liu.seSearch for publications in DiVA
Change search
Refine search result
123 1 - 50 of 126
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Abramian, David
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Refacing: Reconstructing Anonymized Facial Features Using GANS2019Conference paper (Refereed)
    Abstract [en]

    Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.

  • 2.
    Ahlinder, Jon
    et al.
    Totalförsvarets Forskningsinstitut, FOI, Stockholm, Sweden.
    Nordgaard, Anders
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Swedish National Forensic Centre (NFC), Linköping, Sweden.
    Wiklund Lindström, Susanne
    Totalförsvarets Forskningsinstitut, FOI, Stockholm, Sweden.
    Chemometrics comes to court: evidence evaluation of chem–bio threat agent attacks2015In: Journal of Chemometrics, ISSN 0886-9383, E-ISSN 1099-128X, Vol. 29, no 5, p. 267-276Article in journal (Refereed)
    Abstract [en]

    Forensic statistics is a well-established scientific field whose purpose is to statistically analyze evidence in order to support legal decisions. It traditionally relies on methods that assume small numbers of independent variables and multiple samples. Unfortunately, such methods are less applicable when dealing with highly correlated multivariate data sets such as those generated by emerging high throughput analytical technologies. Chemometrics is a field that has a wealth of methods for the analysis of such complex data sets, so it would be desirable to combine the two fields in order to identify best practices for forensic statistics in the future. This paper provides a brief introduction to forensic statistics and describes how chemometrics could be integrated with its established methods to improve the evaluation of evidence in court.

    The paper describes how statistics and chemometrics can be integrated, by analyzing a previous know forensic data set composed of bacterial communities from fingerprints. The presented strategy can be applied in cases where chemical and biological threat agents have been illegally disposed.

  • 3.
    Aitken, Colin
    et al.
    Univ Edinburgh, Scotland.
    Nordgaard, Anders
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Swedish Police Author, Natl Forens Ctr, SE-58194 Linkoping, Sweden.
    The Roles of Participants Differing Background Information in the Evaluation of Evidence2018In: Journal of Forensic Sciences, ISSN 0022-1198, E-ISSN 1556-4029, Vol. 63, no 2, p. 648-649Article in journal (Other academic)
    Abstract [en]

    n/a

  • 4.
    Aitken, Colin
    et al.
    School of Mathematics, University of Edinburgh, Edinburgh, United Kingdom.
    Nordgaard, Anders
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Swedish Police Auhtority, National Forensic Centre (NFC).
    Taroni, Franco
    School of Criminal Justice, Université de Lausanne, Lausanne, Switzerland.
    Biedermann, Alex
    School of Criminal Justice, Université de Lausanne, Lausanne, Switzerland.
    A commentary on Likelihood Ratio as Weight of Forensic Evidence: A Closer Look: by Lund, S. P., and Iyer, H. (2017). J. Res. Natl. Inst. Stand. Technol. 122:272018In: Frontiers in Genetics, ISSN 1664-8021, E-ISSN 1664-8021, Vol. 9, article id 224Article in journal (Refereed)
  • 5.
    Alsaadi, Sarah
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Wänström, Linda
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Sjögren, Björn
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Bjärehed, Marlene
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Thornberg, Robert
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Educational Sciences.
    Collective moral disengagement and school bullying: An initial validation study of the Swedish scale version2016Conference paper (Refereed)
  • 6.
    Anderskär, Erika
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Thomasson, Frida
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Inkrementell responsanalys av Scandnavian Airlines medlemmar: Vilka kunder ska väljas vid riktad marknadsföring?2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Scandinavian Airlines has a large database containing their Eurobonus members. In order to analyze which customers they should target with direct marketing, such as emails, uplift models have been used. With a binary response variable that indicates whether the customer has bought or not, and a binary dummy variable that indicates if the customer has received the campaign or not conclusions can be drawn about which customers are persuadable. That means that the customers that buy when they receive a campaign and not if they don't are spotted. Analysis have been done with one campaign for Sweden and Scandinavia. The methods that have been used are logistic regression with Lasso and logistic regression with Penalized Net Information Value. The best method for predicting purchases is Lasso regression when comparing with a confusion matrix. The variable that best describes persuadable customers in logistic regression with PNIV is Flown (customers that have own with SAS within the last six months). In Lassoregression the variable that describes a persuadable customer in Sweden is membership level1 (the rst level of membership) and in Scandinavia customers that receive campaigns with delivery code 13 are persuadable, which is a form of dispatch.

  • 7.
    Andersson Naesseth, Christian
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.
    Lindsten, Fredrik
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.
    Schon, Thomas B.
    Uppsala Univ, Sweden.
    High-Dimensional Filtering Using Nested Sequential Monte Carlo2019In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 67, no 16, p. 4177-4188Article in journal (Refereed)
    Abstract [en]

    Sequential Monte Carlo (SMC) methods comprise one of the most successful approaches to approximate Bayesian filtering. However, SMC without a good proposal distribution can perform poorly, in particular in high dimensions. We propose nested sequential Monte Carlo, a methodology that generalizes the SMC framework by requiring only approximate, properly weighted, samples from the SMC proposal distribution, while still resulting in a correctSMCalgorithm. This way, we can compute an "exact approximation" of, e. g., the locally optimal proposal, and extend the class of models forwhichwe can perform efficient inference using SMC. We showimproved accuracy over other state-of-the-art methods on several spatio-temporal state-space models.

  • 8.
    Andersson, Olov
    et al.
    Linköping University, Department of Computer and Information Science, Artificial Intelligence and Integrated Computer Systems.
    Sidén, Per
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Dahlin, Johan
    Doherty, Patrick
    Villani, Mattias
    Real-Time Robotic Search using Structural Spatial Point Processes2019Conference paper (Refereed)
  • 9.
    Barakat, Arian
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    What makes an (audio)book popular?2018Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Audiobook reading has traditionally been used for educational purposes but has in recent times grown into a popular alternative to the more traditional means of consuming literature. In order to differentiate themselves from other players in the market, but also provide their users enjoyable literature, several audiobook companies have lately directed their efforts on producing own content. Creating highly rated content is, however, no easy task and one reoccurring challenge is how to make a bestselling story. In an attempt to identify latent features shared by successful audiobooks and evaluate proposed methods for literary quantification, this thesis employs an array of frameworks from the field of Statistics, Machine Learning and Natural Language Processing on data and literature provided by Storytel - Sweden’s largest audiobook company.

    We analyze and identify important features from a collection of 3077 Swedish books concerning their promotional and literary success. By considering features from the aspects Metadata, Theme, Plot, Style and Readability, we found that popular books are typically published as a book series, cover 1-3 central topics, write about, e.g., daughter-mother relationships and human closeness but that they also hold, on average, a higher proportion of verbs and a lower degree of short words. Despite successfully identifying these, but also other factors, we recognized that none of our models predicted “bestseller” adequately and that future work may desire to study additional factors, employ other models or even use different metrics to define and measure popularity.

    From our evaluation of the literary quantification methods, namely topic modeling and narrative approximation, we found that these methods are, in general, suitable for Swedish texts but that they require further improvement and experimentation to be successfully deployed for Swedish literature. For topic modeling, we recognized that the sole use of nouns provided more interpretable topics and that the inclusion of character names tended to pollute the topics. We also identified and discussed the possible problem of word inflections when modeling topics for more morphologically complex languages, and that additional preprocessing treatments such as word lemmatization or post-training text normalization may improve the quality and interpretability of topics. For the narrative approximation, we discovered that the method currently suffers from three shortcomings: (1) unreliable sentence segmentation, (2) unsatisfactory dictionary-based sentiment analysis and (3) the possible loss of sentiment information induced by translations. Despite only examining a handful of literary work, we further found that books written initially in Swedish had narratives that were more cross-language consistent compared to books written in English and then translated to Swedish.

  • 10.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Limit distribution of the quartet balance index for Aldous’s $(\beta \ge 0)$-modelIn: Applicationes Mathematicae, ISSN 1233-7234, E-ISSN 1730-6280Article in journal (Refereed)
    Abstract [en]

    This paper builds on T. Martínez-Coronado, A. Mir, F. Rosselló and G. Valiente’s 2018 work, introducing a new balance index for trees. We show that this balance index, in the case of Aldous’s $(\beta \ge 0)$-model, converges weakly to a distribution that can be characterized as the fixed point of a contraction operator on a class of distributions.

  • 11.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Simulating an infinite mean waiting time2019In: Mathematica Applicanda, ISSN 1730-2668, Vol. 47, no 1, p. 93-102Article in journal (Refereed)
    Abstract [en]

    We consider a hybrid method to simulate the return time to the initial state in a critical-case birth-death process. The expected value of this return time is infinite, but its distribution asymptotically follows a power-law. Hence, the simulation approach is to directly simulate the process, unless the simulated time exceeds some threshold and if it does, draw the return time from the tail of the power law.

  • 12.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    The phylogenetic effective sample size and jumps2018In: MATHEMATICA APPLICANDA (MATEMATYKA STOSOWANA), ISSN 1730-2668, Vol. 46, no 1, p. 25-33Article in journal (Refereed)
    Abstract [en]

    The phylogenetic effective sample size is a parameter that has as its goal the quantification of the amount of independent signal in a phylogenetically correlatedsample. It was studied for Brownian motion and Ornstein-Uhlenbeck models of trait evolution. Here, we study this composite parameter when the trait is allowedto jump at speciation points of the phylogeny. Our numerical study indicates thatthere is a non-trivial limit as the effect of jumps grows. The limit depends on thevalue of the drift parameter of the Ornstein-Uhlenbeck process.

  • 13.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Trait evolution with jumps: illusionary normality2017In: Proceedings of the XXIII National Conference on Applications of Mathematics in Biology and Medicine, 2017, p. 23-28Conference paper (Refereed)
    Abstract [en]

    Phylogenetic comparative methods for real-valued traits usually make use of stochastic process whose trajectories are continuous.This is despite biological intuition that evolution is rather punctuated thangradual. On the other hand, there has been a number of recent proposals of evolutionarymodels with jump components. However, as we are only beginning to understandthe behaviour of branching Ornstein-Uhlenbeck (OU) processes the asymptoticsof branching  OU processes with jumps is an even greater unknown. In thiswork we build up on a previous study concerning OU with jumps evolution on a pure birth tree.We introduce an extinction component and explore via simulations, its effects on the weak convergence of such a process.We furthermore, also use this work to illustrate the simulation and graphic generation possibilitiesof the mvSLOUCH package.

  • 14.
    Bartoszek, Krzysztof
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Uppsala Univ, Sweden.
    Domsta, Joachim
    State Univ Appl Sci Elblag, Poland.
    Pulka, Malgorzata
    Gdansk Univ Technol, Poland.
    Weak Stability of Centred Quadratic Stochastic Operators2019In: BULLETIN OF THE MALAYSIAN MATHEMATICAL SCIENCES SOCIETY, ISSN 0126-6705, Vol. 42, no 4, p. 1813-1830Article in journal (Refereed)
    Abstract [en]

    We consider the weak convergence of iterates of so-called centred quadratic stochastic operators. These iterations allow us to study the discrete time evolution of probability distributions of vector-valued traits in populations of inbreeding or hermaphroditic species, whenever the offsprings trait is equal to an additively perturbed arithmetic mean of the parents traits. It is shown that for the existence of a weak limit, it is sufficient that the distributions of the trait and the perturbation have a finite variance or have tails controlled by a suitable power function. In particular, probability distributions from the domain of attraction of stable distributions have found an application, although in general the limit is not stable.

  • 15.
    Bartoszek, Krzysztof
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Uppsala University, Sweden.
    Glemin, Sylvain
    Uppsala University, Sweden; CNRS University of Montpellier IRD EPHE, France.
    Kaj, Ingemar
    Uppsala University, Sweden.
    Lascoux, Martin
    Uppsala University, Sweden.
    Using the Ornstein-Uhlenbeck process to model the evolution of interacting populations2017In: Journal of Theoretical Biology, ISSN 0022-5193, E-ISSN 1095-8541, Vol. 429, p. 35-45Article in journal (Refereed)
    Abstract [en]

    The Ornstein-Uhlenbeck (OU) process plays a major role in the analysis of the evolution of phenotypic traits along phylogenies. The standard OU process includes random perturbations and stabilizing selection and assumes that species evolve independently. However, evolving species may interact through various ecological process and also exchange genes especially in plants. This is particularly true if we want to study phenotypic evolution among diverging populations within species. In this work we present a straightforward statistical approach with analytical solutions that allows for the inclusion of adaptation and migration in a common phylogenetic framework, which can also be useful for studying local adaptation among populations within the same species. We furthermore present a detailed simulation study that clearly indicates the adverse effects of ignoring migration. Similarity between species due to migration could be misinterpreted as very strong convergent evolution without proper correction for these additional dependencies. Finally, we show that our model can be interpreted in terms of ecological interactions between species, providing a general framework for the evolution of traits between "interacting" species or populations.(C) 2017 Elsevier Ltd. All rights reserved.

  • 16.
    Bartoszek, Krzysztof
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Lio, Pietro
    Univ Cambridge, England.
    MODELLING TRAIT-DEPENDENT SPECIATION WITH APPROXIMATE BAYESIAN COMPUTATION2019In: ACTA PHYSICA POLONICA B PROCEEDINGS SUPPLEMENT, JAGIELLONIAN UNIV , 2019, Vol. 12, no 1, p. 25-47Conference paper (Refereed)
    Abstract [en]

    Phylogeny is the field of modelling the temporal discrete dynamics of speciation. Complex models can nowadays be studied using the Approximate Bayesian Computation approach which avoids likelihood calculations. The fields progression is hampered by the lack of robust software to estimate the numerous parameters of the speciation process. In this work, we present an R package, pcmabc, publicly available on CRAN, based on Approximate Bayesian Computations, that implements three novel phylogenetic algorithms for trait-dependent speciation modelling. Our phylogenetic comparative methodology takes into account both the simulated traits and phylogeny, attempting to estimate the parameters of the processes generating the phenotype and the trait. The user is not restricted to a predefined set of models and can specify a variety of evolutionary and branching models. We illustrate the software with a simulation-reestimation study focused around the branching Ornstein-Uhlenbeck process, where the branching rate depends non-linearly on the value of the driving Ornstein-Uhlenbeck process. Included in this work is a tutorial on how to use the software.

  • 17.
    Bartoszek, Krzysztof
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. Uppsala Univ, Sweden.
    Majchrzak, Marta
    Polish Acad Sci, Poland.
    Sakowski, Sebastian
    Univ Lodz, Poland.
    Kubiak-Szeligowska, Anna B.
    Polish Acad Sci, Poland.
    Kaj, Ingemar
    Uppsala Univ, Sweden.
    Parniewski, Pawel
    Polish Acad Sci, Poland.
    Predicting pathogenicity behavior in Escherichia coli population through a state dependent model and TRS profiling2018In: PloS Computational Biology, ISSN 1553-734X, E-ISSN 1553-7358, Vol. 14, no 1, article id e1005931Article in journal (Refereed)
    Abstract [en]

    The Binary State Speciation and Extinction (BiSSE) model is a branching process based model that allows the diversification rates to be controlled by a binary trait. We develop a general approach, based on the BiSSE model, for predicting pathogenicity in bacterial populations from microsatellites profiling data. A comprehensive approach for predicting pathogenicity in E. coli populations is proposed using the state-dependent branching process model combined with microsatellites TRS-PCR profiling. Additionally, we have evaluated the possibility of using the BiSSE model for estimating parameters from genetic data. We analyzed a real dataset (from 251 E. coli strains) and confirmed previous biological observations demonstrating a prevalence of some virulence traits in specific bacterial sub-groups. The method may be used to predict pathogenicity of other bacterial taxa.

  • 18.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Exact and approximate limit behaviour of the Yule trees cophenetic index2018In: Mathematical Biosciences, ISSN 0025-5564, E-ISSN 1879-3134, Vol. 303, p. 26-45Article in journal (Refereed)
    Abstract [en]

    In this work we study the limit distribution of an appropriately normalized cophenetic index of the pure-birth tree conditioned on n contemporary tips. We show that this normalized phylogenetic balance index is a sub-martingale that converges almost surely and in L-2. We link our work with studies on trees without branch lengths and show that in this case the limit distribution is a contraction-type distribution, similar to the Quicksort limit distribution. In the continuous branch case we suggest approximations to the limit distribution. We propose heuristic methods of simulating from these distributions and it may be observed that these algorithms result in reasonable tails. Therefore, we propose a way based on the quantiles of the derived distributions for hypothesis testing, whether an observed phylogenetic tree is consistent with the pure-birth process. Simulating a sample by the proposed heuristics is rapid, while exact simulation (simulating the tree and then calculating the index) is a time-consuming procedure. We conduct a power study to investigate how well the cophenetic indices detect deviations from the Yule tree and apply the methodology to empirical phylogenies.

  • 19.
    Bergstrand, Frida
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Nguyen, Ngan
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Bakgrundsvariablers påverkan på enkätsvaren i en telefonintervju: En studie om effekt av intervjuarens, respondentens och intervjuns egenskaper2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Norstat recurrently performs a survey that contains questions about how much the respondent is watching different tv-channels, how different media-devices are used, the ownership of different devices and the usage of different tv-channel sites on the internet, social media, internet services, magazine services and streaming services. In this thesis, data from the survey performed during the autumn of 2016 was used. The aim of this thesis is to examine if there is a difference in answers based on different characteristics of the interviewers and respondents. 

    The 15 most important questions from the survey were chosen in this thesis, and to further reduce the number of response variables principal component analysis was used. The new scores that were produced by the analysis were the reduced response variables, which kept the most important information from the questions in the survey. Thereafter multilevel analyses and regression analyses were performed to examine the effects.  

    The results showed that there was an effect of different characteristics in different questions in the survey. The characteristics that showed effect were the age of the interviewer, the length of the employment, the age of the respondent, education, sex and native language. Some of the questions also showed effect based on whether the respondent lived in a metropolitan region or not.

  • 20.
    Bjärehed, Marlene
    et al.
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Sjögren, Björn
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Wänström, Linda
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Thornberg, Robert
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Educational Sciences.
    Bullying and moral disengagement mechanisms2016Conference paper (Refereed)
  • 21. Bjärehed, Marlene
    et al.
    Thornberg, Robert
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Educational Sciences.
    Wänström, Linda
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Mechanisms of Moral Disengagement and their Associations with Indirect Bullying, and Pro-Aggressive Bystander Behavior.2019In: Journal of Early Adolescence, ISSN 0272-4316, E-ISSN 1552-5449Article in journal (Refereed)
  • 22.
    Bjärehed, Marlene
    et al.
    Linköping University, Faculty of Educational Sciences. Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Thornberg, Robert
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Educational Sciences.
    Wänström, Linda
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Gianluca, Gini
    University of Padova.
    Sjögren, Björn
    Linköping University, Faculty of Educational Sciences. Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning.
    Bullying perpetration and victimization and their associations with warm student–teacher relationship, individual and collective moral disengagement, and collective efficacy in a sample of Swedish fourth grade students: A multi-level analysis2017Conference paper (Refereed)
  • 23.
    Bjärehed, Marlene
    et al.
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Arts and Sciences.
    Thornberg, Robert
    Linköping University, Department of Behavioural Sciences and Learning, Education, Teaching and Learning. Linköping University, Faculty of Educational Sciences.
    Wänström, Linda
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Gini, Gianluca
    Univ Padua, Italy.
    Individual Moral Disengagement and Bullying Among Swedish Fifth Graders: The Role of Collective Moral Disengagement and Pro-Bullying Behavior Within Classrooms2019In: Journal of Interpersonal Violence, ISSN 0886-2605, E-ISSN 1552-6518, article id UNSP 0886260519860889Article in journal (Refereed)
    Abstract [en]

    School bullying is a complex social and relational phenomenon with severe consequences for those involved. Most children view bullying as wrong and recognize its harmful consequences; nevertheless, it continues to be a persistent problem within schools. Previous research has shown that childrens engagement in bullying perpetration can be influenced by multiple factors (e.g., different forms of cognitive distortions) and at different ecological levels (e.g., child, peer-group, school, and society). However, the complexity of school bullying warrants further investigation of the interplay between factors, at different levels. Grounded in social cognitive theory, which focuses on both cognitive factors and social processes, this study examined whether childrens bullying perpetration was associated with moral disengagement at the child level and with collective moral disengagement and prevalence of pro-bullying behavior at the classroom level. Cross-level interactions were also tested to examine the effects of classroom-level variables on the association between childrens tendency to morally disengage and bullying perpetration. The studys analyses were based on cross-sectional self-report questionnaire data from 1,577 Swedish fifth-grade children from 105 classrooms (53.5% girls; M-age = 11.3, SD = 0.3). Multilevel modeling techniques were used to analyze the data. The results showed that bullying perpetration was positively associated with moral disengagement at the child level and with collective moral disengagement and pro-bullying behavior at the classroom level. Furthermore, the effect of individual moral disengagement on bullying was stronger for children in classrooms with higher levels of pro-bullying behaviors. These findings further support the argument that both moral processes and behaviors within classrooms, such as collective moral disengagement and pro-bullying behavior, need to be addressed in schools preventive work against bullying.

  • 24.
    Bonneau, Maxime
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Reinforcement Learning for 5G Handover2017Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The development of the 5G network is in progress, and one part of the process that needs to be optimised is the handover. This operation, consisting of changing the base station (BS) providing data to a user equipment (UE), needs to be efficient enough to be a seamless operation. From the BS point of view, this operation should be as economical as possible, while satisfying the UE needs.  In this thesis, the problem of 5G handover has been addressed, and the chosen tool to solve this problem is reinforcement learning. A review of the different methods proposed by reinforcement learning led to the restricted field of model-free, off-policy methods, more specifically the Q-Learning algorithm. On its basic form, and used with simulated data, this method allows to get information on which kind of reward and which kinds of action-space and state-space produce good results. However, despite working on some restricted datasets, this algorithm does not scale well due to lengthy computation times. It means that the agent trained can not use a lot of data for its learning process, and both state-space and action-space can not be extended a lot, restricting the use of the basic Q-Learning algorithm to discrete variables. Since the strength of the signal (RSRP), which is of high interest to match the UE needs, is a continuous variable, a continuous form of the Q-learning needs to be used. A function approximation method is then investigated, namely artificial neural networks. In addition to the lengthy computational time, the results obtained are not convincing yet. Thus, despite some interesting results obtained from the basic form of the Q-Learning algorithm, the extension to the continuous case has not been successful. Moreover, the computation times make the use of reinforcement learning applicable in our domain only for really powerful computers.

  • 25.
    Bovens, Michael
    et al.
    Zurich Forensic Science Institute, Switzerland.
    Ahrens, Björn
    Federal Criminal Police Office, Wiesbaden, Germany.
    Alberink, Ivo
    Netherlands Forensic Institute, The Hague, Netherlands.
    Nordgaard, Anders
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Salonen, Tuomas
    University of Helsinki, Faculty of Science, Department of Mathematics and Statistics.
    Huhtala, Sami
    National Bureau of Investigation, Helsinki, Finland.
    Chemometrics in forensic chemistry — Part I: Implications to the forensic workflow2019In: Forensic Science International, ISSN 0379-0738, E-ISSN 1872-6283, Vol. 301, p. 82-90Article in journal (Refereed)
    Abstract [en]

    The forensic literature shows a clear trend towards increasing use of chemometrics (i.e. multivariate analysis and other statistical methods). This can be seen in different disciplines such as drug profiling, arson debris analysis, spectral imaging, glass analysis, age determination, and more. In particular, current chemometric applications cover low-dimensional (e.g. drug impurity profiles) and high-dimensional data (e.g. Infrared and Raman spectra) and are therefore useful in many forensic disciplines. There is a dominant and increasing need in forensic chemistry for reliable and structured processing and interpretation of analytical data. This is especially true when classification (grouping) or profiling (batch comparison) is of interest.

    Chemometrics can provide additional information in complex crime cases and enhance productivity by improving the processes of data handling and interpretation in various applications. However, the use of chemometrics in everyday work tasks is often considered demanding by forensic scientists and, consequently, they are only reluctantly used. This article and following planned contributions are dedicated to those forensic chemists, interested in applying chemometrics but for any reasons are limited in the proper application of statistical tools — usually made for professionals — or the direct support of statisticians. Without claiming to be comprehensive, the literature reviewed revealed a sufficient overview towards the preferably used data handling and chemometric methods used to answer the forensic question. With this basis, a software tool will be designed (part of the EU project STEFA-G02) and handed out to forensic chemist with all necessary elements of data handling and evaluation.

    Because practical casework is less and less accompanied from the beginning to the end out of the same hand, more and more interfaces are built in through specialization of individuals. This article presents key influencing elements in the forensic workflow related to the most meaningful chemometric application and evaluation.

  • 26.
    Bravo, Gustavo A.
    et al.
    Harvard Univ, MA 02138 USA.
    Antonelli, Alexandre
    Harvard Univ, MA 02138 USA; Gothenburg Global Biodivers Ctr, Sweden; Univ Gothenburg, Sweden; Gothenburg Bot Garden, Sweden.
    Bacon, Christine D.
    Gothenburg Global Biodivers Ctr, Sweden; Univ Gothenburg, Sweden.
    Bartoszek, Krzysztof
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Blom, Mozes P. K.
    Swedish Museum Nat Hist, Sweden.
    Huynh, Stella
    Univ Neuchatel, Switzerland.
    Jones, Graham
    Univ Gothenburg, Sweden.
    Knowles, L. Lacey
    Univ Michigan, MI 48109 USA.
    Lamichhaney, Sangeet
    Harvard Univ, MA 02138 USA.
    Marcussen, Thomas
    Univ Oslo, Norway.
    Morlon, Helene
    Ecole Normale Super Paris, France.
    Nakhleh, Luay K.
    Rice Univ, TX USA.
    Oxelman, Bengt
    Gothenburg Global Biodivers Ctr, Sweden; Univ Gothenburg, Sweden.
    Pfeil, Bernard
    Univ Gothenburg, Sweden.
    Schliep, Alexander
    Chalmers Univ Technol, Sweden; Univ Gothenburg, Sweden.
    Wahlberg, Niklas
    Lund Univ, Sweden.
    Werneck, Fernanda P.
    Inst Nacl de Pesquisas da Amazonia, Brazil.
    Wiedenhoeft, John
    Chalmers Univ Technol, Sweden; Univ Gothenburg, Sweden; Rutgers State Univ, NJ USA.
    Willows-Munro, Sandi
    Univ Kwazulu Natal, South Africa.
    Edwards, Scott V
    Harvard Univ, MA 02138 USA; Univ Gothenburg, Sweden; Chalmers Univ Technol, Sweden.
    Embracing heterogeneity: coalescing the Tree of Life and the future of phylogenomics2019In: PeerJ, ISSN 2167-8359, E-ISSN 2167-8359, Vol. 7, article id e6399Article in journal (Refereed)
    Abstract [en]

    Building the Tree of Life (ToL) is a major challenge of modern biology, requiring advances in cyberinfrastructure, data collection, theory, and more. Here, we argue that phylogenomics stands to benefit by embracing the many heterogeneous genomic signals emerging from the first decade of large-scale phylogenetic analysis spawned by high-throughput sequencing (HTS). Such signals include those most commonly encountered in phylogenomic datasets, such as incomplete lineage sorting, but also those reticulate processes emerging with greater frequency, such as recombination and introgression. Here we focus specifically on how phylogenetic methods can accommodate the heterogeneity incurred by such population genetic processes; we do not discuss phylogenetic methods that ignore such processes, such as concatenation or supermatrix approaches or supertrees. We suggest that methods of data acquisition and the types of markers used in phylogenomics will remain restricted until a posteriori methods of marker choice are made possible with routine whole-genome sequencing of taxa of interest. We discuss limitations and potential extensions of a model supporting innovation in phylogenomics today, the multispecies coalescent model (MSC). Macroevolutionary models that use phylogenies, such as character mapping, often ignore the heterogeneity on which building phylogenies increasingly rely and suggest that assimilating such heterogeneity is an important goal moving forward. Finally, we argue that an integrative cyberinfrastructure linking all steps of the process of building the ToL, from specimen acquisition in the field to publication and tracking of phylogenomic data, as well as a culture that values contributors at each step, are essential for progress.

  • 27.
    Brouwers, Jack
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Thellman, Björn
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Klassificering av vinkvalitet2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The data used in this paper is an open source data, that was collected in Portugal over a three year period between 2004 and 2007. It consists of the physiochemical parameters, and the quality grade of the wines.

    This study focuses on assessing which variables that primarily affect the quality of a wine and how the effects of the variables interact with each other, and also compare which of the different classification methods work the best and have the highest degree of accuracy.

    The data is divided into red and white wine where the response variable is ordered and consists of the grades of quality for the different wines. Due to the distribution in the response variable having too few observations in some of the quality grades, a new response variable was created where several grades were pooled together so that each different grade category would have a good amount of observations.

    The statistical methods used are Bayesian ordered logistic regression as well as two data mining techniques which are neural networks and decision trees.

    The result obtained showed that for the two types of wine it is primarily the alcohol content and the amount of volatile acid that are recurring parameters which have a great influence on predicting the quality of the wines.

    The results also showed that among the three different methods, decision trees were the best at classifying the white wines and the neural network were the best for the red wines.

  • 28.
    Bruzzone, Andrea
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    P-SGLD: Stochastic Gradient Langevin Dynamics with control variates2017Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Year after years, the amount of data that we continuously generate is increasing. When this situation started the main challenge was to find a way to store the huge quantity of information. Nowadays, with the increasing availability of storage facilities, this problem is solved but it gives us a new issue to deal with: find tools that allow us to learn from this large data sets. In this thesis, a framework for Bayesian learning with the ability to scale to large data sets is studied. We present the Stochastic Gradient Langevin Dynamics (SGLD) framework and show that in some cases its approximation of the posterior distribution is quite poor. A reason for this can be that SGLD estimates the gradient of the log-likelihood with a high variability due to naïve sampling. Our approach combines accurate proxies for the gradient of the log-likelihood with SGLD. We show that it produces better results in terms of convergence to the correct posterior distribution than the standard SGLD, since accurate proxies dramatically reduce the variance of the gradient estimator. Moreover, we demonstrate that this approach is more efficient than the standard Markov Chain Monte Carlo (MCMC) method and that it exceeds other techniques of variance reduction proposed in the literature such as SAGA-LD algorithm. This approach also uses control variates to improve SGLD so that it is straightforward the comparison with our approach. We apply the method to the Logistic Regression model. 

  • 29.
    Burdakov, Oleg
    et al.
    Linköping University, Department of Mathematics, Optimization . Linköping University, Faculty of Science & Engineering.
    Sysoev, Oleg
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    A Dual Active-Set Algorithm for Regularized Slope-Constrained Monotonic Regression2017In: Iranian Journal of Operations Research, ISSN 2008-1189, Vol. 8, no 2, p. 40-47Article in journal (Refereed)
    Abstract [en]

    In many problems, it is necessary to take into account monotonic relations. Monotonic (isotonic) Regression (MR) is often involved in solving such problems. The MR solutions are of a step-shaped form with a typical sharp change of values between adjacent steps. This, in some applications, is regarded as a disadvantage. We recently introduced a Smoothed MR (SMR) problem which is obtained from the MR by adding a regularization penalty term. The SMR is aimed at smoothing the aforementioned sharp change. Moreover, its solution has a far less pronounced step-structure, if at all available. The purpose of this paper is to further improve the SMR solution by getting rid of such a structure. This is achieved by introducing a lowed bound on the slope in the SMR. We call it Smoothed Slope-Constrained MR (SSCMR) problem. It is shown here how to reduce it to the SMR which is a convex quadratic optimization problem. The Smoothed Pool Adjacent Violators (SPAV) algorithm developed in our recent publications for solving the SMR problem is adapted here to solving the SSCMR problem. This algorithm belongs to the class of dual active-set algorithms. Although the complexity of the SPAV algorithm is o(n2) its running time is growing in our computational experiments almost linearly with n. We present numerical results which illustrate the predictive performance quality of our approach. They also show that the SSCMR solution is free of the undesirable features of the MR and SMR solutions.

  • 30.
    Bäcklund, JOakim
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Nils, Johdet
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    A Bayesian approach to predict the number of soccer goals: Modeling with Bayesian Negative Binomial regression2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This thesis focuses on a well-known topic in sports betting, predicting the number of goals in soccer games.The data set used comes from the top English soccer league: Premier League, and consists of games played in the seasons 2015/16 to 2017/18.This thesis approaches the prediction with the auxiliary support of the odds from the betting exchange Betfair. The purpose is to find a model that can create an accurate goal distribution. %The other purpose is to investigate whether Negative binomial distribution regressionThe methods used are Bayesian Negative Binomial regression and Bayesian Poisson regression. The results conclude that the Poisson regression is the better model because of the presence of underdispersion.We argue that the methods can be used to compare different sportsbooks accuracies, and may help creating better models.

  • 31.
    Carlsson, Hampus
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Fully Convolutional Networks for Mammogram Segmentation2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Segmentation of mammograms pertains to assigning a meaningful label to each pixel found in the image. The segmented mammogram facilitates both the function of Computer Aided Diagnosis Systems and the development of tools used by radiologists during examination. Over the years many approaches to this problem have been presented. A surge in the popularity of new methods to image processing involving deep neural networks present new possibilities in this domain, and this thesis evaluates mammogram segmentation as an application of a specialized neural network architecture, U-net. Results are produced on publicly available datasets mini-MIAS and CBIS-DDSM. Using these two datasets together with mammograms from Hologic and FUJI, instances of U-net are trained and evaluated within and across the different datasets. A total of 10 experiments are conducted using 4 different models. Averaged over classes Pectoral, Breast and Background the best Dice scores are: 0.987 for Hologic, 0.978 for FUJI, 0.967 for mini-MIAS and 0.971 for CBIS-DDSM.

  • 32.
    Cros, Olivier
    et al.
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV). Aalborg Unversity Hospital, Denmark.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Gaihede, Michael
    Department of Otolaryngology, Head & Neck Surgery, Aalborg University Hospital, Denmark.
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Enhancement of micro-channels within the human mastoid bone based on local structure tensor analysis2016In: Image Proceessing Theory, Tools and Apllications, IEEE, 2016Conference paper (Refereed)
    Abstract [en]

    Numerous micro-channels have recently been discovered in the human temporal bone by x-ray micro-CT-scanning. After a preliminary study suggesting that these micro-channels form a separate blood supply for the mucosa of the mastoid air cells, a structural analysis of the micro-channels using a local structure tensor was carried out. Despite the high-resolution of the micro-CT scan, presence of noise within the air cells along with missing information in some micro-channels suggested the need of image enhancement. This paper proposes an adaptive enhancement of the micro-channels based on a local structure analysis while minimizing the impact of noise on the overall data. Comparison with an anisotropic diffusion PDE based scheme was also performed.

  • 33.
    Cros, Olivier
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV). Department of Otolaryngology, Head & Neck Surgery, Aalborg University Hospital, Denmark.
    Gaihede, Michael
    Department of Otolaryngology, Head & Neck Surgery, Aalborg University Hospital, Denmark; Department of Clinical Medicine, Aalborg University, Denmark.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences.
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Surface and curve skeleton from a structure tensor analysis applied on mastoid air cells in human temporal bones2017In: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), 2017, Institute of Electrical and Electronics Engineers (IEEE), 2017, p. 270-274Conference paper (Refereed)
    Abstract [en]

    The mastoid of human temporal bone contains numerous air cells connected to each others. In order to gain further knowledge about these air cells, a more compact representation is needed to obtain an estimate of the size distribution of these cells. Already existing skeletonization methods often fail in producing a faithful skeleton mostly due to noise hampering the binary representation of the data. This paper proposes a different approach by extracting geometrical information embedded in the Euclidean distance transform of a volume via a structure tensor analysis based on quadrature filters, from which a secondary structure tensor allows the extraction of surface skeleton along with a curve skeleton from its eigenvalues. Preliminary results obtained on a X-ray micro-CT scans of a human temporal bone show very promising results.

  • 34.
    Dang, Khue-Dung
    et al.
    Univ New South Wales, Australia; ARC Ctr Excellence Math and Stat Frontiers ACEMS, Australia.
    Quiroz, Matias
    ARC Ctr Excellence Math and Stat Frontiers ACEMS, Australia; Univ Technol Sydney, Australia.
    Kohn, Robert
    Univ New South Wales, Australia; ARC Ctr Excellence Math and Stat Frontiers ACEMS, Australia.
    Minh-Ngoc, Tran
    ARC Ctr Excellence Math and Stat Frontiers ACEMS, Australia; Univ Sydney, Australia.
    Villani, Mattias
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Arts and Sciences. ARC Ctr Excellence Math and Stat Frontiers ACEMS, Australia; Stockholm Univ, Sweden.
    Hamiltonian Monte Carlo with Energy Conserving Subsampling2019In: Journal of machine learning research, ISSN 1532-4435, E-ISSN 1533-7928, Vol. 20, article id 1Article in journal (Refereed)
    Abstract [en]

    Hamiltonian Monte Carlo (HMC) samples efficiently from high-dimensional posterior distributions with proposed parameter draws obtained by iterating on a discretized version of the Hamiltonian dynamics. The iterations make HMC computationally costly, especially in problems with large data sets, since it is necessary to compute posterior densities and their derivatives with respect to the parameters. Naively computing the Hamiltonian dynamics on a subset of the data causes HMC to lose its key ability to generate distant parameter proposals with high acceptance probability. The key insight in our article is that efficient subsampling HMC for the parameters is possible if both the dynamics and the acceptance probability are computed from the same data subsample in each complete HMC iteration. We show that this is possible to do in a principled way in a HMC-within-Gibbs framework where the subsample is updated using a pseudo marginal MH step and the parameters are then updated using an HMC step, based on the current subsample. We show that our subsampling methods are fast and compare favorably to two popular sampling algorithms that use gradient estimates from data subsampling. We also explore the current limitations of subsampling HMC algorithms by varying the quality of the variance reducing control variates used in the estimators of the posterior density and its gradients.

  • 35.
    De Biase, Alessia
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Generative Adversarial Networks to enhance decision support in digital pathology2019Independent thesis Advanced level (degree of Master (Two Years)), 80 credits / 120 HE creditsStudent thesis
    Abstract [en]

    Histopathological evaluation and Gleason grading on Hematoxylin and Eosin(H&E) stained specimens is the clinical standard in grading prostate cancer. Recently, deep learning models have been trained to assist pathologists in detecting prostate cancer. However, these predictions could be improved further regarding variations in morphology, staining and differences across scanners. An approach to tackle such problems is to employ conditional GANs for style transfer. A total of 52 prostatectomies from 48 patients were scanned with two different scanners. Data was split into 40 images for training and 12 images for testing and all images were divided into overlapping 256x256 patches. A segmentation model was trained using images from scanner A, and the model was tested on images from both scanner A and B. Next, GANs were trained to perform style transfer from scanner A to scanner B. The training was performed using unpaired training images and different types of Unsupervised Image to Image Translation GANs (CycleGAN and UNIT). Beside the common CycleGAN architecture, a modified version was also tested, adding Kullback Leibler (KL) divergence in the loss function. Then, the segmentation model was tested on the augmented images from scanner B.The models were evaluated on 2,000 randomly selected patches of 256x256 pixels from 10 prostatectomies. The resulting predictions were evaluated both qualitatively and quantitatively. All proposed methods outperformed in AUC, in the best case the improvement was of 16%. However, only CycleGAN trained on a large dataset demonstrated to be capable to improve the segmentation tool performance, preserving tissue morphology and obtaining higher results in all the evaluation measurements. All the models were analyzed and, finally, the significance of the difference between the segmentation model performance on style transferred images and on untransferred images was assessed, using statistical tests.

  • 36.
    De Biase, Alessia
    et al.
    Division of Statistics and Machine learning, Department of Computer and Information Science, Linkoping University, Linkoping, Sweden, ContextVision AB, Stockholm, Sweden .
    Burlutskiy, Nikolay
    ContextVision AB, Stockholm, Sweden .
    Pinchaud, Nicolas
    ContextVision AB, Stockholm, Sweden.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Deep Learning Data Augmentation Approach to Improve Cancer Segmentation Performance across Different Scanners2019Conference paper (Refereed)
  • 37.
    Eamrurksiri, Araya
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Applying Machine Learning to LTE/5G Performance Trend Analysis2017Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    The core idea of this thesis is to reduce the workload of manual inspection when the performance analysis of an updated software is required. The Central Process- ing Unit (CPU) utilization, which is one of the essential factors for evaluating the performance, is analyzed. The purpose of this work is to apply machine learning techniques that are suitable for detecting the state of the CPU utilization and any changes in the test environment that affects the CPU utilization. The detection re- lies on a Markov switching model to identify structural changes, which are assumed to follow an unobserved Markov chain, in the time series data. A historical behav- ior of the data can be described by a first-order autoregression. Then, the Markov switching model becomes a Markov switching autoregressive model. Another ap- proach based on a non-parametric analysis, a distribution-free method that requires fewer assumptions, called an E-divisive method, is proposed. This method uses a hi- erarchical clustering algorithm to detect multiple change point locations in the time series data. As the data used in this analysis does not contain any ground truth, the evaluation of the methods is analyzed by generating simulated datasets with known states. Besides, these simulated datasets are used for studying and compar- ing between the Markov switching autoregressive model and the E-divisive method. Results show that the former method is preferable because of its better performance in detecting changes. Some information about the state of the CPU utilization are also obtained from performing the Markov switching model. The E-divisive method is proved to have less power in detecting changes and has a higher rate of missed detections. The results from applying the Markov switching autoregressive model to the real data are presented with interpretations and discussions. 

  • 38.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Repliker. ”Öppen vetenskap behöver inte kosta en enda krona”2016In: Dagens Nyheter, ISSN 1101-2447Article in journal (Other (popular science, discussion, etc.))
  • 39.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Öppen vetenskap behöver inte kosta en krona2017In: Svenska Dagbladet, ISSN 1101-2412Article in journal (Other (popular science, discussion, etc.))
  • 40.
    Eklund, Anders
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Reply to Chen et al.: Parametric methods for cluster inference perform worse for two‐sided t‐tests2019In: Human Brain Mapping, ISSN 1065-9471, E-ISSN 1097-0193, Vol. 40, no 5, p. 1689-1691Article in journal (Other (popular science, discussion, etc.))
    Abstract [en]

    One‐sided t‐tests are commonly used in the neuroimaging field, but two‐sided tests should be the default unless a researcher has a strong reason for using a one‐sided test. Here we extend our previous work on cluster false positive rates, which used one‐sided tests, to two‐sided tests. Briefly, we found that parametric methods perform worse for two‐sided t‐tests, and that nonparametric methods perform equally well for one‐sided and two‐sided tests.

  • 41.
    Eklund, Anders
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Nichols, Thomas E
    Big Data Institute, University of Oxford, Oxford, United Kingdom, Department of Statistics, University of Warwick, Coventry, United KingdomWellcome Trust Centre for Integrative Neuroimaging (WIN-FMRIB), University of Oxford, Oxford, United Kingdom, .
    Cluster failure revisited: Impact of first level design and physiological noise on cluster false positive rates2019In: Human Brain Mapping, ISSN 1065-9471, E-ISSN 1097-0193, Vol. 40, no 7, p. 2017-2032Article in journal (Refereed)
    Abstract [en]

    Methodological research rarely generates a broad interest, yet our work on the validity of cluster inference methods for functional magnetic resonance imaging (fMRI) created intense discussion on both the minutia of our approach and its implications for the discipline. In the present work, we take on various critiques of our work and further explore the limitations of our original work. We address issues about the particular event‐related designs we used, considering multiple event types and randomization of events between subjects. We consider the lack of validity found with one‐sample permutation (sign flipping) tests, investigating a number of approaches to improve the false positive control of this widely used procedure. We found that the combination of a two‐sided test and cleaning the data using ICA FIX resulted in nominal false positive rates for all data sets, meaning that data cleaning is not only important for resting state fMRI, but also for task fMRI. Finally, we discuss the implications of our work on the fMRI literature as a whole, estimating that at least 10% of the fMRI studies have used the most problematic cluster inference method (p = .01 cluster defining threshold), and how individual studies can be interpreted in light of our findings. These additional results underscore our original conclusions, on the importance of data sharing and thorough evaluation of statistical methods on realistic null data.

  • 42.
    Eklund, Anders
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Nichols, Thomas
    University of Warwick, England.
    How open science revealed false positives in brain imaging2017In: Significance, ISSN 1740-9705, E-ISSN 1740-9713Article in journal (Other (popular science, discussion, etc.))
    Abstract [en]

    A team set out to validate software used in fMRI analysis, but ended up invalidating one of neuroscience's most common testing procedures.

  • 43.
    Enoksson, Josefin
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Olausson, Sofia
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Bayesiansk flernivåanalys för att undersöka variationen i elevers trygghet i skolan: En studie baserad på enkäten Om mig2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
  • 44.
    Fischer, Max
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Using Reinforcement Learning for Games with Nondeterministic State Transitions2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Given the recent advances within a subfield of machine learning called reinforcement learning, several papers have shown that it is possible to create self-learning digital agents, agents that take actions and pursue strategies in complex environments without any prior knowledge. This thesis investigates the performance of the state-of-the-art reinforcement learning algorithm proximal policy optimization, when trained on a task with nondeterministic state transitions. The agent’s policy was constructed using a convolutional neural network and the game Candy Crush Friends Saga, a single-player match-three tile game, was used as the environment.

    The purpose of this research was to evaluate if the described agent could achieve a higher win rate than average human performance when playing the game of Candy Crush Friends Saga. The research also analyzed the algorithm's generalization capabilities on this task. The results showed that all trained models perform better than a random policy baseline, thus showing it is possible to use the proximal policy optimization algorithm to learn tasks in an environment with nondeterministic state transitions. It also showed that, given the hyperparameters chosen, it was not able to perform better than average human performance.

  • 45.
    Fredrik, Schlyter
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Predicting Personal Taxi Destinations Using Artificial Neural Networks2018Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Taxi Stockholm is a Swedish taxi company which would like to improve their mobile phone application with a destination prediction feature. This thesis has created an algo- rithm which predicts a destination to which a taxi customer would like to go. The problem is approached using the KDD process and data mining methods. A dataset consisting of previous taxi rides is cleaned, transformed, and then used to evaluate the performance of three machine learning models. More specifically a neural network model paired with K- Means clustering, a random forest model, and a k-nearest neighbour model. The results show that the models that were developed in this thesis could be used as a first step in a destination prediction system. The results also show that personal data increase the accu- racy of the neural network model and that there exists a threshold for how much personal information is needed to increase the performance.

