Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "random forest" wg kryterium: Temat


Tytuł:
Surrogate modeling for selected pharmacokinetic endpoints
Modelowanie surogatywne dla wybranych farmakokinetycznych punktów końcowych
Autorzy:
Berny, Kornelia
Opis:
Obliczenia parametrów farmakokinetycznych są obecnie wykonywane za pomocą symulacji komputerowych, które wykorzystują zaawansowane modele do dokładnego opisu procesów zachodzących w żywych organizmach. Modelowanie surogatywne stało się użytecznym narzędziem, które może znacznie uprościć obliczenia, ponieważ zaawansowane modele, składające się z dużej liczby skomplikowanych równań matematycznych, wymagają dużej mocy obliczeniowej a ich czas obliczeniowy jest długi. Ważnym aspektem jest również możliwość interpretacji modelu, aby możliwe było jego ponowne wykorzystanie. W poniższej pracy zastosowano trzy techniki modelowania surogatywnego: Cubist, random Forest oraz sieć neuronową MONMLP. Wszystkie te systemy są w stanie wykonywać obliczenia nawet przy użyciu obszernej bazy danych, są powszechnie dostępne i nie wymagają dużej mocy obliczeniowej. Modele, które zostały wcześniej odpowiednio przeszkolone przy użyciu walidacji krzyżowej, zostały wykorzystane do przewidywania wartości parametrów farmakokinetycznych i porównywania ich z rzeczywistymi wynikami uzyskanymi z oryginalnego modelu. Modele zastępcze wykazywały ogromny potencjał, zwłaszcza gdy były wdrażane w postaci wielopoziomowych zespołów/komitetów eksperckich. Opłacalność obliczeniowa modeli zastępczych została potwierdzona poprzez uzyskanie poprawy wielkości czasu przetwarzania o wynik dwóch rzędów.
Calculations of pharmacokinetic parameters nowadays are performed by computer simulations, which are using advanced models to describe accurately processes that take place in live organisms. Surrogate modeling has become a useful tool which can significantly simplify the calculations, because the advanced models, consisting of a large number of complex mathematical equations require high computing power and their computational time is long. An important aspect is also the interpretability of the model so that it can be reused. In the following work, three surrogate modeling techniques were used: Cubist, random Forest and the MONMLP neural network. All these systems are able to perform calculations even with the use of a large database, are freely available and do not require substantial computational power. Models that had been properly trained using cross-validation were used to predict pharmacokinetic parameters and compared to actual results derived from the original model. Surrogate models showed great potential, especially when implemented in the form of the multi-level ensembles/expert committees. Computational cost-efficiency of the surrogate models was confirmed resulting in the two orders of magnitude improvement of the processing time.
Dostawca treści:
Repozytorium Uniwersytetu Jagiellońskiego
Inne
Tytuł:
Impacts of forest spatial structure on variation of the multipath phenomenon of navigation satellite signals
Autorzy:
Brach, Michał
Stereńczak, Krzysztof
Bolibok, Leszek
Kwaśny, Łukasz
Krok, Grzegorz
Laszkowski, Michał
Tematy:
GNSS
multipath
random forest
Borut
forest structure
LiDAR
Pokaż więcej
Wydawca:
Instytut Badawczy Leśnictwa
Powiązania:
https://bibliotekanauki.pl/articles/2044153.pdf  Link otwiera się w nowym oknie
Opis:
The GNSS (Global Navigation Satellite System) receivers are commonly used in forest management in order to determine objects coordinates, area or length assessment and many other tasks which need accurate positioning. Unfortunately, the forest structure strongly limits access to satellite signals, which makes the positioning accuracy much weak comparing to the open areas. The main reason for this issue is the multipath phenomenon of satellite signal. It causes radio waves reflections from surrounding obstacles so the signal do not reach directly to the GNSS receiver’s antenna. Around 50% of error in GNSS positioning in the forest is because of multipath effect. In this research study, an attempt was made to quantify the forest stand features that may influence the multipath variability. The ground truth data was collected in six Forest Districts located in different part of Poland. The total amount of data was processed for over 2,700 study inventory plots with performed GNSS measurements. On every plot over 25 forest metrics were calculated and over 25 minutes of raw GNSS observations (1500 epochs) were captured. The main goal of this study was to find the way of multipath quantification and search the relationship between multipath variability and forest structure. It was reported that forest stand merchantable volume is the most important factor which influence the multipath phenomenon. Even though the similar geodetic class GNSS receivers were used it was observed significant difference of multipath values in similar conditions.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Impacts of forest spatial structure on variation of the multipath phenomenon of navigation satellite signals
Autorzy:
Brach, Michał
Laszkowski, Michał
Bolibok, Leszek
Stereńczak, Krzysztof
Kwaśny, Łukasz
Krok, Grzegorz
Wydawca:
The Committee on Forestry Sciences and Wood Technology of the Polish Academy of Sciences and the Forest Research Institute in Sekocin Stary
Cytata wydawnicza:
Brach, Michał & Stereńczak, Krzysztof & Bolibok, Leszek & Kwaśny, Łukasz & Krok, Grzegorz & Laszkowski, Michał. (2019). Impacts of forest spatial structure on variation of the multipath phenomenon of navigation satellite signals. Folia Forestalia Polonica, Series A. 51. 3-21. 10.2478/ffp-2019-0001.
