Filtry
wszystkich: 1708
-
Katalog
- Publikacje 1540 wyników po odfiltrowaniu
- Czasopisma 11 wyników po odfiltrowaniu
- Konferencje 7 wyników po odfiltrowaniu
- Osoby 35 wyników po odfiltrowaniu
- Projekty 3 wyników po odfiltrowaniu
- Kursy Online 18 wyników po odfiltrowaniu
- Wydarzenia 2 wyników po odfiltrowaniu
- Dane Badawcze 92 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: support vector regressor
-
Dual drive control under SVPWM, experimental results
Dane BadawczeThe dataset contains the experimental results of the project: A universal algorithm of space vector pulse width modulation for three-level three and multi-phase NPC inverters with DC-link voltage balancing. The analysis includes the behaviour of the drive system, examining the dynamic system response to speed and angle changes, and encompassing data...
-
Australian Conference for Knowledge Management and Intelligent Decision Support
Konferencje -
International Conference on Decision Support Through Knowledge Management
Konferencje -
International Workshop on Business Process Modelling, Development, and Support
Konferencje -
Data recorded for the purpose of the 3D sound intensity visualization around the organ pipe (des sound)
Dane BadawczeThe set contains data recorded using the Cartesian robot and multichannel acoustic vector sensor (from Microflown) for the purpose of the 3D sound intensity visualization of radiated acoustic energy around the organ pipe.
-
Efficiency comparison of selected endoscopic video analysis algorithms
PublikacjaIn the paper, selected image analysis algorithms were examined and compared in the task of identifying informative frames, blurry frames, colorectal cancer and healthy tissue on endoscopic videos. In order to standardize the tests, the algorithms were modified by removing from them parts responsible for the classification, and replacing them with Support Vector Machines and Artificial Neural Networks. The tests were performed in...
-
Comparative analysis of spectral and cepstral feature extraction techniques for phoneme modelling
PublikacjaPhoneme parameter extraction framework based on spectral and cepstral parameters is proposed. Using this framework, the phoneme signal is divided into frames and Hamming window is used. The performances are evaluated for recognition of Lithuanian vowel and semivowel phonemes. Different feature sets without noise as well as at different level of noise are considered. Two classical machine learning methods (Naive Bayes and Support...
-
Determination Of Gas Mixture Components Using Fluctuation Enhanced Sensing And The LS-SVM Regression Algorithm
PublikacjaThis paper analyses the effectiveness of determining gas concentrations by using a prototype WO3 resistive gas sensor together with fluctuation enhanced sensing. We have earlier demonstrated that this method can determine the composition of a gas mixture by using only a single sensor. In the present study, we apply Least-Squares Support-Vector-Machine-based (LS-SVM-based) nonlinear regression to determine the gas concentration...
-
Comparison of selected electroencephalographic signal classification methods
PublikacjaA variety of methods exists for electroencephalographic (EEG) signals classification. In this paper, we briefly review selected methods developed for such a purpose. First, a short description of the EEG signal characteristics is shown. Then, a comparison between the selected EEG signal classification methods, based on the overview of research studies on this topic, is presented. Examples of methods included in the study are: Artificial...
-
Anna Lis dr hab. inż.
OsobyAnna Lis od 2019 roku pełni funkcję kierownika Katedry Zarządzania w Przemyśle, na Wydziale Zarządzania i Ekonomii PG. W 2005 r. otrzymała stopień doktora nauk ekonomicznych w zakresie nauk o zarządzaniu, zaś w 2019 – stopień doktora habilitowanego w dziedzinie nauk społecznych w dyscyplinie nauk o zarządzaniu i jakości. W latach 2004-2009 była zatrudniona na Wydziale Inżynierii Produkcji Politechniki Warszawskiej. W latach 2006-2007...
-
Ekologiczne łożysko foliowe smarowane wodą - budowa i analiza wpływu wybranych parametrów konstrukcyjnych na sztywność podparcia łożyska = Environmentaly friendly water lubricated foil braing-design and influence analysis of selected design parameters bearing support stiffness
PublikacjaW artykule opisano budowę prototypowego łożyska foliowego smarowanego wodą ze szczególnym uwzględnieniem wpływu geometrii elementów podatnych łożyska na jego sztywność. Opisano technologię jego wykonania oraz model obliczeniowy łożyska opracowany z wykorzystaniem MES, przedstawiono wyniki wybranych analiz obliczeniowych.
