JAIF -- Articles to Appear in a Future Issue
"Possibilistic Medical Knowledge Representation Model"
H. Alsun, TELECOM Bretagne, France, L. Lecornu, TELECOM Bretagne and Latim, Inserm, France, C. Le Guillou, Latim, Inserm, France, B. Solaiman, TELECOM Bretagne, France
Medical Decision Support Systems involve two main issues: medical knowledge representation and reasoning mechanisms adapted to the considered representation model. This paper proposes an approach to construct a new medical knowledge representation model, based on the use of possibility theory. The major interest of using the possibility theory comes from its capacity to represent different types of information (quantitative, qualitative, binary, etc.), as well as different forms of information imperfections such as uncertainty, imprecision, ambiguity and incompleteness. Starting from the medical knowledge description, carried out by an expert giving the patient information representation, the proposed approach consists in building a possibilistic model including the Medical Knowledge Base (MKB). Moreover, the proposed approach integrates several possibilistic reasoning mechanisms on the considered information. The validation of the proposed approach is then conducted using Endoscopic Knowledge and Endoscopic Case Bases. The proposed representation, reasoning model and the obtained validation results show a real interest in order to achieve various goals of Medical Decision Support Systems such as classification, similarity estimation, etc.
"Experimental Results and Challenges in Automated Support for Intelligence in Asymmetric Operations"
L. Snidaro, University of Udine, Italy, J. Biermann, Fraunhofer, FKIE, Germnay, P. Hörling, Swedish Defence Research Agency, Sweden
This paper presents some findings of the NATO RTO Task Group on Information Fusion in Asymmetric Operations. It briefly describes the functional processing steps in military intelligence presenting the underlying aspects of information processing and fusion and revealing main challenges for automatic support of the required functionalities. The extraction and structuring of relevant information from unstructured text documents is shown to be one of the fundamental steps where human operators need assistance. As an example of the state of the art the interactive tools PARANOID and CoALA are presented. They provide the basic information and knowledge structure for all subsequent information processing like Link Analysis and Social Network Analysis. The use and benefit of CoALA will be illustrated by results from a military experiment. Finally, with respect to further research, open questions and new approaches for the support of intelligence production are discussed concerning automatic information structuring and discovery as well as pattern and behaviour based threat assessment.
"High-level Information Fusion: An Overview"
P. H. Foo, DSO National Laboratories, Singapore
Data and information fusion (DIF) involves a process of combining data and information from multiple inputs.
The purpose is to derive enriched information compared to that obtained from each individual input. DIF techniques were first introduced to the research community in the 1970's. The scope of applications that use DIF techniques for problem-solving has extended tremendously from the military arena at the initial stage to many non-military sectors at present. The Joint Directors of Laboratories data fusion (JDL DF) model is possibly the most widely used model for data fusion. In this functional model, the hierarchical process of data and information fusion comprises two stages, the low-level fusion processes and the high-level fusion processes. After years of intensive research that is mainly focused on low-level information fusion (IF), the focus is currently shifting towards high-level information fusion. Compared to the increasingly mature field of low-level IF, theoretical and practical challenges posed by high-level IF are more difficult to handle. Contributing factors include the lack of: well-defined spatio-temporal constraints on relevant evidence, well-defined ontological constraints on relevant evidence and suitable models for causality. In this survey paper, we first review process models proposed for data and information fusion over the past few decades. Next, we present an overview of existing work on high-level information fusion, based on the fusion levels of the current JDL DF model. Finally, we discuss relevant application areas and topics with potential for further research.
"Efficient 2D Sensor Location Estimation Using Targets of Opportunity"
D. Crouse, Naval Research Laboratory, USA, R. Osborne III, University of Connecticut, USA, K. Pattipati, University of Connecticut, USA, P. Willett, University of Connecticut, USA, Y. Bar-Shalom, University of Connecticut, USA
This paper discusses the Maximum Likelihood (ML) algorithm for self-localization of passive (angular) or active (angle and range) sensors using targets of opportunity. The approach, which works in two dimensions, is appropriate when traditional alternatives, such as the use of known-location targets or satellite navigation systems, are unavailable. It is not assumed that the sensors can "see" each other, though they are assumed to take measurements with respect to a common (biased) axis. Unlike previous ML algorithms, we take into account the circular nature of the angular measurements, allowing for more accurate estimates to be obtained. A simple least-squares method is additionally provided for initialization. Simulations demonstrate that the accuracy of the ML estimator approaches the Cramér Rao Lower Bound (CRLB), something that similar algorithms have been unable to achieve.
"Bearings-only Localization with Distributed Reflected AoAs"
P. Willett, University of Connecticut, USA, X. Song, University of Connecticut, USA, S. Zhou, University of Connecticut, USA
Bearings-only localization with light-of-sight (LOS) propagation is well understood. This paper concentrates on bearings-only localization with non-line-of-sight (NLOS) measurements, where target images arrive at a network of sensors each after a single specular reflection. The reflecting surface can be (1) flat or (2) circular (inner side of a circle), and is assumed known. In this paper, we derive the least squares (LS), Stansfield, and maximum likelihood (ML) estimators for both cases. As to the former, their estimation performances are similar to their counterparts in LOS localization: Stansfield is very close to ML, and both are usually significantly better than LS. As regards the second, since the target-sensor geometry has multiple possibilities, the ML solution is extremely intricate. However, if a concentric opaque circle (such as the earth) lies within the reflecting one, e.g. the earth within the ionospheric layer, the propagation path becomes unique; a grid search based ML is available for such a circumstance. ML is computationally intensive for a circularly reflecting surface; two suboptimal algorithms, LS and Stansfield, are developed based on small angle approximation. These algorithms perform differently from those for the flat case: ML significantly outperforms LS and Stansfield, especially for a large observation error; however, Stansfield is not necessarily better than LS.
"Shooter Localization using Wireless Sensor Network of Soldier-Worn Gunfire Detection Systems"
J. George, US Army Research Laboratory, USA, L. Kaplan, US Army Research Laboratory, USA
This paper addresses the problem of shooter localization using a wireless sensor network of soldier-worn gunfire detection systems. If the sensor is within the field of view of the shockwave generated by the supersonic projectile, then using acoustic phenomena analysis, the gunfire detection system can localize the source of the incoming fire with respect to the sensor location. These relative solutions from individual gunfire detection systems are relayed to the central node, where they are fused to yield a highly accurate geo-rectified solution, which is then relayed back to the soldiers for added situational awareness. Detailed formulation of the fusion methodology presented here indicates that the multi-sensor fusion algorithm for soldier-worn gunfire detection systems is essentially a weighted nonlinear least-squares algorithm, which can easily be implemented using the Gauss-Newton method. The performance analysis of the proposed fusion algorithm through numerical simulations reveals that the fused solution is much more accurate compared to the individual best sensor solution and the simple averaged sensor solution. Since the proposed fusion algorithm requires consistent weighting of individual sensor solutions, a consistency-based weighting scheme is introduced to tackle the lack of reliability among sensor provided weights. Implementation of the proposed fusion scheme along with the consistency-based weighting scheme on experimental data further confirms the numerical results.