Opis:
The GNSS (Global Navigation Satellite System) receivers are commonly used in forest management in order to determine objects coordinates, area or length assessment and many other tasks which need accurate positioning. Unfortunately, the forest structure strongly limits access to satellite signals, which makes the positioning accuracy much weak comparing to the open areas. The main reason for this issue is the multipath phenomenon of satellite signal. It causes radio waves reflections from surrounding obstacles so the signal do not reach directly to the GNSS receiver’s antenna. Around 50% of error in GNSS positioning in the forest is because of multipath effect. In this research study, an attempt was made to quantify the forest stand features that may influence the multipath variability. The ground truth data was collected in six Forest Districts located in different part of Poland. The total amount of data was processed for over 2,700 study inventory plots with performed GNSS measurements. On every plot over 25 forest metrics were calculated and over 25 minutes of raw GNSS observations (1500 epochs) were captured. The main goal of this study was to find the way of multipath quantification and search the relationship between multipath variability and forest structure. It was reported that forest stand merchantable volume is the most important factor which influence the multipath phenomenon. Even though the similar geodetic class GNSS receivers were used it was observed significant difference of multipath values in similar conditions.
Dostawca treści:
Repozytorium Centrum Otwartej Nauki
Artykuł
Tytuł:
Predicting immunogenicity in murine hosts with use of Random Forest classifier
Przewidywanie immunogenności u myszy przy użyciu klasyfikatora Random Forest
Autorzy:
Marciniak, Anna
Tarczewska, Martyna
Kloska, Sylwester
Tematy:
Random Forest Classifier
immunogenicity
machine learning
entropy
Gini index
klasyfikator Random Forest
immunogenność
uczenie maszynowe
entropia
Pokaż więcej
Wydawca:
Politechnika Bydgoska im. Jana i Jędrzeja Śniadeckich. Wydawnictwo PB
Powiązania:
https://bibliotekanauki.pl/articles/2016293.pdf  Link otwiera się w nowym oknie
Opis:
Biomedical data are difficult to interpret due to their large amount. One of the solutions to cope with this problem is to use machine learning. Machine learning can be used to capture previously unnoticed dependencies. The authors performed random forest classifier with entropy and Gini index criteria on immunogenicity data. Input data consisted of 3 columns: epitope (8-11 amino acids long peptide), major histocompatibility complex (MHC) and immune response. Presented model can predict the immune response based on epitope-MHC complex. Achieved results had accuracy of 84% for entropy and 83% for Gini index. The results are not fully satisfying but are a fair start for more complexed experiments and could be used as an indicator for further research.
