Darren Emge

Semi-Automated Detection of Trace Explosives in Fingerprints on Strongly Interfering Surfaces with Raman Chemical Imaging

We have previously demonstrated the use of wide-field Raman chemical imaging (RCI) to detect and identify the presence of trace explosives in contaminated fingerprints. In this current work we demonstrate the detection of trace explosives in contaminated fingerprints on strongly Raman scattering surfaces such as plastics and painted metals using an automated background subtraction routine. We demonstrate the use of partial least squares subtraction to minimize the interfering surface spectral signatures, allowing the detection and identification of explosive materials in the corrected Raman images. The resulting analyses are then visually superimposed on the corresponding bright field images to physically locate traces of explosives. Additionally, we attempt to address the question of whether a complete RCI of a fingerprint is required for trace explosive detection or whether a simple non-imaging Raman spectrum is sufficient. This investigation further demonstrates the ability to nondestructively identify explosives on fingerprints present on commonly found surfaces such that the fingerprint remains intact for further biometric analysis.

Non-Negative Matrix Factorization with Orthogonality Constraints for Chemical Agent Detection in Raman Spectra

We introduce non-negative matrix factorization with orthogonality constraints (NMF-OC) for detection of a target spectrum in a given set of Raman spectra data. An orthogonality measure is defined and two different orthogonality constraints are imposed on the standard NMF to incorporate prior information into the estimation and hence to facilitate the subsequent detection procedure. Experimental results are presented to compare NMF-OC with the basic NMF and ICA methods in detection, and to demonstrate its effectiveness in the chemical agent detection problem

Trace explosive detection in fingerprints with Raman chemical imaging

Wide-field Raman chemical imaging (RCI) has been used to detect and identify the presence of trace explosives in contaminated fingerprints. A background subtraction routine was developed to minimize the Raman spectral features produced by surfaces on which the fingerprint was examined. The Raman image was analyzed with a spectral angle mapping routine to detect and identify the explosives. This study shows the potential capability to identify explosives non-destructively so that the fingerprint remains intact for further biometric analysis.

Independent vector analysis for SSVEP signal enhancement

Steady state visual evoked potentials (SSVEP) have been identified as a highly viable solution for brain computer interface (BCI) systems. The SSVEP is observed in the scalp-based recordings of electroencephalogram (EEG) signals, and is one component buried amongst the normal brain signals and complex noise. By taking advantage of sample diversity, higher order statistics and statistical dependencies associated with the analysis of multiple datasets, independent vector analysis (IVA) can be used to enhance the detection of the SSVEP signal content. In this paper, we present a novel method for detecting SSVEP signals by treating each EEG signal as a stand alone data set. IVA is used to exploit the correlation across the estimated sources, as well as statistical diversity within datasets to enhance SSVEP detection, offering a significant improvement over averaging based methods for the detection of the SSVEP signal.

Subspace Partitioning for Target Detection and Identification

Detection of a given target or set of targets from observed data is a problem countered in many applications. Regardless of the algorithm selected, detection performance can be severely degraded when the subspace defined by the target data set is singular or ill conditioned. High correlations between target components and their linear combinations lead to false positives and misidentifications, especially for subspace-based detectors. In this paper, we propose a subspace partitioning scheme that allows for detection to be performed in a number of better conditioned subspaces instead of the original subspace. The proposed technique is applied to Raman spectroscopic data analysis. Through both simulation and experimental results, we demonstrate the improvement in the overall detection performance when using the proposed subspace partitioning scheme in conjunction with several subspace detection methods that are commonly used in practice.

Unsupervised Target Detection using Canonical Correlation Analysis and its Application to Raman Spectroscopy

We present an unsupervised detection approach, detection with canonical correlation (DCC), for target detection based on a linear mixture model. Our aim is determining the existence of certain targets in a given mixture without specific information on the targets or the background. We use canonical correlations between the target set and the mixed components as the detection index, such that the coefficients of the canonical vector are used to determine the indices of components from a given target library, thus enabling both detection and identification of the components that might be present in the mixture. For applications where the contributions of components are non-negative, we incorporate non- negativity constraints into the canonical correlation analysis framework and derive the corresponding algorithm. We show that DCC and especially its nonnegative variant leads to significant performance gain when applied to detection of surface-deposited chemical agents in Raman spectroscopy.

