Filters
total: 3058
filtered: 2717
-
Catalog
Chosen catalog filters
displaying 1000 best results Help
Search results for: PRE-TRAINED MODELS
-
Metabolic transformation of antitumor acridinone C-1305 but not C-1311 via selective cellular expression of UGT1A10 increases cytotoxic response: implications for clinical use.
PublicationThe acridinone derivates C-1305 and C-1311 are promising antitumor agents with high activity against several experimental cellular and tumor models and which are under evaluation in pre-clinical and early phase clinical trials. Recent evidence from our laboratories has indicated that both compounds were conjugated by several UGT isoforms with the most active being extrahepatic UGT1A10. The present studies were designed to test...
-
Comparative study on total nitrogen prediction in wastewater treatment 1 plant and effect of various feature selection methods on machine learning algorithms performance
PublicationWastewater characteristics prediction in wastewater treatment plants (WWTPs) is valuable and can reduce the number of sampling, energy, and cost. Feature Selection (FS) methods are used in the pre-processing section for enhancing the model performance. This study aims to evaluate the effect of seven different FS methods (filter, wrapper, and embedded methods) on enhancing the prediction accuracy for total nitrogen (TN) in the WWTP...
-
Wczesny Mickiewicz jako zapowiadający się historiozof
PublicationThe paper shows young Mickiewicz’s family and historical experiences. It discussesthe knightly premises for his historiosophy and explains its radicalism and structureon the grounds of the knightly tradition. The study reveals the pre-Slavic deposits ofspiritual archeology in the Romantic poet. It proves that the activation of these depositsshaped Mickiewicz’s view on the collision between Poland and...
-
Review of historical buildings' foundations
PublicationThe paper presents in brief the history of foundation engineering with a particular regard to its development, applied techniques and materials. Different types of old foundations in relation to various soil conditions are considered. Basic methods of preservation of old foundations, with special emphasis given to their faults and advantages are discussed. Finally, some problems of the reuse of pre-existing foundations are raised....
-
Real‐Time PPG Signal Conditioning with Long Short‐Term Memory (LSTM) Network for Wearable Devices
PublicationThis paper presents an algorithm for real‐time detection of the heart rate measured on a person’s wrist using a wearable device with a photoplethysmographic (PPG) sensor and accelerometer. The proposed algorithm consists of an appropriately trained LSTM network and the Time‐Domain Heart Rate (TDHR) algorithm for peak detection in the PPG waveform. The Long Short‐Term Memory (LSTM) network uses the signals from the accelerometer...
-
Exposure of a small Arctic seabird, the little auk (Alle alle) breeding in Svalbard, to selected elements throughout the course of a year
PublicationThe Arctic marine ecosystem can be altered by processes of natural and anthropogenic origin. Spatio-temporal variation in species exposure to contamination is still poorly understood. Here, we studied elemental concentrations in the non-lethally collected samples from the most numerous seabird in European Arctic, the little auk (Alle alle) nesting in one breeding colony in Svalbard. This seabird spent the breeding season in the...
-
Accuracy analysis of 3D model obtained by photogrammetric method on the example of historic room from Wisłoujście Fortress
PublicationThe article presents a comparison of obtained models of a test object. Close range photogrammetry was used to obtain 3D models. As test object was used one of the rooms located in Wisłoujście Fortress in Gdańsk, Poland. Different models were obtained by using different distribution and number of reference points. Article contains analysis of differences between coordinates of control points obtained from total station measurements...
-
Ab initio chemical kinetics of Isopropyl acetate oxidation with OH radicals
PublicationGlobal reactivity descriptors of isopropyl acetate (IPA) and thermo-kinetic aspects of its oxidation via OH radicals have been studied. Transition state theory (TST) was utilized to estimate the bimolecular rate constants. Ten oxidation pathways have been investigated, and all of them are exothermic. The potential energy diagram has been sketched using different pre- and post-reactive complexes for all reaction pathways. Rate coefficient...
-
Behaviour of deformed steel columns exposed to impact load during earthquakes - experimental study
PublicationIt has been observed during major earthquakes that the so called soft-storey failure of an upper floor of a structure results in large impact load acting on structural members of the lower storeys. It may further lead to progressive collapse of the whole structure substantially intensifying human and material losses. The aim of this paper is to investigate experimentally the behaviour of horizontally deformed columns (deformation...
