Results 1  10
of
12
DempsterShafer clustering using Potts spin mean field theory
 Soft Computing
, 2001
"... In this article we investigate a problem within DempsterShafer theory where 2^q  1 pieces of evidence are clustered into q clusters by minimizing a metaconflict function, or equivalently, by minimizing the sum of weight of conflict over all dusters. Previously one of us developed a method based on ..."
Abstract

Cited by 18 (14 self)
 Add to MetaCart
In this article we investigate a problem within DempsterShafer theory where 2^q  1 pieces of evidence are clustered into q clusters by minimizing a metaconflict function, or equivalently, by minimizing the sum of weight of conflict over all dusters. Previously one of us developed a method based on a Hopfield and Tank model. However, for very large problems we need a method with lower computational complexity. We demonstrate that the weight of conflict of evidence can, as an approximation, be linearized and mapped to an antiferromagnetic Potts spin model. This facilitates efficient numerical solution, even for large problem sizes. Optimal or nearly optimal solutions are found for DempsterShafer clustering benchmark tests with a time complexity of approximately O(N^2 log^2 N). Furthermore, an isomorphism between the antiferromagnetic Potts spin model and a graph optimization problem is shown. The graph model has dynamic variables living on the links, which have a priori probabilities that are directly related to the pairwise conflict between pieces of evidence. Hence, the relations between three different models are shown.
Fast DempsterShafer clustering using a neural network structure
 Proceedings of the Seventh International Conference on Information Processing and Management of Uncertainty in Knowledgebased Systems (IPMU´'98)
, 1998
"... In this paper we study a problem within DempsterShafer theory where 2^n − 1 pieces of evidence are clustered by a neural structure into n clusters. The clustering is done by minimizing a metaconflict function. Previously we developed a method based on iterative optimization. However, for large scal ..."
Abstract

Cited by 12 (10 self)
 Add to MetaCart
In this paper we study a problem within DempsterShafer theory where 2^n − 1 pieces of evidence are clustered by a neural structure into n clusters. The clustering is done by minimizing a metaconflict function. Previously we developed a method based on iterative optimization. However, for large scale problems we need a method with lower computational complexity. The neural structure was found to be effective and much faster than iterative optimization for larger problems. While the growth in metaconflict was faster for the neural structure compared with iterative optimization in medium sized problems, the metaconflict per cluster and evidence was moderate. The neural structure was able to find a global minimum over ten runs for problem sizes up to six clusters.
A Realistic (NonAssociative) Logic And a Possible Explanations of 7±2 Law
, 2000
"... When we know the subjective probabilities (degrees of belief) p1 and p2 of two statements S1 and S2 , and we have no information about the relationship between these statements, then the probability of S1 &S2 can take any value from the interval [max(p1 + p2 \Gamma 1; 0); min(p1 ; p2 )]. If we ..."
Abstract

Cited by 11 (9 self)
 Add to MetaCart
When we know the subjective probabilities (degrees of belief) p1 and p2 of two statements S1 and S2 , and we have no information about the relationship between these statements, then the probability of S1 &S2 can take any value from the interval [max(p1 + p2 \Gamma 1; 0); min(p1 ; p2 )]. If we must select a single number from this interval, the natural idea is to take its midpoint. The corresponding "and" operation p1 & p2 def = (1=2) \Delta (max(p1 +p2 \Gamma 1; 0)+min(p1 ; p2)) is not associative. However, since the largest possible nonassociativity degree j(a & b) & c \Gamma a & (b & c)j is equal to 1/9, this nonassociativity is negligible if the realistic "granular" degree of belief have granules of width 1=9. This may explain why humans are most comfortable with 9 items to choose from (the famous "7 plus minus 2" law). We also show that the use of interval computations can simplify the (rather complicated) proofs. 1 1 In Expert Systems, We Need Estimates for the Degree of...
Simultaneous DempsterShafer clustering and gradual determination of number of clusters using a neural network structure
 Proceedings of the 1999 Information, Decision and Control Conference (IDC'99)
, 1999
"... In this paper we extend an earlier result within DempsterShafer theory ["Fast DempsterShafer Clustering Using a Neural Network Structure," in Proc. Seventh Int. Conf. Information Processing and Management of Uncertainty in KnowledgeBased Systems (IPMU’98)] where several pieces of eviden ..."
Abstract

