datasets
Dotaz
Zobrazit nápovědu
Registration of laser scans, or point clouds in general, is a crucial step of localization and mapping with mobile robots or in object modeling pipelines. A coarse alignment of the point clouds is generally needed before applying local methods such as the Iterative Closest Point (ICP) algorithm. We propose a feature-based approach to point cloud registration and evaluate the proposed method and its individual components on challenging real-world datasets. For a moderate overlap between the laser scans, the method provides a superior registration accuracy compared to state-of-the-art methods including Generalized ICP, 3D Normal-Distribution Transform, Fast Point-Feature Histograms, and 4-Points Congruent Sets. Compared to the surface normals, the points as the underlying features yield higher performance in both keypoint detection and establishing local reference frames. Moreover, sign disambiguation of the basis vectors proves to be an important aspect in creating repeatable local reference frames. A novel method for sign disambiguation is proposed which yields highly repeatable reference frames.
- MeSH
- algoritmy MeSH
- datové soubory jako téma * MeSH
- robotika MeSH
- Publikační typ
- časopisecké články MeSH
Functional connectivity analysis of resting-state fMRI data has recently become one of the most common approaches to characterizing individual brain function. It has been widely suggested that the functional connectivity matrix is a useful approximate representation of the brain's connectivity, potentially providing behaviorally or clinically relevant markers. However, functional connectivity estimates are known to be detrimentally affected by various artifacts, including those due to in-scanner head motion. Moreover, as individual functional connections generally covary only very weakly with head motion estimates, motion influence is difficult to quantify robustly, and prone to be neglected in practice. Although the use of individual estimates of head motion, or group-level correlation of motion and functional connectivity has been suggested, a sufficiently sensitive measure of individual functional connectivity quality has not yet been established. We propose a new intuitive summary index, Typicality of Functional Connectivity, to capture deviations from standard brain functional connectivity patterns. In a resting-state fMRI dataset of 245 healthy subjects, this measure was significantly correlated with individual head motion metrics. The results were further robustly reproduced across atlas granularity, preprocessing options, and other datasets, including 1,081 subjects from the Human Connectome Project. In principle, Typicality of Functional Connectivity should be sensitive also to other types of artifacts, processing errors, and possibly also brain pathology, allowing extensive use in data quality screening and quantification in functional connectivity studies as well as methodological investigations.
- MeSH
- artefakty MeSH
- atlasy jako téma * MeSH
- datové soubory jako téma * MeSH
- dospělí MeSH
- hlava - pohyby MeSH
- konektom * metody normy MeSH
- lidé MeSH
- magnetická rezonanční tomografie * metody normy MeSH
- mladý dospělý MeSH
- mozek diagnostické zobrazování fyziologie MeSH
- počítačové zpracování obrazu * metody normy MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
This paper introduces a new Czech Political Candidate Dataset (CPCD), which compiles comprehensive data on all candidates who have run in any municipal, regional, national, and/or European Parliament election in the Czech Republic since 1993. For each candidate, the CPCD includes their first name, last name, age, gender, place of residence, university degree, party membership, party affiliation, ballot position, and election results for candidates and for parties. We match candidates over various elections by using algorithms that rely on their personal information. We add information on political donations made to political parties. We source donation information from the Czech Political Donation Dataset (CPDD), our other newly built dataset, in which we compile records of individual donations to 12 leading political parties from official records for the period from 2017 to 2023. CPDD is publicly available along with the CPCD.
- MeSH
- lidé MeSH
- politika * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- dataset MeSH
- Geografické názvy
- Česká republika MeSH
BACKGROUND: Recently, deep neural networks have been successfully applied in many biological fields. In 2020, a deep learning model AlphaFold won the protein folding competition with predicted structures within the error tolerance of experimental methods. However, this solution to the most prominent bioinformatic challenge of the past 50 years has been possible only thanks to a carefully curated benchmark of experimentally predicted protein structures. In Genomics, we have similar challenges (annotation of genomes and identification of functional elements) but currently, we lack benchmarks similar to protein folding competition. RESULTS: Here we present a collection of curated and easily accessible sequence classification datasets in the field of genomics. The proposed collection is based on a combination of novel datasets constructed from the mining of publicly available databases and existing datasets obtained from published articles. The collection currently contains nine datasets that focus on regulatory elements (promoters, enhancers, open chromatin region) from three model organisms: human, mouse, and roundworm. A simple convolution neural network is also included in a repository and can be used as a baseline model. Benchmarks and the baseline model are distributed as the Python package 'genomic-benchmarks', and the code is available at https://github.com/ML-Bioinfo-CEITEC/genomic_benchmarks . CONCLUSIONS: Deep learning techniques revolutionized many biological fields but mainly thanks to the carefully curated benchmarks. For the field of Genomics, we propose a collection of benchmark datasets for the classification of genomic sequences with an interface for the most commonly used deep learning libraries, implementation of the simple neural network and a training framework that can be used as a starting point for future research. The main aim of this effort is to create a repository for shared datasets that will make machine learning for genomics more comparable and reproducible while reducing the overhead of researchers who want to enter the field, leading to healthy competition and new discoveries.
