Timothy S Khuon Version: **/****

*** ******* ******, *********, ** 02420

adu2w4@r.postjobfree.com, Mobile 781-***-****

linkedin.com/in/timkhuon/

Secret Clearance (09/16/2021-Present)

ACTIVE TS/SCI Eligibility Clearance (208-2026) Expired in 2026 and Polygraph (2008-2021)

Image Processing, Neural Net Learning, Mod&Sim, signal processing, Computer Vision

Technical Experience

Booz Allen Hamilton – 17 Mar 2021 – 1, August 2022

Title: Radar Data Scientist Lead specialized in Aerospace programs.

Loc: Lexington, MA

Responsibility: Detection and Tracking, ISR, Electronic Warfare Study, Machine Learning and tracker radar, studying ISR radar using Deep Learning.

SAIC, Radar Scientist and Contracted to NRO, Jan 2019-Feb 2021

Title: Spectral Sensor Scientist

Responsibility:

Back-end Exploitations: Technical Analysis of Methods and Data plus research in false target electric warfare

defensively and offensively studying including ECCM.

BAE Systems, Contractor to NGA, Image Quality Assessment, May 2017-Jan 2019.

Title: Imagery Scientist

Responsibility: Signal and Imagery Science in Advanced Signal Processing

Research and algorithm development in advanced algorithms feature extractions and non-linearly classifiers to extract invariant imagery features and fused them with machine learning for NIIRS prediction. Feature extractions are performed with signal pressing including modulation transfer function and Fourier domain filtering of resolution, signal to noise ratio, gradient sharpness. Imagery quality prediction is performed by mean of machine learning in subsumption approach by data fusion of multi features.

Booz Allen Hamilton, Contracted to NGA Research, Springfield, VA, 01/2010 - 05/2017

Title: Remote Sensing Scientist; Profession: Sensor Signal Processing Scientist;

Program: Advanced Remote Sensor

Responsibility: Advanced Sensor Signal Processing/ATR/Nonlinear Classifier (Deep Learning) Research

Research and algorithm development in Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment. Responsible for signal/image processing algorithm developments in geospatial remote sensing programs. Involve in development spectral and spatial segmentation and adaptive pattern recognition, sensor fusion, compressive sensing, dictionary learning, and sparse reconstruction algorithms for a new HSI compressive sensing sensor, and also to explore some essential exploitations. Also creating a techniques for feature extraction, and signature retrieval including directional wavelet from HSI for training and classification by with neural network classifiers. Devised algorithm for sensor fusion of HSI and Lidar for new data collected from missions. The result was presented in NGA high technology workshop. Study dimensional manifold in Lidar 4D segmentation and classification. Devised associative memory for spectral and spatial sensor fusion successfully for Lidar and HSI data. Internally presented in spatial and spectral of Lidar and HSI data plus compressive sensing, radar fundamentals including SAR image formation and coherent/amplitude change detection. Devising algorithm to perform SAR image speckle mitigation, registration, amplitude and coherent change detection in advanced phase based (without amplitude) change detection. The advanced phase based change detection provides permanent features and change detections that cannot be achieved by any other known coherent change detection algorithms. Devising 3D interferometric radar imaging algorithm. Helps the group to organize AIGA (Advancing Image Geospatial Analysis) program and provide technical Expertise in Lidar data exploitation, HSI Non-linear classification, and neural net sensor fusion. Devising algorithms for super-resolution, spatial segmentation and classification, for spectral classification, and for neural net based sensor fusion. The results have been presented with technical papers internally for government research community and for the AIGA research-based program (Advancing Imagery for Geospatial Analysis), ASPRS, International Lidar Mapping, SPIE DSS, SPIE Optical Engineering, IEEE IGRSS, IEEE AIPR, National Academic Research Program @ National Academy of Science, GEOINT Science Journal. Theoretical studying advanced imaging algorithms for synthetic aperture sonar side scan imagery with frequency jitter waveform to achieve high power gain at higher frequency for higher range resolution for under-sea navigation. Improving imagery resolution with dictionary learning by compressive sensing.

