Wyszukiwarka
Filtry
wszystkich: 30103
-
Katalog
- Publikacje 7456 wyników po odfiltrowaniu
- Czasopisma 59 wyników po odfiltrowaniu
- Konferencje 20 wyników po odfiltrowaniu
- Osoby 173 wyników po odfiltrowaniu
- Wynalazki 1 wyników po odfiltrowaniu
- Projekty 5 wyników po odfiltrowaniu
- Aparatura Badawcza 1 wyników po odfiltrowaniu
- Kursy Online 130 wyników po odfiltrowaniu
- Wydarzenia 7 wyników po odfiltrowaniu
- Dane Badawcze 22251 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: hyperparameter tuning
-
Damage detection of structures using spectral element method.
PublikacjaW pracy przedstawion mozlwiości detekcji uszkodzeń w postaci pęknięć zmęczeniowych i delaminacji z wykorzystaniem modeli budowanych za pomocą metody spektralnych elementów skończonych.
-
Vertical axis wind engines using Magnus effect.
PublikacjaZaprezentowano krótki zarys historii wykorzystania energii wiatru. Opisano efekt Magnusa oraz dotychczasowe próby wykorzystania go w budowie silników wiatrowych. Przedstawiono obliczenia, za pomocą, których oszacowano możliwe do osiągnięcia sprawności silników wiatrowych o osi pionowej wyposażonych w rotory Magnusa.
-
Seabed characterisation using spectral moments of the echo signal
PublikacjaZbadano użyteczność zastosowania momentów spektralnych obwiedni echa w rozpoznawaniu i klasyfikacji dna morskiego. Przeprowadzono obliczenia momentów spektralnych dla około 15000 ech od dna zarejestrowanych w rejonie Bałtyku Południowego i potwierdzono tezę, że wartości tych momentów skorelowane są silnie z typem dna i rodzajem osadów.
-
Photo-oxidation of dissolved cyanide using TiO2 catalyst
PublikacjaZbadano utlenianie katalityczne jonów cyjankowych w układzie UV/TiO2. Szybkość utleniania zbadano dla różnego stężenia początkowego CN-, wartość pH, formy katalizatora, temperatury oraz wprowadzanej formy gazowej. Stwierdzono że szybkość degradacji cyjanków w układzie UV/TiO2/O2 wzrasta dwukrotnie, jakkolwiek jest niezależna od ciśnienia cząstkowego tlenu (0,2-1,0 atm.). Wzrost temperatury środowiska reakcji w zakresie od 20 do...
-
Towards Cancer Patients Classification Using Liquid Biopsy
PublikacjaLiquid biopsy is a useful, minimally invasive diagnostic and monitoring tool for cancer disease. Yet, developing accurate methods, given the potentially large number of input features, and usually small datasets size remains very challenging. Recently, a novel feature parameterization based on the RNA-sequenced platelet data which uses the biological knowledge from the Kyoto Encyclopedia of Genes and Genomes, combined with a classifier...
-
Smart city and fire detection using thermal imaging
PublikacjaIn this paper, we summarize the results obtained from fire experiments. The aim of the work was to develop new methods of fire detection using IR thermal imaging cameras and dedicated image processing. We conducted 4 experiments in different configurations and with the use of different objects. The conducted experiments have shown the great usefulness of infrared cameras for detecting the seeds of a fire. Even cheap low-resolution...
-
Analysing the Residential Market Using Self-Organizing Map
PublikacjaAlthough the residential property market has strong connections with various sectors, such as construction, logistics, and investment, it works through different dynamics than other markets; thus, it can be analysed from various perspectives. Researchers and investors are mostly interested in price trends, the impact of external factors on residential property prices, and price prediction. When analysing price trends, it is beneficial...
-
Detection of petroleum products using optical coherence tomography
PublikacjaIn this work, we present a novel method developed for the analysis of the properties of thin layers for detecting petroleum products on a water surface using a commercially available optical coherence tomography (OCT) system. The spectral density analysis of the signal from a spectroscopic OCT (S-OCT) enables us to perform the precision calculation of the thin layer thickness and other properties like homogeneity, and dispersion,...