Omics-based methods are increasingly used in current ecotoxicology. Therefore, a large number of observations for various toxic substances and organisms are available and may be used for identifying modes of action, adverse outcome pathways, or novel biomarkers. For these purposes, good statistical analysis of toxicogenomic data is vital. In contrast to established ecotoxicological techniques, concentration-response modeling is rarely used for large datasets. Instead, statistical hypothesis testing is prevalent, which provides only a limited scope for inference. The present study therefore applied automated concentration-response modeling for 3 different ecotoxicotranscriptomic and ecotoxicometabolomic datasets. The modeling process was performed by simultaneously applying 9 different regression models, representing distinct mechanistic, toxicological, and statistical ideas that result in different curve shapes. The best-fitting models were selected by using Akaike's information criterion. The linear and exponential models represented the best data description for more than 50% of responses. Models generating U-shaped curves were frequently selected for transcriptomic signals (30%), and sigmoid models were identified as best fit for many metabolomic signals (21%). Thus, selecting the models from an array of different types seems appropriate, because concentration-response functions may vary because of the observed response type, and they also depend on the compound, the organism, and the investigated concentration and exposure duration range. The application of concentration-response models can help to further tap the potential of omics data and is a necessary step for quantitative mixture effect assessment at the molecular response level.
- MeSH
- dánio pruhované růst a vývoj metabolismus MeSH
- ekosystém * MeSH
- embryo nesavčí účinky léků metabolismus MeSH
- genomika * MeSH
- látky znečišťující životní prostředí toxicita MeSH
- lineární modely MeSH
- metabolomika * MeSH
- rychlé screeningové testy MeSH
- sekvenční analýza hybridizací s uspořádaným souborem oligonukleotidů MeSH
- tetrachlorethylen toxicita MeSH
- transkriptom účinky léků MeSH
- zvířata MeSH
- Check Tag
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
BACKGROUND: The event-related potentials technique is widely used in cognitive neuroscience research. The P300 waveform has been explored in many research articles because of its wide applications, such as lie detection or brain-computer interfaces (BCI). However, very few datasets are publicly available. Therefore, most researchers use only their private datasets for their analysis. This leads to minimally comparable results, particularly in brain-computer research interfaces. Here we present electroencephalography/event-related potentials (EEG/ERP) data. The data were obtained from 20 healthy subjects and was acquired using an odd-ball hardware stimulator. The visual stimulation was based on a three-stimulus paradigm and included target, non-target and distracter stimuli. The data and collected metadata are shared in the EEG/ERP Portal. FINDINGS: The paper also describes the process and validation results of the presented data. The data were validated using two different methods. The first method evaluated the data by measuring the percentage of artifacts. The second method tested if the expectation of the experimental results was fulfilled (i.e., if the target trials contained the P300 component). The validation proved that most datasets were suitable for subsequent analysis. CONCLUSIONS: The presented datasets together with their metadata provide researchers with an opportunity to study the P300 component from different perspectives. Furthermore, they can be used for BCI research.
- Publikační typ
- časopisecké články MeSH
At the time of the COVID-19 pandemic, providing access to data (properly optimised regarding personal data protection) plays a crucial role in providing the general public and media with up-to-date information. Open datasets also represent one of the means for evaluation of the pandemic on a global level. The primary aim of this paper is to describe the methodological and technical framework for publishing datasets describing characteristics related to the COVID-19 epidemic in the Czech Republic (epidemiology, hospital-based care, vaccination), including the use of these datasets in practice. Practical aspects and experience with data sharing are discussed. As a reaction to the epidemic situation, a new portal COVID-19: Current Situation in the Czech Republic (https://onemocneni-aktualne.mzcr.cz/covid-19) was developed and launched in March 2020 to provide a fully-fledged and trustworthy source of information for the public and media. The portal also contains a section for the publication of (i) public open datasets available for download in CSV and JSON formats and (ii) authorised-access-only section where the authorised persons can (through an online generated token) safely visualise or download regional datasets with aggregated data at the level of the individual municipalities and regions. The data are also provided to the local open data catalogue (covering only open data on healthcare, provided by the Ministry of Health) and to the National Catalogue of Open Data (covering all open data sets, provided by various authorities/publishers, and harversting all data from local catalogues). The datasets have been published in various authentication regimes and widely used by general public, scientists, public authorities and decision-makers. The total number of API calls since its launch in March 2020 to 15 December 2020 exceeded 13 million. The datasets have been adopted as an official and guaranteed source for outputs of third parties, including public authorities, non-governmental organisations, scientists and online news portals. Datasets currently published as open data meet the 3-star open data requirements, which makes them machine-readable and facilitates their further usage without restrictions. This is essential for making the data more easily understandable and usable for data consumers. In conjunction with the strategy of the MH in the field of data opening, additional datasets meeting the already implemented standards will be also released, both on COVID-19 related and unrelated topics.
- MeSH
- COVID-19 * epidemiologie MeSH
- lidé MeSH
- pandemie prevence a kontrola MeSH
- SARS-CoV-2 MeSH
- šíření informací MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Geografické názvy
- Česká republika MeSH
Feature selection is a significant part of many machine learning applications dealing with small-sample and high-dimensional data. Choosing the most important features is an essential step for knowledge discovery in many areas of biomedical informatics. The increased popularity of feature selection methods and their frequent utilisation raise challenging new questions about the interpretability and stability of feature selection techniques. In this study, we compared the behaviour of ten state-of-the-art filter methods for feature selection in terms of their stability, similarity, and influence on prediction performance. All of the experiments were conducted on eight two-class datasets from biomedical areas. While entropy-based feature selection appears to be the most stable, the feature selection techniques yielding the highest prediction performance are minimum redundance maximum relevance method and feature selection based on Bhattacharyya distance. In general, univariate feature selection techniques perform similarly to or even better than more complex multivariate feature selection techniques with high-dimensional datasets. However, with more complex and smaller datasets multivariate methods slightly outperform univariate techniques.
- MeSH
- algoritmy MeSH
- databáze faktografické MeSH
- lidé MeSH
- multivariační analýza MeSH
- Parkinsonova nemoc diagnóza MeSH
- sekvenční analýza hybridizací s uspořádaným souborem oligonukleotidů metody MeSH
- software MeSH
- statistické modely MeSH
- výpočetní biologie metody MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- srovnávací studie MeSH
2 CD-ROMy