JHUAPL, MD 09/2007 – 01/2010

Title: Technical Staff; Profession: Lidar Research Engineer

Responsibility: Lidar Data Exploitation and Foliage Penetration

Responsible for signal/image processing algorithm developments in foliage penetration, feature extraction, and 3D segmentation of Lidar data from various sensors. Advanced mean shift clustering algorithm is capable to capture natural clutters as well as man-made objects in open area and foliage area. Devising dispersion algorithms for target classification. In addition, provides analysis and exploitation of various Lidar sensors. In addition, an obstruction extraction algorithm is also devised for flight-path safety. Algorithm development of data interferometric imaging from a single phase center by illuminating green and red laser, to form a 2D fringe. Then applying phase unwrapping of differential phases to form 3D image. The 3D face recognition can be done by feature extraction from the image and train features on neural net. Studied digital image mapping between internal data and real time sensed data for navigation. Forward mapping and backward mapping were studied for feasibility, complexity, and correctness, and then compared. Provide technical presentations and papers to DARPA in Lidar Data Exploitation.

MIT Lincoln Laboratory, MA (1987-2007)

Title: Research/Technical Staff; Profession: Research Scientist/Engineer

Responsibility: Advanced Scientific and Engineering Algorithm Research

Advanced Sensor, Missile Defense (2003-2007)

Radar RF and Antenna Feed and Architecture, Missile Defense Sensor System 12/2002 – 08/2007

Responsible for simulated and analysis tools to problems of design, data reduction, and parameter sensitivity. Responsible for multi-static analysis of missile trajectory and antenna parameters. Provide simulated missile and aircraft trajectory predictions for monostatic and bistatic radar parameter estimation. Single-person design of dual-band monopulse detection/tracking radar in amplitude and phase interferometric.

Devise beam-forming algorithm to form antenna pattern of prime-focus and cassegrain antennas. Use E/M simulations for antenna feed and reflector. Analyze PMRF reflector and feed; pinpointed the problem, and then provided the solution. Analyze pre-flight trajectory, velocity estimation, and interferometric image formation from data received at multiple phase-centers and channels.

Provide preflight analyses of monostatic and bistatic radar position selection with respect to simulated missile trajectories including trajectory prediction. To handle original data errors, compute best-fit using original trajectory radar and missile launch positions by minimizing error. To implement this, WGS-84 metric data is transformed into a local-geographic Cartesian coordinates. Then velocity, acceleration, azimuth/elevation angles, aspect angle, range, estimated RCS etc… were analyzed. With known radar parameters, all essential antenna parameters such as instantaneous optimal PRF, baseline beamwidth, and separation parameters are also approximated. Also applied changes in trajectory and radar position. In addition to the missile, aircrafts were also simulated and then analyzed. Support multiple phase centers radar in an interferometer image formed from data received at multiple phase-centers and channels.

Design antenna feeds and reflectors for a tracking radar including analysis of prime-focus and cassegrain antennas. The cassegrain geometry was designed with a hyperbolic subreflector as well as a shaped subreflector. Design cassegrain feeds with the two frequency bands (X-Band and Ku-Band) and analyze its antenna patterns for trackability. Performed metric data transformation between (range, elevation angle, azimuth angle) and (WGS-84). Track merge/reduction is also performed to reduce false alarm rate.

Design the cassegrain Westford 60-foot antenna and its corrugated-horn feed for its geometry and performance. Simulate it to obtain its antenna pattern and gain. Perform sensitivity analysis of the antenna.

Evaluate an antenna’s feed cover and its dome radius to handle X-Band power. This includes an investigation of the microwave radiation pattern from the feed based on the distance to the feed cover and a study of its problem.

Calculate filter transmittance loss in a medium consisting of dielectric slabs of different refractive indices and lengths.

A.Airborne Radar Research, Advanced Sensor Technology, 06/1999 – 08/2003

Synthetic Aperture Radar (Backpropagation) Signal Processing and Digital filtering

Involved in a performance assessment of clutter cancellation with various space-time adaptive processing (STAP)

algorithms for a ground moving target indication (GMTI) system and SAR image data analysis.

