| 1. |
- Röding, Magnus, et al.
(författare)
-
Machine learning-accelerated small-angle X-ray scattering analysis of disordered two- and three-phase materials
- 2022
-
Ingår i: Frontiers in Materials. - : Frontiers Media S.A.. - 2296-8016. ; 9
-
Tidskriftsartikel (refereegranskat)abstract
- Small-angle X-ray scattering (SAXS) is a useful technique for nanoscale structural characterization of materials. In SAXS, structural and spatial information is indirectly obtained from the scattering intensity in the spectral domain, known as the reciprocal space. Therefore, characterizing the structure requires solving the inverse problem of finding a plausible structure model that corresponds to the measured scattering intensity. Both the choice of structure model and the computational workload of parameter estimation are bottlenecks in this process. In this work, we develop a framework for analysis of SAXS data from disordered materials. The materials are modeled using Gaussian Random Fields (GRFs). We study the case of two phases, pore and solid, and three phases, where a third phase is added at the interface between the two other phases. Further, we develop very fast GPU-accelerated, Fourier transform-based numerical methods for both structure generation and SAXS simulation. We demonstrate that length scales and volume fractions can be predicted with good accuracy using our machine learning-based framework. The parameter prediction executes virtually instantaneously and hence the computational burden of conventional model fitting can be avoided. Copyright © 2022 Röding, Tomaszewski, Yu, Borg and Rönnols.
|
|
| 2. |
- Frimodig, Sara, et al.
(författare)
-
Comparing Optimization Methods for Radiation Therapy Patient Scheduling using Different Objectives
- 2023
-
Ingår i: Operations Research Forum. - : Springer Nature. - 2662-2556. ; 4:4
-
Tidskriftsartikel (refereegranskat)abstract
- Radiation therapy (RT) is a medical treatment to kill cancer cells or shrink tumors. To manually schedule patients for RT is a time-consuming and challenging task. By the use of optimization, patient schedules for RT can be created automatically. This paper presents a study of different optimization methods for modeling and solving the RT patient scheduling problem, which can be used as decision support when implementing an automatic scheduling algorithm in practice. We introduce an Integer Programming (IP) model, a column generation IP model (CG-IP), and a Constraint Programming model. Patients are scheduled on multiple machine types considering their priority for treatment, session duration and allowed machines. Expected future arrivals of urgent patients are included in the models as placeholder patients. Since different cancer centers can have different scheduling objectives, the models are compared using multiple objective functions, including minimizing waiting times, and maximizing the fulfillment of patients’ preferences for treatment times. The test data is generated from historical data from Iridium Netwerk, Belgium’s largest cancer center with 10 linear accelerators. The results demonstrate that the CG-IP model can solve all the different problem instances to a mean optimality gap of less than 1 % within one hour. The proposed methodology provides a tool for automated scheduling of RT treatments and can be generally applied to RT centers.
|
|
| 3. |
- Tahvili, Sahar, et al.
(författare)
-
Solving complex maintenance planning optimization problems using stochastic simulation and multi-criteria fuzzy decision making
- 2014
-
Ingår i: 10TH INTERNATIONAL CONFERENCE ON MATHEMATICAL PROBLEMS IN ENGINEERING, AEROSPACE AND SCIENCES: ICNPAA 2014 Conference date: 15–18 July 2014 Location: Narvik, Norway ISBN: 978-0-7354-1276-7 Editor: Seenith Sivasundaram Volume number: 1637 Published: 10 december 2014. - : American Institute of Physics (AIP). - 9780735412767 ; , s. 766-775
-
Konferensbidrag (refereegranskat)abstract
- One of the most important factors in the operations of many cooperations today is to maximize profit and one important tool to that effect is the optimization of maintenance activities. Maintenance activities is at the largest level divided into two major areas, corrective maintenance (CM) and preventive maintenance (PM). When optimizing maintenance activities, by a maintenance plan or policy, we seek to find the best activities to perform at each point in time, be it PM or CM. We explore the use of stochastic simulation, genetic algorithms and other tools for solving complex maintenance planning optimization problems in terms of a suggested framework model based on discrete event simulation.
|
|
| 4. |
- Tahvili, Sahar, et al.
(författare)
-
Strategic maintenance planning by fuzzy AHP and Markov Decision Processes
- 2015
-
Ingår i: ASMDA 2015 Proceedings. - : ISAST: International Society for the Advancement of Science and Technology. - 9786185180058 ; , s. 991-1004, s. 297-310
-
Konferensbidrag (refereegranskat)abstract
- The work of engineering and business professionals includes making a series of decisions and optimizations. Real world decision making problems faced by decision makers (DM) involve multiple, usually conflicting, criteria. These multicriteria decision making problems (MCDM) are usually complicated and large in scale. In strategic Maintenance planning, choices are made on where to focus time and effort, where to spend money. We consider a framework for strategic maintenance planning in a modern maintenance driven organization. Our focus is on a multi-stage framework in which the planning is divided into two stages, identifying an optimal set of possible actions and finding the optimal decision policy for these actions for each point in time as a function of the stochastically evolving system state. To this respect we consider the MCDM method of AHP (Analytical hierarchical programming) in a fuzzy environment, and Markov decision processes (MDP).
|
|
| 5. |
- Wandebäck, Fredrik, et al.
(författare)
-
Variation Feedback and 3D Visualization of Geometrical Inspection Data
- 2010
-
Ingår i: Proceedings of the ASME 2009 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference IDETC/CIE, August 30 - September 2, 2009, San Diego, California, USA. - 9780791849057 ; 8, s. 197-208
-
Konferensbidrag (refereegranskat)abstract
- There is no type of manufacturing process that is not afflicted by variation. Activities intended to ensure the quality of a company's geometry processes are usually referred to as geometry assurance activities. One clear industrial problem is to understand the relations between the products concept and the manufacturing process. Dimensional data is a very important source of experience of how a product's geometry has worked in the interaction with the actual manufacturing system. Users therefore need good analysis and presentation tools of geometry outcomes to support both the product developers and production engineers in the analysis of the production output and its consequences. Today the dimensional data can be difficult to obtain or access, and is not necessarily presented in such a way as to provide the user with all necessary information. This paper presents how presentation and analysis tools of geometrical inspection data can be taken a step further. New functionality for feature based 3D visualization of inspection data has been developed which integrates the variation simulation platform and the inspection data database. The goal has been to create better tools for analysis of geometrical variation and increase the understanding of the sources of variation.
|
|
| 6. |
- Alabdallah, Abdallah, 1979-, et al.
(författare)
-
The Concordance Index decomposition : A measure for a deeper understanding of survival prediction models
- 2024
-
Ingår i: Artificial Intelligence in Medicine. - Amsterdam : Elsevier B.V.. - 0933-3657 .- 1873-2860. ; 148
-
Tidskriftsartikel (refereegranskat)abstract
- The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. In this paper, we propose a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases. This decomposition enables a finer-grained analysis of the relative strengths and weaknesses between different survival prediction methods. The usefulness of this decomposition is demonstrated through benchmark comparisons against classical models and state-of-the-art methods, together with the new variational generative neural-network-based method (SurVED) proposed in this paper. The performance of the models is assessed using four publicly available datasets with varying levels of censoring. Using the C-index decomposition and synthetic censoring, the analysis shows that deep learning models utilize the observed events more effectively than other models. This allows them to keep a stable C-index in different censoring levels. In contrast to such deep learning methods, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events.
|
|
| 7. |
- Johannesson, Pär, 1969, et al.
(författare)
-
Laplace distribution models for road topography and roughness
- 2017
-
Ingår i: International Journal of Vehicle Performance. - 1745-3194 .- 1745-3208. ; 3:3, s. 224-258
-
Tidskriftsartikel (refereegranskat)abstract
- Gaussian models are frequently used for road elevations. However,these models are often only valid for short sections of the road. Here we presenta comprehensive approach to describe various aspects of road surface/elevationby using extensions of Gaussian models arising from random gamma distributedvariances. These random variances result in the Laplace distribution and thuswe refer to the so defined models as Laplace models. The approach is shownto perform well in modelling road topography, road roughness and multi-valuedresponses of forces and bending moments containing transients. The differentLaplace models are presented together with numerical examples and Matlab codefor simulation.
|
|
| 8. |
- Longfils, Marco, 1990, et al.
