Filtry
wszystkich: 11217
wybranych: 9232
-
Katalog
- Publikacje 9232 wyników po odfiltrowaniu
- Czasopisma 336 wyników po odfiltrowaniu
- Konferencje 82 wyników po odfiltrowaniu
- Osoby 194 wyników po odfiltrowaniu
- Projekty 17 wyników po odfiltrowaniu
- Laboratoria 1 wyników po odfiltrowaniu
- Zespoły Badawcze 1 wyników po odfiltrowaniu
- Kursy Online 183 wyników po odfiltrowaniu
- Wydarzenia 11 wyników po odfiltrowaniu
- Dane Badawcze 1160 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: —TRANSFER LEARNING, DEEP LEARNING, PROTEIN STRUCTURE, FUNCTION, AND INTERACTION PREDICTION, SEQUENCE MODELLING
-
Modular machine learning system for training object detection algorithms on a supercomputer
PublikacjaW pracy zaprezentowano architekturę systemu służącego do tworzenia algorytmów wykorzystujących metodę AdaBoost i służących do wykrywania obiektów (np. twarzy) na obrazach. System został podzielony na wyspecjalizowane moduły w celu umożliwienia łatwej rozbudowy i efektywnego zrównoleglenia implementacji przeznaczonej dla superkomputera. Na przykład, system może być rozszerzony o nowe cechy i algorytmy ich ekstrakcji bez konieczności...
-
Learning from Imbalanced Data Using Over-Sampling and the Firefly Algorithm
Publikacja -
Efficient sampling of high-energy states by machine learning force fields
Publikacja -
Beesybees-Agent-Based, Adaptive & Learning Workflow Execution Module for BeesyCluster
PublikacjaPrezentujemy projekt oraz implementację adaptacyjnego i uczącego się modułu przeznaczonego dowykonywania scenariuszy w środowisku BeesyCluster. BeesyCluster pozwala na modelowaniescenariuszy w formie acyklicznego grafu skierowanego, w którym wierzchołki oznaczają zadania,a krawędzie określają zależności między nimi. Przedstawiamy także kooperatywne wykonaniescenariusza przez grupę agentów zdolnych do zbierania, składowania i korzystania...
-
Stacking and rotation-based technique for machine learning classification with data reduction
Publikacja -
Designing RBF Networks Using the Agent-Based Population Learning Algorithm
Publikacja -
The Role of Dopaminergic Genes in Probabilistic Reinforcement Learning in Schizophrenia Spectrum Disorders
Publikacja -
Confirmation Bias in the Course of Instructed Reinforcement Learning in Schizophrenia-Spectrum Disorders
Publikacja -
A Note on Knowledge Management Education: Towards Implementing Active Learning Methods
PublikacjaKnowledge Management as an area of education is still a big challenge for teachers and practitioners. Nevertheless, there are several useful teaching methods in active education, especially oriented towards courses where innovation and delivering dynamic knowledge are critical. The goal of the paper is to present and discuss criteria relevant in the selection of active educational methods supporting knowledge management courses....
-
Evaluation of aspiration problems in L2 English pronunciation employing machine learning
PublikacjaThe approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers’ pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones...
-
IT support for OKNO broadband Internet-based distant learning system at WUT
Publikacja -
Developing ICT-rich lifelong learning opportunities trough EU-projects.
PublikacjaArtykuł opisuje doświadczenia Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej od 1997 roku we wdrażaniu kształcenia na odległość. Głównym zadaniem CEN PG jest tworzenie dostępu do materiałów, skryptów, kursów i środowiska internetowego w sieciach LAN i WAN. Udostępniane moduły kursowe zostały opracowane głównie w międzynarodowych zespołach projektowych w wyniku realizowanych unijnych programów Leonardo da Vinci, Socrates...
-
Analysis of network infrastructure and QoS requirements for modern remote learning systems.
PublikacjaW referacie przedstawiono różne modele zdalnego nauczania. Podjęto próbę oceny wymagań nakładanych na infrastrukturę sieci. Ponadto przedstawiono mechanizmy QoS spotykane w sieciach teleinformatycznych oraz dokonano oceny możliwości ich współpracy w systemach edukacji zdalnej
-
E-learning - prawdziwa czy fikcyjna koncepcja edukacyjnego rozwoju uczelni
PublikacjaNie można zaprzeczyć, że wykorzystanie narzędzi multimedialnych oraz Internetu pozwala na dodanie istotnych, z punku widzenia dydaktyki, komponentów edukacyjnych tworzących kompetencje i umiejętności zawodowe, a także te czysto akademickie. Trzeba rozważyć, czy wszystkie strony procesu dydaktycznego na uczelni są przygotowane do e−learningu. Oczywistym wymogiem jest posiadanie odpowiedniej bazy sprzętowej i przygotowanej kadry...