Post-Doppler element-space/beam-space STAP for a phase array radar GMTI study. Used these algorithms to analyze RLSTAP (Rome-Lab airborne radar data for STAP processing) simulated phase-array radar data. Used SNR Loss from STAP processing to estimate minimum detectable velocity (MDV) by the system. Generate RLSTAP simulated data for a multiple-phase-centers system to be tested by the above STAP software.

STAP processed with above algorithms the multi-channel X-band data obtained from a DARPA program's Northrop Grumman platform's 12-elements phase array radar and compared its MDV against RLSTAP simulated data MDV.

Transformed multi-channel airborne radar detections in range and Azimuth angle into a local Cartesian coordinate to match against ground truths with known location. Design software to display targets with respect to platform including GPS time alignment and radar parameters calculations.

Developed algorithms for SAR image data calibration, statistics analysis, and clutter phenomenology including approximations of range/cross-range resolutions, RCS 0. Develop software to display detection scatters (assumed stationary) on registered digital maps with the platform, moving targets, and repeaters/MTS.

B Advanced Adaptive Beamforming Research, Air Defense Systems, 05/1999 - 03/2000

Space-Time Adaptive Processing for electronically scanned array: Adaptive Beam-Forming and Beam-Steering.

Contributed scientific and analytical software in various statistical and signal processing-based techniques for

radar data and system analysis. Participated in STAP and Adaptive Beamforming.

Developed algorithms for modified CFAR radar detection and target’s azimuth angle calculation by beam-splitting method. Also involved in software and extensive algorithm for adaptive beam-forming for RF interference rejection and space-time adaptive processing (STAP) for mitigation of main-beam clutter filtering, electronic counter/counter measure.

Developed and tested a complex signal processing software suite that was used on an advanced sensor system in digital filtering sub-system in the areas of general front-end signal processing including channel equalization, pulse compression, and Doppler filtering. Developed algorithms in determining target’s ground location from known range and cone angle.

Developed data analysis software to correlate processed sensor outputs with geographical databases by registering sensor data with other sources of data such as DTED (such as display of platform, airborne detection over a ground map). Involve in STAP development for phase array sensors and data transcription.

Provided some keys results for program PMR and for discussions.

Involved with an effort to estimate diagonal loading in covariance matrix and STAP Hot Clutter study.

C.Multi-Modal Multi Sensor Fusion & Radar Imaging, 04/1987 – 05/1994

Adaptive Robotic Subsumption (Cascaded Deep Learning Architecture)

Responsible for feature extraction and neural network sensor fusion, satellite maneuver prediction based on its narrowband data signature, ISAR imaging of satellite, and SAR background clutter modeling.

Developed algorithm for Neural Net applications on data and sensor fusion and design of 2-dimensional back propagation neural net algorithm and programs for a sensor fusion. Feature extraction algorithm is also developed. Three sensors were used for the fusion: X-band radar, Laser coherent radar, and IR sensor.

Development of programs for performance measures for adaptive decisioning systems. Performed statistics experiments on a number of adaptive systems (neural net-based back propagation).

Mitigation of error propagation of satellite positioning system.

Development of recursive auto-regressive model programs to detect the transition of satellite maneuvers. Develop programs to model low-pass filtered time-series data, the radar cross-section, as a stochastic autoregressive process, and another to detect spectral transitions based on the dual-approach for non-stationary wideband and narrowband data. Utilizing neural net for motion solution for satellite maneuvers.

Developed Inverse Synthetic Aperture Radar (ISAR) imaging of satellites, posed determination from ISAR, and SAR background clutter modeling. Became a key designer of a very successful ISAR imaging toolbox, which has found applications throughout DoD.

D.Biological Neural Net Researcher, MIT Brain and Cognitive Science Dept., April/1987-May/1992

Comparison between Artificial Intelligence (Simulated) and Real Intelligence (Biological)

Neural Net research under MIT Innovative Research Project for massive adaptive learning system by emulating human brain. Performed electrical signal stimulation into living neural system (deep ocean specie) grown in a biochip and acquired output signal from the chip and store into a real-time computer for signal processing analysis.

Involved in the biological chip project at the MIT Brain Science Department. These include collection and processing of data from biochip amplifiers.

Provided data acquisition and analysis of data received from the biochip.

