Scholars@Duke
Stacy L. Tantum

Stacy L. Tantum

Bell-Rhodes Associate Professor of the Practice of Electrical and Computer Engineering
Electrical and Computer Engineering
stacy.tantum@duke.edu
Box 90291, Durham, NC 27708-0291
3579 Fitzpatrick CIEMAS, Durham, NC 27708

Selected Publications

Concordance-based Predictive Uncertainty (CPU)-Index: Proof-of-concept with application towards improved specificity of lung cancers on low dose screening CT.

Journal Article Artif Intell Med · February 2025 In this paper, we introduce a novel concordance-based predictive uncertainty (CPU)-Index, which integrates insights from subgroup analysis and personalized AI time-to-event models. Through its application in refining lung cancer screening (LCS) predictions ... Full text Link to item Cite

Work in Progress: Evaluation of 360 Coaching to Support Whole-Student Advising in the First-Year

Conference ASEE Annual Conference and Exposition Conference Proceedings · June 25, 2023 Cite

WIP - 360 Coaching to Support Whole-Student Advising in the First-Year

Conference ASEE Annual Conference and Exposition Conference Proceedings · August 23, 2022 Cite

Supporting Students' Skillful Learning: Lessons Learned from a Faculty Development Workshop

Conference ASEE Annual Conference and Exposition Conference Proceedings · July 26, 2021 We describe the implementation of an on-campus workshop focused on supporting faculty as they develop metacognitive interventions for their educational contexts. This on-campus workshop at Duke University included engineering faculty as well as other facul ... Cite

The impact of time on seizure prediction performance in the FSPEEG database.

Journal Article Epilepsy & behavior : E&B · July 2015 We demonstrate evidence that high discriminability between preictal and interictal intracranial electroencephalogram (iEEG) recordings [1,2] of the Freiburg database (FSPEEG) may be due to the amount of time that occurred between recordings, as opposed to ... Full text Cite

Target detection and identification using synthetic aperture acoustics

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2014 Recent research has shown that synthetic aperture acoustic (SAA) imaging may be useful for object identification. The goal of this work is to use SAA information to detect and identify four types of objects: jagged rocks, river rocks, small concave capped ... Full text Cite

Target classification and identification using sparse model representations of frequency-domain electromagnetic induction sensor data

Journal Article IEEE Transactions on Geoscience and Remote Sensing · January 1, 2013 Frequency-domain electromagnetic induction (EMI) sensors can measure object-specific signatures that can be used to discriminate landmines from harmless clutter. In a model-based signal processing paradigm, the object signatures can often be decomposed int ... Full text Cite

Sparse model inversion and processing of spatial frequency-domain electromagnetic induction sensor array data for improved landmine discrimination

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2013 Frequency-domain electromagnetic induction (EMI) sensors have been shown to provide target signatures which enable discrimination of landmines from harmless clutter. In particular, frequency-domain EMI sensors are well-suited for target characterization by ... Full text Cite

Investigation of the effects of operator technique on handheld sensor data for landmine detection

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2012 Ground penetrating radar (GPR) is a commonly employed sensing modality for landmine detection. It has been successfully deployed in vehicular systems, and is also being integrated into handheld systems. Handheld mine detection systems are typically deploye ... Full text Cite

Feature extraction and processing of spatial frequency-domain electromagnetic induction sensor data for improved landmine discrimination

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2012 Frequency-domain electromagnetic induction (EMI) sensors have been shown to provide target signatures which enable discrimination of landmines from harmless clutter. In particular, frequency-domain EMI sensors are well-suited for target characterization by ... Full text Cite

Frequency-domain electromagnetic induction sensor data feature extraction and processing for improved landmine detection

Conference Proceedings of SPIE the International Society for Optical Engineering · July 13, 2011 Frequency-domain electromagnetic induction (EMI) sensors have the ability to provide target signatures which enable discrimination of landmines from harmless clutter. In particular, frequency-domain EMI sensors are well-suited for target characterization b ... Full text Cite

Sparse model representations of target signatures for improved landmine detection using frequency-domain electromagnetic induction sensors

Conference Proceedings of SPIE the International Society for Optical Engineering · December 1, 2010 Frequency-domain electromagnetic induction (EMI) sensors have the ability to measure target signatures which enable discrimination of landmines from harmless clutter. In a model-based signal processing paradigm, the target signatures can be decomposed into ... Full text Cite

Modeling position error probability density functions for statistical inversions using a Goff-Jordan rough surface model

