Bayesian fusion: Modeling and application

Sander, Jennifer; Beyerer, Jürgen

doi:10.1109/sdf.2013.6698254

Cited by 12 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By consolidating between different information sources, information fusion can perform data mining to reduce uncertainty and achieve a better understanding of the information. By adopting Bayesian statistics, it can provide several methods for information fusion [22], for instance, the Bayesian Classifier above.…”

Section: Bayesian Fusion and Neural Networkmentioning

confidence: 99%

Enhancing Health Risk Prediction with Deep Learning on Big Data and Revised Fusion Node Paradigm

Zhong

Xiao

2017

Scientific Programming

View full text Add to dashboard Cite

With recent advances in health systems, the amount of health data is expanding rapidly in various formats. This data originates from many new sources including digital records, mobile devices, and wearable health devices. Big health data offers more opportunities for health data analysis and enhancement of health services via innovative approaches. The objective of this research is to develop a framework to enhance health prediction with the revised fusion node and deep learning paradigms. Fusion node is an information fusion model for constructing prediction systems. Deep learning involves the complex application of machine-learning algorithms, such as Bayesian fusions and neural network, for data extraction and logical inference. Deep learning, combined with information fusion paradigms, can be utilized to provide more comprehensive and reliable predictions from big health data. Based on the proposed framework, an experimental system is developed as an illustration for the framework implementation.

show abstract

Section: Bayesian Fusion and Neural Networkmentioning

confidence: 99%

Enhancing Health Risk Prediction with Deep Learning on Big Data and Revised Fusion Node Paradigm

Zhong

Xiao

2017

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…As a baseline, we used three approaches: Platt scaling [39], Weighted Sum (WS) [33], and Bayesian fusion [29].…”

Section: Baseline Fusion Methodsmentioning

confidence: 99%

“…Wei et al [28] combines remotely sensed multi-band images for scene analysis. Sander and Beyerer [29] introduced a variety of applications of Bayesian fusion, followed by its theoretical analysis. However, as previously mentioned, the Bayesian fusion approach cannot inherently leverage the level of uncertainty induced by indistinctive or unclear observation mainly triggered by various deficiencies of the subject detector, which eventually leads to performance degradation.…”

Section: Late Fusion (Probabilistic Fusion)mentioning

confidence: 99%

DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors

Lee,

Kwon

2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel and highly practical score-level fusion approach called dynamic belief fusion (DBF ) that directly integrates inference scores of individual detections from multiple object detection methods. To effectively integrate the individual outputs of multiple detectors, the level of ambiguity in each detection score is estimated using a confidence model built on a precision-recall relationship of the corresponding detector. For each detector output, DBF then calculates the probabilities of three hypotheses (target, non-target, and intermediate state (target or non-target)) based on the confidence level of the detection score conditioned on the prior confidence model of individual detectors, which is referred to as basic probability assignment. The probability distributions over three hypotheses of all the detectors are optimally fused via the Dempster's combination rule. Experiments on the ARL, PASCAL VOC 07, and 12 datasets show that the detection accuracy of the DBF is significantly higher than any of the baseline fusion approaches as well as individual detectors used for the fusion.

show abstract

“…For representing all the information contained in the OOWM and for deriving further conclusions on it, a generic approach based on Bayesian information modeling and processing (see e.g. [8]) can be used. The representation of an observed domain entity in the WM is denoted as a representative R and stored as the set of observed entity attributes A R .…”

Section: Object-oriented World Model (Oowm)mentioning

confidence: 99%

High-Level information management in joint ISR based on an object-oriented approach

Kuwertz

Sander

Pfirrmann

et al. 2017

2017 Sensor Data Fusion: Trends, Solutions, Applications (SDF)

Self Cite

View full text Add to dashboard Cite

We present research with regard to a world modeling component called Object-Oriented World Model (OOWM) in order to perform High-Level Information Management (HLIM) in Joint ISR (Intelligence, Surveillance, and Reconnaissance). The OOWM allows to structure a priori available domain knowledge as well as current information gathered, e.g., according to specific collection and exploitation tasks, in an object-oriented way, i.e., by storing all available information in a structure which explicitly represents state, properties and relations of the relevant objects in the environment. It serves as a central information hub for HLIM components like High-Level Data Fusion (HLDF) modules and, by the employment of a domain model, it allows establishing a common understanding of terms. The OOWM concept supplements the CSD (Coalition Shared Data) concept which is the agreed state-of-the-art approach for interoperable information sharing in Joint ISR. In this publication, a special focus is placed on using current information given in form of formal exploitation reports. Based on this, we also present a new concept called Object-Oriented Reporting (OOR) which corresponds to a version of formal reporting being even more suitable for and closely related to the OOWM approach than current formal exploitation reports already are.

show abstract

Bayesian fusion: Modeling and application

Cited by 12 publications

References 26 publications

Enhancing Health Risk Prediction with Deep Learning on Big Data and Revised Fusion Node Paradigm

Enhancing Health Risk Prediction with Deep Learning on Big Data and Revised Fusion Node Paradigm

DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors

High-Level information management in joint ISR based on an object-oriented approach

Contact Info

Product

Resources

About