Kuochu C Chang

George Mason University | GMU · Department of Systems Engineering and Operations Research

Portfolio optimization and quantitative risk management have been studied extensively since the 1990s and began to attract even more attention after the 2008 financial crisis. This disastrous occurrence propelled portfolio managers to reevaluate and mitigate the risk and return trade-off in building their clients’ portfolios. The advancement of mac...

We propose a portfolio rebalance framework that integrates machine learning models into the mean-risk portfolios in multi-period settings with risk-aversion adjustment. In each period, the risk-aversion coefficient is adjusted automatically according to market trend movements predicted by machine learning models. We employ Gini’s Mean Difference (G...

Only a few publications exist at present on heterogeneous track-to-track fusion (T2TF). A common limitation of current work on heterogeneous T2TF is that the cross-covariance due to common process noise cannot be computed. This is due to the fact that two local trackers use different dynamic models and hence it is difficult to account for the commo...

This document describes corrections to the early access version of the following IEEE TAES paper in IEEE Xplores: Heterogeneous Track-to-Track Fusion in 3D Using IRST Sensor and Air MTI Radar Mahendra Mallick , Kuo-Chu Chang , Sanjeev Arulampalam , Yanjun Yan IEEE Transactions on Aerospace and Electronic Systems DOI. No. 10.1109/TAES.2019.2898302...

Dynamic asset allocation in financial investment with an optimal equity growth principle based on mutual information in communication theory is considered. Specifically, the asset allocation formula using Kelly's criteria derived from channel capacity of a binary symmetric channel is developed. The goal is to determine the optimal fraction of equit...

This paper is generally related to analytic methods for evaluating tracking performance, in particular for predicting track accuracy in dense target environments. A very simple analytic expression is derived to predict the effects of mis-associations on track accuracy. The paper analyzes an optimal track-to-measurement assignment algorithm in track...

This paper describes a continuous-time state-process, discrete-time observation, Interacting Multiple Model (IMM) tracking algorithm, and its applications to financial market modeling and asset allocation. The system state is modeled as a continuous-time, affine-Gaussian stochastic dynamical process driven by a white process noise, as well as by st...

Uncertainties regarding wireless propagation environments pose challenges for spectrum management in general and specifically hinder the implementation of dynamic spectrum sharing systems. Without the ability to reliably evaluate interference risks, spectrum sharing policies specify spectrum access behaviors such as exclusion zones and maximum tran...

This chapter presents a new analytical approach for quantifying the long-run performance of a multisensor, discrete-state classification system, under the assumption of independent, asynchronous measurements. The chapter also consolidates earlier research. The methodology described in this research has been applied to fusion performance evaluation...

In this chapter, the author develops a hybrid propagation algorithm for general Bayesian networks with mixed discrete and continuous variables. It reviews the Pearl's message passing formulae. The chapter discusses the message representation and manipulation for continuous variable and how to propagate messages between continuous variables with non...

Emerging satellite communication (SATCOM) systems are envisioned to incorporate advanced capabilities for dynamically adapting link and network configurations to meet user performance needs. These advanced capabilities require an understanding of the operating environment as well as the potential outcomes of adaptation decisions. A SATCOM situation...

This paper addresses the problem of distributed fusion when the conditional independence assumptions on sensor measurements or local estimates are not met. A new data fusion algorithm called Copula fusion is presented. The proposed method is grounded on Copula statistical modeling and Bayesian analysis. The primary advantage of the Copula-based met...

This paper presents a satellite communications (SATCOM) situational awareness and decision-making methodology that incorporates situational uncertainty with a probabilistic reasoning representation of the SATCOM network and operating environment. The situational awareness and decision model is developed using probabilistic Functional Causal Modelin...

Accurate prediction of satellite communications (SATCOM) data link loss is critical for SATCOM systems to effectively achieve required Quality of Service (QoS) and link availability. A major challenge is to account for various sources of uncertainties (such as atmospheric loss, rain loss, depolarization loss, pointing offset loss, etc.,) and their...

This paper explores the value of situational awareness information to Dynamic Spectrum Access (DSA) systems, which access wireless spectrum in an ad hoc manner to meet user needs while avoiding harmful interference to other spectrum users. In general, DSA systems must make adaptation decisions with imperfect information in factors such as local pro...

A dynamic path-planning algorithm is proposed for routing unmanned air vehicles (UAVs) in order to track ground targets under path constraints, wind effects, and obstacle avoidance requirements. We first present the tangent vector field guidance (TVFG) and the Lyapunov vector field guidance (LVFG) algorithms. We demonstrate that the TVFG outperform...

While Dynamic Spectrum Access (DSA) is premised upon the existence of technologies and policies that enable flexible access to spectrum, a quantitative understanding of the coupling among DSA technologies, policy definition, and spectrum sharing potential remains largely unexplored. Over ten years of technology research, development, and prototype...

Stochastic simulation approaches perform probabilistic inference in Bayesian networks by estimating the probability of an event based on the frequency that the event occurs in a set of simulation trials. This paper describes the evidence weighting mechanism, for augmenting the logic sampling stochastic simulation algorithm [Henrion, 1986]. Evidence...

In almost all situation assessment problems, it is useful to dynamically contract and expand the states under consideration as assessment proceeds. Contraction is most often used to combine similar events or low probability events together in order to reduce computation. Expansion is most often used to make distinctions of interest which have signi...

Research on Symbolic Probabilistic Inference (SPI) [2, 3] has provided an algorithm for resolving general queries in Bayesian networks. SPI applies the concept of dependency directed backward search to probabilistic inference, and is incremental with respect to both queries and observations. Unlike traditional Bayesian network inferencing algorithm...

Recent research on the Symbolic Probabilistic Inference (SPI) algorithm[2] has focused attention on the importance of resolving general queries in Bayesian networks. SPI applies the concept of dependency-directed backward search to probabilistic inference, and is incremental with respect to both queries and observations. In response to this researc...

This paper presents an initial study of imperfect awareness impacts on DSA decision-making and behavior. The investigation utilizes a multiattribute spectrum utility function based on preference and decision theory concepts that enables decision-making under uncertainty. The approach incorporates technical, regulatory, and economic factors into the...

Dynamic Spectrum Access (DSA) systems combine situational awareness development, decision assessment, and spectrum adaptation to provide greater spectrum access to wireless systems. While significant progress has been made in system dynamics and policy conformance reasoning, concern still exists with regards a DSA system's ability to reliably deter...

Distributed processing of multiple sensor data has advantages over centralized processing because of lower bandwidth for communicating data and lower processing load at each site. However, distributed fusion has to address dependence issues not present in centralized fusion. Bayesian distributed fusion combines local probabilities or estimates to g...

Bayesian network (BN) structure learning is a NP-hard problem. In this paper, we present an improved approach to enhance efficiency of BN structure learning. To avoid premature convergence in traditional single-group genetic algorithm (GA), we propose an immune allied genetic algorithm (IAGA) in which the multiple-population and allied strategy are...

A new Bayesian network (BN) learning method using a hybrid algorithm and chaos theory is proposed. The principles of mutation and crossover in genetic algorithm and the cloud-based adaptive inertia weight were incorporated into the proposed simple particle swarm optimization (sPSO) algorithm to achieve better diversity, and improve the convergence...

Dynamic Spectrum Access (DSA) networks seek to opportunistically utilize unused RF capacity rather than relying on static spectrum assignments. The networks change their spectrum access characteristics such as fre- quency, power, and modulation to adapt and allow for access to spectrum while not causing harmful interference to other spectrum users....

The work presented here demonstrates a new methodology of using star observations and advanced nonlinear estimation algorithms to improve the ability of a space-based electro-optical (EO) tracking system to track targets in space. Nominally, the tracking system consists of two satellites flying in a lead-follower formation tracking a ballistic or s...

This paper presents numerical performance evaluation of various algorithms that have been developed for track-to-track fusion and association problems, through a long history of the distributed multiple target tracking algorithm development. We will use a general linear-Gaussian standard model both for the target state and the sensor observation mo...

In an increasingly interconnected world information comes from various sources, usually with distinct, sometimes inconsistent semantics. Transforming raw data into high-level information fusion (HLIF) products, such as situation displays, automated decision support, and predictive analysis, relies heavily on human cognition. There is a clear lack o...

Situational awareness and prediction are essential elements of information fusion. Both involve various types of uncertainty and require a sound automated inferential process. Probabilistic ontologies support uncertainty management in se-mantically aware systems, and facilitate modular, interoperable systems. This paper describes the process of dev...

Underwater mines are inexpensive and highly effective weapons. They are difficult to detect and classify. Hence detection and classification of underwater mines is essential for the safety of naval vessels. This necessitates a formulation of highly efficient classifiers and detection techniques. Current techniques primarily focus on signals from on...

A new BN structure learning method using a cloud-based adaptive immune genetic algorithm (CAIGA) is proposed. Since the probabilities of crossover and mutation in CAIGA are adaptively varied depending on X-conditional cloud generator, it could improve the diversity of the structure population and avoid local optimum. This is due to the stochastic n...