-
Examining Classifiers Applied to Static Hand Gesture Recognition in Novel Sound Mixing System
PublikacjaThe main objective of the chapter is to present the methodology and results of examining various classifiers (Nearest Neighbor-like algorithm with non-nested generalization (NNge), Naive Bayes, C4.5 (J48), Random Tree, Random Forests, Artificial Neural Networks (Multilayer Perceptron), Support Vector Machine (SVM) used for static gesture recognition. A problem of effective gesture recognition is outlined in the context of the system...
-
Piotr Samól dr inż. arch.
OsobyPiotr Samól jest adiunktem w Katedrze Historii, Teorii Architektury i Konserwacji Zabytków Wydziału Architektury Politechniki Gdańskiej. Ukończył architekturę i historię. Jego badania skupiają się na zagadnieniach historii architektury oraz urbanistyki Gdańska i regionu nadbałtyckiego. Rozprawę doktorską (nauki techniczne, architektura i urbanistyka) o architekturze kościołów dominikańskich w dawnym państwie zakonu krzyżackiego...
-
Real time operating systems - lectures & exercises, 2023 summer
Kursy OnlineSupport course for real-time operating systems
-
Two Stage SVM and kNN Text Documents Classifier
PublikacjaThe paper presents an approach to the large scale text documents classification problem in parallel environments. A two stage classifier is proposed, based on a combination of k-nearest neighbors and support vector machines classification methods. The details of the classifier and the parallelisation of classification, learning and prediction phases are described. The classifier makes use of our method named one-vs-near. It is...
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublikacjaThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
Sperm segmentation and abnormalities detection during the ICSI procedure using machine learning algorithms
Publikacja(1) About 15-20% of couples struggle with the problem of infertility. 30 to 40% of these cases are caused by abnormalities in the structure and motility of sperm. Sometimes the only possibility for such people is to use the procedure of artificial insemination. CASA systems are used to increase the efficiency of this procedure by selecting the appropriate sperm cell. (2) This paper presents an approach to the sperm classification...
-
Ontology clustering by directions algorithm to expand ontology queries
PublikacjaThis paper concerns formulating ontology queries. It describes existing languages in which ontologies can be queried. It focuses on languages which are intended to be easily understood by users who are willing to retrieve information from ontologies. Such a language can be, for example, a type of controlled natural language (CNL). In this paper a novel algorithm called Ontology Clustering by Directions is presented. The algorithm...
-
Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data
PublikacjaThis paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost...
-
Informatization Strategies 24_25
Kursy OnlineThis eCourse is designed to support lectures and laboratories to the subject: Informatization strategies
-
Real-time Operating Systems - Seminar 2023/4
Kursy OnlinePage to support seminar clases of Real-time Operating Systems
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublikacjaAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Marek Blok dr hab. inż.
OsobyMarek Blok w 1994 roku ukończył studia na kierunku Telekomunikacja wydziału Elektroniki Politechniki Gdańskiej i uzyskał tytuł mgra inżyniera. Doktorat w zakresie telekomunikacji uzyskał w 2003 roku na Wydziale Elektroniki, Telekomunikacji i Informatyki Politechniki Gdańskiej. W 2017 roku uzyskał stopień naukowy dra habilitowanego w dyscyplinie telekomunikacja. Jego zainteresowania badawcze ukierunkowane są na telekomunikacyjne...
-
Tax preferences in CIT in numbers 2009-2015
Dane BadawczeThese data contain information prepared by the Ministry of Finance on the value of tax preferences by areas of support in Corporate Income Tax (CIT) between 2009-2015.
-
Histogram of Gradients with Cell Average Intensity for Human Detection
PublikacjaThe modification of the descriptor in human detector using Histogram of Oriented Gradients and support vector machine is presented. The proposed modification requires inserting the average cell intensitiesresulting with the increase of the length of the descriptor from 3780 to 4200 values, but it is easy to compute and instantly gives 14-26% of miss rate improvement at 10^-4 False Positives Per Window (FPPW). The modification...
-
Selecting Features with SVM
PublikacjaA common problem with feature selection is to establish how many features should be retained at least so that important information is not lost. We describe a method for choosing this number that makes use of Support Vector Machines. The method is based on controlling an angle by which the decision hyperplane is tilt due to feature selection. Experiments were performed on three text datasets generated from a Wikipedia dump. Amount...
-
In uence of Low-Level Features Extracted from Rhythmic and Harmonic Sections on Music Genre Classi cation
PublikacjaWe present a comprehensive evaluation of the infuence of 'harmonic' and rhythmic sections contained in an audio file on automatic music genre classi cation. The study is performed using the ISMIS database composed of music files, which are represented by vectors of acoustic parameters describing low-level music features. Non-negative Matrix Factorization serves for blind separation of instrument components. Rhythmic components...
