Pierre Valin

Information Fusion Measures of Effectiveness (MOE) for Decision Support

For decades, there have been discussions on measures of merits (MOM) that include measures of effectiveness (MOE) and measures of performance (MOP) for system-level performance. As the amount of sensed and collected data becomes increasingly large, there is a need to look at the architectures, metrics, and processes that provide the best methods for decision support systems. In this paper, we overview some information fusion methods in decision support and address the capability to measure the effects of the fusion products on user functions. The current standard Information Fusion model is the Data Fusion Information Group (DFIG) model that specifically addresses the needs of the user in an information fusion system. Decision support implies that information methods augment user decision making as opposed to the machine making the decision and displaying it to user. We develop a list of suggested measures of merits that facilitate decision support decision support Measures of Effectiveness (MOE) metrics of quality, information gain, and robustness, from the analysis based on the measures of performance (MOPs) of timeliness, accuracy, confidence, throughput, and cost. We demonstrate in an example with motion imagery to support the MOEs of quality (time/decision confidence plots), information gain (completeness of annotated imagery for situation awareness), and robustness through analysis of imagery over time and repeated looks for enhanced target identification confidence.

High Level data fusion system for CanCoastWatch

In this paper, a goal-driven net-enabled distributed data fusion system is described for CanCoastWatch (CCW) project. Multiple sensors are deployed and managed to achieve the goals of situation assessment using a net-enabled architecture. The local tracks reported by multiple sensors are first integrated into global tracks. Decision making is then performed on basic sub-goals that can be directly derived from the fused global tracks. Finally, a goal-driven rule-based expert system uses the basic sub-goal decisions for goal reasoning.

A distributed information fusion testbed for coastal surveillance

MacDonald Dettwiler is leading a PRECARN partnership project to develop an advanced simulation testbed for the evaluation of the effectiveness of Network Enabled Operations in a coastal large volume surveillance situation. The main focus of this testbed is to study concepts like distributed information fusion, dynamic resources and networks configuration management, and self synchronising units and agents. This article presents the system architecture with an emphasis on our approach for distributed information fusion.

DSmT applied to seismic and acoustic sensor fusion

In this paper, we explore the use of the Dezert-Smarandache Theory (DSmT) for seismic and acoustic sensor fusion. The seismic/acoustic data is noisy which leads to classification errors and conflicts in declarations. DSmT affords the redistribution of masses when there is a conflict. The goal of this paper is to present an application and comparison on DSmT with other classifier methods to include the support vector machine(SVM) and Dempster-Shafer (DS) methods. The work is based on two key references (1) Marco Duarte with the initial SVM classifier application of the seismic and acoustic sensor data and (2) Arnaud Martin in Vol. 3 with the Proportional Conflict Redistribution Rule 5/6 (PCR5/PCR6) developments. By using the developments of Duarte and Martin, we were able to explore the various aspects of DSmT in an unattended ground sensor scenario. Using the receiver operator curve (ROC), we compare the methods for individual classification as well as a measure of overall classification using the area under the curve (AUC). Conclusions of the work show that the DSmT results with a maximum forced choice are comparable to the SVM.

Testbed for distributed high-level information fusion and dynamic resource management

The testbed allows experimenting with highlevel distributed information fusion, dynamic resource management and configuration management given multiple constraints on the resources and their communication networks. The testbed provides general services that are useful for testing many information fusion applications. Services include a multi-layer plug-and-play architecture, and a general multi-agent framework based on John Boyds OODA loop.

Prediction, tracking, and retrodiction for path-constrained targets

This paper presents algorithms for prediction, tracking, and retrodiction for targets whose motion is constrained by external conditions (e.g., shipping lanes, roads). The targets are moving along a path, defined by way-points and segments. Measurements are obtained by sensors at low revisit rates (e.g., spaceborne). Existing tracking algorithms assume that the targets follow the same motion model between successive measurements, but in a low revisit rate scenario targets may change the motion model between successive measurements. The proposed prediction algorithm addresses this issue by considering possible motion model whenever targets move to a different segment. Further, when a target approaches a junction, it has the possibility to travel into one of the multiple segments connected to that junction. To predict the probable locations, multiple hypotheses for segments are introduced and a probability is calculated for each segment hypothesis. When measurements become available, segment hypothesis probability is updated based on a combined mode likelihood and a sequential probability ratio test is carried out to reject the hypotheses. Retrodiction for path constrained targets is also considered, because in some scenarios it is desirable to find out the targets exact location at some previous time (e.g., at the time of an oil leakage). A retrodiction algorithm is also developed for path constrained targets so as to facilitate motion forensic analysis. Simulation results are presented to validate the proposed algorithm.

