A5077821870- Statistical Methods and Inference
- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- Fault Detection and Control Systems
- Bioinformatics and Genomic Networks
- Bayesian Methods and Mixture Models
- Advanced Statistical Methods and Models
- Genomics and Chromatin Dynamics
- Explainable Artificial Intelligence (XAI)
- Machine Learning and Data Classification
- Advanced Battery Technologies Research
- Genetic Associations and Epidemiology
- RNA and protein synthesis mechanisms
- Chromosomal and Genetic Variations
- Epigenetics and DNA Methylation
- Control Systems and Identification
- Reliability and Maintenance Optimization
- Genetics, Bioinformatics, and Biomedical Research
- Statistical Methods and Bayesian Inference
- Sports Analytics and Performance
- Algorithms and Data Compression
- Genetic Mapping and Diversity in Plants and Animals
- MicroRNA in disease regulation
- Sparse and Compressive Sensing Techniques
- Maritime Navigation and Safety
University of Oslo
2015-2024
Norwegian Institute of Public Health
2019
Oslo University Hospital
2013
University of Bergen
2013
Norwegian Computing Center
2013
Norwegian University of Science and Technology
2013
The traditional kernel density estimator of an unknown is by construction completely nonparametric in the sense that it has no preferences and will work reasonably well for all shapes. present paper develops a class semiparametric methods are designed to better than broad neighbourhood given parametric densities, example, normal, while not losing much precision when true far from class. idea multiply initial estimate with kernel-type necessary correction factor. This works cases where factor...
Abstract Summary: CGH-Explorer is a program for visualization and statistical analysis of microarray-based comparative genomic hybridization (array-CGH) data. The has preprocessing facilities, tools graphical exploration individual arrays or groups arrays, identification regions amplification deletion. Availability: available as Java class files that runs on any platform with the 2 runtime environment (J2SE JRE) installed, Windows executable. source are also available. See...
Abstract Classical smoothers have limited usefulness in image processing, because sharp "edges" tend to be blurred. There is a literature on edge-preserving smoothers, but these all require moderately large "smooth stretches." Here we discuss an approach this problem called "sigma filtering" and propose improvement based running M estimation. Both computational theoretical aspects are developed. For the methods niche between standard filtering approaches Bayes–Markov random-field analysis.
The immense increase in the generation of genomic scale data poses an unmet analytical challenge, due to a lack established methodology with required flexibility and power. We propose first principled approach statistical analysis sequence-level information. provide growing collection generic biological investigations that query pairwise relations between tracks, represented as mathematical objects, along genome. Genomic HyperBrowser implements is available at http://hyperbrowser.uio.no .
The continuous growth in maritime traffic and recent developments towards autonomous navigation have directed increasing attention to navigational safety which new tools are required identify real-time risk complex situations. These of paramount importance avoid potentially disastrous consequences accidents promote safe at sea. In this study, an adaptive ship-safety-domain is proposed with spatial functions both collision grounding based on motion maneuverability conditions for all vessels....
DNA methylation affects expression of associated genes and may contribute to the missing genetic effects from genome-wide association studies osteoporosis. To improve insight into mechanisms postmenopausal osteoporosis, we combined transcript profiling with analyses in bone. RNA were isolated 84 bone biopsies donors varying markedly mineral density (BMD). In all, 2529 CpGs top 100 most significantly BMD analyzed. The levels at 63 differed between healthy osteoporotic women 10% false...
We present a new approach to regression function estimation in which non‐parametric estimator is guided by parametric pilot estimate with the aim of reducing bias. New classes parametrically kernel weighted local polynomial estimators are introduced and formulae for asymptotic expectation variance, hence approximated mean squared error integrated error, derived. It shown that have very same large sample variance as standard setting, while there substantial room bias if chosen belongs wide...
Integrative analysis of gene dosage, expression, and ontology (GO) data was performed to discover driver genes in the carcinogenesis chemoradioresistance cervical cancers. Gene dosage expression profiles 102 locally advanced cancers were generated by microarray techniques. Fifty-two these patients also analyzed with Illumina method confirm results. An independent cohort 41 used for validation expressions associated clinical outcome. Statistical identified 29 recurrent gains losses 3 (on 3p,...
Autonomous ships are promoted as the future of maritime transport industry aiming to overcome conventional vessels in terms performance, safety and environmental impact. Yet their tangled cyber-physical-social interactions new emerging properties induce questions regarding liability trustworthiness. Digital simulations sea trials launched assure requirements social expectations met a priori. This paper presents design realistic testbed scenarios from huge historical data through...
Longevity and safety of lithium-ion batteries are facilitated by efficient monitoring adjustment the battery operating conditions. Hence, it is crucial to implement fast accurate algorithms for State Health (SoH) on Battery Management System. The task challenging due complexity multitude factors contributing capacity degradation, especially because different degradation processes occur at various timescales their interactions play an important role. Data-driven methods bypass this issue...
The lasso is one of the most commonly used methods for high-dimensional regression, but can be unstable and lacks satisfactory asymptotic properties variable selection. We propose to use weighted with integrated relevant external information on covariates guide selection towards more stable results. Weighting penalties gives each regression coefficient a covariate specific amount penalization improve upon standard that do not such by borrowing knowledge from material. method applied two...
Lithium-ion batteries are a prominent technology for the electrification of transport sector, which itself is key measure towards departure from fossil fuels. The "green shift" taking place in marine industry too, where number battery-powered vessels fastly growing. In this case, monitoring battery State Health essential more than ever to optimise use, promote safety, and ensure coverage ship power energy demands. Classification societies typically require annual capacity tests purpose;...
Abstract. Several old and new density estimators may have good theoretical performance, but are hampered by not being bona fide densities; they be negative in certain regions or integrate to 1. One can therefore simulate from them, for example. This paper develops general modification methods that turn any estimator into one which is a density, always better performance under set of conditions arbitrarily close complementary conditions. improvement‐for‐free procedure can, particular, applied...
Missing values are problematic for the analysis of microarray data. Imputation methods have been compared in terms similarity between imputed and true simulation experiments not their influence on final analysis. The focus has missing at random, while entries also random.We investigate imputation detection differentially expressed genes from cDNA We apply ANOVA microarrays SAM look to that lost because imputation. show this new measure provides useful information traditional root mean...
The immense increase in availability of genomic scale datasets, such as those provided by the ENCODE and Roadmap Epigenomics projects, presents unprecedented opportunities for individual researchers to pose novel falsifiable biological questions. With this opportunity, however, are faced with challenge how best analyze interpret their genome-scale datasets. A powerful way representing data is feature-specific coordinates relative reference genome assemblies, i.e. tracks. Genomic HyperBrowser...
Graph-based representations are considered to be the future for reference genomes, as they allow integrated representation of steadily increasing data on individual variation. Currently available tools de novo assembly graph-based alignment new read sets graph well certain analyses like variant calling and haplotyping. We here present a first method ChIP-Seq peaks aligned genome. The is generalization peak caller MACS2, implemented in an open source tool, Graph Peak Caller. By using existing...
We propose novel modifications to an anomaly detection methodology based on multivariate signal reconstruction followed by residuals analysis. The reconstructions are made using Auto Associative Kernel Regression (AAKR), where the query observations compared historical called memory vectors, representing normal operation. When data set with grows large, naive approach all used as vectors will lead unacceptable large computational loads, hence a reduced of should be intelligently selected....
Recent large-scale undertakings such as ENCODE and Roadmap Epigenomics have generated experimental data mapped to the human reference genome (as genomic tracks) representing a variety of functional elements across large number cell types. Despite high potential value these publicly available for broad investigations, little attention has been given analytical methodology necessary their widespread utilisation.
Abstract This paper tests two data-driven approaches for predicting the state of health (SOH) lithium-ion-batteries (LIBs) purpose monitoring maritime battery systems. First, non-sequential are investigated and various models tested: ridge, lasso, support vector regression, gradient boosted trees. Binning is proposed feature engineering these types to capture temporal structure in data. Such binning creates histograms accumulated time LIB has been within voltage, temperature, current ranges....
The study of chromatin 3D structure has recently gained much focus owing to novel techniques for detecting genome-wide contacts using next-generation sequencing. A deeper understanding the architecture DNA inside nucleus is crucial gaining insight into fundamental processes such as transcriptional regulation, genome dynamics and stability. Chromatin conformation capture-based methods, Hi-C ChIA-PET, are now paving way routine studies in a range organisms tissues. However, appropriate methods...
It has been proposed that future reference genomes should be graph structures in order to better represent the sequence diversity present a species. However, there is currently no standard method genomic intervals, such as positions of genes or transcription factor binding sites, on graph-based genomes. We formalize offset-based coordinate systems and introduce methods for representing intervals these structures. show advantage our by representation newest assembly human genome (GRCh38) its...
Abstract Classical smoothers have limited usefulness in image processing, because sharp "edges" tend to be blurred. There is a literature on edge-preserving smoothers, but these all require moderately large "smooth stretches." Here we discuss an approach this problem called "sigma filtering" and propose improvement based running M estimation. Both computational theoretical aspects are developed. For the methods niche between standard filtering approaches Bayes–Markov random-field analysis....
In this paper we present an application of sensor-based anomaly detection in maritime transport. The study is based on real sensor data streamed from a ship to shore, where the analysed through big analytics platform. novelty work originates use sensors covering different aspects operation, exemplified here by propulsion power, speed over ground and motion four degrees freedom. developed method employs Auto Associative Kernel Regression (AAKR) for signal reconstruction, Sequential...