Journal Article Stochastic Environmental Research and Risk Assessment · January 1, 2009 Buried unexploded ordnance (UXO) continues to be a difficult remediation problem from both a sensing and a discrimination point of view. Modern approaches to both the sensing and discrimination problems utilize high bandwidth electromagnetic induction (EMI ... Full text Cite

Comparison of a distance-based likelihood ratio test and k-nearest neighbor classification methods

Conference Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing Mlsp 2008 · December 1, 2008 Several studies of the k-nearest neighbor (KNN) classifier have proposed the use of non-uniform weighting on the k neighbors. It has been suggested that the distance to each neighbor can be used to calculate the individual weights in a weighted KNN approac ... Full text Cite

Bayesian mitigation of sensor position errors to improve unexploded ordnance detection

Journal Article IEEE Geoscience and Remote Sensing Letters · January 1, 2008 Phenomenological modeling coupled with statistical signal processing has been shown to significantly improve capabilities for discriminating unexploded ordnance (UXO) from benign clutter using electromagnetic induction (EMI) sensor data. The general premis ... Full text Cite

Independent component analysis for UXO detection in highly cluttered environments

Journal Article Journal of Applied Geophysics · March 19, 2007 Statistical signal processing techniques have shown progress in discriminating UXO from clutter when the objects occur in isolation. Under this condition, only a single object contributes to the measured sensor data. For multiple closely spaced subsurface ... Full text Cite

Kalman filtering for weak signal detection in remote sensing

Chapter · January 1, 2007 Magnetic signal, and then analyzing the returned signal to infer characteristics of the investigated region. It is not uncommon for the measured signal to be relatively weak or for ambient noise to interfere with the sensor’s ability to isolate and measure ... Cite

Kalman filtering for weak signal detection in remote sensing

Chapter · January 1, 2006 Remote sensing often involves probing a region of interest with a transmitted electromagnetic signal, and then analyzing the returned signal to infer characteristics of the investigated region. It is not uncommon for the measured signal to be relatively we ... Cite

Statistical and adaptive signal processing for UXO discrimination for next-generation sensor data

Conference Piers 2006 Cambridge Progress in Electromagnetics Research Symposium Proceedings · January 1, 2006 Until recently, detection algorithms could not reliably distinguish between buried UXO and clutter, leading to many false alarms. Over the last several years modern geophysical techniques have been developed that merge more sophisticated sensors, underlyin ... Full text Cite

Kalman filtering for enhanced landmine detection using quadrupole resonance

Journal Article IEEE Transactions on Geoscience and Remote Sensing · July 1, 2005 Quadrupole resonance (QR) is a novel technology recently applied to landmine detection. The detection process is specific to the chemistry of the explosive, and therefore is less susceptible to the types of false alarms experienced by metal detectors and g ... Full text Cite

Uxo discrimination using blind source separation

Conference Proceedings of the Symposium on the Application of Geophyics to Engineering and Environmental Problems Sageep · January 1, 2005 Statistical signal processing techniques have shown progress in discriminating UXO from clutter when the objects occur in isolation. Under this condition, only a single object contributes to the sensor measurement. For multiple closely-spaced subsurface ob ... Full text Cite

Signal processing for improved explosives detection using quadrupole resonance

Conference Proceedings of SPIE the International Society for Optical Engineering · December 20, 2004 Quadrupole resonance (QR) technology for explosives detection is of crucial importance in an increasing number of applications. For landmine detection, where the detection system cannot be adequately shielded, QR has proven to be highly effective if the QR ... Full text Cite

Data analysis for classification of UXO filler using pulsed neutron techniques

Conference Proceedings of SPIE the International Society for Optical Engineering · December 20, 2004 Irradiating substances with pulsed neutrons results in several types of interactions which cause the emission of gamma rays. The energy of these gamma rays is characteristic of the nuclei with which the reaction occurred, and can therefore be used as an in ... Full text Cite

EMI-based classification of multiple closely spaced subsurface objects via independent component analysis

Journal Article IEEE Transactions on Geoscience and Remote Sensing · November 1, 2004 Previous work in subsurface object discrimination using electromagnetic induction data has shown that discrimination algorithms based on statistical signal processing techniques are effective for classifying data from objects that occur in isolation. Howev ... Full text Cite

Cramer-Rao lower bound for estimating quadrupole resonance signals in non-Gaussian noise

Journal Article IEEE Signal Processing Letters · May 1, 2004 Quadrupole resonance (QR) technology for the detection of explosives is of crucial importance in an increasing number of applications. For landmine detection, where the detection system cannot be shielded, QR has proven to be highly effective if the QR sen ... Full text Cite