-
Key issues in modeling and optimization of lignocellulosic biomass fermentative conversion to gaseous biofuels
PublicationThe industrial-scale production of lignocellulosic-based biofuels from biomass is expected to benefit society and the environment. The main pathways of residues processing include advanced hydrolysis and fermentation, pyrolysis, gasification, chemical synthesis and biological processes. The products of such treatment are second generation biofuels. The degree of fermentation of organic substances depends primarily on their composition...
-
Effects of CO2 and Nd:YAG Laser Remelting of the Ti6Al4V Alloy on the Surface Quality and Residual Stresses
PublicationThe titanium alloys are materials susceptible to tribological wear and the laser treatment can be applied in surface treatment processes to obtain for example higher hardness level. From the other side, it is important to take into consideration, that hardness increase that can be connected with cracks . The aim of this research was to investigate the effects of different lasers and the process parameters on the form and level...
-
Investigation on Mode I Fracture Behavior of Hybrid Fiber-Reinforced Geopolymer Composites
PublicationRecent reports in the literature have shown that fber-reinforced geopolymer composites (FRGC) made with monofbers exhibit a signifcant enhancement in fracture energy. However, many aspects of the fracture performance of hybrid fberreinforced geopolymer composites (HFRGC) remain largely unexploited, and these are predominant for the structures. For the frst time, the mode I fracture energy of HFRGC is investigated. The mode I behavior...
-
AUTOMATYCZNA KLASYFIKACJA MOWY PATOLOGICZNEJ
PublicationAplikacja przedstawiona w niniejszym rozdziale służy do automatycznego wykrywania mowy patologicznej na podstawie bazy nagrań. W pierwszej kolejności przedstawiono założenia leżące u podstaw przeprowadzonych badan wraz z wyborem bazy mowy patologicznej. Zaprezentowano również zastosowane algorytmy oraz cechy sygnału mowy, które pozwalają odróżnić mowę niezaburzoną od mowy patologicznej. Wytrenowane sieci neuronowe zostały następnie...
-
Badanie stanu nawierzchni drogowej z wykorzystaniem uczenia maszynowego
PublicationW artykule opisano budowę systemu informowania o stanie nawierzchni drogowej z wykorzystaniem metod cyfrowego przetwarzania obrazów oraz uczenia maszynowego. Efektem wykonanych prac badawczych jest eksperymentalna platforma, pozwalająca na rejestrację uszkodzeń na drogach, system do analizy, przetwarzania i klasyfikacji danych oraz webowa aplikacja użytkownika do przeglądu stanu nawierzchni w wybranej lokalizacji.
-
Analytical modeling of electric drives for vehicle traction control systems
PublicationWheel-torque control bandwidth in vehicle dynamics model is crucial in evaluating optimal tracking ability of tire slip and in analysis of control system stability. Electric drives’ control dynamics are influenced by timing of digital control events, e.g. by sampling instant of motor currents. Reflecting this timing in drive analytical models is therefore important for analysis of vehicle traction systems. The paper considers five...
-
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublicationThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
Multi-Camera Vehicle Tracking Using Local Image Features and Neural Networks
PublicationA method for tracking moving objects crossing fields of view of multiple cameras is presented. The algorithm utilizes Artificial Neural Networks (ANNs). Each ANN is trained to recognize images of one moving object acquired by a single camera. Local image features calculated in the vicinity of automatically detected interest points are used as object image parameters. Next, ANNs are employed to identify the same objects captured...
-
Intelligent system supporting diagnosis of malignant melanoma
PublicationMalignant melanomas are the most deadly type of skin cancers. Early diagnosis is a key for successful treatment and survival. The paper presents the system for supporting the process of diagnosis of skin lesions in order to detect a malignant melanoma. The paper describes the development process of an intel-ligent system purposed for the diagnosis of malignant melanoma. Presented sys-tem can be used as a decision support system...
-
A Bayesian regularization-backpropagation neural network model for peeling computations
PublicationA Bayesian regularization-backpropagation neural network (BRBPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network...