-
Obtaining a Well-Trained Artificial Intelligence Algorithm from Cross-Validation in Endoscopy
PublikacjaThe article shortly discusses endoscopic video analysis problems and artificial intelligence algorithms supporting it. The most common method of efficiency testing of these algorithms is to perform intensive cross-validation. This allows for accurately evaluate their performance of generalization. One of the main problems of this procedure is that there is no simple and universal way of obtaining a specific instance of a well-trained...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublikacjaThe aim of the study is to compare electroencephalographic (EEG) signal feature extraction methods in the context of the effectiveness of the classification of brain activities. For classification, electroencephalographic signals were obtained using an EEG device from 17 subjects in three mental states (relaxation, excitation, and solving logical task). Blind source separation employing independent component analysis (ICA) was...
-
Comparing the Effectiveness of ANNs and SVMs in Forecasting the Impact of Traffic-Induced Vibrations on Building
PublikacjaTraffic - induced vibrations may cause damage to structural elements and may even lead to structural collapse. The aim of the article is to compare the effectiveness of algorithms in forecasting the impact of vibrations on buildings using the Machine Learning (ML) methods. The paper presents two alternative approaches by using Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). Factors that may affect traffic-induced...
-
Source code - AI models (MLM1-5 - series I-III - QNM opt)
Dane BadawczeSource code - AI models (MLM1-5 - series I-III - QNM opt) for the paper "Computational Complexity and Its Influence on Concrete Compressive Strength Prediction Capabilities of Machine Learning Models for Concrete Mix Design Support" accepted for publication.
-
DC-link voltage balancing in cascaded H-Bridge converters
PublikacjaIn the paper a DC-link voltage balancing strategy for multilevel Cascaded H-Bridge (CHB) converter is proposed. Presented solution bases on optimal choice of active vector durations in Space-Vector Pulse Width Modulation (SV-PWM). It makes it possible to DC-link voltages control and to properly generate the output voltage vector in the case of DC-link voltage unbalance. Results of simulation and experimental researches...
-
Mathematical models of process quality on the example of the bakery industry
PublikacjaThis article presents a new approach to quantitative dimensionless assessment of the efficiency and competitiveness of production processes. New concepts of process quality and relative product quality have been introduced. Process quality was expressed in vector and scalar. The process quality vector ono was expressed by the product of reliability by the vector from the sum of three components taking into account the composition...
-
Krzysztof Goczyła prof. dr hab. inż.
OsobyKrzysztof Goczyła, profesor zwyczajny Politechniki Gdańskiej, informatyk, specjalista z inżynierii oprogramowania, inżynierii wiedzy i baz danych. Ukończył studia wyższe na Wydziale Elektroniki Politechniki Gdańskiej w 1976 r. jako magister inżynier elektronik w specjalności automatyka. Na Politechnice Gdańskiej pracuje od 1976. Na Wydziale Elektroniki PG w 1982 r. uzyskał doktorat z informatyki, a w 1999 r. habilitację. W 2012...
-
Informatization strategies 23/24
Kursy OnlineThis eCourse is designed to support lectures and laboratories to the subject: Informatization strategies - academic yesr: 23/24
-
SASD Support for training and career development of researchers
ProjektyProjekt realizowany w Wydział Zarządzania i Ekonomii zgodnie z porozumieniem 247549 z dnia 2010-09-10
-
Coupling coefficients for the space group of the hexagonal close-packed structure
PublikacjaWe have computed the Clebsch-Gordan coefficients of the representations for the space group of the hexagonal close-packed structure for the points:V, A, H, K, L, M. We enumerate all arms of the wave vector stars and all wave vector selection rules.
-
Detection of Denatonium Benzoate (Bitrex) Remnants in Noncommercial Alcoholic Beverages by Raman Spectroscopy
PublikacjaIllegal alcoholic beverages are often introduced into market using cheap technical alcohol, which is contaminated by denatonium benzoate (Bitrex) of very small concentration. Bitrex is the most bitter chemical compound and has to be removed before alcohol consumption. The home-made methods utilize sodium hypochlorite to disintegrate particles of denatonium benzoate in alcohol and to remove bitter taste before trading. In this experimental...
-
Sleep Apnea Detection by Means of Analyzing Electrocardiographic Signal
PublikacjaObstructive sleep apnea (OSA) is a condition of cyclic, periodic ob-struction (stenosis) of the upper respiratory tract. OSA could be associated with serious cardiovascular problems, such as hypertension, arrhythmias, hearth failure or peripheral vascular disease. Understanding the way of connection between OSA and cardiovascular diseases is important to choose proper treatment strategy. In this paper, we present a method for integrated...