Spectral unmixing of agents on surfaces for the Joint Contaminated Surface Detector (JCSD)

ITT Corporation, Advanced Engineering and Sciences Division, is currently developing the Joint Contaminated Surface Detector (JCSD) technology under an Advanced Concept Technology Demonstration (ACTD) managed jointly by the U.S. Army Research, Development, and Engineering Command (RDECOM) and the Joint Project Manager for Nuclear, Biological, and Chemical Contamination Avoidance for incorporation on the Armys future reconnaissance vehicles. This paper describes the design of the chemical agent identification (ID) algorithm associated with JCSD. The algorithm detects target chemicals mixed with surface and interferent signatures. Simulated data sets were generated from real instrument measurements to support a matrix of parameters based on a Design Of Experiments approach (DOE). Decisions based on receiver operating characteristics (ROC) curves and area-under-the-curve (AUC) measures were used to down-select between several ID algorithms. Results from top performing algorithms were then combined via a fusion approach to converge towards optimum rates of detections and false alarms. This paper describes the process associated with the algorithm design and provides an illustrating example.

Detection Using Correlation Bound and its Application to Raman Spectroscopy

A detection approach, detection with correlation bound (DCB), is introduced based on a linear mixture model. We use the upper bound of the correlation between the target and mixing components as the detection index, and derive the expression for this correlation bound using the observed data. The proposed method is more robust and provides better detection performance than the currently used supervised and unsupervised approaches in Raman spectroscopy. We also apply the correlation bound to independent component analysis (ICA) within the framework of constrained ICA (c-ICA), and show how it can help improve the detection performance of ICA. Simulation results are presented to demonstrate the effectiveness of the proposed method in Raman spectroscopy for detection of surface-deposited chemical agents

A algorithm benchmark data suite for chemical and biological (chem/bio) defense applications

A Chem/Bio Defense Algorithm Benchmark is proposed as a way to leverage algorithm expertise and apply it to high fidelity Chem/Bio challenge problems in a high fidelity simulation environment. Initially intended to provide risk mitigation to the DTRA-sponsored US Army CUGR ACTD, its intent is to enable the assessment and transition of algorithms to support P3I of future spiral updates. The key chemical sensor in the CUGR ACTD is the Joint Contaminated Surface Detector (JCSD), a short-range stand-off Raman spectroscopy sensor for tactical in-the-field applications. The significant challenges in discriminating chemical signatures in such a system include, but are not limited to, complex background clutter and low signal to noise ratios (SNR). This paper will present an overview of the Chem-Bio Defense Algorithm Benchmark, and the JCSD Challenge Problem specifically.

Mid-wave infrared hyperspectral imaging of unknown chemical warfare agents

The ability of a stand-off chemical detector to distinguish two different chemical warfare agents is demonstrated in this paper. Using Negative Contrast Imaging, based upon IR absorption spectroscopy, we were able to detect 1 μl of VX, sulfur mustard and water on a subset of representative surfaces. These experiments were performed at a range of 1.3 metres and an angle of 45° to the surface. The technique employed utilises a Q-switched intracavity MgO:PPLN crystal that generated 1.4 – 1.8 μm (shortwave) and 2.6 – 3.6 μm (midwave) infrared radiation (SWIR and MWIR, respectively). The MgO:PPLN crystal has a fanned grating design which, via translation through a 1064 nm pump beam, enables tuning through the SWIR and MWIR wavelength ranges. The SWIR and MWIR beams are guided across a scene via a pair of raster scanned mirrors allowing detection of absorption features within these spectral regions. This investigation exploited MWIR signatures, as they provided sufficient molecular information to distinguish between toxic and benign chemicals in these proof-of-concept experiments.