Jasper De Bock

ORCID: 0000-0003-1950-0059
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Bayesian Modeling and Causal Inference
  • Decision-Making and Behavioral Economics
  • Rough Sets and Fuzzy Logic
  • Logic, Reasoning, and Knowledge
  • Computability, Logic, AI Algorithms
  • Gene Regulatory Network Analysis
  • Risk and Portfolio Optimization
  • Stochastic processes and financial applications
  • Data Management and Algorithms
  • Formal Methods in Verification
  • Multi-Criteria Decision Making
  • Philosophy and History of Science
  • Fault Detection and Control Systems
  • Advanced Database Systems and Queries
  • Markov Chains and Monte Carlo Methods
  • Fuzzy Systems and Optimization
  • Benford’s Law and Fraud Detection
  • Economic theories and models
  • Bayesian Methods and Mixture Models
  • Advanced Optical Network Technologies
  • Data Mining Algorithms and Applications
  • Control Systems and Identification
  • Advanced Topology and Set Theory
  • Probability and Statistical Research
  • Advanced Queuing Theory Analysis

Ghent University
2014-2024

Ghent University Hospital
2010-2022

University Foundation
2021-2022

Durham University
2021

Institute of Flight
2021

University of Liverpool
2021

De Montfort University
2021

Bhabha Atomic Research Centre
2021

Universidade Federal de São Carlos
2015

10.1016/j.ijar.2017.06.012 article EN International Journal of Approximate Reasoning 2017-07-04

Motivated by its connection to the limit behaviour of imprecise Markov chains, we introduce and study so-called convergence upper transition operators: condition that for any function, orbit resulting from iterated application this operator converges. In contrast, existing notion `ergodicity' requires a constant. We derive very general (and practically verifiable) sufficient in terms accessibility lower reachability, prove is also necessary whenever (i) all transient states are absorbed or...

10.48550/arxiv.2502.04509 preprint EN arXiv (Cornell University) 2025-02-06

We provide a decision-theoretic framework for dealing with uncertainty in quantum mechanics. This is two-fold: on the one hand there may be about state system in, and other hand, as essential to mechanical uncertainty, even if known, measurements still produce an uncertain outcome. In our framework, therefore play role of acts outcome simple postulates ensure that Born's rule encapsulated utility functions associated such acts. approach allows us uncouple (precise) probability theory from...

10.48550/arxiv.2503.20607 preprint EN arXiv (Cornell University) 2025-03-26

10.1016/j.ijar.2014.07.002 article EN publisher-specific-oa International Journal of Approximate Reasoning 2014-07-09

10.1007/s00332-016-9328-3 article EN Journal of Nonlinear Science 2016-08-29

Supervised hyperspectral image (HSI) classification relies on accurate label information. However, it is not always possible to collect perfectly labels for training samples. This motivates the development of classifiers that are sufficiently robust some reasonable amounts errors in data labels. Despite growing importance this aspect, has been studied literature yet. In paper, we analyze effect erroneous sample probability distributions principal components HSIs, and provide way a...

10.3390/s20185262 article EN cc-by Sensors 2020-09-15

We present an efficient exact algorithm for estimating state sequences from outputs or observations in imprecise hidden Markov models (iHMMs). The uncertainty linking one to the next, and that a its output, is represented by set of probability mass functions instead single such function. consider as best estimates maximal posterior joint model conditioned on observed output sequence, associated with gain function indicator sequence. This corresponds generalises finding sequence highest...

10.1613/jair.4385 article EN publisher-specific-oa Journal of Artificial Intelligence Research 2014-05-31

The possibility of flexibly assigning spectrum resources with channels different sizes greatly improves the spectral efficiency optical networks, but can also lead to unwanted fragmentation. We study this problem in a scenario where traffic demands are categorized two types (low or high bit-rate) by assessing performance three allocation policies. Our first contribution consists exact Markov chain models for these policies, which allow us numerically compute relevant measures. However, do...

10.1109/tcomm.2018.2846235 article EN IEEE Transactions on Communications 2018-06-11

10.1016/j.ijar.2015.08.006 article EN publisher-specific-oa International Journal of Approximate Reasoning 2015-08-29

10.1016/j.ijar.2020.12.017 article EN publisher-specific-oa International Journal of Approximate Reasoning 2020-12-29

10.1016/j.ijar.2021.06.018 article EN International Journal of Approximate Reasoning 2021-07-12

10.1016/j.ijar.2024.109241 article EN cc-by International Journal of Approximate Reasoning 2024-07-01

Coherent reasoning under uncertainty can be represented in a very general manner by coherent sets of desirable gambles. In context that does not allow for indecision, this leads to an approach is mathematically equivalent working with conditional probabilities. If we do more foundation (imprecise-)probabilistic inference. framework, and given finite category set, predictive inference exchangeability using Bernstein cones multivariate polynomials on the simplex generated set. This powerful...

10.1613/jair.4490 article EN cc-by Journal of Artificial Intelligence Research 2015-01-10

Imprecise continuous-time Markov chains are a robust type of that allow for partially specified time-dependent parameters. Computing inferences them requires the solution non-linear differential equation. As there is no general analytical expression this solution, efficient numerical approximation methods essential to applicability model. We here improve uniform method Krak et al. (2016) in two ways and propose novel more adaptive method. For ergodic chains, we also provide allows us...

10.48550/arxiv.1702.07150 preprint EN other-oa arXiv (Cornell University) 2017-01-01
Coming Soon ...