A5025745794- Bayesian Modeling and Causal Inference
- Multi-Criteria Decision Making
- Rough Sets and Fuzzy Logic
- Neural Networks and Applications
- AI-based Problem Solving and Planning
- Logic, Reasoning, and Knowledge
- Simulation Techniques and Applications
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Clustering Algorithms Research
- Military Strategy and Technology
- Semantic Web and Ontologies
- Complex Systems and Decision Making
- Anomaly Detection Techniques and Applications
- Water Systems and Optimization
- Bayesian Methods and Mixture Models
- Time Series Analysis and Forecasting
- Advanced Multi-Objective Optimization Algorithms
- Data Management and Algorithms
- Image Processing and 3D Reconstruction
- Face and Expression Recognition
- Evolutionary Algorithms and Applications
- Psychotherapy Techniques and Applications
- Machine Learning and Algorithms
- Advanced Database Systems and Queries
- Distributed Sensor Networks and Detection Algorithms
Swedish Defence Research Agency
2011-2022
Psychoanalytical Association
2021
KTH Royal Institute of Technology
2018
Division of Information Systems
1995
ABB (Sweden)
1981
When simultaneously reasoning with evidences about several different events it is necessary to separate the evidence according event. These should then be hand independently. However, when propositions of are weakly specified in sense that may not certain which event they referring, this directly possible. In article a criterion for partitioning into subsets representing established. This criterion, derived from conflict within each subset, involves minimizing function overall partition. an...
In this paper we develop an evidential force aggregation method intended for classification of intelligence into recognized structures. We assume that the has already been partitioned clusters and use individually in each cluster. The is based on a measure fitness between template fused makes it possible to handle reports with multiple nonspecific uncertain propositions. With can aggregate level-by-level basis, starting from general achieve complete structure units all hierarchical levels.
In an earlier article [J. Schubert, "On nonspecific evidence," Int. J. Intell. Syst. 8(6), 711–725 (1993)] we established within Dempster-Shafer theory a criterion function called the metaconflict function. With this can partition into subsets set of several pieces evidence with propositions that are weakly specified in sense it may be uncertain to which event proposition is referring. Each subset partitioning representing separate event. The was derived as plausibility correct when viewing...
In this article, we describe simulation-based decision support techniques for evaluation of operational plans within effects-based planning. Using a tool, developers are able to evaluate thousands alternative against possible courses events and decide which these capable achieving desired end state. The objective study is examine the potential system that helps analysts understand consequences numerous through simulation evaluation. Operational described in approach operations concept as set...
We demonstrate that it is possible to manage intelligence in constant time as a pre-process information fusion through series of processes dealing with issues such clustering reports, ranking reports respect importance, extraction prototypes from clusters and immediate classification newly arriving reports. These methods are used when arrive which concerns different events should be handled independently, not known priori event each report related. use runs back-end process partition the...
In this paper we develop a particle filtering approach for grouping observations into an unspecified number of clusters. Each cluster corresponds to potential target from which the originate. A clustering with specified clusters is represented by association hypothesis. Whenever new report arrives, posterior distribution over all hypotheses iteratively calculated prior distribution, update model and likelihood function. The based on probability given false detection derived unobserved...
In this paper we describe decision support and simulation techniques to facilitate effects-based planning. By using a tool, maker is able test number of feasible plans against possible courses events decide which those capable achieving the desired military end state. The purpose evaluate understand their consequences through simulating producing outcomes result from making alternative decisions. Plans are described in approach operations concept as set effects activities that together will...
In an earlier article [J. Schubert, “On nonspecific evidence,” Int. J. Intell. Syst. 8(6), 711–725 (1993)] we established within Dempster-Shafer theory a criterion function called the metaconflict function. With this can partition into subsets set of several pieces evidence with propositions that are weakly specified in sense it may be uncertain to which event proposition is referring. Each subset partitioning representing separate event. The was derived as plausibility correct when viewing...
In this paper we describe the development of a decision support system for crowd control. Decision is provided by suggesting control strategy needed to specific current riot situation. Such strategies consists deployment several police barriers with barrier positions and strengths riot. The optimal situation found comparing pre-stored example situations different sizes. are derived these using genetic algorithms where successive trial evaluated stochastic agent-based simulation.