Cited by 7 (7 self)
 Add to MetaCart
In this paper we extend an earlier result within DempsterShafer theory ["Fast DempsterShafer Clustering Using a Neural Network Structure," in Proc. Seventh Int. Conf. Information Processing and Management of Uncertainty in KnowledgeBased Systems (IPMU’98)] where several pieces of evidence were clustered into a fixed number of clusters using a neural structure. This was done by minimizing a metaconflict function. We now develop a method for simultaneous clustering and determination of number of clusters during iteration in the neural structure. We let the output signals of neurons represent the degree to which a pieces of evidence belong to a corresponding cluster. From these we derive a probability distribution regarding the number of clusters, which gradually during the iteration is transformed into a determination of number of clusters. This gradual determination is fed back into the neural structure at each iteration to influence the clustering process.
410 Archipelagic ASW a Difficult Enterprise in Need of Holistic Approaches
"... The paper discusses architectural options for providing Dominant Battlespace Awareness (DBA) for Archipelagic AntiSubmarine Warfare (AASW) in the Baltic Sea, against experience from submarine intelligence data analysis and fusion research during the recent historical episode which involved recurren ..."
Abstract
 Add to MetaCart
The paper discusses architectural options for providing Dominant Battlespace Awareness (DBA) for Archipelagic AntiSubmarine Warfare (AASW) in the Baltic Sea, against experience from submarine intelligence data analysis and fusion research during the recent historical episode which involved recurrent submarine intrusions into Swedish coastal waters.
Archipelagic ASW  a Difficult Enterprise in Need of Holistic Approaches
"... The paper discusses architectural options for providing Dominant Battlespace Awareness (DBA) for Archipelagic AntiSubmarine Warfare (AASW) in the Baltic Sea, against experience from submarine intelligence data analysis and fusion research during the recent historical episode which involved rec ..."
Abstract
 Add to MetaCart
The paper discusses architectural options for providing Dominant Battlespace Awareness (DBA) for Archipelagic AntiSubmarine Warfare (AASW) in the Baltic Sea, against experience from submarine intelligence data analysis and fusion research during the recent historical episode which involved recurrent submarine intrusions into Swedish coastal waters.
DECISION SUPPORT FOR CROWD CONTROL: USING GENETIC ALGORITHMS WITH SIMULATION TO LEARN CONTROL STRATEGIES
"... In this paper we describe the development of a decision support system for crowd control. Decision support is provided by suggesting a control strategy needed to control a specific current riot situation. Such control strategies consists of deployment of several police barriers with specific barrier ..."
Abstract
 Add to MetaCart
(Show Context)
In this paper we describe the development of a decision support system for crowd control. Decision support is provided by suggesting a control strategy needed to control a specific current riot situation. Such control strategies consists of deployment of several police barriers with specific barrier positions and barrier strengths needed to control the riot. The optimal control strategy for the current situation is found by comparing the current situation with prestored example situations of different sizes. The control strategies are derived for these prestored example situations by using genetic algorithms where successive trial strategies are evaluated using stochastic agentbased simulation.
A survey of some Information Fusion research fields applicable in Operations Other Than War
, 2006
"... During a decade, information fusion within the military domain has focussed on putting together a situation picture from the "battle field" where an enemy, known regarding organisation and doctrine, is moving ahead. Clustering and association of observation reports, target tracking and man ..."
Abstract
 Add to MetaCart
During a decade, information fusion within the military domain has focussed on putting together a situation picture from the "battle field" where an enemy, known regarding organisation and doctrine, is moving ahead. Clustering and association of observation reports, target tracking and management of sensors and other information collecting resources were prioritised. Todayâs situation where Swedish military personnel are expected to act abroad in peace supporting and peace enforcing missions (OOTW â Operations Other Than War) means that the information that is gathered often have a more police than military type of character. It is important too keep contact with the local police and inhabitants, as well as being able to handle riots if needed. Intelligence gathered by humans (Humint) will often be more important than intelligence gathered with sensors. An important intelligence source will be the observations from the soldierâs daily patrolling. The adversary is more diffuse regarding organisation, resources and intentions. The information that is available when the mission is commenced, as well as that collected during an ongoing mission must be structured and made searchable in an efficient way. This report briefly describes the current stateoftheart within selected areas of information fusion related research that has a potential to support OOTW. Various approaches to text mining, information structuring using wiki technology, uncertainty handling in ontology design, new aspects on usercentric situation awareness, riot simulation and riot control are described.
A Realistic (NonAssociative) Logic And a Possible Explanations of 7
, 2000
"... When we know the subjective probabilities (degrees of belief) p1 and p2 of two statements S1 and S2 , and we have no information about the relationship between these statements, then the probability of S1 &S2 can take any value from the interval [max(p1 + p2 \Gamma 1; 0); min(p1 ; p2 )]. If we ..."
Abstract
 Add to MetaCart
When we know the subjective probabilities (degrees of belief) p1 and p2 of two statements S1 and S2 , and we have no information about the relationship between these statements, then the probability of S1 &S2 can take any value from the interval [max(p1 + p2 \Gamma 1; 0); min(p1 ; p2 )]. If we must select a single number from this interval, the natural idea is to take its midpoint. The corresponding "and" operation p1 & p2 def = (1=2) \Delta (max(p1 +p2 \Gamma 1; 0)+min(p1 ; p2)) is not associative. However, since the largest possible nonassociativity degree j(a & b) & c \Gamma a & (b & c)j is equal to 1/9, this nonassociativity is negligible if the realistic "granular" degree of belief have granules of width 1=9. This may explain why humans are most comfortable with 9 items to choose from (the famous "7 plus minus 2" law). We also show that the use of interval computations can simplify the (rather complicated) proofs. 1 1 In Expert Systems, We Need Estimates for the Degree of Certainty of S 1 &S 2 and S 1 S 2 In many areas (medicine, geophysics, military decisionmaking, etc.), top quality experts make good decisions, but they cannot handle all situations. It is therefore desirable to incorporate their knowledge into a decisionmaking computer system. Experts describe their knowledge by statements S 1 ; : : : ; Sn (e.g., by ifthen rules). Experts are often not 100% sure about these statements S i ; this uncertainty is described by the subjective probabilities p i (degrees of belief, etc.) which experts assign to their statements. The conclusion C of an expert system normally depends on several statements S i . For example, if we can deduce C either from S 2 and S 3 , or from S 4 , then the validity of C is equivalent to the validity of a Boolean combination...