-
Ranking Speech Features for Their Usage in Singing Emotion Classification
PublikacjaThis paper aims to retrieve speech descriptors that may be useful for the classification of emotions in singing. For this purpose, Mel Frequency Cepstral Coefficients (MFCC) and selected Low-Level MPEG 7 descriptors were calculated based on the RAVDESS dataset. The database contains recordings of emotional speech and singing of professional actors presenting six different emotions. Employing the algorithm of Feature Selection based...
-
Highlighting interlanguage phoneme differences based on similarity matrices and convolutional neural network
PublikacjaThe goal of this research is to find a way of highlighting the acoustic differences between consonant phonemes of the Polish and Lithuanian languages. For this purpose, similarity matrices are employed based on speech acoustic parameters combined with a convolutional neural network (CNN). In the first experiment, we compare the effectiveness of the similarity matrices applied to discerning acoustic differences between consonant...
-
Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models
PublikacjaThis work addresses artificial-intelligence-based buried object characterization using 3-D full-wave electromagnetic simulations of a ground penetrating radar (GPR). The task is to characterize cylindrical shape, perfectly electric conductor (PEC) object buried in various dispersive soil media, and in different positions. The main contributions of this work are (i) development of a fast and accurate data driven surrogate modeling...
-
ANALIZA PARAMETRÓW SYGNAŁU MOWY W KONTEKŚCIE ICH PRZYDATNOŚCI W AUTOMATYCZNEJ OCENIE JAKOŚCI EKSPRESJI ŚPIEWU
PublikacjaPraca dotyczy podejścia do parametryzacji w przypadku klasyfikacji emocji w śpiewie oraz porównania z klasyfikacją emocji w mowie. Do tego celu wykorzystano bazę mowy i śpiewu nacechowanego emocjonalnie RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song), zawierającą nagrania profesjonalnych aktorów prezentujących sześć różnych emocji. Następnie obliczono współczynniki mel-cepstralne (MFCC) oraz wybrane deskryptory...
-
Rapid Evaluation of Poultry Meat Shelf Life Using PTR-MS
PublikacjaThe use of proton transfer reaction mass spectrometry (PTR-MS) for freshness classification of chicken and turkey meat samples was investigated. A number of volatile organic compounds (VOCs) were selected based on the correlation (> 95%) of their concentration during storage at 4 °C over a period of 5 days with the results of the microbial analysis. In order to verify if the selected compounds are not sample-specific, a number...
-
An electronic nose for quantitative determination of gas concentrations
PublikacjaThe practical application of human nose for fragrance recognition is severely limited by the fact that our sense of smell is subjective and gets tired easily. Consequen tly, there is considerable need for an instrument that can be a substitution of the human sense of smell. Electronic nose devices from the mid 1980s are used in growing number of applications. They comprise an array of several electrochemical gas sensors...
-
Multiscalar Model Based Control Systems for AC Machines
PublikacjaContents of the Chapter: Nonlinear transformations and feedback linearization. Models of the squirrel cage induction machine: Vector model of the squirrel cage induction machine. Multiscalar models of the squirrel cage induction machine.Feedback linearization of multiscalar models of the induction motor.Models of the double fed induction machine: Vector model of the double fed induction machine. Multiscalar model of the...
-
XRD for MoS2-Carbon Based Materials
Dane BadawczeThe presented data showcases the results of XRD analysis conducted on molybdenum sulfide modified with carbon. The MoS2-carbon base materials were prepared via a facile hydrothermal method. Structural characterization confirmed the successful incorporation of carbon into the MoS2 support. XRD was recorded using an X-ray diffractometer (Philips X”Pert...
-
Policy of supporting scientific and research activities in selected private universities in Gdańsk, Sopot and Gdynia in 2010
Dane BadawczeAs the research results show, all surveyed universities support research primarily by helping to obtain funds from the EU and providing resources for scientific literature. 6 universities declare financing investments in equipment and activities supporting research, as well as assistance in obtaining funds from other sources. However, none of the universities...
-
Output voltage, current and DC-link voltages under SPWM, experimental results
Dane BadawczeThe dataset contains the experimental results of the project: A universal algorithm of space vector pulse width modulation for three-level three and multi-phase NPC inverters with DC-link voltage balancing. The output line-to-line voltage, output current and DC-link voltages were included. The Carrier-Based Pulse-Width Modulation (CBPWM) technique was...
-
A Note on Fractional Curl Operator
PublikacjaIn this letter, we demonstrate that the fractional curl operator, widely used in electromagnetics since 1998, is essentially a rotation operation of components of the complex Riemann–Silberstein vector representing the electromagnetic field. It occurs that after the wave decomposition into circular polarisations, the standard duality rotation with the angle depending on the fractional order is applied to the left-handed basis vector...