In addition to computing the posterior distributions for hidden variables in Bayesian networks, one other important inference task is to find the most probable explanation (MPE). MPE provides the most likely configurations to explain away the evidence and helps to manage hypotheses for decision making. In recent years, researchers have proposed a f...

Mixture distributions such as Gaussian mixture model (GMM) have been used in many applications for dynamic state estimation. These applications include robotics, image and acoustic processing, distributed tracking, and multisensor data fusion. However, the recursive processing of the mixture distributions incurs rapidly growing computational requir...

This paper is concerned with analytical and semi-analytical methods for predicting performance of track-to-track association, in terms of probability of each track being correctly associated with the track that shares the same origin, when association is performed by an optimal assignment algorithm. The focus of this paper is to quantify how much f...

To support decision making, it is important to understand the convergence property of an optimization algorithm in order to design an effective system. Genetic algorithm has been applied to many difficult optimization problems. However, it is non-trivial to analyze its convergence property. In this paper, we first introduce an allied strategy and p...

The theoretical fundamentals of distributed information fusion have been developed over the past two decades and are now fairly well established. However, practical applications of these theoretical results to dynamic sensor networks have remained a challenge. There has been a great deal of work in developing distributed fusion algorithms applicabl...

Network-centric operations demand an increasingly sophisticated level of interoperation and information fusion for an escalating number and throughput of sensors and human processes. The resulting complexity of the systems being developed to face this environment render lower level fusion techniques alone simply insufficient to ensure interoperabil...

Information in the battlefield comes from reports from diverse sources, in distinct syntax, and with different meanings. There are many kinds of uncertainty involved in this process, e.g., noise in sensors, incorrect, incomplete, or deceptive human intelligence, and others, which makes it essential to have a coherent, consistent, and principled mea...

The simplest hybrid Bayesian network is Conditional Linear Gaussian (CLG). It is a hybrid model for which exact inference can be performed by the Junction Tree (JT) algorithm. However, the traditional JT only provides the exact first two moments for hidden continuous variables. In general, the complexity of exact inference algorithms is exponential...

The change of focus in modern warfare from individual platforms to the network has caused a con-comitant shift in supporting concepts and technologies. Greater emphasis is placed on interoperability and com-poseability. New technologies such as SOA and semanti-cally aware systems have come into the spotlight. This paper argues that just as the prob...

Gaussian mixture reduction is traditionally conducted by recursively selecting two components that appear to be most similar to each other, and merging them. Different definitions on similarity measure have been used in literature. For the case of one-dimensional Gaussian mixtures, K-means algorithms and some variations are recently proposed to clu...

Many applications require measuring the distance between mixture distributions. For example in the content-based image retrieval (CBIR) systems and audio speech identification a distance measure between mixture models are often required. This is also an important element for multisensor tracking and fusion where different types of state representat...

Genetic algorithms (GAs) have been applied to many difficult optimization problems such as track assignment and hypothesis managements for multisensor integration and data fusion. However, premature convergence has been a main problem for GAs. In order to prevent premature convergence, we introduce an allied strategy based on biological evolution a...

Probabilistic inference for hybrid Bayesian networks, which involves both discrete and continuous variables, has been an important research topic over the recent years. This is not only because a number of efficient inference algorithms have been developed and used maturely for simple types of networks such as pure discrete model, but also for the...

The traditional message passing algorithm was originally developed by Pearl in the 1980s for computing exact inference solutions for discrete polytree Bayesian networks (BN). When a loop is present in the network, propagating messages are not exact, but the loopy algorithm usually converges and provides good approximate solutions. However, in gener...

This paper formulates a simple two-sensor track association and fusion problem and derives a solution, using the finite point process formalism, expressed by prior and posterior Janossy measure density functions. The main objective of this paper is to show how the track association and fusion solution can be derived exclusively through manipulation...

The change of focus in modern warfare from individual platforms to the network has caused a concomitant shift in supporting concepts and technologies. Greater emphasis is placed on interoperability and composeability. New technologies such as SOA and semantically aware systems have come into the spotlight. This paper argues that just as the problem...

Multi-sensor fusion is founded on the principle that combining information from different sensors will enable a better understanding of the surroundings. However, it would be desirable to evaluate how much one gains by combining different sensors in a fusion system, even before implementing it. This paper presents a tool that allows a user to evalu...

This paper proposes a methodology for removing sensor bias from a space-based infrared (IR) tracking system through the use of stars detected in the background field of the sensor. The tracking system consists of several satellites each equipped with a narrow-view IR sensor that provides bearing observations of the target. As stars are detected the...

