Khanh Pham

Dr. Khanh Pham


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2007 in Journal of Aerospace Information Systems
Verified
Journal Article
Closed access
MWMo Wei
Mo Wei
GCGenshe Chen
Genshe Chen
JCJose B. Cruz
Jose B. Cruz
LHLeonard S. Haynes
Leonard S. Haynes
KPKhanh Pham
Khanh Pham
EBErik Blasch
Erik Blasch

1 March 2018
Verified
Conference Paper
Closed access
BJBin Jia
Bin Jia
KPKhanh Pham
Khanh Pham
EBErik Blasch
Erik Blasch
ZWZhonghai Wang
Zhonghai Wang
DSDan Shen
Dan Shen
GCGenshe Chen
Genshe Chen
Space object classification is desired for space situational awareness to be able to discern resident space object (RSO) characteristics, behaviors, and perspective changes. Due to the limited sensing resources and observations, it is challenging for space object classification to be responsive to unfolding and unexpected events. Many machine learning algorithms are already used to classify space objects based on various sensor observations from radar and telescope. In this paper, the use of deep neural networks (DNN) is proposed to classify space objects due to DNN robust performance in many classification tasks, such as face recognition and object recognition. This paper explores DNN using light curve data. Conventional classification algorithms, such as k nearest neighbor (k-NN), are implemented and compared to the proposed DNN based classification algorithms, including the popular convolutional neural network (CNN) and the recurrent neural network (RNN), in terms of accuracy. Inherent advantages and disadvantages of the deep neural network based classification algorithms are summarized and the potential for future space object classification tasks is analyzed and postulated.

13 May 2011
Verified
Conference Paper
Closed access
PDF file
DSDan Shen
Dan Shen
KPKhanh Pham
Khanh Pham
EBErik Blasch
Erik Blasch
HCHuimin Chen
Huimin Chen
GCGenshe Chen
Genshe Chen
This paper develops and evaluates a pursuit-evasion orbital game approach for satellite interception and collision avoidance. Using a coupled zero-sum differential pursuit-evasion game, the pursuer minimizes the satellite interception time, and the evader tries to maximize interception time for collision avoidance. For the satellite interception problem we design an algorithm for pursuer and one for collision avoidance, where the game solution controls the evader satellite. The interception-avoidance (IA) game approach provides a worst-case solution, which is the robust lower-bound performance case. We divide our IA algorithm into two parts: first, the pursuer will rotate its orbit to the same plane of the evader; and second, the two spacecraft will play a zero-sum pursuit-evasion (PE) game. A two-step setup saves energy during the PE game because rotating a pursuer orbit requires more energy than maneuvering within the orbit plane. For the PE orbital game, an optimum open loop feedback saddle-point equilibrium solution is calculated between the pursuer and evader control structures. Using the open-loop feedback control rule, each player will calculate their distributed control track state. Numerical simulations are calculated to demonstrate the performance.

27 April 2007
Verified
Conference Paper
Closed access
PDF file
XWXu Wang
Xu Wang
JCJr. Jose B. Cruz
Jr. Jose B. Cruz
GCGenshe Chen
Genshe Chen
KPKhanh Pham
Khanh Pham
EBErik Blasch
Erik Blasch
In this paper, we consider a multi-pursuer multi-evader pursuit evasion game where some evaders' maximal speeds are higher than those of all pursuers. In multi-player pursuit evasion game, hierarchical framework is applied widely in order to decompose the original complicated multi-player game into multiple small scale games, i.e. one-pursuer one-evader games and multi-pursuer single-evader games. The latter is especially required for superior evaders. Although usually only suboptimal results are obtained, the resulted decentralized approaches are favored by researchers from the point view of communication aspect for practical applications. Based on our previous work, for a multi-pursuer single-superior- evader game on a plane, we first study the number of pursuers which necessitates the capture. Regarding each player as a mass point, a moving planar coordinate system is fixed on the evader. Then formation control is used for pursuers in their pursuit strategies deriving to 1) avoid collision between pursuers; 2) reduce the distance between each pursuer and the evader over the evolution of game; 3) keep the pursuers' angular distribution around the evader invariant during the pursuit process and enclose the superior evader within the union of each pursuer's capture domain at the end of game. The validity of our method is illustrated by two simulation examples.

23 January 2023 in IEEE Aerospace and Electronic Systems Magazine
Verified
Journal Article
Closed access
HHHui Huang
Hui Huang
YLYi Li
Yi Li
JLJiaoyue Liu
Jiaoyue Liu
DSDan Shen
Dan Shen
GCGenshe Chen
Genshe Chen
KPKhanh Pham
Khanh Pham
Low Probability of Intercept (LPI) radar waveform recognition is one of the crucial functions in the electronic intelligence systems. Advances in artificial intelligence promote the performance of the LPI waveform recognition with various signal features defined with analytical expressions. However, noisy LPI waveform recognition is still a challenge for traditional approaches even with noise elimination techniques, especially for the heavily contaminated noisy LPI signals. Recently, the adaptive analysis techniques such as Variational Mode Decomposition (VMD) and Empirical Mode Decomposition (EMD) provide potential methods that explore the inherent features of signals and formulate adaptive features for signal recognitions. In this paper, we propose an adaptive feature construction framework that utilizes both the adaptive features (via VMD and EMD) and pre-defined analytical features (via Wigner-Ville Distribution (WVD), Choi-William Distribution (CWD), and wavelet analysis) to construct the fusion feature, which is further applied on the Convolutional Neural Networks (CNN) based LPI waveform recognition system. The experimental results show that the proposed Feature Adaptive LPI Network-based Exploitation (FALPINE) approach achieves higher probability of correct classification (PCC) than state-of-the-art works, which demonstrates the superior performance of the proposed approach.

10 April 2018 in IEEE Aerospace and Electronic Systems Magazine
Verified
Journal Article
Closed access
YXYiran Xu
Yiran Xu
GWGang Wang
Gang Wang
SWSixiao Wei
Sixiao Wei
Erik BlaschErik Blasch
Erik Blasch
KPKhanh Pham
Khanh Pham
GCGenshe Chen
Genshe Chen
With the ever-growing attention on advanced cyber threats to aerospace systems, research activities on cyber resiliency have accelerated in both academic and industrial communities. For example, in mobile wireless devices, machine-to-machine architectures, as well as broadband transport computing technology, protection and security are a shared responsibility and liability across both government and commercial sectors [1]. Airborne networks are envisioned as an infrastructure consisting of Internet protocol–based airborne nodes and onboard platforms that provide interconnectivity between terrestrial and space networks [2]. The airborne networks will be critical for avionics systems communication, navigation, display, and control [3]. As a consequence, airborne systems, as well as satellite communication (SATCOM) systems, require fast and robust data transfer in a hostile action or adverse conditions.