Vehicle Engine Classification Using Spectral Tone-Pitch Vibration Indexing and Neural Network

Vehicle Engine Classification Using Spectral Tone-Pitch Vibration Indexing and Neural Network

Jie Wei (Department of Computer Science, City College of New York, New York, NY, USA), Karmon Vongsy (Air Force Research Laboratory, Wright-Patterson AFB, Dayton, OH, USA), Olga Mendoza-Schrock (Air Force Research Laboratory, Wright-Patterson AFB, Dayton, OH, USA) and Chi-Him Liu (Department of Computer Science, City College of New York, New York, NY, USA)
DOI: 10.4018/IJMSTR.2014070102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

As a non-invasive and remote sensor, the Laser Doppler Vibrometer (LDV) has found a broad spectrum of applications in various areas such as civil engineering, biomedical engineering, and even security and restoration within art museums. LDV is an ideal sensor to detect threats earlier and provide better protection to society, which is of utmost importance to military and law enforcement institutions. However, the use of LDV in situational surveillance, in particular vehicle classification, is still in its infancy due to the lack of systematic investigations on its behavioral properties. In this work, as a result of the pilot project initiated by Air Force Research Laboratory, the innate features of LDV data from many vehicles are examined, beginning with an investigation of feature differences compared to human speech signals. A spectral tone-pitch vibration indexing scheme is developed to capture the engine's periodic vibrations and the associated fundamental frequencies over the vehicles' surface. A two-layer feed-forward neural network with 20 intermediate neurons is employed to classify vehicles' engines based on their spectral tone-pitch indices. The classification results using the proposed approach over the complete LDV dataset collected by the project are exceedingly encouraging; consistently higher than 96% accuracies are attained for all four types of engines collected from this project.
Article Preview

Introduction

The use of a Laser Doppler Vibrometer (LDV) as one important multi-modal imaging instrument has been consistently growing in recent years due to the unique advantage it can provide. An LDV sends out a laser beam to a reflective surface S which is then reflected back to the LDV, the amplitude and frequency of S’s vibrations are extracted from the Doppler shift of the reflected laser beam frequency due to the S’s vibrating motion. LDV sensors provide many advantages:

  • 1.

    Non-contact and non-destructive measurements: No mass or pressure is applied during LDV’s measurement process; they are almost entirely harmless (only some high power types may cause damage to human eyes if viewed directly). LDV exerts no additional pain in non-invasive medical applications such as body temperature and pulse monitoring during medical operations, and causes no extra damages in non-intrusive civil engineering applications such as inspections of bridges, railways and buildings (Willemann, Castellini, Revel, & Tomasini, 2004) (Kubota, 2007) and delicate inspections of murals and antique fresco paintings in museums where LDV is the only viable means for inspection purposes (Castellini, Paone, & Tomasini, 1996). By contrast, the small dose of radiation from CT or X-ray in medical applications can have side effects to human cells; and the water penetration and/or corrosion are troublesome side effects in traditional ultrasonic tests.

  • 2.

    High spatial and spectral resolution: the expansive and wide range of amplitudes and frequencies provided by LDV sensors confer researchers and developers with valuable information in both spatial and frequency domains for ensuing intensive analysis and classification.

The use of LDV in many research and development subjects has become increasingly more popular due precisely to the foregoing advantages. As a non-invasive and remote sensor with the afore-mentioned benefits, LDV measured data are an ideal modality/phenomenology to detect potential threats earlier and provides better protection to society, which is of utmost importance to military and law enforcement institutions. The use of LDV in vehicle classification using signature analysis is of crucial interest to military and law enforcement institutions, but is still in its infancy due to the lack of systematic investigations on its behavioral properties.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 4 Issues (2017): 2 Released, 2 Forthcoming
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing