A5043185295- Statistical Methods and Inference
- Financial Risk and Volatility Modeling
- Advanced Statistical Methods and Models
- Gene expression and cancer classification
- Neural Networks and Applications
- Cancer, Lipids, and Metabolism
- Statistical Methods and Bayesian Inference
- Gene Regulatory Network Analysis
- Bioinformatics and Genomic Networks
- Imbalanced Data Classification Techniques
- Rough Sets and Fuzzy Logic
- Cell death mechanisms and regulation
- Stochastic processes and financial applications
- Probability and Risk Models
- Spectroscopy and Chemometric Analyses
- Time Series Analysis and Forecasting
- Material Science and Thermodynamics
- Cancer, Hypoxia, and Metabolism
- Statistical and numerical algorithms
- Advanced Statistical Process Monitoring
- Advanced Scientific Research Methods
- Morphological variations and asymmetry
- Machine Learning and Data Classification
- Anomaly Detection Techniques and Applications
- Bayesian Methods and Mixture Models
Wrocław University of Science and Technology
2006-2024
AGH University of Krakow
2024
Institute of Mathematics
2006-2023
University of Toronto
2006
Cancer radiotherapy (RT) induces response of the whole patient’s body that could be detected at blood level. We aimed to identify changes induced in serum lipidome during RT and characterize their association with doses volumes irradiated tissue. Sixty-six patients treated conformal because head neck cancer were enrolled study. Blood samples collected before, about one month after end RT. Lipid extracts analyzed using MALDI-oa-ToF mass spectrometry positive ionization mode. The major...
In this paper we consider a general framework for clustering expression data that permits integration of various biological sources through combination corresponding dissimilarity measures. the briefly review currently published attempts to genomic fusion and discuss problem validating results from data. We apply our approach real microarray dataset which induces correlation-based matrix, use gene ontology - process annotations derive GO-based matrix. The proposed procedure is verified using...
While clustering genes remains one of the most popular exploratory tools for expression data, it often results in a highly variable and biologically uninformative clusters. This paper explores data fusion approach to microarray data. Our method, which combined Gene Ontology (GO)-derived information, is applied on real set perform genome-wide clustering. A novel proposed validate pick fair value infusion coefficient. These measure stability, biological relevance, distance from expression-only...
Summary We discuss two novel approaches to inter‐distributional comparisons in the classical two‐sample problem. Our starting point is properly standardised and combined, very popular several areas of statistics data analysis, ordinal dominance receiver characteristic curves, denoted by ODC ROC, respectively. The proposed new curves are termed comparison curves. Their estimates, being weighted rank processes on (0,1), form basis inference. These intuitive, well‐suited for visual inspection...
In the article, we consider construction of prediction intervals for stationary time series using Bühlmann's [8], [9] sieve bootstrap approach.Basic theoretical properties concerning consistency are proved.We extend results obtained earlier by Stine [21], Masarotto and Grigoletto [13] an autoregressive finite order to rich class linear invertible models.Finite sample performance constructed is investigated computer simulations.
This work explores the use of gradient boosting in context classification. Four popular implementations, including original GBM algorithm and selected state-of-the-art frameworks (i.e. XGBoost, LightGBM CatBoost), have been thoroughly compared on several publicly available real-world datasets sufficient diversity. In study, special emphasis was placed hyperparameter optimization, specifically comparing two tuning strategies, i.e. randomized search Bayesian optimization using Tree-stuctured...
We discuss two novel approaches to the classical two-sample problem. Our starting point are properly standardized and combined, very popular in several areas of statistics data analysis, ordinal dominance receiver characteristic curves, denoted by ODC ROC, respectively. The proposed new curves termed comparison curves. Their estimates, being weighted rank processes on (0,1), form basis inference. These intuitive, well-suited for visual inspection at hand, also useful constructing some formal...
The main focus of our paper is to compare the performance different model selection criteria used for multivariate reduced rank time series. We consider one most commonly model, that is, vector autoregression (RRVAR (p, r)) introduced by Velu et al. [Reduced models multiple Biometrika. 1986;7(31):105–118]. In study, popular are included. divided into two groups, simultaneous and two-step criteria, accordingly. Methods from former group select both an autoregressive order p a r...
A histogram sieve estimator of the drift function in Ito processes and some semimartingales is constructed. It proved that pointwise $L^{1}$ consistent its finite-dimensional distributions are asymptotically normal. Our approac
In the paper, construction of unconditional bootstrap prediction intervals and regions for some class second order stationary multivariate linear time series models is considered. Our approach uses sieve procedure introduced by Kreiss 1992 Bühlmann 1997. Basic theoretical results concerning consistency replications are proved. We present a simulation study comparing proposed methods with Box–Jenkins approach.