Fusing multiple Bayesian knowledge sources

Santos, Eugene; Wilkinson, John; Santos, Eunice E.

doi:10.1016/j.ijar.2011.01.008

Cited by 27 publications

(30 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To fuse multiple BKBs, we apply the BKB fusion algorithm developed by Santos Jr. et al [9]. This resulting fused BKB (FBKB) is the Knowledge Base that the BKFCS framework will reason on.…”

Section: Subsystem Probabilisticmentioning

confidence: 99%

“…Fusion also preserves the distributions and variable relationships in the base subsystems without loss of information. In general, a fused BKB cannot be represented as a BN since both cycles and different parent I-node combinations can occur for each target I-node drawn from the different BKBs being fused together [9]. We provide the details of the BKB fusion algorithm in Appendix B.…”

Section: Subsystem Probabilisticmentioning

confidence: 99%

“…This appendix details the BKB fusion algorithm initially designed by Santos Jr. et al [9] and analyzes its time complexity.…”

Section: B Bkb Fusion Algorithmmentioning

confidence: 99%

“…. , } learned from distinct subsystems, we integrate them into a single BKB that reflects the entire complex system through BKB fusion [9]. Santos Jr. et al have proven that if all individual BKBs are valid BKBs, the fused BKB is also a valid BKB.…”

Section: B Bkb Fusion Algorithmmentioning

confidence: 99%

“…In brief, we first learn subsystem dynamics through a probabilistic graphical model called Bayesian Knowledge Bases (BKBs) [8] from observations on each subsystem. Then we fuse these BKBs into one BKB via the BKB fusion algorithm [9], which includes interactions among subsystems both probabilistically and structurally sound. We name the fused BKB as FBKB.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Emergence Detection in Complex Systems

Santos

Zhao

2017

Complexity

Self Cite

View full text Add to dashboard Cite

Complex systems consist of multiple interacting subsystems, whose nonlinear interactions can result in unanticipated (emergent) system events. Extant systems analysis approaches fail to detect such emergent properties, since they analyze each subsystem separately and arrive at decisions typically through linear aggregations of individual analysis results. In this paper, we propose a quantitative definition of emergence for complex systems. We also propose a framework to detect emergent properties given observations of its subsystems. This framework, based on a probabilistic graphical model called Bayesian Knowledge Bases (BKBs), learns individual subsystem dynamics from data, probabilistically and structurally fuses said dynamics into a single complex system dynamics, and detects emergent properties. Fusion is the central element of our approach to account for situations when a common variable may have different probabilistic distributions in different subsystems. We evaluate our detection performance against a baseline approach (Bayesian Network ensemble) on synthetic testbeds from UCI datasets. To do so, we also introduce a method to simulate and a metric to measure discrepancies that occur with shared/common variables. Experiments demonstrate that our framework outperforms the baseline. In addition, we demonstrate that this framework has uniform polynomial time complexity across all three learning, fusion, and reasoning procedures.

show abstract

“…To fuse multiple BKBs, we apply the BKB fusion algorithm developed by Santos Jr. et al [9]. This resulting fused BKB (FBKB) is the Knowledge Base that the BKFCS framework will reason on.…”

Section: Subsystem Probabilisticmentioning

confidence: 99%

Section: Subsystem Probabilisticmentioning

confidence: 99%

“…This appendix details the BKB fusion algorithm initially designed by Santos Jr. et al [9] and analyzes its time complexity.…”

Section: B Bkb Fusion Algorithmmentioning

confidence: 99%

Section: B Bkb Fusion Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Emergence Detection in Complex Systems

Santos

Zhao

2017

Complexity

Self Cite

View full text Add to dashboard Cite

show abstract

A Multiagent System for Integrated Detection of Pharmacovigilance Signals

Koutkias

Jaulent

2015

J Med Syst

View full text Add to dashboard Cite

Pharmacovigilance is the scientific discipline that copes with the continuous assessment of the safety profile of marketed drugs. This assessment relies on diverse data sources, which are routinely analysed to identify the so-called "signals", i.e. potential associations between drugs and adverse effects, that are unknown or incompletely documented. Various computational methods have been proposed to support domain experts in signal detection. However, recent comparative studies illustrated that current methods exhibit high false-positive rates, significantly variable performance across different datasets used for analysis and events of interest, but also complementarity in their outcomes. In this regard, in order to reinforce accurate and timely signal detection, we elaborated through an agent-based approach towards systematic, joint exploitation of multiple heterogeneous signal detection methods, data sources and other drug-related resources under a common, integrated framework. The approach relies on a multiagent system operating based on a collaborative agent interaction protocol, aiming to implement a comprehensive workflow that comprises of method selection and execution, as well as outcomes' aggregation, filtering, ranking and annotation. This paper presents the design of the proposed multiagent system, discusses implementation issues and demonstrates the applicability of the proposed solution in an example signal detection scenario. This work constitutes a step towards large-scale, integrated and knowledge-intensive computational signal detection.

show abstract

Knowledge fusion through academic articles: a survey of definitions, techniques, applications and challenges

Wang

Saberi

et al. 2020

Scientometrics

View full text Add to dashboard Cite

The ever growing volume of academic articles stresses the need for a new generation of knowledge management method to intelligently reuse the academic knowledge and facilitate the development of scientific research. Knowledge fusion (KF) serves a key element of such method addressing those needs, and breakthrough progress has taken place in the field of KF. This brings a great opportunity for the academic community to expedite the process of literature review and automatically retrieve the required knowledge from academic publications. Therefore, a survey reviewing the KF studies in terms of the related technologies and applications for valuable insights to reuse academic knowledge, which is missing from the state-of-the-art literature, is in need. Motivated to bridge this gap, this paper conducts a systematic survey reviewing the existing studies on KF, meanwhile discussing the opportunities and challenges of applying KF through academic articles. To this end, we revisit the definitions of knowledge and KF in the context of academic articles, and summarise the fusion patterns and their usage in existing applications. Furthermore, we review the techniques and applications of KF, especially those with academic articles as sources of knowledge. Finally, we discuss the challenges and future directions in order to bring new insights to researchers and practitioners to deepen their understanding of knowledge fusion and to develop versatile functions.

show abstract

Fusing multiple Bayesian knowledge sources

Cited by 27 publications

References 9 publications

Automatic Emergence Detection in Complex Systems

Automatic Emergence Detection in Complex Systems

A Multiagent System for Integrated Detection of Pharmacovigilance Signals

Knowledge fusion through academic articles: a survey of definitions, techniques, applications and challenges

Contact Info

Product

Resources

About