A dynamic path-planning algorithm is proposed for routing UAVs in order to track ground targets. Based on a combination of tangent vector field guidance (TVFG) and Lyapunov vector field guidance (LVFG), a theoretically optimal path is derived with UAV operational constraints given a target position and the current UAV dynamic state. In this paper,...

This paper provides the results of a proposed methodology for removing sensor bias from a space-based infrared (IR) tracking system through the use of stars detected in the background field of the tracking sensor. The tracking system consists of two satellites flying in a lead-follower formation tracking a ballistic target. Each satellite is equipp...

Bio terrorism can be a very refined and a catastrophic approach of attacking a nation. This requires the development of a complete architecture dedicatedly designed for this purpose which includes but is not limited to Sensing/Detection, Tracking and Fusion, Communication, and others. In this paper we focus on one such architecture and evaluate its...

A dynamic path-planning algorithm is proposed for UAV tracking. Based on tangent lines between two dynamic UAV turning and objective circles, analytical optimal path is derived with UAV operational constraints given a target position and the current UAV dynamic state. In this paper, we first illustrate that path planning for UAV tracking a ground t...

A new nonlinear filtering and prediction (NFP) algorithm with input estimation is proposed for maneuvering target tracking. In the proposed method, the acceleration level is determined by a decision process, where a least squares (LS) estimator plays a major role in detecting target maneuvering within a sliding window. We first illustrate that the...

Advances in bandwidth and processing power, together with maturing technology for low-level fusion, have created both the need and the opportunity for the emergence of new approaches to the problem of high-level fusion. Current approaches to high-level fusion require cognitively burdensome manual processing. Because uncertainty is ubiquitous, suppo...

In state estimation of dynamic systems, Kalman filters and HMM filters have been applied to linear-Gaussian models and models with finite state spaces. However, they do not work well in most practical problems with nonlinear and non-Gaussian models. Even when the state space is finite, the dynamic Bayesian networks describing the HMM model could be...

Surveillance and ground target tracking using multiple electro-optical and infrared video sensors onboard unmanned aerial vehicles (UAVs) has drawn a great deal of interest in recent years. We compare a number of track-to-track fusion algorithms using a single target with the nearly constant velocity dynamic model and two UAVs. A local tracker is a...

This paper examines the effect of sensor bias error on the tracking quality of a space-based infrared (IR) tracking system that utilizes a Linearized Kalman Filter (LKF) for the highly non-linear problem of tracking a ballistic missile. The tracking system consists of two satellites flying in a lead-follower formation tracking a ballistic target. E...

Pearl's traditional message passing algorithm developed in 1980s is the first exact inference algorithm for Bayesian networks (BNs). Although it originally was developed for discrete polytree networks only, it has been used widely in networks with loops by providing approximate solutions. In such case, messages propagated in the loops are not exact...

A distributed data fusion system consists of a network of sensors, each capable of local processing and fusion of sensor data. There has been a great deal of work in developing distributed fusion algorithms applicable to a network centric architecture. Currently there are at least a few approaches including naive fusion, cross-correlation fusion, i...

The theoretic fundamentals of distributed information fusion are well developed. However, practical applications of these theoretical results to dynamic sensor networks have remained a challenge. There has been a great deal of work in developing distributed fusion algorithms applicable to a network centric architecture. In general, in a distributed...

A common problem in classification is to use one/more sensors to observe repeated measurements of a target's features/attributes, and in turn update the targets' posterior classification probabilities to aid in target identification. This paper addresses the following questions: 1. How do we quantify the classification performance of a sensor? 2. W...

The traditional message passing algorithm developed by Pearl in 1980s provides exact inference for discrete poly-tree Bayesian networks. When there are multiple paths (loops) in the network, we can still apply Pearl's algorithm to provide approximate solutions and it is so-called "loopy propagation". However, when mixed random variables (continuous...

Surveillance and ground target tracking using multiple electro-optical and infrared video sensors onboard unmanned aerial vehicles (UAVs) have drawn a great deal of interest in recent years due to inexpensive video sensors and sensor platforms. In this paper, we compare the convex combination fusion algorithm with the centralized fusion algorithm u...

A Bayesian network (BN) is a compact representation for probabilistic models and inference. They have been used successfully for many military and civilian applications. It is well known that, in general, the inference algorithms to compute the exact a posterior probability of a target node given observed evidence are either computationally infeasi...

Since Bayesian network (BN) was introduced in the field of artificial intelligence in 1980s, a number of inference algorithms have been developed for probabilistic reasoning. However, when continuous variables are present in Bayesian networks, their dependence relationships could be nonlin- ear and their probability distributions could be arbitrary...

Uncertainty in communication channel characteristics is a significant factor for data fusion operations in wireless networks. Burst and random errors, message delays, user mobility, and link outages are significant factors that influence data fusion performance. These factors become even more significant in future mobile ad hoc networking environme...

The concept of network centric operations is a process the military is just beginning to struggle with. Distributed information and data fusion provides the foundation to determine target track state estimation within a network centric structure. This paper addresses the overall effectiveness of two popular fusion approaches - the information filte...

A new non-linear filtering and predication (NFP) algorithm with input estimation is proposed for maneuvering target tracking. In the proposed method, the acceleration level is determined by a decision process, where a least squares (LS) estimator plays a major role to detect target maneuvering within a sliding window. In this paper, we first illust...

This paper examines the use of various estimation filters on the highly non-linear problem of tracking a ballistic missile during boost phase from a moving airborne platform. The aircraft receives passive bearing data from an IR sensor and range data from a laser rangefinder. The aircraft is assumed to have a laser weapon system that requires highl...

This paper examines the use of various estimation filters on the highly non-linear problem of tracking a ballistic missile during boost phase from a moving airborne platform. The aircraft receives passive bearing data from an IR sensor and range data from a laser rangefinder. The aircraft is assumed to have a laser weapon system that requires highl...

In state estimation of dynamic systems, sequential Monte Carlo methods, also known as particle filters, have been introduced to deal with practical problems of nonlinear, non-Gaussian situations. They allow us to treat any type of probability distribution, nonlinearity and non-stationarity although they usually suffer major drawbacks of sample dege...

Probabilistic inference for Bayesian networks is in general computationally intensive using either exact algorithms or approximate methods. For general hybrid dynamic Bayesian networks, one has to rely on the approximate methods such as stochastic simulation to provide a solution. Sequential Monte Carlo methods, also known as particle filters, have...

This paper establishes a distributed data fusion method for ad hoc networks, enabling each device or agent to operate autonomously and collaboratively. In such a network, no infrastructure exists for centralized processing, and a lack of fixed network membership creates ambiguous data fusion and reasoning architectures, communications patterns, and...

This paper examines data fusion and target tracking issues involved within net centric publish and subscribe architectures with respect to the quality of information (QOI) provided to the end user. These architectures are commonly selected in shared knowledge environments to enable access to all information by all users. DoD, DOJ, FAA, and other go...

Advanced optimization-based algorithms for sensor resource management have been a recent research focus area in multisensor tracking and fusion. These algorithms offer the potential for automating the sensor management process in response to level 1 (object or track-level) sensor fusion estimates. We have previously presented a hierarchical target...

This paper is a revision of a paper presented at the SPIE conference on Signal Processing, Senior Fusion, and Target Recognition XII, Aug. 2004, Orlando, Florida. The paper presented there appears (unrefereed) in SPIE Proceedings Vol. 5429. Bayesian networks for static as well as for dynamic cases have been the subject of a great deal of theoretica...

Bayesian network has been applied widely in many areas such as multi-sensor fusion, situation assessment, and decision making under uncertainty. It is well known that, in general when dealing with large complex networks, the exact probabilistic inference methods are computationally difficult or impossible. To deal with the difficulty, the "anytime"...

Probabilistic inference for Bayesian networks is in general NP-hard using either exact algorithms or approximate methods. However, for very complex networks, only the approximate methods such as stochastic sampling could be used to provide a solution given any time constraint. There are several simulation methods currently available. They include l...

In recent decades, Bayesian Network (BN) has shown its power to solve probabilistic inference problems because of its expressive representation of dependence relationships among random variables and the dramatic development of inference algorithms. They have been applied for decision under uncertainty in many areas such as data fusion, target recog...

Multisensor Fusion allow us to combine information from sensors with different physical characteristics to enhance the understanding of our surroundings and provide the basis for planning and decision-making. Much effort has been made toward the development of building different types of fusion methodologies and architectures. However, it would be...

Bayesian networks for the static as well as for the dynamic cases have been the subject of a great deal of theoretical analysis and practical inference approximations in the research community of artificial intelligence, machine learning and pattern recognition. After exploring the quite well known theory of discrete and continuous Bayesian network...

Dynamic collection/sensor management (DSM) systems require the ability to plan in advance deployment and use of platforms/sensors to optimally locate and identify time critical and time sensitive ground targets (TST) at some future anticipated time. In order to provide long-term planning, track fusion based initial target kinematic and classificati...

Tracking within dense clutter environments has severely stressed modern tracking capabilities. When this is compounded by large sensor uncertainties, different platform geometries, and poor sensor quality against targets that operate under variable speeds (often below thresholds detectable by GMTI sensors) and under high maneuvers, most tracking ap...