-
The importance of the shape of the protein-water interface of a kinesin motor domain for dynamics of the surface atoms of the protein
PublikacjaSingle kinesin motor domain immersed in water has been investigated using molecular dynamics. It has been found that local properties of water in solvation shell change along with the nature of neighboring protein surface. However, a detailed analysis leads to the conclusion that the geometrical features of hydrogen bonds and overall structure of kinesin hydration water is not very different from bulk water. The local values of...
-
The importance of the shape of the protein–water interface of a kinesin motor domain for dynamics of the surface atoms of the protein
PublikacjaA single kinesin motor domain immersed in water has been investigated using molecular dynamics. It has been found that local properties of water in the solvation shell change along with the nature of the neighboring protein surface. However, a detailed analysis leads to the conclusion that the geometrical features of hydrogen bonds and overall structure of kinesin hydration water are not very different from bulk water. The local...
-
Intelligent Decision Forest Models for Customer Churn Prediction
PublikacjaCustomer churn is a critical issue impacting enterprises and organizations, particularly in the emerging and highly competitive telecommunications industry. It is important to researchers and industry analysts interested in projecting customer behavior to separate churn from non‐churn consumers. The fundamental incentive is a firm’s intent desire to keep current consumers, along with the exorbitant expense of gaining new ones....
-
Influence of soil–structure interaction on seismic pounding between steel frame buildings considering the effect of infill panels
PublikacjaThe present research aims to study the influence of the soil-structure interaction (SSI) and existence or absence of masonry infill panels in steel frame structures on the earthquake-induced pounding-involved response of adjacent buildings. The study was further extended to compare the pounding-involved behavior versus the independent behavior of structures without collisions, focusing much on dynamic behavior of single frames....
-
MutS3: a MutS homologue of unknown biological function
PublikacjaThe homologues of MutS proteins are widespread among both Prokaryotes and Eukaryotes. MutS designated as MutS1 is a part of MMR (mismatch repair) system which is responsible for removal of mispaired bases and small insertion/deletion loops in DNA. Initially, the only MutS homologues known were those engaged in mismatch repair and these were later designated as MutS1. Subsequently, the MutS2 homologue was distinguished. MutS2 does...
-
Modelling of Mechatronic Systems with Distributed Parameter Components
PublikacjaThe paper presents an uniform, port-based approach to modelling of both lumped and distributed parameter systems. Port-based model of distributed system has been defined by application of the bond graph methodology and the distributed transfer function method (DTFM). The proposed method of modelling enables to formulate input data for computer analysis by application of the DTFM. The computational package for the analysis of complex...
-
Synthesis, crystal structure and spectroscopic characterization of new anionic iridium(III) complexes and their interaction with biological targets
PublikacjaThe synthesis and characterisation of new anionic iridium(II) complexes (NH4)2[IrCl4(κ2N,N’-H2biim)]2 · 5H2O (1) and ((CH3)2NH2)[IrCl4(κ2N,N’-PyBIm)] · H2O (2) are presented in this article. Spectroscopic methods (1H, 13C and 15N NMR, FTIR, UV-Vis) were used to characterize these new complexes. Solid-state structural analysis (SC-XRD) of complexes 1 and 2 shows a slightly distorted octahedral geometry of Ir(III) ions, which is...
-
Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network
PublikacjaIn recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep...
-
Age Prediction from Low Resolution, Dual-Energy X-ray Images Using Convolutional Neural Networks
PublikacjaAge prediction from X-rays is an interesting research topic important for clinical applications such as biological maturity assessment. It is also useful in many other practical applications, including sports or forensic investigations for age verification purposes. Research on these issues is usually carried out using high-resolution X-ray scans of parts of the body, such as images of the hands or images of the chest. In this...
-
Forecasting energy consumption and carbon dioxide emission of Vietnam by prognostic models based on explainable machine learning and time series
PublikacjaThis study assessed the usefulness of algorithms in estimating energy consumption and carbon dioxide emissions in Viet- nam, in which the training dataset was used to train the models linear regression, random forest, XGBoost, and AdaBoost, allowing them to comprehend the patterns and relationships between population, GDP, and carbon dioxide emissions, energy consumption. The results revealed that random forest, XGBoost, and AdaBoost...
-
RESIDENTIAL FUNCTION IN MULTI-CRITERIA MULTIFUNCTIONAL BUILDING SYSTEM DESIGN PROCESS
PublikacjaThe paper presents the multi-criteria approach in the design process of residential structure as a part of a multifunctional building system. The purpose of work was to broaden the field of multifunctional building system design process. Background for the presented work is to define the direction of architectural growth of the modern city center area where actually are built complex and large capacity structures with a great impact...
-
t-SNE Highlights Phylogenetic and Temporal Patterns of SARS-CoV-2 Spike and Nucleocapsid Protein Evolution
PublikacjaWe propose applying t-distributed stochastic neighbor embedding to protein sequences of SARS-CoV-2 to construct, visualize and study the evolutionary space of the coronavirus. The basic idea is to explore the COVID-19 evolution space by using modern manifold learning techniques applied to evolutionary distances between variants. Evolutionary distances have been calculated based on the structures of the nucleocapsid and spike proteins.
-
The impact of the AC922 Architecture on Performance of Deep Neural Network Training
PublikacjaPractical deep learning applications require more and more computing power. New computing architectures emerge, specifically designed for the artificial intelligence applications, including the IBM Power System AC922. In this paper we confront an AC922 (8335-GTG) server equipped with 4 NVIDIA Volta V100 GPUs with selected deep neural network training applications, including four convolutional and one recurrent model. We report...
-
On the regularity of the displacement sequence of an orientation preserving circle homeomorphism
PublikacjaWe investigate the regularity properties of the displacemnet sequence of an orientation preserving circle homeomorphism. is rational, then ηn(z) is asymptotically periodic with semi-period q. This
-
Deep neural network architecture search using network morphism
PublikacjaThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Photoinduced electron transfer in 5-bromouracil labeled DNA. A contrathermodynamic mechanism revisited by electron transfer theories
PublikacjaThe understanding of the 5-bromouracil (BrU) based photosensitization mechanism of DNA damage is of large interest due to the potential applications in photodynamic therapy. Photoinduced electron transfer (ET) in BrU labeled duplexes comprising the 50 -GBrU or 50 -ABrU sequence showed that a much lower reactivity was found for the 50 -GBrU pattern. Since the ionization potential of G is lower than that of A, this sequence selectivity...
-
Free convective heat transfer structures as a function of the width of isothermal horizontal rectangular plates
PublikacjaZaprezentowano rezultaty badań eksperymentalnych konwekcyjnej wymiany ciepła od izotermicznych płyt prostokątnych skierowanych ku górze. Na podstawie przeprowadzonych wizualizacji zaproponowano dwa modele struktur przepływu. Rozwiązania analityczne dla tych modeli przedstawiono w postaci zależności liczb Nusselta Rayleigh'a. Stwierdzono, że przepływ koncentryczny występuje dla małych wartości liczb Ra, szczególnie w przypadku płyt...
-
Application of the fluid–structure interaction technique for the analysis of hydrodynamic lubrication problems
Publikacja -
Effects of Coulomb interaction on the electronic structure and lattice dynamics of the Mott insulatorFe2SiO4spinel
Publikacja -
Thermal-FSI modeling of flow and heat transfer in a heat exchangerbased on minichanels
PublikacjaIn this paper selected numerical modelling problems for an advanced thermal-FSI ("Fluid Solid Interaction") mini-channel heat exchanger model are presented. Special attention is given to the heat transfer between the separated mediums for different mass flows. Similar modelling problems have also been discussed in the literature dedicated to numerical and theoretical modelling problems for typical heat exchangers [1, 2, 3]. Basic...
-
Cloud solutions as a platform for building advanced learning platform, that stimulate the real work environment for project managers
PublikacjaImproving skills of managers and executives require, that during the transfer of knowledge (in different ways: during studies, trainings, workshops and other forms of education) it is necessary to use tools and solutions that are (or will be) used in real world environments, where people being educated are working or will work. Cloud solutions allow educational entities (universities, training companies, trainers, etc.) to provide...
-
Local basis function estimators for identification of nonstationary systems
PublikacjaThe problem of identification of a nonstationary stochastic system is considered and solved using local basis function approximation of system parameter trajectories. Unlike the classical basis function approach, which yields parameter estimates in the entire analysis interval, the proposed new identification procedure is operated in a sliding window mode and provides a sequence of point (rather than interval) estimates. It is...
-
Robust-adaptive dynamic programming-based time-delay control of autonomous ships under stochastic disturbances using an actor-critic learning algorithm
PublikacjaThis paper proposes a hybrid robust-adaptive learning-based control scheme based on Approximate Dynamic Programming (ADP) for the tracking control of autonomous ship maneuvering. We adopt a Time-Delay Control (TDC) approach, which is known as a simple, practical, model free and roughly robust strategy, combined with an Actor-Critic Approximate Dynamic Programming (ACADP) algorithm as an adaptive part in the proposed hybrid control...
-
Enhancing seismic performance of rigid and semi-rigid connections equipped with SMA bolts incorporating nonlinear soil-structure interaction
PublikacjaNowadays, using smart connections can improve the performance of buildings with some recentering features that are from the superelastic behavior of Shape Memory Alloys (SMAs). It seems that there is different rigidity between the designed connection and the real one in Steel Moment-Resisting Frames (SMRFs), which can be considered as a problematic issue due to the importance of connections in seismic performance assessment. This...
-
Investigation of interaction between xanthene dye rhodamine B and metagenomic-derivated methylthioadenosine phosphorylase RSFP
PublikacjaIn the previous study we found that the expression of the metagenomic - derived methylthioadenosine phosphorylase gene (rsfp) in E. coli cells and the presence of rhodamine B in the growth medium were crucial for the pink fluorescence of one E. coli colony from Antarctic soil metagenomic library (Cieśliński et al., 2009). In this study, rsfp gene expression was induced by an arabinose promoter in an LMG194 E. coli strain and the...
-
Fluid structure interaction study of non-Newtonian Casson fluid in a bifurcated channel having stenosis with elastic walls
PublikacjaFluid–structure interaction (FSI) gained a huge attention of scientists and researchers due to its applications in biomedical and mechanical engineering. One of the most important applications of FSI is to study the elastic wall behavior of stenotic arteries. Blood is the suspension of various cells characterized by shear thinning, yield stress, and viscoelastic qualities that can be assessed by using non-Newtonian models. In this...
-
Fluorescence resonance energy transfer usage to track the sequence promoter changes in CGB5 gene in ovarian cancer patients
Publikacja -
A DISCRETE-CONTINUOUS METHOD OF MECHANICAL SYSTEM MODELLING
PublikacjaThe paper describes a discrete-continuous method of dynamic system modelling. The presented approach is hybrid in its nature, as it combines the advantages of spatial discretization methods with those of continuous system modelling methods. In the proposed method, a three-dimensional system is discretised in two directions only, with the third direction remaining continuous. The thus obtained discrete-continuous model is described...
-
An automated learning model for twitter sentiment analysis using Ranger AdaBelief optimizer based Bidirectional Long Short Term Memory
PublikacjaSentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day-to-day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi-LSTM RAO)...
-
The modelling method of discrete-continuous systems
PublikacjaThe paper introduces a method of discrete-continuous systems modelling. In the proposed method a three-dimensional system is divided into finite elements in only two directions, with the third direction remaining continuous. The thus obtained discrete-continuous model is described by a set of partial differential equations. General difference equations of discrete system are obtained using the rigid finite element method. The limit...
-
Interactions of telomeric proteins with nucleic acids: sequence recognition on intact and oxidatively damaged telomeres
PublikacjaTelomeres are complex nucleoprotein assemblies that play a vital role in the maintenance of functional ends of linear chromosomes. Telomeric DNA, composed of tandem repeats of the 5'-TTAGGG-3' motif, solves the so-called end replication problem: as chromosomes shorten with each cell division, no information is lost, and the telomere can be re-extended. In the cell, many protein factors regulate telomere length, nuclear positioning...
-
Modified Peptide Molecules As Potential Modulators of Shelterin Protein Functions; TRF1
PublikacjaIn this work, we present studies on relatively new and still not well-explored potential anticancer targets which are shelterin proteins, in particular the TRF1 protein can be blocked by in silico designed "peptidomimetic" molecules. TRF1 interacts directly with the TIN2 protein, and this protein-protein interaction is crucial for the proper functioning of telomere, which could be blocked by our novel modified peptide molecules....
-
Learning Feedforward Control Using Multiagent Control Approach for Motion Control Systems
Publikacja -
Learning from Imbalanced Data Streams Based on Over-Sampling and Instance Selection
Publikacja -
Machine Learning and data mining tools applied for databases of low number of records
Publikacja -
Machine learning techniques combined with dose profiles indicate radiation response biomarkers
Publikacja