis, Dan
• Erickson, Jeff S.

Author Organization(s):

• NAVAL RESEARCH LAB WASHINGTON DC

Report Date:

2021-12-15

Abstract:

This effort describes testing of alternate detection algorithms including evaluating the applicability of deep learning methods such as the application of Multivariate Long Short-Term Memory Fully Convolutional Network (MLSTM-FCN) approaches. The work is specifically intended to generate additional capabilities for these prototype devices allowing for their utilization in providing enhanced monitoring of chemical threats to the health of personnel in confined spaces both during a critical exposure event and as a result of long duration low level exposures. It was determined that deep learning methods are not appropriate for the type of data collected. The Kwiatkowski-Phillips-Schmidt-Shin (KPSS) test was found to have equivalent accuracy to the already developed algorithm.

Document Type:

Conference:

Journal:

Pages:

18

File Size:

1.08MB

Contracts:

Grants:

Descriptors:

Identifiers:

• Detection algorithm
• Threat detection

SubjectCategory:

• Behavioral and Social Sciences
• Mathematical and Computer Sciences
• Navigation, Detection and Countermeasures

Communities of Interest:

• Sensors

Distribution Statement:

Approved For Public Release

View The Document