Correcting GPS Measurement Errors Induced by System Motion over Uneven Terrain

Conference Proceedings of SPIE the International Society for Optical Engineering · November 26, 2003 Many cart- and vehicular-based UXO detection systems employ GPS receivers to accurately determine the system's position. However, the unevenness of the terrain often causes the system to tilt during the data collection, introducing errors in the GPS measur ... Full text Cite

Performance bounds and a parameter transformation for decay rate estimation

Journal Article IEEE Transactions on Geoscience and Remote Sensing · October 1, 2003 Decay rate estimation has been proposed as an effective method for signal characterization in many application areas, including subsurface sensing using time-domain electromagnetic induction (EMI) sensors. The physical basis for this strategy is that every ... Full text Cite

Enhanced auditory displays for improved landmine detection using EMI sensors

Journal Article Subsurface Sensing Technologies and Applications · July 2003 Cite

The performance of matched-field track-before-detect methods using shallow-water Pacific data.

Journal Article The Journal of the Acoustical Society of America · July 2002 Matched-field track-before-detect processing, which extends the concept of matched-field processing to include modeling of the source dynamics, has recently emerged as a promising approach for maintaining the track of a moving source. In this paper, optima ... Full text Cite

A comparison of algorithms for landmine detection and discrimination using ground penetrating radar

Conference Proceedings of SPIE - The International Society for Optical Engineering · 2002 Ground penetrating radar (GPR) has been proposed as an effective sensing modality for reducing the excessively high false alarm rates often encountered in landmine detection applications. Ground penetrating radar is sensitive to discontinuities in the inte ... Full text Link to item Cite

Sensor fusion of EMI and GPR data for improved landmine detection

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2002 It is widely accepted that single sensors cannot simultaneously achieve both high detection rates and low false alarm rates for the landmine detection problem. Thus, in this paper we consider the fusion of two types of sensors, electromagnetic induction (E ... Full text Cite

A parameter transformation for improved decay rate estimation

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2002 Decay rate estimation has been proposed as an effective method for landmine and unexploded ordnance (UXO) detection and discrimination when electromagnetic induction (EMI) sensors are employed. The phenomenological basis for this strategy is that every obj ... Full text Cite

A parameter transformation and cramér-rao bounds for estimating decay rates from exponential signals

Conference International Geoscience and Remote Sensing Symposium IGARSS · January 1, 2002 Weighted sums of decaying exponentials characterize the response of many physical systems. Therefore, accurate decay rate estimation is a goal in many diverse disciplines. In this paper, a parameter transformation which improves decay rate estimation is pr ... Cite

Landmine detection with nuclear quadrupole resonance

Conference International Geoscience and Remote Sensing Symposium IGARSS · January 1, 2002 Nuclear Quadrupole Resonance (NQR) technology for the detection of explosives is of crucial importance in an increasing number of applications. For landmine detection, NQR has proven to be highly effective if the NQR sensor is not exposed to radio frequenc ... Cite

Enhanced signal and auditory processing for landmine detection using EMI sensors

Conference Proceedings of SPIE the International Society for Optical Engineering · December 1, 2001 Although the ability of EMI sensors to detect landmines has improved significantly, false alarm rate reduction remains a challenging problem. However, experienced operators can often discriminate mines from metallic clutter with the aid of an audio transdu ... Full text Cite

Model-based statistical signal processing using electromagnetic induction data for landmine detection and classification

Conference IEEE Workshop on Statistical Signal Processing Proceedings · December 1, 2001 Traditionally, electromagnetic induction (EMI) sensors are operated in the time-domain and the response strength is related to the amount of metal present in the object. These sensors have been used almost exclusively for landmine detection. Unfortunately, ... Cite

A comparison of algorithms for subsurface target detection and identification using time-domain electromagnetic induction data

Journal Article IEEE Transactions on Geoscience and Remote Sensing · June 1, 2001 In this paper, the performance of subsurface target identification algorithms using data from time-domain electromagnetic induction (EMI) sensors is investigated. The response of time-domain EMI sensors to the presence of a conducting object may be modeled ... Full text Cite

Signal processing of ground penetrating radar data for subsurface object detection

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2001 Ground penetrating radar (GPR) generates a cross-sectional profile of the soil by transmitting electromagnetic waves that reflect back in a manner associated with the electrical properties and geometry of the objects buried underground. The responses of th ... Full text Cite

Performance bounds for target identification using decay rates estimates from EMI measurements

Conference International Geoscience and Remote Sensing Symposium IGARSS · December 1, 2000 Decay rate estimation has been proposed as an effective method for landmine and unexploded ordnance (UXO) detection. The physical basis for this strategy is that every object in the target library possesses a unique set of decay rates. In theory, the chara ... Cite