-
Vibro piles performance prediction using result of CPT
PublikacjaVibro piles belong to the group of full displacement piles with an expanded base, characterised by a very high load capacity, especially in non-cohesive soils. The problem is to adopt a reliable method for the determination of full load–settlement (Q–s) curve. A frequent difficulty is the determination of the load capacity limit based on the static load test because the course of the load–settlement curve is of a linear nature....
-
Optimization of Bread Production Using Neuro-Fuzzy Modelling
PublikacjaAutomation of food production is an actively researched domain. One of the areas, where automation is still not progressing significantly is bread making. The process still relies on expert knowledge regarding how to react to procedure changes depending on environmental conditions, quality of the ingredients, etc. In this paper, we propose an ANFIS-based model for changing the mixer speed during the kneading process. Although the...
-
Wavelet filtering of signals without using model functions
PublikacjaThe effective wavelet filtering of real signals is impossible without determining their shape. The shape of a real signal is related to its wavelet spectrum. For shape analysis, a continuous color wavelet spectrogram of signal level is often used. The disadvantage of continuous wavelet spectrogram is the complexity of analyzing a blurry color image. A real signal with additive noise strongly distorts the spectrogram based on continuous...
-
Stress Detection of Children With ASD Using Physiological Signals
PublikacjaThis paper proposes a physiological signal-based stress detection approach for children with autism spectrum disorder (ASD) to be used in social and assistive robot inter- vention. Electrodermal activity (EDA) and blood volume pulse (BVP) signals are collected with an E4 smart wristband from children with ASD in different countries. The peak count and signal amplitude features are derived from EDA signal and used in order to detect...
-
Training of Deep Learning Models Using Synthetic Datasets
PublikacjaIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Analysis of elementary cellular automata using the theory of conflict
PublikacjaThe paper contains decomposition of elementary cellular automata (ECA in short) to subsystems that are defined according to a new theory called theory of conflict (ToC in short). The decomposition is a completely new approach to analysis of ECA and complex systems in general.
-
Impeller pump development using rapid prototyping methods
PublikacjaMetody szybkiego prototypowania przy wspomaganiu komputerowym projektowania 3D wraz z systemami wspomagania inżynierskiego pozwalają uzyskać wyrób o prognozowanych właściwościach technologicznych i użytkowych.W artykule przedstawiono studium przypadku zastosowania metod szybkiego prototypowania w rozwoju elementów pomp wirowych.
-
Broken-dam simulations using Smoothed Particle Hydrodynamics
Publikacja -
The rheological properties of hydroxylated soybean oil by using bioglycols
PublikacjaPraca zawiera opis właściwości fizykochemicznych i reologicznych hydroksylowanych olejów sojowych zmodyfikownych przy użyciu wybranych bioglikoli.
-
Comparative Analysis of Text Representation Methods Using Classification
PublikacjaIn our work, we review and empirically evaluate five different raw methods of text representation that allow automatic processing of Wikipedia articles. The main contribution of the article—evaluation of approaches to text representation for machine learning tasks—indicates that the text representation is fundamental for achieving good categorization results. The analysis of the representation methods creates a baseline that cannot...
-
Monitoring of underdeck corrosion by using acoustic emission method
PublikacjaThis paper presents first short characteristics of underdeck corrosion process as well as a problem of its monitoring. Next is described an acoustic emission (AE) method elaborated by Department of Ship Technology , Quality Systems and Material Engineering, Gdańsk University of Technology in cooperation with partners of CORFAT project realized within 7th EU Frame Program . Further are presented short characteristics of the emission...
-
Self diagnostics using smart glasses - preliminary study
Publikacjan this preliminary study we analyzed the possibility of the reliable measurement of biomedical signals with some potential hardware extensions of smart glasses. Using specially designed experimental prototypes four category of biomedical signals were measured: electrocardiograms, electromyograms, electroencephalograms and respiration waveforms. Experi- ments with volunteers proved that using even simple construc- tion of sensors...
-
Evaluating the position of a mobile robot using accelerometer data
PublikacjaThis paper analyses the problem of determining the position of a robot using an accelerometer, which is an essential part of inertial measurement units (IMU). The information gained from such a gauge, however, requires double integration of sensor data. To assure an expected effect, a mathematical model of a low-cost accelerometer of the MEMS type is derived. Moreover, in order to improve the performance of positioning based on...
-
Separation of CO2 from biogas using absorption columns
PublikacjaBiogaz zawiera ok. 50-70% metanu, 30-40% di tlenku węgla oraz niewielkie ilości innych związków jak siarkowodór czy amoniaku. Dla uzyskania wysokokalorycznego gazu konieczne jest usunięcie ze strumienia di tlenku węgla. Praca opisuje potencjał użycia do tego celu kolumn absorpcyjnych oraz cieczy jonowych jako absorbenta
-
Determination of impurities in pharmaceutical products using LC-MS
PublikacjaPharmaceutical products can be contaminated by residues of solvents, reagents (used for the synthesis) or degradation products. Impurities in drug may pose a risk to human health and life, therefore analysis and identification of impurities in pharmaceutical products is veryimportant and inevitable.High performance liquid chromatography coupled with mass spectrometry (MS) is very useful technique for identification impurities in...
-
Using concentrated spectrogram for analysis of audio acoustic signals
PublikacjaThe paper presents results of time-frequency analysis of audio acoustic signals using the method of Concentrated Spectrograph also known as ''Cross-spectral method'' or ''Reassignment method''. Presented algorithm involves signal's local group delay and channelized instantaneous frequency to relevantly redistribute all Short-time Fourier transform lines in time-frequency plain. The main intention of the paper is to compare various...
-
Seafloor Characterisation and Imaging Using Multibeam Sonar Data
PublikacjaThe approach to seafloor characterisation and imaging is presented. It relies on the combined, concurrent use of several techniques of multibeam sonar data processing. The first one is based on constructing the grey-level sonar images of seabed using the backscattering strength calculated for the echoes received in the consecutive beams. Then, the set of parameters describing the local region of sonar image is calculated. The second...
-
Diagnosis of damages in family buildings using neural networks
PublikacjaThe article concerns a problem of damages in family buildings, which result from traffic-induced vibrations. These vibrations arise from various causes and their size is influenced by many factors. The most important is the type of a road, type and weight of vehicles that run on the road, type and condition of the road surface, the distance from the house to the source of vibrations and many others which should be taken into account....
-
Quality Evaluation of Agricultural Distillates Using an Electronic Nose
PublikacjaThe paper presents the application of an electronic nose instrument to fast evaluation of agricultural distillates differing in quality. The investigations were carried out using a prototype of electronic nose equipped with a set of six semiconductor sensors by FIGARO Co., an electronic circuit converting signal into digital form and a set of thermostats able to provide gradient temperature characteristics to a gas mixture. A volatile fraction...
-
Modelling a 6-dof manipulator using Matlab software
PublikacjaThis paper presents an alternative approach to modelling a revolute robot. The manipulator in question is Kuka KR 16-2. The main problem in robot modelling is a kinematic analysis. The revolute robot consist of six rotary joints (6-DOF) with base, shoulder, elbow and wirst. The kinematics problem is defined as a transformation from the cartesian space to the joint space. The Denavit- Hartenberg (D-H) model of representation was...
-
Small Antenna Design Using Surrogate-Based Optimization
PublikacjaIn this work, design of small antennas using efficient numerical optimization is investigated. We exploit variable-fidelity electromagnetic (EM) simulations and the adaptively adjusted design specifications (AADS) technique. Combination of these methods allows us to simultaneously adjust multiple geometry parameters of the antenna structure of interest in a computationally feasible manner, leading to substantial reduction of the...
