The majority of evidential fusion models presented in the literature is based on optimistic assumptions about the reliability of the models producing beliefs and assumes that they are equally reliable. At the same time, the belief models used in combination may have some limitations and may result in different reliabilities, which may decrease the performance of the combination. One way to confront this problem is to consider a discount rule utilizing reliability coefficients. One of the problems of using discounting is the way of modeling reliability coefficients. This paper proposes modeling reliability coefficients by considering a new effective measure of belief uncertainty. The new reliability coefficients are introduced in a multilayer decision fusion-based Convolutional Neural Network (CNN) architecture built within the Transferable Belief Model, as well as in a multimodal deep learning scenario. Case study results demonstrate the feasibility of representing reliability by the belief uncertainty measure considered.

This paper describes a multi-model threat prediction scheme for autonomous agents making decisions in dynamic environments. The proposed multi-layered scheme utilizes argumentation, Transferrable Belief Model, Anytime Decision Making, rule-based techniques, and Choquet Integral based decision theory for situational awareness and action selection. We discuss theoretical foundations and provide high level architecture of an agent. We illustrate the scheme with an example scenario.

Context has received significant attention in recent years within the Information Fusion community as it can bring several advantages to information fusion processing by allowing for refining estimations, explaining observations and constraining processing and thereby improving the quality of inferences. At the same time context utilization involves concerns about the quality of the contextual information and its relationship with the quality of information obtained from observation and estimations that may be of low fidelity, contradictory, or redundant. Knowledge of the quality of this information and its effect on the quality of context characterization can improve contextual knowledge. At the same time, knowledge about a current context can improve the quality of observation and fusion results. This paper discusses the issues associated with understanding and evaluating Information Quality as well as Quality of Context, their relationships and their effect on fusion system performance.

The overall goal of the research presented in this paper is to design an intelligent system to aid geologists in processing complex rock characteristics for interpreting eruption patterns, and thereby to aid eruption forecasting for volcanic chains and fields. The objective of this paper is to describe application of data fusion techniques to designing an intelligent system. The processing of geological data described in this paper includes both a hybrid classifier for recognition of tephra layers utilizing lithostratigraphic tephra characteristics and clustering of geochemical features aimed at defining the size and position of potential zones of partial melt in volcanic regions. Special attention is paid to the description of a new evidential method of combining several clustering results. The method of fusion of several clustering results is not specific to geochemical data and can be used in other applications.

The overall goal of this paper is to provide a formal ontological analysis of threat. In particular, this paper discusses the formal ontological structure of threats as integrated wholes possessing three interrelated parts: intentions, capabilities and opportunities, and shows how these elements stand to one another, as well as to states of vulnerability. This discussion offers a means for understanding variations of threat conditions such as potential vs. viable threats and dispersed threats. A general, metaphysical, upper-level framework for the development of a formal threat ontology (ThrO) offers a necessary foundation for designing consistent and comprehensive models for threat prediction and mitigation

The purpose of situation and impact assessment is to infer and approximate the critical characteristics of the environment in relation to the particular goals, capabilities and policies of the decision makers. The process of situation and impact assessment involves dynamic generation of hypotheses about the states of the environment and evaluation of their plausibility via reasoning about situational items, their aggregates at different levels of granularity, relationships between them, and their behavior within a specific context. This paper addresses the problem of reasoning for situation and impact assessment to support early-phase crisis management. Special attention is paid to "inference for best explanation" aimed at discovery of the underlying causes of observed situational items and their behavior, an important component of situation and impact assessment. The presented method of discovery of underlying causes is illustrated by the discovery of an unreported HAZMAT incident within an early-phase earthquake response scenario