Bell Laboratories (09/1985 - 04/1987)

Title: Member of Technical Staff

Profession: Distributed Processing Research Engineer

Responsibility: Development of 5ESS distributed system.

Participated in the system development of telephony digital network in call processing, routing, and networking.

Responsible for Project Requirements, High-level algorithm and Software Development for the 5ESS Digital Switching System.

Software development of a distributed processing system specifically in the areas of Call Processing, Network Routing, and ISDN. These included high-level design, program coding and interfacing.

Simulation/Modeling and System Experience: Supercomputer Systems on MIT-Cray YMP, Project-Athena, Mercury array processors, Linux, MATLAB, C/C++, CUDA GPGPU, Vector Machines, IDL, Advanced Visual System (AVS), ENVI, Electromagnetic Simulation Satcom/ESP, GRASP-9, WIPL, MIT-FERM, participated in AFRL-RLSTAP on Doppler Affects.

Professional & Educational Activity

Education & Training

Illinois Institute of Technology, B.S. Computer-Science/Electrical Engineering, 8/1980-5/1984. Yes graduate

Illinois Institute of Technology, M.S. Computer-Science/Electrical Engineering,6/1984 -12/1985. Yes, graduate

Massachusetts Institute of Technology, Graduate Study, 9/1987 – 05/1994, For MS/PhD, not graduate

Professional Society:

Nominated/Elected for Sigma Xi Chapter of MIT in 1994.

IEEE Society with MIT Affiliation in 1988

Artificial Neural Network Society with MIT affiliation 1990

SPIE Society with MIT/NGA-RESEARCH Affiliations.

Publications:

Timothy Khuon, Phase (coherence system) Interferometry and Interference Phase Correlation (Fourier domain) in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, LCOP, Boston, 2017.

Timothy Khuon, Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, ATR Workshop, Washington DC, 2016.

Timothy Khuon, Spectral and Spatial Sensor Fusion for Automatic Target Recognition with Deep Learning, ATR Workshop, Washington DC, 2016.

Recognizable 3D Scene Reconstruction from 2D Imagery with Deep Learning, IEEE Advanced Imagery Pattern Recognition, Washington, DC, October 2015.

Adaptive Automatic Target Recognition in Single and Multi-Modal Sensor Data, IEEE Advanced Imagery Pattern Recognition, Washington, DC, October 2014.

Invariant-feature-based adaptive automatic target recognition in Obscured 3D point clouds, presented at SPIE Defense Security Sensing, May 2014, Baltimore, MD.

Distributed Fusion Architecture with Genetic Algorithm Based Support Vector Machine, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2013.

Sensor Fusion with Genetic Algorithm-based Support Vector Machine Neural Net, NARP-2013 at National Academy of Science, Washington, DC, September 2013.

Multimodal Sensor Fusion for HSI and LIDAR Classifications, ASPRS-213, Baltimore, MD, April 2013.

Super-resolution Imagery Sensor Fusion of Lidar and Hyperspectral Classification, presented and published in IEEE Pattern Recognition, Washington DC, October 2012.

Distributed Adaptive Sensor Fusion with Super-resolution of Lidar and HSI, presented in NARP of National Academy of Sciences in Washington DC, August 2012.

Advancing Image Geospatial Analysis, Fusion of Lidar and HSI Classification, to be presented in August 2012.

Advancing Image Geospatial Analysis, Fusion of Lidar and HSI Classification, 18 April 2012.

Spectral and Spatial Sensor Fusion of Hyperspectral and Lidar Data, presented at International Lidar Mapping Forum, 24 Jan 2012, Denver, Colorado.

Neural Sensor Fusion of Lidar Spatial and HSI Spectral classifications, presented at SPIE Defense Security Sensing, 25 April 2012, Baltimore, MD.

Hyperspectral Imagery and Lidar Data Fusion for Subpixel Mapping, IEEE IGARSS, presented on 20 July 2012, Munich, Germany.

A Semi-Automated Analysis Framework for the Spatial/Spectral Fusion of LIDAR and HSI Data, NGA Innovision Basic Research Presentation, 25 Oct 2012, Springfield, VA.

Fusion of Multi-dimensional classification of HSI and LIdar data, NGA Innovision Workshop, July 2011.

Sensor Fusion of multi-dimensional data, ASPRS Government, Chantily, VA, November, 2011.

Advancing Image Geospatial Analysis, Fusion of Lidar and HSI Classification, 9 June 2011.

Supervised Neural Net Spatial Segmentation and Classification of Multi-dimensional data, AIGA, NGA Innovision Workshop, July 2011.

Spatial Segmentation and Classification of Multi-dimensional data, AIGA, NGA Innovision Workshop, Jan 2011.

Multi-Dimensional Mean Shift Segmentation and Classification on Lidar Data for Data Exploitation, JHU Applied Physics Laboratory, AISD Dept., Sep. 2008.

Tracking Antenna and Transmitter/Receiver Design, MIT Lincoln Laboratory, January, 2007.

PRF and Doppler Radar Parameter Optimizations for Multi-static radar positions with-respect-to high-speed moving targets, MIT Lincoln Laboratory, Jan-June 2006.

PMRF-Reflector Antenna Pattern Analysis and Correction, Jan, 2004.

Range/Cross-range Resolution and RCS Analysis and Terrain Clutter Phenomenology in SAR Image, MIT Lincoln Laboratory, August, 2002.

Training set based performance measures for data-adaptive decisioning systems, SPIE Symposiums, San Diego, July 1992.

Neural Network Data Fusion Concepts and Application, IEEE Joint-Conference on Neural Networks Symposiums, Baltimore, June 1992.

Neural Net Sensor Fusion, MIT Lincoln Laboratory, September, 1991.

Neural Network for Distributed Sensor Data Fusion: The Firefly Experiment, SPIE Symposium, Boston, MA, 10-15 Nov. 1991.

Neural Network Data Fusion Concepts and Application, IEEE International Joint Conference on Neural Networks Symposiums, San Diego, June 1990.

Adaptive Preprocessing of Nonstationary Signals, MIT Lincoln Laboratory, May, 1989.

Learning Algorithms For the Multilayer Perception, MIT Lincoln Laboratory, October, 1988

Perceptron Hypothesis Testing of Satellite RCS Data, MIT Lincoln Laboratory, Nov

Timothy Khuon, Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, ATRWG, Washington DC, 2016.

Timothy Khuon, Distributed Adaptive Framework for MSI/HSI Imagery and 3D Point Cloud Fusion, SPIE Optical Engineering, 2016.

Timothy Khuon, Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, ATR Workshop, Washington DC, 2016.

Timothy Khuon, Spectral and Spatial Sensor Fusion for Automatic Target Recognition with Deep Learning, ATR Workshop, Washington DC, 2016.

Timothy Khuon, Adaptive Automatic Target Recognition in Single and Multi-Modal Sensor Data, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2014.

Distributed Fusion Architecture with Genetic Algorithm Based Support Vector Machine, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2013.

Invariant-feature-based adaptive automatic target recognition in Obscured 3D point clouds, presented at SPIE Defense Security Sensing, May 2014, Baltimore, MD.

Distributed Fusion Architecture with Genetic Algorithm Based Support Vector Machine, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2013.

Distributed Adaptive Spectral and Spatial Sensor Fusion for Super-resolution Classification, IEEE Applied Imagery Pattern Recognition, Washignton DC, October 2012.

Sparse Modeling For Hyperspectral Imagery with Lidar Data Fusion for Subpixel Mapping, IEEE IGRSS, July 2012, Munich, Germany.

Distributed Adaptive Super-resolved Hyperspectral and LIDAR Sensor Fusion for Classification, National Academic Research Program, National Academy of Science, August 2012.

Spectral and Spatial Sensor Fusion of Hyperspectral and Lidar Data, presented at International Lidar Mapping Forum, 24 Jan 2012, Denver, Colorado.

Neural Sensor Fusion of Lidar Spatial and HSI Spectral classifications, SPIE Defense Security Sensing, 25 April 2012, Baltimore, MD.

Advancing Image Geospatial Analysis, Fusion of Lidar and HSI Classification, 18 April 2012.

A Semi-Automated Analysis Framework for the Spatial/Spectral Fusion of LIDAR and HSI Data, published on GEOINT Science Journal, November, 2012.

Feature Based Neural Net Sensor Fusion for Hyperspectral and LIDAR Data, ASPRS, Chantily, VA, November, 2011.

HSI and Lidar Sensor Fusion for multi-dimensional Classification, Feb 2011, NGA.

Multi-Dimensional Mean Shift Segmentation and Classification on Lidar Data for Data Exploitation, 2008, JHUAPL.

T.Khuon, Chebychev Dielectric Filter, Technical Memorandum, December, 2004.

PMRF-Reflector Antenna Pattern Analysis and Correction, Technical Memorandum, June, 2004.

T.Khuon, Tracking Antenna and Transmitter/Receiver Design, Technical Memorandum, January, 2007.

T.Khuon, Multi-static Antenna Analysis for Ballistic Missile flights, Technical Memorandum, July, 2006.

T.Khuon, Post-doppler STAP processing for GMTI analysis of a phased array system based on RLSTAP simulated data, 2001.

T.Khuon, Moving Clutter Interference Phenomenology on Airborne Multi-Phase Radar, 2002.

R. Levine, T. Khuon, Perceptron Hypothesis Testing of Satellite RCS Data, MIT Lincoln Laboratory Technical Memorandum 93L-0010, 19 Nov. 1987.

M. Eggers, T. Khuon, Learning Algorithms For the Multilayer Perception, MIT Lincoln Laboratory Technical Report, DTIC AD-A-202682, 28 October, 1988.

R. Levine, T. Khuon, The Neocognitron Network For Robust Signature Identification, MIT Lincoln Laboratory Technical Memorandum 93L-0014, 23 January, 1989.

M. Eggers, T. Khuon, Neural Network Data Fusion For Decision Making, in 1989 Tri-Service Data Fusion Symposium Technical Proceedings, Volume 1, Naval Air Development Center, Warminster, PA, May 1989.

M. Eggers, T. Khuon, Adaptive Preprocessing of Nonstationary Signals, MIT Lincoln Laboratory Technical Report TR 849, 9 May, 1989.

M. Eggers, T. Khuon, Neural Network Data Fusion Concepts and Application, IEEE International Joint Conference on Neural Networks Symposiums, Vol. 2, San Diego, June 1990.

R. Levine, T. Khuon, A Comparison of Neural Net Learning by Back Propagation and Simulated Annealing, MIT Lincoln Laboratory Technical Memorandum 93L-0019, 7 Feb. 1990.

R. Levine, T. Khuon, Neural Net Sensor Fusion, MIT Lincoln Laboratory Technical Report TR 926, 5 September, 1991.

M. Eggers, D. Erhlich, T. Khuon, et al, Biochip Technology Development, MIT Lincoln Laboratory Technical Report 901, 9 Nov. 1990.

R. Levine, T. Khuon, Performance Measures for Adaptive Decisioning Systems, MIT Lincoln Laboratory Technical Report TR 927, 11 September, 1991, and also accepted to Neural Networks Conference in 1992.

R. Levine, T. Khuon, Neural Network for Distributed Sensor Data Fusion: The Firefly Experiment, SPIE Symposium on Intelligence Robotic Systems, Boston, MA, 10-15 Nov. 1991.

R. Levine, T. Khuon, Decision-level Neural Net Sensor Fusion, Handbook of Statistics, Vol. 10, Signal Processing and Its Applications; N.K. Bose and C.R. Rao, North Holland Publishing Co.

R. Levine, T. Khuon, Training Set-based Performance Measures for Neural Net Hypothesis Testing, IEEE Joint-Conference on Neural Networks Symposiums, Baltimore, June 1992.

T. Khuon, Array Processors Experiments, MIT Lincoln Laboratory Technical Memorandum, 12 Sep. 1992.

R. Levine, T. Khuon, Training-Set Based Performance Measures for Data-adaptive Decisioning systems, SPIE Symposiums, San Diego, July 1992.

PRESENTATIONS

1.Timothy Khuon, Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, ATRWG, Washington DC, 2016.

2.Timothy Khuon, Distributed Adaptive Framework for MSI/HSI Imagery and 3D Point Cloud Fusion, SPIE Optical Engineering, 2016.

3.Timothy Khuon, Interference Phase Correlation in Nonlinear/Multi-dimension Auto Regression for nonlinear registration/alignment, ATR Workshop, Washington DC, 2016.

4.Timothy Khuon, Spectral and Spatial Sensor Fusion for Automatic Target Recognition with Deep Learning, ATR Workshop, Washington DC, 2016.

5.Timothy Khuon, Adaptive Automatic Target Recognition in Single and Multi-Modal Sensor Data, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2014.

6.Distributed Fusion Architecture with Genetic Algorithm Based Support Vector Machine, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2013.

7.Invariant-feature-based adaptive automatic target recognition in Obscured 3D point clouds, presented at SPIE Defense Security Sensing, May 2014, Baltimore, MD.

8.Distributed Fusion Architecture with Genetic Algorithm Based Support Vector Machine, IEEE Advanced Imagery Pattern Recognition, Washington DC, October 2013.

9.Distributed Adaptive Spectral and Spatial Sensor Fusion for Super-resolution Classification, IEEE Applied Imagery Pattern Recognition, Washignton DC, October 2012.

10.Sparse Modeling For Hyperspectral Imagery with Lidar Data Fusion for Subpixel Mapping, IEEE IGRSS, July 2012, Munich, Germany.

11.Distributed Adaptive Super-resolved Hyperspectral and LIDAR Sensor Fusion for Classification, National Academic Research Program, National Academy of Science, August 2012.

12.Spectral and Spatial Sensor Fusion of Hyperspectral and Lidar Data, presented at International Lidar Mapping Forum, 24 Jan 2012, Denver, Colorado.

13.Neural Sensor Fusion of Lidar Spatial and HSI Spectral classifications, SPIE Defense Security Sensing, 25 April 2012, Baltimore, MD.

14.Advancing Image Geospatial Analysis, Fusion of Lidar and HSI Classification, 18 April 2012.

15.A Semi-Automated Analysis Framework for the Spatial/Spectral Fusion of LIDAR and HSI Data, published on GEOINT Science Journal, November, 2012.

16.Feature Based Neural Net Sensor Fusion for Hyperspectral and LIDAR Data, ASPRS, Chantily, VA, November, 2011.

17.HSI and Lidar Sensor Fusion for multi-dimensional Classification, Feb 2011, NGA.

18.Multi-Dimensional Mean Shift Segmentation and Classification on Lidar Data for Data Exploitation, 2008, JHUAPL.

19.T.Khuon, Chebychev Dielectric Filter, Technical Memorandum, December, 2004.

20.PMRF-Reflector Antenna Pattern Analysis and Correction, Technical Memorandum, June, 2004.

21.T.Khuon, Tracking Antenna and Transmitter/Receiver Design, Technical Memorandum, January, 2007.

22.T.Khuon, Multi-static Antenna Analysis for Ballistic Missile flights, Technical Memorandum, July, 2006.

23.T.Khuon, Post-doppler STAP processing for GMTI analysis of a phased array system based on RLSTAP simulated data, 2001.

24.T.Khuon, Moving Clutter Interference Phenomenology on Airborne Multi-Phase Radar, 2002.

25.R. Levine, T. Khuon, Perceptron Hypothesis Testing of Satellite RCS Data, MIT Lincoln Laboratory Technical Memorandum 93L-0010, 19 Nov. 1987.

26.M. Eggers, T. Khuon, Learning Algorithms For the Multilayer Perception, MIT Lincoln Laboratory Technical Report, DTIC AD-A-202682, 28 October, 1988.

27.R. Levine, T. Khuon, The Neocognitron Network For Robust Signature Identification, MIT Lincoln Laboratory Technical Memorandum 93L-0014, 23 January, 1989.

28.M. Eggers, T. Khuon, Neural Network Data Fusion For Decision Making, in 1989 Tri-Service Data Fusion Symposium Technical Proceedings, Volume 1, Naval Air Development Center, Warminster, PA, May 1989.

29.M. Eggers, T. Khuon, Adaptive Preprocessing of Nonstationary Signals, MIT Lincoln Laboratory Technical Report TR 849, 9 May, 1989.

30.M. Eggers, T.

Contact this candidate