-
TDOA Navigation Using CDMA2000 Signals – Experimental Results
PublikacjaThis paper presents results of an experiments on the possibility to estimate position of a CDMA2000 receiver on the basis of TDOA measurements. The hardware and software structure of a navigation receiver used during investigation is briefly described with focus on drawbacks and limitations. The main part of this paper contains basic information about CDMA2000 network in northern Poland, which signals were recorded during tests...
-
Developing competences of IT project managers using simulation games
PublikacjaProject Management is a domain in which methodological approach is developing very rapidly. Project managers are required to present knowledge of the various methods of project management and apply them to the management of specific projects. It means that project managers must constantly develop their competence, mainly based on good practices from different formal methods of project management. The purpose of this article is...
-
Density smoothness estimation problem using a wavelet approach
PublikacjaIn this paper we consider a smoothness parameter estimation problem for a density function. The smoothness parameter of a function is defined in terms of Besov spaces. This paper is an extension of recent results (K. Dziedziul, M. Kucharska, B. Wolnik, Estimation of the smoothness parameter ). The construction of the estimator is based on wavelets coefficients. Although we believe that the effective estimation of the smoothness...
-
Free randomness amplification using bipartite chain correlations
PublikacjaA direct analysis of the task of randomness amplification from Santha-Vazirani sources using the violation of the chained Bell inequality is performed in terms of the convex combination of no-signaling boxes required to simulate quantum violation of the inequality. This analysis is used to find the exact threshold value of the initial randomness parameter from which perfect randomness can be extracted in the asymptotic limit of...
-
Vibroflotation Control of Sandy Soils using DMT and CPTU
PublikacjaVibroflotation is a typical improvement method for the cohesionless deposits of high thickness. The compaction method was applied to densify sandy deposits in Gdynia Port. Compaction control was verified with CPTU and DMT tests. Some examples of interpretation of soundings in pre-treated and compacted sands are shown. The classification diagrams are given for pre-treated and compacted sand. The stress history of the deposits is...
-
Evaluating the mobile robot positions using accelerometer data
PublikacjaThis paper analyzes the problem of determining the position of a robot using an accelerometer, which is an essential part of inertial measurement units (IMU). The information gained from such a gauge, however, requires double integration of sensor data. To assure an expected effect, a mathematical model of a low-cost accelerometer of the MEMS type is derived. Moreover, in order to improve the performance of positioning based on...
-
Music Mood Visualization Using Self-Organizing Maps
PublikacjaDue to an increasing amount of music being made available in digital form in the Internet, an automatic organization of music is sought. The paper presents an approach to graphical representation of mood of songs based on Self-Organizing Maps. Parameters describing mood of music are proposed and calculated and then analyzed employing correlation with mood dimensions based on the Multidimensional Scaling. A map is created in which...
-
Single-Anchor Indoor Localization Using ESPAR Antenna
PublikacjaIn this paper a new single-anchor indoor localization concept employing Electronically Steerable Parasitic Array Radiator (ESPAR) antenna has been proposed. The new concept uses a simple fingerprinting algorithm adopted to work with directional main beam and narrow minimum radiation patterns of ESPAR antenna that scans 360° area around the base station, while the signal strength received from a mobile terminal is being recorded...
-
Pile Model Tests Using Strain Gauge Technology
PublikacjaOrdinary pile bearing capacity tests are usually carried out to determine the relationship between load and displacement of pile head. The measurement system required in such tests consists of force transducer and three or four displacement gauges. The whole system is installed at the pile head above the ground level. This approach, however, does not give us complete information about the pile-soil interaction. We can only determine...
-
Detection of Face Position and Orientation Using Depth Data
PublikacjaIn this paper an original approach is presented for real-time detection of user's face position and orientation based only on depth channel from a Microsoft Kinect sensor which can be used in facial analysis on scenes with poor lighting conditions where traditional algorithms based on optical channel may have failed. Thus the proposed approach can support, or even replace, algorithms based on optical channel or based on skeleton...