Prediction and retrodiction algorithms for path-constrained targets

This paper presents algorithms for prediction and retrodiction of targets whose motion is constrained by external conditions (e.g., shipping lanes, roads). The targets are moving along paths defined by waypoints and segments. Measurements are obtained by sensors (e.g., spaceborne) at low revisit rates. Existing tracking algorithms assume that the targets follow the same motion model between successive measurements, but in a low revisit rate scenario targets may change the motion model between successive measurements. The proposed prediction algorithm addresses this issue by considering the possible changes in the motion model whenever targets move to a different segment. Further, when a target approaches an intersection, it has the possibility to travel into one of the multiple segments beyond that intersection. To predict the probable locations, multiple hypotheses for segments are introduced and a probability is calculated for each segment hypothesis. When measurements become available later, segment hypothesis probabilities are updated based on a combined mode likelihood and a sequential probability ratio test (SPRT) is carried out to reject the unlikely hypotheses. Retrodiction for path-constrained targets is also considered, because in some scenarios it is desirable to find out a targets location at some previous time (e.g., at the time of an accident) given all subsequent measurements. A retrodiction algorithm is also developed for path-constrained targets so as to facilitate motion forensic analysis. Simulation results and a performance measure for path-constrained target tracking are presented to validate the proposed algorithms.

Simulation of large-scale multitarget tracking scenarios using GPUs

The increased availability of Graphical Processing Units (GPUs) in personal computers has made parallel pro- gramming worthwhile, but not necessarily easier. This paper will take advantage of the power of a GPU, in conjunction with the Central Processing Unit (CPU), in order to simulate target trajectories for large-scale scenarios, such as wide-area maritime or ground surveillance. The idea is to simulate the motion of tens of thousands of targets using a GPU by formulating an optimization problem that maximizes the throughput. To do this, the proposed algorithm is provided with input data that describes how the targets are expected to behave, path information (e.g., roadmaps, shipping lanes), and available computational resources. Then, it is possible to break down the algorithm into parts that are done in the CPU versus those sent to the GPU. The ultimate goal is to compare processing times of the algorithm with a GPU in conjunction with a CPU to those of the standard algorithms running on the CPU alone. In this paper, the optimization formulation for utilizing the GPU, simulation results on scenarios with a large number of targets and conclusions are provided.

INFORM Lab: a testbed for high-level information fusion and resource management

DRDC Valcartier and MDA have created an advanced simulation testbed for the purpose of evaluating the effectiveness of Network Enabled Operations in a Coastal Wide Area Surveillance situation, with algorithms provided by several universities. This INFORM Lab testbed allows experimenting with high-level distributed information fusion, dynamic resource management and configuration management, given multiple constraints on the resources and their communications networks. This paper describes the architecture of INFORM Lab, the essential concepts of goals and situation evidence, a selected set of algorithms for distributed information fusion and dynamic resource management, as well as auto-configurable information fusion architectures. The testbed provides general services which include a multilayer plug-and-play architecture, and a general multi-agent framework based on John Boyds OODA loop. The testbeds performance is demonstrated on 2 types of scenarios/vignettes for 1) cooperative search-and-rescue efforts, and 2) a noncooperative smuggling scenario involving many target ships and various methods of deceit. For each mission, an appropriate subset of Canadian airborne and naval platforms are dispatched to collect situation evidence, which is fused, and then used to modify the platform trajectories for the most efficient collection of further situation evidence. These platforms are fusion nodes which obey a Command and Control node hierarchy.

Fusion of ESM reports through Dempster-Shafer and Dezert-Smarandache theories

We address the problem of fusing ESM reports by two evidential reasoning schemes, namely Dempster-Shafer theory and Dezert-Smarandache theory. These schemes provide results in different frames of discernment, but are able to fuse realistic ESM data. We discuss their advantages and disadvantages under varying conditions of sensor data certainty and fusion reliability, the latter coming from errors in the association process. A thresholded version of Dempster-Shafer theory is fine-tuned for performance across a wide range of values for certainty and reliability. The results are presented first for typical scenarios, and secondly for Monte-Carlo studies of scenarios under varying sensor certainty and fusion reliability. The results exhibit complex non-linear functions, but for which clear trends can nevertheless be extracted. A compromise has to be achieved between stability under occasional miss-associations, and reaction time latency under a real change of allegiance. The alternative way of reporting results through Dezert-Smarandache theory is studied under similar conditions, and shown to provide good results, which are however more dependent on the unreliability, and slightly less stable. In this case however, the frame of discernment is larger, and permits additional interpretations, which are outside the scope of Dempster-Shafer.