(författare)
-
Single particle raster image analysis of diffusion for particle mixtures
- 2018
-
Ingår i: Journal of Microscopy. - : Wiley. - 0022-2720 .- 1365-2818. ; 269:3, s. 269-281
-
Tidskriftsartikel (refereegranskat)abstract
- Recently we complemented the raster image correlation spectroscopy (RICS) method of analysing raster images via estimation of the image correlation function with the method single particle raster image analysis (SPRIA). In SPRIA, individual particles are identified and the diffusion coefficient of each particle is estimated by a maximum likelihood method. In this paper, we extend the SPRIA method to analyse mixtures of particles with a finite set of diffusion coefficients in a homogeneous medium. In examples with simulated and experimental data with two and three different diffusion coefficients, we show that SPRIA gives accurate estimates of the diffusion coefficients and their proportions. A simple technique for finding the number of different diffusion coefficients is also suggested. Further, we study the use of RICS for mixtures with two different diffusion coefficents and investigate, by plotting level curves of the correlation function, how large the quotient between diffusion coefficients needs to be in order to allow discrimination between models with one and two diffusion coefficients. We also describe a minor correction (compared to published papers) of the RICS autocorrelation function. Lay description Diffusion is a key mass transport mechanism for small particles. Efficient methods for estimating diffusion coefficients are crucial for analysis of microstructures, for example in soft biomaterials. The sample of interest may consist of a mixture of particles with different diffusion coefficients. Here, we extend a method called Single Particle Raster Image Analysis (SPRIA) to account for particle mixtures and estimation of the diffusion coefficients of the mixture components. SPRIA combines elements of classical single particle tracking methods with utilizing the raster scan with which images obtained by using a confocal laser scanning microscope. In particular, single particles are identified and their motion estimated by following their center of mass. Thus, an estimate of the diffusion coefficient will be obtained for each particle. Then, we analyse the distribution of the estimated diffusion coefficients of the population of particles, which allows us to extract information about the diffusion coefficients of the underlying components in the mixture. On both simulated and experimental data with mixtures consisting of two and three components with different diffusion coefficients, SPRIA provides accurate estimates and, with a simple criterion, the correct number of mixture components is selected in most cases.
|
|
| 9. |
- Maghsood, Roza, 1980, et al.
(författare)
-
Detection of steering events using hidden Markov models with multivariate observations
- 2016
-
Ingår i: International Journal of Vehicle Systems Modelling and Testing. - 1745-6436 .- 1745-6444. ; 11:4, s. 313-329
-
Tidskriftsartikel (refereegranskat)abstract
- In this article we propose a method to identify steering events, such as curves and manoeuvres for vehicles. We use a hidden Markov model with multidimensional observations, to estimate the number of events. Three signals, lateral acceleration, steering angle speed and vehicle speed, are used as observations. We demonstrate that hidden Markov models with a combination of continuous and discrete distributions for observations can be used to detect steering events. Further, the expected number of events is estimated using the transition matrix of hidden states. The results from both measured and simulated data show that the method works well and accurately estimates the number of steering events.
|
|
| 10. |
- Skarstrom, V. W., et al.
(författare)
-
DeepFRAP: Fast fluorescence recovery after photobleaching data analysis using deep neural networks
- 2021
-
Ingår i: Journal of Microscopy. - : Wiley. - 0022-2720 .- 1365-2818. ; 282:2, s. 146-161
-
Tidskriftsartikel (refereegranskat)abstract
- Conventional analysis of fluorescence recovery after photobleaching (FRAP) data for diffusion coefficient estimation typically involves fitting an analytical or numerical FRAP model to the recovery curve data using non-linear least squares. Depending on the model, this can be time consuming, especially for batch analysis of large numbers of data sets and if multiple initial guesses for the parameter vector are used to ensure convergence. In this work, we develop a completely new approach, DeepFRAP, utilizing machine learning for parameter estimation in FRAP. From a numerical FRAP model developed in previous work, we generate a very large set of simulated recovery curve data with realistic noise levels. The data are used for training different deep neural network regression models for prediction of several parameters, most importantly the diffusion coefficient. The neural networks are extremely fast and can estimate the parameters orders of magnitude faster than least squares. The performance of the neural network estimation framework is compared to conventional least squares estimation on simulated data, and found to be strikingly similar. Also, a simple experimental validation is performed, demonstrating excellent agreement between the two methods. We make the data and code used publicly available to facilitate further development of machine learning-based estimation in FRAP.
|
|