Dane biomedyczne są trudne do interpretacji ze względu na ich dużą ilość. Jednym z rozwiązań radzenia sobie z tym problemem jest wykorzystanie uczenia maszynowego. Techniki te umożliwiają wychwycenie wcześniej niezauważonych zależności. W artykule przedstawiono wykorzystanie klasyfikatora Random Forest z kryterium entropii i indeksem Gini na danych dotyczących immunogenności. Dane wejściowe składają się z 3 kolumn: epitop (peptyd o długości 8-11 aminokwasów), główny kompleks zgodności tkankowej (MHC) i odpowiedź immunologiczna. Zaprezentowany model przewiduje odpowiedź immunologiczną na podstawie kompleksu epitop-MHC. Uzyskane wyniki osiągnęły dokładność na poziomie 84% (entropia) i 83% (indeks Gini). Wyniki nie są w pełni satysfakcjonujące, ale stanowią dobry początek dla bardziej złożonych eksperymentów i wyznacznik do dalszych badań.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Assessing the efficiency of a random forest regression model for estimating water quality indicators
Autorzy:
Zavareh, Maryam
Maggioni, Viviana
Zhang, Xinxuan
Tematy:
Random Forest
water quality
hydrometeorological information
Pokaż więcej
Wydawca:
Instytut Meteorologii i Gospodarki Wodnej - Państwowy Instytut Badawczy
Powiązania:
https://bibliotekanauki.pl/articles/27810498.pdf  Link otwiera się w nowym oknie
Opis:
This work evaluates the efficiency of Random Forest (RF) regression for predicting water quality indicators and investigates factors affecting water quality in 11 watersheds in Virginia, District of Columbia, and Maryland. Ten years of daily water quality data along with hydro-meteorological information (such as precipitation) and watershed physiology and characteristics (e.g., size, soil type, land use) are used to predict dissolved oxygen (DO), specific conductivity (K), and turbidity (Tu) across the selected watersheds. The RF regression model is developed for six scenarios, with an increasing number of predictors introduced in each scenario. The first scenario contains the smallest amount of information (water quality indicators DO, K and Tu), while scenario 6 contains all the available variables. The RF model is evaluated based on three statistical metrics: the relative root mean square error, the correlation coefficient, and the percentage of variance explained. In addition, the degree of importance for each predictor is used to rank their importance within each scenario. The model shows excellent performance for DO as the predicted variable. The model predicting K slightly outperforms the one predicting Tu. Scenario 4 (built based on water quality indicators, hydro-meteorological data, watershed physiology and land cover information) provided the best tradeoff between performance and efficiency (quantified in terms of the amount of information needed to develop the model). In conclusion, based on the RF model, land cover plays a significant role in predicting water quality indicators. In addition, the developed RF regression model is adaptable to watersheds in this region over a range of climates.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Classification of Seizure Types Using Random Forest Classifier
Autorzy:
Basri, Ashjan
Arif, Muhammad
Tematy:
EEG
fast fourier transform
seizure
random forest
Pokaż więcej
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Powiązania:
https://bibliotekanauki.pl/articles/2123290.pdf  Link otwiera się w nowym oknie
Opis:
Epilepsy is one of the most common mental disorders in the world, affecting 65 million people. The prevalence in Arab countries of Epilepsy is estimated at 174 per 100,000 individuals, and in Saudi Arabia is 6.54 per 1,000 individuals. Epilepsy seizures have different types, and each patient needs to have a treatment plan according to the seizure type. Hence, accurate classification of seizure type is an essential part of diagnosing and treating epileptic patients. In this paper, features based on fast Fourier transform from EEG montages are used to classify different types of seizures. Since the distribution of classes is not uniform and the dataset suffers from severe imbalance. Various algorithms are used to under-sample the majority class and over-sample the minority classes. Random forest classifier produced classification accuracy of 96% to differentiate three types of seizures from the healthy EEG reading.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A novel drift detection algorithm based on features’ importance analysis in a data streams environment
Autorzy:
Duda, Piotr
Przybyszewski, Krzysztof
Wang, Lipo
Tematy:
data stream mining
random forest
features importance
Pokaż więcej
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Powiązania:
https://bibliotekanauki.pl/articles/1837417.pdf  Link otwiera się w nowym oknie
Opis:
The training set consists of many features that influence the classifier in different degrees. Choosing the most important features and rejecting those that do not carry relevant information is of great importance to the operating of the learned model. In the case of data streams, the importance of the features may additionally change over time. Such changes affect the performance of the classifier but can also be an important indicator of occurring concept-drift. In this work, we propose a new algorithm for data streams classification, called Random Forest with Features Importance (RFFI), which uses the measure of features importance as a drift detector. The RFFT algorithm implements solutions inspired by the Random Forest algorithm to the data stream scenarios. The proposed algorithm combines the ability of ensemble methods for handling slow changes in a data stream with a new method for detecting concept drift occurrence. The work contains an experimental analysis of the proposed algorithm, carried out on synthetic and real data.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Application of the Random Forest Model to Predict the Plasticity State of Vertisols