  • 46.
    Gebremariam, Merhawi Tewolde
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Predicting the life cycle of technologies from patent data2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Analysis of patent documents is one way to learn about trends in the evolutionof technologies. In this thesis, we propose a mixture of life cycle Poisson modelfor predicting the life cycle of technologies from patent count data. The aim is topredict the life cycle of technologies and determine the stage of the technology inthe development S-curve. The model is constructed from historical data on patentpublications of technologies and also from experts’ belief of life cycle of technologies. The methods used to estimate the model are based on Bayesian methods, inparticular we use a combination of Gibbs sampling and slice sampling to simulatefrom the posterior distribution of the model parameters. We apply the model on adataset of 123 technologies from the electricity sector. As a preliminary exploratorystep clustering analysis is also applied on the dataset. Finally we evaluate the modelhow it performs to predict the trend of life cycle of technologies based on differentbase years. Results reveal that the model is capable of predicting the life cycleof technologies based on its different stages. However, the predictions of expectedbehavior become more accurate when more data is used to construct the prediction.

  • 47.
    Grek, Viktoria
    et al.
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Gabrielsson, Molinia
    Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning.
    Analys av nutidens tågindelning: Ett uppdrag framtaget av Trafikverket2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The information used in this paper comes from Trafikverket's delivery monitoring system. It consists of information about planned train missions on the Swedish railways for the years 2014 to 2017 during week four (except planned train missions on Roslagsbanan and Saltsjöbanan).

    Trafikanalys with help from Trafikverket presents public statistics for short-distance trains, middle-distance trains and long-distance trains on Trafikanalys website. The three classes of trains have no scientific basis. The purpose of this study is therefore to analyze if today's classes of trains can be used and which variables that have importance for the classification. The purpose of this study is also to analyze if there is a better way to categorize the classes of trains when Trafikanalys publishes public statistics. The statistical methods that are used in this study are decision tree, neural network and hierarchical clustering.

    The result obtained from the decision tree was a 92.51 percent accuracy for the classification of Train type. The most important variables for Train type were Train length, Planned train kilometers and Planned km/h.Neural networks were used to investigate whether this method could also provide a similar result as the decision tree too strengthening the reliability. Neural networks got an 88 percent accuracy when classifying Train type. Based on these two results, it indicates that the larger proportion of train assignments could be classified to the correct Train Type. This means that the current classification of Train type works when Trafikanalys presents official statistics.

    For the new train classification, three groups were analyzed when hierarchical clustering was used. These three groups were not the same as the group's short-distance trains, middle-distance trains and long-distance trains. Because the new divisions have blended the various passenger trains, this result does not help to find a better subdivision that can be used for when Trafikanalys presents official statistics.

  • 48.
    Gu, Xuan
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Repeated Tractography of a Single Subject: How High Is the Variance?2017In: Modeling, Analysis, and Visualization of Anisotropy / [ed] Thomas Schultz, Evren Özarslan, Ingrid Hotz, Springer, 2017, p. 331-354Chapter in book (Other academic)
    Abstract [en]

    We have investigated the test-retest reliability of diffusion tractography, using 32 diffusion datasets from a single healthy subject. Preprocessing was carried out using functions in FSL (FMRIB Software Library), and tractography was carried out using FSL and Dipy. The tractography was performed in diffusion space, using two seed masks (corticospinal and cingulum gyrus tracts) created from the JHU White-Matter Tractography atlas. The tractography results were then warped into MNI standard space by a linear transformation. The reproducibility of tract metrics was examined using the standard deviation, the coefficient of variation (CV) and the Dice similarity coefficient (DSC), which all indicated a high reproducibility. Our results show that the multi-fiber model in FSL is able to reveal more connections between brain areas, compared to the single fiber model, and that distortion correction increases the reproducibility.

  • 49.
    Gu, Xuan
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Özarslan, Evren
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Using the wild bootstrap to quantify uncertainty in mean apparent propagator MRI2019In: Frontiers in Neuroinformatics, ISSN 1662-5196, E-ISSN 1662-5196, Vol. 13, article id 43Article in journal (Refereed)
    Abstract [en]

    Purpose: Estimation of uncertainty of MAP-MRI metricsis an important topic, for several reasons. Bootstrap deriveduncertainty, such as the standard deviation, providesvaluable information, and can be incorporated in MAP-MRIstudies to provide more extensive insight.

    Methods: In this paper, the uncertainty of different MAPMRImetrics was quantified by estimating the empirical distributionsusing the wild bootstrap. We applied the wildbootstrap to both phantom data and human brain data, andobtain empirical distributions for theMAP-MRImetrics returnto-origin probability (RTOP), non-Gaussianity (NG) and propagatoranisotropy (PA).

    Results: We demonstrated the impact of diffusion acquisitionscheme (number of shells and number of measurementsper shell) on the uncertainty of MAP-MRI metrics.We demonstrated how the uncertainty of these metrics canbe used to improve group analyses, and to compare differentpreprocessing pipelines. We demonstrated that withuncertainty considered, the results for a group analysis canbe different.

    Conclusion: Bootstrap derived uncertain measures provideadditional information to the MAP-MRI derived metrics, andshould be incorporated in ongoing and future MAP-MRIstudies to provide more extensive insight.

  • 50.
    Gu, Xuan
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Knutsson, Hans
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Nilsson, Markus
    Department of Clinical Sciences, Radiology, Lund UniversityLundSweden.
    Eklund, Anders
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Generating Diffusion MRI Scalar Maps from T1 Weighted Images Using Generative Adversarial Networks2019In: Image Analysis: Lecture Notes in Computer Science / [ed] Felsberg M., Forssén PE., Sintorn IM., Unger J., Springer Publishing Company, 2019, p. 489-498Conference paper (Refereed)
    Abstract [en]

    Diffusion magnetic resonance imaging (diffusion MRI) is a non-invasive microstructure assessment technique. Scalar measures, such as FA (fractional anisotropy) and MD (mean diffusivity), quantifying micro-structural tissue properties can be obtained using diffusion models and data processing pipelines. However, it is costly and time consuming to collect high quality diffusion data. Here, we therefore demonstrate how Generative Adversarial Networks (GANs) can be used to generate synthetic diffusion scalar measures from structural T1-weighted images in a single optimized step. Specifically, we train the popular CycleGAN model to learn to map a T1 image to FA or MD, and vice versa. As an application, we show that synthetic FA images can be used as a target for non-linear registration, to correct for geometric distortions common in diffusion MRI.

123 1 - 50 of 126
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf