Browsing by Subject "REGULARIZATION"

Sort by: Order: Results:

Now showing items 1-11 of 11
  • Bleyer, Ismael Rodrigo; Lybeck, Lasse; Auvinen, Harri; Airaksinen, Manu; Alku, Paavo; Siltanen, Samuli (2017)
    A new method is proposed for solving the glottal inverse filtering (GIF) problem. The goal of GIF is to separate an acoustical speech signal into two parts: the glottal airflow excitation and the vocal tract filter. To recover such information one has to deal with a blind deconvolution problem. This ill-posed inverse problem is solved under a deterministic setting, considering unknowns on both sides of the underlying operator equation. A stable reconstruction is obtained using a double regularization strategy, alternating between fixing either the glottal source signal or the vocal tract filter. This enables not only splitting the nonlinear and nonconvex problem into two linear and convex problems, but also allows the use of the best parameters and constraints to recover each variable at a time. This new technique, called alternating minimization glottal inverse filtering (AM-GIF), is compared with two other approaches: Markov chain Monte Carlo glottal inverse filtering (MCMC-GIF), and iterative adaptive inverse filtering (IAIF), using synthetic speech signals. The recent MCMC-GIF has good reconstruction quality but high computational cost. The state-of-the-art IAIF method is computationally fast but its accuracy deteriorates, particularly for speech signals of high fundamental frequency (F0). The results show the competitive performance of the new method: With high F0, the reconstruction quality is better than that of IAIF and close to MCMC-GIF while reducing the computational complexity by two orders of magnitude.
  • White, Brian S.; Khan, Suleiman A.; Mason, Mike J.; Ammad-ud-din, Muhammad; Potdar, Swapnil; Malani, Disha; Kuusanmäki, Heikki; Druker, Brian J.; Heckman, Caroline; Kallioniemi, Olli; Kurtz, Stephen E.; Porkka, Kimmo; Tognon, Cristina E.; Tyner, Jeffrey W.; Aittokallio, Tero; Wennerberg, Krister; Guinney, Justin (2021)
    The FDA recently approved eight targeted therapies for acute myeloid leukemia (AML), including the BCL-2 inhibitor venetoclax. Maximizing efficacy of these treatments requires refining patient selection. To this end, we analyzed two recent AML studies profiling the gene expression and ex vivo drug response of primary patient samples. We find that ex vivo samples often exhibit a general sensitivity to (any) drug exposure, independent of drug target. We observe that this "general response across drugs" (GRD) is associated with FLT3-ITD mutations, clinical response to standard induction chemotherapy, and overall survival. Further, incorporating GRD into expression-based regression models trained on one of the studies improved their performance in predicting ex vivo response in the second study, thus signifying its relevance to precision oncology efforts. We find that venetoclax response is independent of GRD but instead show that it is linked to expression of monocyte-associated genes by developing and applying a multi-source Bayesian regression approach. The method shares information across studies to robustly identify biomarkers of drug response and is broadly applicable in integrative analyses.
  • Lee, Yunsung; Haftorn, Kristine L.; Denault, William R. P.; Nustad, Haakon E.; Page, Christian M.; Lyle, Robert; Lee-Odegard, Sindre; Moen, Gunn-Helen; Prasad, Rashmi B.; Groop, Leif C.; Sletner, Line; Sommer, Christine; Magnus, Maria C.; Gjessing, Hakon K.; Harris, Jennifer R.; Magnus, Per; Haberg, Siri E.; Jugessur, Astanand; Bohlin, Jon (2020)
    BackgroundEpigenetic clocks have been recognized for their precise prediction of chronological age, age-related diseases, and all-cause mortality. Existing epigenetic clocks are based on CpGs from the Illumina HumanMethylation450 BeadChip (450K) which has now been replaced by the latest platform, Illumina MethylationEPIC BeadChip (EPIC). Thus, it remains unclear to what extent EPIC contributes to increased precision and accuracy in the prediction of chronological age.ResultsWe developed three blood-based epigenetic clocks for human adults using EPIC-based DNA methylation (DNAm) data from the Norwegian Mother, Father and Child Cohort Study (MoBa) and the Gene Expression Omnibus (GEO) public repository: 1) an Adult Blood-based EPIC Clock (ABEC) trained on DNAm data from MoBa (n=1592, age-span: 19 to 59years), 2) an extended ABEC (eABEC) trained on DNAm data from MoBa and GEO (n=2227, age-span: 18 to 88years), and 3) a common ABEC (cABEC) trained on the same training set as eABEC but restricted to CpGs common to 450K and EPIC. Our clocks showed high precision (Pearson correlation between chronological and epigenetic age (r)>0.94) in independent cohorts, including GSE111165 (n=15), GSE115278 (n=108), GSE132203 (n=795), and the Epigenetics in Pregnancy (EPIPREG) study of the STORK Groruddalen Cohort (n=470). This high precision is unlikely due to the use of EPIC, but rather due to the large sample size of the training set.ConclusionsOur ABECs predicted adults' chronological age precisely in independent cohorts. As EPIC is now the dominant platform for measuring DNAm, these clocks will be useful in further predictions of chronological age, age-related diseases, and mortality.