Autorzy:
Al Masmoudi, Yassine
Bouslihim, Yassine
Doumali, Kaoutar
El Aissaoui, Abdellah
Namr, Khalid Ibno
Tematy:
soil plasticity
random forest
moroccan vertisol
soil degradation
Pokaż więcej
Wydawca:
Polskie Towarzystwo Inżynierii Ekologicznej
Powiązania:
https://bibliotekanauki.pl/articles/1839081.pdf  Link otwiera się w nowym oknie
Opis:
Vertisol plasticity is related to moisture content, and it requires an in-depth physicochemical characterization. This information allows us to use the land under the most adequate conditions and avoid soil physical degradation, especially its compaction. The objective of this study was to characterize the Vertisol in the Moroccan region of Doukkala-Abda and to predict soil plasticity based on the physicochemical parameters of soil, such as texture, electrical conductivity, Soil Organic Matter (SOM) and other chemical parameters for 120 samples. Determination of soil plasticity using Atterberg limits is a challenging and time-consuming method. Thus, this study aimed to develop a new model that can predict soil plasticity using the Random Forest algorithm. The soils presented homogeneity in the majority of physicochemical parameters, except a significant difference observed in the SOM and the electrical conductivity, which in turn influenced the soil plasticity state. The results showed significant and positive correlations between SOM, Soil Clay Content (SCC), Electrical Conductivity (EC), and plasticity in the Vertisol fields of the region. For the training phase, the model gave excellent results with a coefficient of determination of 0.995 and an RMSE of 0.164. Almost the same results were observed in the validation phase with a coefficient of determination of 0.974 and an RMSE of 0.361, which shows that the model succeeded in predicting plasticity in both phases. On the basis of these results, this model can be used for the plasticity prediction using other physicochemical parameters and the Random Forest Model. The prediction of soil plasticity is an important parameter to respect the timing of introducing machines/tools in the fields and avoid Vertisol degradation.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
EQUITY ISSUANCE AND CORPORATE DIVIDEND POLICY IN EMERGING ECONOMY CONTEXT
Autorzy:
Rohov, Heorhiy
Solesvik, Marina Z.
Tematy:
dividend policy
emission policy
random forest algorithm
Ukraine
Pokaż więcej
Wydawca:
Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Katedra Ekonometrii i Statystyki
Powiązania:
https://bibliotekanauki.pl/articles/453403.pdf  Link otwiera się w nowym oknie
Opis:
This article explores links between the size of a company, industrial sector in which a company operates, concentration of capital, size of business and emission and dividend policy in the Ukrainian corporate sector. Guided by insights from the bird-in-hand theory, clientele theory, signaling theory, and agency theory, we justify factors that determine the choice of shares’ placement by Ukrainian public joint stock companies and forming of their dividend policy related to the current operating conditions of the Ukrainian corporate sector. Using mathematical approach of tree classification construction in the form of random forest algorithm, we found out that maximization of the share capital value, that is involved in shares issuance of Ukrainian PJSCs, is not a priority for owners of corporate rights. 86.1 per cent of companies have selected private placements of shares. In the non-financial sector, 87.5 per cent of companies opted private placements. The study revealed also only a small share (3.5%) of Ukrainian joint stock companies paid dividends to shareholders. However, the dividend policy of Ukrainian joint stock companies changed when they listed their shares on foreign stock markets. In this case two thirds of explored firms paid dividends.
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Machine learning-based front detection in Central Europe
Autorzy:
Ustrnul, Zbigniew
Kubacka, Danuta
Bochenek, Bogdan
Wypych, Agnieszka
Opis:
Extreme weather phenomena such as wind gusts, heavy precipitation, hail, thunderstorms, tornadoes, and many others usually occur when there is a change in air mass and the passing of a weather front over a certain region. The climatology of weather fronts is difficult, since they are usually drawn onto maps manually by forecasters; therefore, the data concerning them are limited and the process itself is very subjective in nature. In this article, we propose an objective method for determining the position of weather fronts based on the random forest machine learning technique, digitized fronts from the DWD database, and ERA5 meteorological reanalysis. Several aspects leading to the improvement of scores are presented, such as adding new fields or dates to the training database or using the gradients of fields.
Dostawca treści:
Repozytorium Uniwersytetu Jagiellońskiego
Artykuł

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies