Kenan Šehić

Kenan Šehić
Lund University | LU · Department of Computer Science

PhD

About

10
Publications
757
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
10
Citations
Introduction
Kenan Sehic currently works at the Department Computer Science, Lund University. Kenan does research in Uncertainty Quantification, Machine Learning and Computer Engineering. He received her doctorate in computational mathematics in 2020 at the Technical University of Denmark. He hols a master's degree in Mechanical Engineering from University of Sarajevo.
Education
January 2017 - April 2020
Technical University of Denmark
Field of study
  • Computational mathematics
October 2013 - July 2015
University of Sarajevo
Field of study
  • Mechanical Process Engineering
October 2010 - June 2013
University of Sarajevo
Field of study
  • Mechanical Process Engineering

Publications

Publications (10)
Preprint
Full-text available
Cyber-physical systems (CPSs) are usually complex and safety-critical; hence, it is difficult and important to guarantee that the system's requirements, i.e., specifications, are fulfilled. Simulation-based falsification of CPSs is a practical testing method that can be used to raise confidence in the correctness of the system by only requiring tha...
Preprint
Full-text available
Artificial Intelligence (AI) is one of the most promising technologies of the 21. century, with an already noticeable impact on society and the economy. With this work, we provide a short overview of global trends, applications in industry and selected use-cases from our international experience and work in industry and academia. The goal is to pre...
Article
Full-text available
Big Data analytics and Artificial Intelligence (AI) technologies have become the focus of recent research due to the large amount of data. Dimensionality reduction techniques are recognized as an important step in these analyses. The multidimensional nature of Quality of Experience (QoE) is based on a set of Influence Factors (IFs) whose dimensiona...
Preprint
Even though Weighted Lasso regression has appealing statistical guarantees, it is typically avoided due to its complex search space described with thousands of hyperparameters. On the other hand, the latest progress with high-dimensional HPO methods for black-box functions demonstrates that high-dimensional applications can indeed be efficiently op...
Article
Full-text available
We model shallow-water waves using a one-dimensional Korteweg–de Vries equation with the wave generation parameterized by random wave amplitudes for a predefined sea state. These wave amplitudes define the high-dimensional stochastic input vector for which we estimate the short-term wave crest exceedance probability at a reference point. For this h...
Article
Full-text available
In offshore engineering design, nonlinear wave models are often used to propagate stochastic waves from an input boundary to the location of an offshore structure. Each wave realization is typically characterized by a high-dimensional input time-series, and a reliable determination of the extreme events is associated with substantial computational...
Preprint
In offshore engineering design, nonlinear wave models are often used to propagate stochastic waves from an input boundary to the location of an offshore structure. Each wave realization is typically characterized by a high-dimensional input time series, and a reliable determination of the extreme events is associated with substantial computational...
Preprint
Full-text available
We here consider the subset simulation method which approaches a failure event using a decreasing sequence of nested intermediate failure events. The method resembles importance sampling, which actively explores a probability space by conditioning the next evaluation on the previous evaluations using a Markov chain Monte Carlo (MCMC) algorithm. A M...
Preprint
Full-text available
We model shallow-water waves using a one-dimensional Korteweg-de Vries equation with the wave generation parameterized by random wave amplitudes for a predefined sea state. These wave amplitudes define the high-dimensional stochastic input vector for which we estimate the short-term wave crest exceedance probability at a reference point. For this h...
Article
Full-text available
We demonstrate that a single 6mm line sample of simulated near-field speckle intensity suffices for accurate estimation of the concentration of dielectric micro-particles over a range from 104 to 6⋅106 particles per ml. For this estimation, we analyze the speckle using both standard methods (linear principal component analysis, support vector machi...

Network

Cited By

Projects

Projects (2)
Project
Mission of DeRisk Cost reduction within offshore wind energy is central for achieving the 2020 goal of 50% wind share of the Danish electricity supply. DeRisk provides a key contribution by providing new design methods with reduced risk and uncertainty for extreme wave loads (ULS, Ultimate Limit State) which are often design-giving for the support structure. DeRisk examines the design chain from met-ocean data to structural response. Joint-probability methods are developed for analysis of met-ocean data. Wave transformation over depth is computed with ground-breaking fully nonlinear, GPU-accelerated wave models. The detailed physical load effects of 3D wave spreading, bed-slope, wave-current interaction and formation of extreme irregular waves are quantified experimentally. Specialised tools for high-frequency ringing-type and breaking wave loads are developed. Advanced LES-based CFD methods are developed and applied to extreme wave impacts with wall friction. The structural response for wind turbine structures of mono-pod and jacket type are examined through aero-elastic calculations and analysis of lab and field data. For the first time, new methods for numerical uncertainty quantification are applied to quantify the model sensitivity. The new tools and detailed investigations are synthesized into a de-risked design procedure for ULS wave loads (see figure below).
Archived project
The purpose of the PhD project is to develop, implement, validate and apply numerical Uncertainty Quantification methods to achieve accelerated and improved prediction of marine loads on offshore wind turbines. Modern numerical models for wave transformation enable accurate deterministic computation of these loads, but in a realistic setting several model parameters, such as incident wave elevation and bottom friction, are stochastic variables. The vision for this project is to surpass the quality of the load prediction and parameter sensitivity analysis achieved by the Monte Carlo approach commonly used in offshore engineering today. First, a detailed, model-intrusive analysis and numerical investigation will be conducted of the propagation of uncertainty through the forward model (that transforms the incident wave to the resultant load). Then, the forward model will be fitted to extreme events, and a formal link will be found between short-term and long-term load statistics. The numerical work will revolve around the OceanWave3D wave transformation model and the Mike21 SW model of large-scale wave energy propagation. The research will be conducted in close interaction with the industrial partners.