  • JET Contributors; Mlynar, Jan; Ahlgren, T.; Aho-Mantila, L.; Airila, M.; Björkas, C.; Jarvinen, A.; Lahtinen, A.; Makkonen, T.; Nordlund, K.; Safi, E.; Sipila , S. K.; Asunta, O.; Groth, M.; Hakola, A.; Karhunen, J.; Koivuranta, S.; Koskela, T.; Kurki-Suonio, T.; Lomanowski, B.; Lonnroth, J.; Salmi, A.; Santala, M. I. K. (2019)
    Retrieving spatial distribution of plasma emissivity from line integrated measurements on tokamaks presents a challenging task due to ill-posedness of the tomography problem and limited number of the lines of sight. Modern methods of plasma tomography therefore implement a-priori information as well as constraints, in particular some form of penalisation of complexity. In this contribution, the current tomography methods under development (Tikhonov regularisation, Bayesian methods and neural networks) are briefly explained taking into account their potential for integration into the fusion reactor diagnostics. In particular, current development of the Minimum Fisher Regularisation method is exemplified with respect to real-time reconstruction capability, combination with spectral unfolding and other prospective tasks.
  • Lees, John A.; Mai, T. Tien; Galardini, Marco; Wheeler, Nicole E.; Horsfield, Samuel T.; Parkhill, Julian; Corander, Jukka (2020)
    Discovery of genetic variants underlying bacterial phenotypes and the prediction of phenotypes such as antibiotic resistance are fundamental tasks in bacterial genomics. Genome-wide association study (GWAS) methods have been applied to study these relations, but the plastic nature of bacterial genomes and the clonal structure of bacterial populations creates challenges. We introduce an alignment-free method which finds sets of loci associated with bacterial phenotypes, quantifies the total effect of genetics on the phenotype, and allows accurate phenotype prediction, all within a single computationally scalable joint modeling framework. Genetic variants covering the entire pangenome are compactly represented by extended DNA sequence words known as unitigs, and model fitting is achieved using elastic net penalization, an extension of standard multiple regression. Using an extensive set of state-of-the-art bacterial population genomic data sets, we demonstrate that our approach performs accurate phenotype prediction, comparable to popular machine learning methods, while retaining both interpretability and computational efficiency. Compared to those of previous approaches, which test each genotype-phenotype association separately for each variant and apply a significance threshold, the variants selected by our joint modeling approach overlap substantially. IMPORTANCE Being able to identify the genetic variants responsible for specific bacterial phenotypes has been the goal of bacterial genetics since its inception and is fundamental to our current level of understanding of bacteria. This identification has been based primarily on painstaking experimentation, but the availability of large data sets of whole genomes with associated phenotype metadata promises to revolutionize this approach, not least for important clinical phenotypes that are not amenable to laboratory analysis. These models of phenotype-genotype association can in the future be used for rapid prediction of clinically important phenotypes such as antibiotic resistance and virulence by rapid-turnaround or point-of-care tests. However, despite much effort being put into adapting genome-wide association study (GWAS) approaches to cope with bacterium-specific problems, such as strong population structure and horizontal gene exchange, current approaches are not yet optimal. We describe a method that advances methodology for both association and generation of portable prediction models.
  • Bubba, Tatiana A.; Kutyniok, Gitta; Lassas, Matti; März, Maximilian; Samek, Wojciech; Siltanen, Samuli; Srinivasan, Vignesh (2019)
    The high complexity of various inverse problems poses a significant challenge to model-based reconstruction schemes, which in such situations often reach their limits. At the same time, we witness an exceptional success of data-based methodologies such as deep learning. However, in the context of inverse problems, deep neural networks mostly act as black box routines, used for instance for a somewhat unspecified removal of artifacts in classical image reconstructions. In this paper, we will focus on the severely ill-posed inverse problem of limited angle computed tomography, in which entire boundary sections are not captured in the measurements. We will develop a hybrid reconstruction framework that fuses model-based sparse regularization with data-driven deep learning. Our method is reliable in the sense that we only learn the part that can provably not be handled by model-based methods, while applying the theoretically controllable sparse regularization technique to the remaining parts. Such a decomposition into visible and invisible segments is achieved by means of the shearlet transform that allows to resolve wavefront sets in the phase space. Furthermore, this split enables us to assign the clear task of inferring unknown shearlet coefficients to the neural network and thereby offering an interpretation of its performance in the context of limited angle computed tomography. Our numerical experiments show that our algorithm significantly surpasses both pure model- and more data-based reconstruction methods.
  • Drouard, Gabin; Ollikainen, Miina; Mykkänen, Juha; Raitakari, Olli; Lehtimäki, Terho; Kähönen, Mika; Mishra, Pashupati P.; Wang, Xiaoling; Kaprio, Jaakko (2022)
    Abnormal blood pressure is strongly associated with risk of high-prevalence diseases, making the study of blood pressure a major public health challenge. Although biological mechanisms underlying hypertension at the single omic level have been discovered, multi-omics integrative analyses using continuous variations in blood pressure values remain limited. We used a multi-omics regression-based method, called sparse multi-block partial least square, for integrative, explanatory, and predictive interests in study of systolic and diastolic blood pressure values. Various datasets were obtained from the Finnish Twin Cohort for up to 444 twins. Blocks of omics-including transcriptomic, methylation, metabolomic-data as well as polygenic risk scores and clinical data were integrated into the modeling and supported by cross-validation. The predictive contribution of each omics block when predicting blood pressure values was investigated using external participants from the Young Finns Study. In addition to revealing interesting inter-omics associations, we found that each block of omics heterogeneously improved the predictions of blood pressure values once the multi-omics data were integrated. The modeling revealed a plurality of clinical, transcriptomic, and metabolomic factors consistent with the literature and that play a leading role in explaining unit variations in blood pressure. These findings demonstrate (1) the robustness of our integrative method to harness results obtained by single omics discriminant analyses, and (2) the added value of predictive and exploratory gains of a multi-omics approach in studies of complex phenotypes such as blood pressure.
  • Mattsson, Markus T. (2019)
    The way people behave in traffic is not always optimal from the road safety perspective: drivers exceed speed limits, misjudge speeds or distances, tailgate other road users or fail to perceive them. Such behaviors are commonly investigated using self-report-based latent variable models, and conceptualized as reflections of violation- and error-proneness. However, attributing dangerous behavior to stable properties of individuals may not be the optimal way of improving traffic safety, whereas investigating direct relationships between traffic behaviors offers a fruitful way forward. Network models of driver behavior and background factors influencing behavior were constructed using a large UK sample of novice drivers. The models show how individual violations, such as speeding, are related to and may contribute to individual errors such as tailgating and braking to avoid an accident. In addition, a network model of the background factors and driver behaviors was constructed. Finally, a model predicting crashes based on prior behavior was built and tested in separate datasets. This contribution helps to bridge a gap between experimental/theoretical studies and self-report-based studies in traffic research: the former have recognized the importance of focusing on relationships between individual driver behaviors, while network analysis offers a way to do so for self-report studies.
  • Hänninen, H.; Lappi, T.; Paatelainen, R. (2018)
    We develop methods needed to perform loop calculations in light cone perturbation theory using a helicity basis, refining the method introduced in our earlier work. In particular this includes implementing a consistent way to contract the four-dimensional tensor structures from the helicity vectors with d -dimensional tensors arising from loop integrals, in a way that can be fully automatized. We demonstrate this explicitly by calculating the one-loop correction to the virtual photon to quark–antiquark dipole light cone wave function. This allows us to calculate the deep inelastic scattering cross section in the dipole formalism to next-to-leading order accuracy. Our results, obtained using the four dimensional helicity scheme, agree with the recent calculation by Beuf using conventional dimensional regularization, confirming the regularization scheme independence of this cross section.
  • Agapiou, Sergios; Burger, Martin; Dashti, Masoumeh; Helin, Tapio (2018)
    We consider the inverse problem of recovering an unknown functional parameter u in a separable Banach space, from a noisy observation vector y of its image through a known possibly non-linear map G. We adopt a Bayesian approach to the problem and consider Besov space priors (see Lassas et al (2009 Inverse Problems Imaging 3 87-122)), which are well-known for their edge-preserving and sparsity-promoting properties and have recently attracted wide attention especially in the medical imaging community. Our key result is to show that in this non-parametric setup the maximum a posteriori (MAP) estimates are characterized by the minimizers of a generalized Onsager-Machlup functional of the posterior. This is done independently for the so-called weak and strong MAP estimates, which as we show coincide in our context. In addition, we prove a form of weak consistency for the MAP estimators in the infinitely informative data limit. Our results are remarkable for two reasons: first, the prior distribution is non-Gaussian and does not meet the smoothness conditions required in previous research on non-parametric MAP estimates. Second, the result analytically justifies existing uses of the MAP estimate in finite but high dimensional discretizations of Bayesian inverse problems with the considered Besov priors.
  • Kauppi, Jukka-Pekka; Hahne, Janne; Müller, Klaus-Robert; Müller, Klaus-Robert (2015)
    Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.