-
L'humanisation de la justice criminelle dans la France desLumieres
PublicationIn pre-revolutionary France criminal justice is regulated by the Ordinance Louis XIV of 1670. This Ordinance provides for torture as the major method of investigation and for the death penalty as the most commonly used form of punishment. One of the major concerns of French eighteenthcentury philosophers is therefore a radical reform of criminal justice and its humanisation in the spirit of Enlightenment. Many philosophers take...
-
A method for preliminary estimation of the length of midship body block to be inserted during ship’s conversion
PublicationThe paper presents a method for preliminary estimation of the length of the midship body block, which inserted in the original hull, increases the deadweight of the ship in line with a required quantity. The method may be useful for establishing the scope of conversion to better adjust the ship for transportation tasks. The problem is formulated by using a mathematical model so selected that its solution, under set of assumptions,...
-
From a Point Cloud to a 3D Model - an Exercise for Users of AutoCAD and Revit
PublicationThe paper presents a proposal of the topic of an exercise for students of building faculties as part of classes on 3D modelling. The task consists in creating a three-dimensional model based on the measurement obtained with the Leica P30 laser scanner. Due to the maximum number of points in the cloud in the presented programs, the output files must be properly cleared and reduced. The point cloud was pre-processed in Cyclone software....
-
Analysis of High Resolution Clouds of Points as a Source of Biometric Data
PublicationThe article presents the analysis devoted to human face data obtained by means of precise photographic scanners. Collected point clouds were used to make high precision meshes of human face. The essence of these studies is the comparison of relative features as well as the comparison of absolute models which require as precisely as possible matching of face models. The article focuses on the analysis of various parts of the human...
-
The role of biodegradable particulate and colloidal organic compounds in biological nutrient removal activated sludge systems
PublicationThe efficiency of denitrification and enhanced biological phosphorus removal in biological nutrient removal activated sludge systems is strongly dependent on the availability of appropriate carbon sources. Due to high costs of commercial compounds (such as methanol, ethanol, acetic acid, etc.) and acclimation periods (usually) required, the effective use of internal substrates is preferred. The aim of this study was to determine...
-
Binary-Encounter Model for Direct Ionization of Molecules by Positron-Impact
PublicationWe introduce two models for the computation of direct ionization cross sections by positron impact over a wide range of collision energies. The models are based on the binary-encounter-Bethe model and take into account an extension of the Wannier theory. The cross sections computed with these models show good agreement with experimental data. The extensions improve the agreement between theory and experiment for collision energies...
-
Assessment of Trajectories of Non-bankrupt and Bankrupt Enterprises
PublicationThe aim of this study is to show how long-term trajectories of enterprises can be used to increase the forecasting horizon of bankruptcy prediction models. The author used seven popular forecasting models (two from Europe, two from Asia, two from North America and one from Latin America). These models (five multivariate discriminant analysis models and two logit models) were used to develop 17-year trajectories separately for non-bankrupt...
-
Prediction of protein assemblies, the next frontier: The CASP14‐CAPRI experiment
PublicationWe present the results for CAPRI Round 50, the 4th joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of 12 targets, including 6 dimers, 3 trimers, and 3 higher-order oligomers. Four of these were easy targets, for which good structural templates were available either for the full assembly, or for the main interfaces (of the higher-order oligomers). Eight were difficult targets for which only distantly...
-
Does one currency mean one price? An analysis of the euro effect on price dispersion and convergence
PublicationThis paper examines price differentials in the European Union to investigate whether the European Monetary Union has lowered the degree of price dispersion in the euro zone and increased the speed of price convergence. Both euro effects are evaluated using difference-in-difference methodology. Applied to the issue of introducing a single currency, the euro effects identified are the estimated differences in price dispersion and...
-
STEADY STATE VISUALLY EVOKED POTENTIALS FOR BRAIN COMPUTER INTERFACE
PublicationAn experiment conducted to validate a possibility of use a single active electrode EEG device for detecting Steady State Visually Evoked Potentials (SSVEP) is shown. A LED stimulator was applied to stimulate patients with two different frequencies - 13 Hz and 17 Hz. First, EEG signals were recorded and pre-processed using MATLAB software. In the next step recordings were analysed and classified employing the WEKA software. As indicated...
-
Report of the ISMIS 2011 Contest : Music Information Retrieval
PublicationThis report presents an overview of the data mining contestorganized in conjunction with the 19th International Symposiumon Methodologies for Intelligent Systems (ISMIS 2011), in days betweenJan 10 and Mar 21, 2011, on TunedIT competition platform. The contestconsisted of two independent tasks, both related to music information retrieval:recognition of music genres and recognition of instruments, for agiven music sample represented...
-
Numerical studies on the influence of selected construction features and road conditions on the performance of road cable barriers
PublicationCable barriers are commonly used on Polish roads, including motorways and local roads. Their main elements are pre-stressed wire ropes, which are usually anchored at two ends in concrete blocks buried in the soil. In this work numerical studies concerning the influence of selected construction features and parameters of the vehicle motion on the performance of cable barriers were performed. Numerical simulations are a useful tool...
-
Real and imaginary motion classification based on rough set analysis of EEG signals for multimedia applications
PublicationRough set-based approach to the classification of EEG signals of real and imaginary motion is presented. The pre-processing and signal parametrization procedures are described, the rough set theory is briefly introduced, and several classification scenarios and parameters selection methods are proposed. Classification results are provided and discussed with their potential utilization for multimedia applications controlled by the...
-
Przedwojenne wydawnictwa Stowarzyszenia Elektryków Polskich w bibliotekach i bibliotekach cyfrowych
PublicationArtykuł przedstawia krótką historię piśmiennictwa z dziedziny elektrotechniki. Po 1918 r. obserwuje się wzrost liczby publikacji, a wraz z rozwojem nauki zwiększa się obszar tematyczny literatury fachowej. Ogromną zasługę w tym rozwoju miało Stowarzyszenie Elektryków Polskich. W artykule pokazano sposoby wyszukiwania wydawnictw przedwojennych SEP, ich dostępność w bibliotekach, także cyfrowych. Przedstawia w jaki sposób zwiększyć...
-
DEEP LEARNING BASED ON X-RAY IMAGING IMPROVES COXARTHROSIS DETECTION
PublicationObjective: The purpose of the study was to create an Artificial Neural Network (ANN) based on X-ray images of the pelvis, as an additional tool to automate and improve the diagnosis of coxarthrosis. The research is focused on joint space narrowing, which is a radiological symptom showing the thinning of the articular cartilage layer, which is translucent to X-rays. It is the first and the most important of the radiological signs...
-
Model-Based Adaptive Machine Learning Approach in Concrete Mix Design
PublicationConcrete mix design is one of the most critical issues in concrete technology. This process aims to create a concrete mix which helps deliver concrete with desired features and quality. Contemporary requirements for concrete concern not only its structural properties, but also increasingly its production process and environmental friendliness, forcing concrete producers to use both chemically and technologically complex concrete...
-
Designing acoustic scattering elements using machine learning methods
PublicationIn the process of the design and correction of room acoustic properties, it is often necessary to select the appropriate type of acoustic treatment devices and make decisions regarding their size, geometry, and location of the devices inside the room under the treatment process. The goal of this doctoral dissertation is to develop and validate a mathematical model that allows predicting the effects of the application of the scattering...
-
Ionic liquids-based microextraction techniques
PublicationIn recent years, the development of highly efficient analytical techniques is of great importance, however, the direct analysis of complex sample matrix is still impossible in many cases. Therefore, the step of sample preparation is commonly involved in an analytical procedure. Over the years, it has been realized that the major source of inaccuracy and imprecision on general analysis results from the operations associated to sample...
-
Genotoxic properties of glucosinolates and isothiocyanates present in Brassica vegetables
PublicationThe bioactive phytochemicals found in Brassica vegetables, in this number glucosinolates (GLS), as well as products of their degradation such as isothiocyanates (ITC) and indoles, are regarded as the most promising chemopreventive compounds. These secondary metabolites display stron antibiological activity and constitute defence system preventing the development of agrophages attacking Brassica plants. Such properties suggest...
-
3D Object Shape Reconstruction from Underwater Multibeam Data and Over Ground Lidar Scanning
PublicationThe technologies of sonar and laser scanning are an efficient and widely used source of spatial information with regards to underwater and over ground environment respectively. The measurement data are usually available in the form of groups of separate points located irregularly in three-dimensional space, known as point clouds. This data model has known disadvantages, therefore in many applications a different form of representation,...
-
Behaviour of deformed steel columns exposed to impact load during earthquakes: numerical analysis
PublicationIt has been observed during earthquakes that the so called soft-storey failure of an upper floor of a building leads to considerable vertical impact load acting on structural members of the lower storeys. The aim of this paper is to investigate numerically the behaviour of horizontally deformed columns (deformation as the result of earthquake loading) that are additionally subjected to vertical impact load. In the first stage of...
-
Influence of laser processing of the low alloy medium carbon structural steel on the development of the fatigue crack
PublicationThe paper contains the results of the structural analysis, hardness tests and fatigue tests conducted for the medium carbon structural steel with low content of Cr and Ni after its processing with CO2 laser beam. Pre-cracks were made in the round compact tension (RCT) specimen used for fatigue test. Next, four paths, parallel to each other, were melted on both sides of the samples using a laser beam. The paths were perpendicular...
-
Wavelet Transform Analysis of Heart Rate to Assess Recovery Time for Long Distance Runners
PublicationThe diagnostics of the condition of athletes has become a field of special scientific interest and activity. The aim of this study was to verify the effect of a long (100 km) run on a group of runners, as well as to assess the recovery time that is required for them to return to the pre-run state. The heart rate (HR) data presented were collected the day before the extreme physical effort, on the same day as, but after, the physical...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Road noise mapping in the city area: measurements compared to model-based estimations
PublicationThe paper presents an approach to the verification of noise prediction models in selected localization in the city of Gdansk. The experiments described include a comparison between environmentalmeasurement results performed in the terrain and the noise level prediction results. The NMPB-96 (Nouvelle Méthode de Prévision du Bruit) and Harmonoise models outcomes provide the subject ofthe analysis. The proposed solution of continuous...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublicationThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
PERFORMANCE OF ENDOSCOPIC IMAGE ANALYSIS ALGORITHMS IN LARGE BOWEL VIDEOS PROCESSING
PublicationComputer-assisted endoscopy is a rapidly developing eld of study. Many image anal- ysis algorithms exist, achieving very high rates of eciency at processing single endoscopic images. However, most of them were never tested in processing real-life endoscopic videos. In the article such tests of 16 endoscopy image analysis algorithms are presented and dis- cussed. Tests were performed on two real-life endoscopic videos of a human...
-
Multimodal Approach For Polysensory Stimulation And Diagnosis Of Subjects With Severe Communication Disorders
Publicationis evaluated on 9 patients, data analysis methods are described, and experiments of correlating Glasgow Coma Scale with extracted features describing subjects performance in therapeutic exercises exploiting EEG and eyetracker are presented. Performance metrics are proposed, and k-means clusters used to define concepts for mental states related to EEG and eyetracking activity. Finally, it is shown that the strongest correlations...
-
Real and Virtual Instruments in Machine Learning – Training and Comparison of Classification Results
PublicationThe continuous growth of the computing power of processors, as well as the fact that computational clusters can be created from combined machines, allows for increasing the complexity of algorithms that can be trained. The process, however, requires expanding the basis of the training sets. One of the main obstacles in music classification is the lack of high-quality, real-life recording database for every instrument with a variety...
-
Design of residential buildings in architecture education
PublicationThis article is based on an analysis of residential building designs made by students of the Faculty of Architecture at Gdańsk University of Technology (FA-GUT), Poland, and on the results of a survey conducted among these students. The purpose of the survey was to verify the broad, interdisciplinary knowledge of the students required in preparation for taking up design issues, as well as their ability to use this knowledge in...
-
Degradation of organic coatings subjected to alternating mechanical stress impact.
PublicationW pracy przedstawiono wyniki badań nad wpływem cyklicznych naprężeń mechanicznych na dwa rodzaje systemów powłokowych stosowanych do ochrony konstrukcji mostowych. Powłoki epoksydowe i winylowe poddano cyklom zginanie/odpuszczenie w granicach odkształceń elastycznych materiału podłoża. Stan powłok oceniano przy użyciu techniki elektrochemicznej spektroskopii impedancyjnej. Otrzymane wyniki porównano z zachowaniem analogicznych...