-
Determining heat transfer coefficients using evolutionary alogrithms
PublikacjaPokazano sposób kalibracji współczynnika wymiany ciepła za pomocą algorytmów ewolucyjnych. Wykorzystano tu minimalizację błędu między pomiarami a obliczeniami. Pokazano dwie metody optymalizacji: wielokryterialną i jednokryterialną.
-
Dimensionless Analysis of Stirling Engine using of Optimization Methods
PublikacjaW pracy zaprezetowano wyniki analizy wpływu parametrów konstrukcyjnych silnika Stirlinga na jego wskaźniki jakości.Analizę przeprowadzono na modelu bezwymiarowym wykorzystując metody optymalizacji parametrycznej.
-
Clothes Detection and Classification Using Convolutional Neural Networks
PublikacjaIn this paper we describe development of a computer vision system for accurate detection and classification of clothes for e-commerce images. We present a set of experiments on well established architectures of convolutional neural networks, including Residual networks, SqueezeNet and Single Shot MultiBox Detector (SSD). The clothes detection network was trained and tested on DeepFashion dataset, which contains box annotations...
-
On autoregressive spectrum estimation using the model averaging technique
PublikacjaThe problem of estimating spectral density of a nonstationary process satisfying local stationarity conditions is considered. The proposed solution is a two step procedure based on local autoregressive (AR) modeling. In the first step Bayesian-like averaging of AR models, differing in order, is performed. The main contribution of the paper is development of a new final-prediction-error-like statistic, which can be used to select...
-
Detection of the Bee Queen Presence Using Sound Analysis
PublikacjaThis work describes the system and methods of data analysis we use for beehive monitoring. We present overview of the hardware infrastructures used in hive monitoring systems and we describe algorithms used for analysis of this kind of data. Based on acquisited signals we construct the application that is capable to detect an absence of honey bee queen. We describe our method of signal analysis and present results that allow us...
-
Determination of the Vehicles Speed Using Acoustic Vector Sensor
PublikacjaThe method for determining the speed of vehicles using acoustic vector sensor and sound intensity measurement technique was presented in the paper. First, the theoretical basis of the proposed method was explained. Next, the details of the developed algorithm of sound intensity processing both in time domain and in frequency domain were described. Optimization process of the method was also presented. Finally, the proposed measurement...
-
Counting and tracking vehicles using acoustic vector sensors
PublikacjaA method is presented for counting vehicles and for determining their movement direction by means of acoustic vector sensor application. The assumptions of the method employing spatial distribution of sound intensity determined with the help of an integrated 3D intensity probe are discussed. The intensity probe developed by the authors was used for the experiments. The mode of operation of the algorithm is presented in conjunction...
-
Detecting Lombard Speech Using Deep Learning Approach
PublikacjaRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
CONCRETE MIX DESIGN USING ABRAMS AND BOLOMEY METHODS
PublikacjaOne way to reduce the consumption of cement is to optimize its use. Many known methods of concrete design, based on the Abrams law and the Bolomey method. Therefore, the authors chose those methods for analysis. The concrete composition with the assumed strength class, calculated by any method differs significantly. This applies especially to the cement content, as its content in the composition of concrete varies from 20 to 50%....
-
Modelling of concrete using lattice and discrete element method
PublikacjaModelowanie betonu przy zastosowaniu metody siatkowej i metody elementów dyskretnych.
-
Improving the prediction of biochar production from various biomass sources through the implementation of eXplainable machine learning approaches
PublikacjaExamining the game-changing possibilities of explainable machine learning techniques, this study explores the fast-growing area of biochar production prediction. The paper demonstrates how recent advances in sensitivity analysis methodology, optimization of training hyperparameters, and state-of-the-art ensemble techniques have greatly simplified and enhanced the forecasting of biochar output and composition from various biomass...