On array design for matched-field processing

Journal Article The Journal of the Acoustical Society of America · April 2000 Conventional plane-wave beamforming array design guidelines are motivated by the desire to obtain particular beampattern characteristics, such as main lobe width and side lobe levels. These design guidelines are appropriate for arrays employed for beamform ... Full text Cite

Improved detection of low-metallic content landmines using EMI data

Conference Proceedings of SPIE - The International Society for Optical Engineering · 2000 EMI sensors are used extensively to detect landmines, and operate by detecting the metal that is present in mines. However, mines vary in their construction from metal-cased varieties with a large mass of metal to plastic-cased varieties with minute amount ... Full text Link to item Cite

Detection and classification of landmine-like targets in a non-Gaussian noise environment

Conference Proceedings of SPIE - The International Society for Optical Engineering · 2000 Many statistical signal processing approaches to target detection and classification assume the measurement is corrupted by independent, identically distributed (i.i.d.) white Gaussian noise. This common assumption often results in simpler, and less comput ... Full text Link to item Cite

Physics-based statistical signal processing for improved landmine detection and classification via decay rate estimation

Conference Proceedings of SPIE - The International Society for Optical Engineering · 2000 Target discrimination via decay rate (pole) estimation has been proposed as an effective method for landmine and UXO detection. The physical basis for this strategy is that every object in the target library (i.e., landmine and/or UXO target) possesses a u ... Full text Link to item Cite

Improved detection of low-metallic content landmines using EMI data

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2000 EMI sensors are used extensively to detect landmines, and operate by detecting the metal that is present in mines. However, mines vary in their construction from metal-cased varieties with a large mass of metal to plastic-cased varieties with minute amount ... Cite

Physics-based statistical signal processing for improved landmine detection and classification via decay rate estimation

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2000 Target discrimination via decay rate (pole) estimation has been proposed as an effective method for landmine and UXO detection. The physical basis for this strategy is that every object in the target library (i.e., landmine and/or UXO target) possesses a u ... Cite

Statistical signal processing for detection of buried landmines using quadrupole resonance

Conference DETECTION AND REMEDIATION TECHNOLOGIES FOR MINES AND MINELIKE TARGETS V, PTS 1 AND 2 · 2000 Full text Cite

Detection and classification of landmine-like targets in a non-Gaussian noise environment

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2000 Many statistical signal processing approaches to target detection and classification assume the measurement is corrupted by independent, identically distributed (i.i.d.) white Gaussian noise. This common assumption often results in simpler, and less comput ... Cite

Statistical signal processing techniques for the detection of low-metal landmines using EMI and GPR sensors (topic area: E.1)

Conference International Geoscience and Remote Sensing Symposium IGARSS · December 1, 1999 The Joint UXO Coordination Office (JUXOCO) at Ft. Belvoir, VA is sponsoring a series of experiments designed to establish a performance baseline for a variety of sensors. The purpose of these experiments is to determine if advanced algorithms are useful fo ... Cite

Signal processing for NQR discrimination of buried landmines

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 1999 Nuclear quadrupole resonance (NQR) is a technique that discriminates mines from clutter by exploiting unique properties of explosives, rather than the attributes of the mine that exist in many forms of anthropic clutter (e.g., metal content). After excitin ... Full text Cite

Single sensor processing and sensor fusion of GPR and EMI data for landmine detection

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 1999 In our previous work, we have shown theoretically that a model-based Bayesian approach to the detection of landmines affords significant performance gains over standard thresholding techniques. These performance gains hold for both time- and frequency-doma ... Cite

Bayesian signal detection for multiple aspect targets with an uncertain look angle

Journal Article Proceedings of SPIE the International Society for Optical Engineering · January 1, 1999 An optimal signal detection theory (likelihood ratio) approach is presented for the determination of the presence or absence of a target observed at multiple aspects in noise, where there is uncertainty in the initial look angle at which the aspects are ob ... Cite

Effects of signal-to-noise ratio mismatch on Bayesian matched-field source localization performance

Journal Article ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · January 1, 1999 The signal-to-noise ratio of real data is rarely known with complete certainty. However, Bayesian matched-field processing techniques for ocean acoustic source localization often require the signal-to-noise ratio (SNR) to be known a priori. In this paper, ... Cite

Tracking and localizing a moving source in an uncertain shallow water environment

Journal Article Journal of the Acoustical Society of America · January 1, 1998 An optimal approach to tracking a moving source in the presence of environmental variability is presented. This tracking algorithm, called the optimum uncertain field tracking algorithm (OUFTA), incorporates a model for the source motion as well as the unc ... Full text Cite