displaying 1000 best results Help
Search results for: final prediction error
-
Jacek Stefański prof. dr hab. inż.
PeopleJJacek Stefański received M.Sc., Ph.D. and D.Sc. degrees in telecommunications engineering from Gdansk University of Technology (GUT), Poland, in 1993, 2000 and 2012, respectively. Awarded title of Professor by the President of Poland in 2020. Currently, he works as a professor at the Department of Radio Communication Systems and Networks (DRCSN) in GUT. From 2005 to 2009, he worked as an assistant professor in the National Institute...
-
Olgun Aydin dr
PeopleOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Principal Machine Learning Engineer in Nike, and works as Assistant Professor in Gdansk University of Technology in Poland. Dr. Aydin is part of editorial board of "Journal of Artificial Intelligence and Data Science" Dr. Aydin served as Vice-Chairman of Why R? Foundation and is member of Polish Artificial Intelligence Society. Olgun is...
-
Analiza porównawcza metod predykcji chwili zgodności fazowejw automatycznym synchronizatorze prądnic = Comparison of the methods of prediction time phase coincidence in automatic synchronizer of power generators
PublicationW artykule porównano dokładność wybranych metod realizacji warunku fazowego podczas synchronizacji obiektów elektroenergetycznych. Do porównania wybrano trzy metody: liniową, wielomianową oraz metodę adaptacyjnej synchronizacji prądnic z ekstrapolacją funkcją wymierną. Badania przeprowadzono dla różnych warunków pracy. Przyjęto stałą różnicę częstotliwości napięć synchronizowanych obiektów, różnicę częstotliwości zmieniającą się...
-
Validation of EORTC, CUETO, and EAU risk stratification in prediction of recurrence, progression, and death of patients with initially non–muscle‐invasive bladder cancer (NMIBC): A cohort analysis
Publication -
Comparative Study of Pavement Rehabilitation Using Hot in-Place Recycling and Hot-Mix Asphalt: Performance Evaluation, Pavement Life Prediction, and Life Cycle Cost Analysis
Publication -
Theoretical designing of selenium heterocyclic non-fullerene acceptors with enhanced power conversion efficiency for organic solar cells: a DFT/TD-DFT-based prediction and understanding
PublicationIn this study, we have designed and explored a new series of non-fullerene acceptors for possible applications in organic solar cells. We have designed four molecules named as APH1 to APH4 after end-capped modification of recently synthesized Y6-Se-4Cl molecule. Density functional theory and time dependent-density functional theory have been employed for computing geometric and photovoltaic parameters of the designed molecules....
-
Review of Research into Enterprise Bankruptcy Prediction in Selected Central and Eastern European Countries (prezentacja na konferencji TWENTY-SIXTH ANNUAL CONFERENCE MULTINATIONAL FINANCE SOCIETY)
PublicationUlotka konferencyjna: http://www.mfsociety.org/modules/modMainContent/uploadFiles/miscFiles/1562848077-MFC2019-Booklet-for-Distribution_2019-06-25.pdf
-
AOP173 key event associated pathway predictor – online application for the prediction of benchmark dose lower bound (BMDLs) of a transcriptomic pathway involved in MWCNTs-induced lung fibrosis
Publication -
Cytokine TGFβ Gene Polymorphism in Asthma: TGF-Related SNP Analysis Enhances the Prediction of Disease Diagnosis (A Case-Control Study With Multivariable Data-Mining Model Development)
Publication -
Productivity Enhancement by Prediction of Liquid Steel Breakout during Continuous Casting Process in Manufacturing of Steel Slabs in Steel Plant Using Artificial Neural Network with Backpropagation Algorithms
Publication -
Piotr Figura dr inż.
PeoplePiotr Figura is employed as an assistant professor at the Department of Finance at the Faculty of Management and Economics, Gdansk University of Technology. He is a member of Commission for the Verification of Learning Outcomes, as well as an academic reviewer of the Central Exemination Booard. He is the author or co-author of several scientific monographs including: Standard financial indicators for stock enterprises; Classical...
-
International Symposium on Applied Algebra, Algebraic Algorithms and Error-Correcting Codes
Conferences -
Square root RC Nyquist filter of fractional delay
PublicationIn this paper we propose a discrete-time FIR (finite impulse response) filter which couples the role of square root Nyquist filter with fractional delay filter. This filter enables to substitute for a cascade of square root RC (SRRC) Nyquist filter and fractional delay filter in one device/algorithm. The aim is to compensate for transmission delay in communication system. Statistically defined performances, e.g. BER (bit error...
-
Validation of EORTC, CUETO and EAU risk stratification in prediction of recurrence, progression and death of patients with initially non-muscle invasive bladder cancer (NMIBC): a cohort analysis with systematic review.
Publication -
Reply to “Comment on ‘Crystal Structure Prediction by Global Optimization as a Tool for Evaluating Potentials: Role of the Dipole Moment Correction Term in Successful Predictions'” by B. P. van Eijck and J. Kroon
Publication -
Leszek Ziemczonek dr
PeopleUniversity education 1973-1978 – Nicolaus Copernicus University in Toruń, University of Gdańsk in Gdańsk, Mathematical Physics, M. Sc. 1979 – Diploma of Postgraduate Studies, Pedagogics 1989 – Institute of Physics, Polish Academy of Sciences in Warsaw, Theoretical Physics, Ph. D. 2010-2012 – Diploma of Postgraduate Studies, Mathematics Training: · 09.1983 – Trieste (Italy) – International Centre for Theoretical Physics...
-
Source code - AI models (MLM1-5 - series I-III - QNM opt)
Open Research DataSource 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.
-
Zdzisław Kowalczuk prof. dr hab. inż.
PeopleZdzislaw Kowalczuk received his M.Sc. degree in 1978 and Ph.D. degree in 1986, both in Automatic Control from Technical University of Gdańsk (TUG), Gdańsk, Poland. In 1993 he received his D.Sc. degree (Dr Habilitus) in Automatic Control from Silesian Technical University, Gliwice, Poland, and the title of Professor from the President of Poland in 2003. Since 1978 he has been with Faculty of Electronics, Telecommunications and Informatics...
-
Employing flowgraphs for forward route reconstruction in video surveillance system
PublicationPawlak’s flowgraphs were utilized as a base idea and knowledge container for prediction and decision making algorithms applied to experimental video surveillance system. The system is used for tracking people inside buildings in order to obtain information about their appearance and movement. The fields of view of the cameras did not overlap. Therefore, when an object was moving through unsupervised areas, prediction was needed...
-
A Computationally Efficient Model for Predicting Successful Memory Encoding Using Machine-Learning-based EEG Channel Selection
PublicationComputational cost is an important consideration for memory encoding prediction models that use data from dozens of implanted electrodes. We propose a method to reduce computational expense by selecting a subset of all the electrodes to build the prediction model. The electrodes were selected based on their likelihood of measuring brain activity useful for predicting memory encoding better than chance (in terms of AUC). A logistic...
-
MP3vec: A Reusable Machine-Constructed Feature Representation for Protein Sequences
Publication—Machine Learning (ML) methods have been used with varying degrees of success on protein prediction tasks, with two inherent limitations. First, prediction performance often depends upon the features extracted from the proteins. Second, experimental data may be insufficient to construct reliable ML models. Here we introduce MP3vec, a transferable representation for protein sequences that is designed to be used specifically for sequence-to-sequence...
-
Karolina Zielińska-Dąbkowska dr inż. arch.
PeopleKarolina M. Zielinska-Dabkowska, Ph.D., Eng. Arch., M. Arch., is an Assistant Professor at the Faculty of Architecture of Gdańsk University of Technology (GUT). In 2002, she completed her studies of Architecture and Urban Planning at Gdańsk University of Technology (Gdańsk Tech) and in 2004, Architectural Engineering at the University of Applied Sciences and Arts (HAWK) in Hildesheim, Germany. After graduation, she worked for several...
-
Marcin Kulawiak dr hab. inż.
People -
Automated Reduced Model Order Selection
PublicationThis letter proposes to automate generation of reduced-order models used for accelerated -parameter computation by applying a posteriori model error estimators. So far,a posteriori error estimators were used in Reduced Basis Method (RBM) and Proper Orthogonal Decomposition (POD) to select frequency points at which basis vectors are generated. This letter shows how a posteriori error estimators can be applied to automatically select...
-
Implementation of magnitude calculation of complex numbers using improved alpha max plus beta min algorithm
PublicationThe paper presents the hardware implementation of the improved alpha max plus beta min algorithm for calculating the magnitude of complex numbers. This version of the algorithm requires the general division which is performed using a noniterative multiplicative division algorithm. We analyze in detail the division algorithm, its error and the impact of finite word-length signal representations on the assumed total computation error....
-
Simulation of the weight averaging of pulse frequency modulated sensor output signal
Open Research DataThe aim of the research is investigation of the efficiency of weight averaging of pulse frequency modulated signal. It was shown that from the point of view of the reduction of the sampling error the best are polynomial weighing functions, for which the maximum of this component error decreases proportionally to the appropriate power of the number of...
-
FPGA computation of magnitude of complex numbers using modified CORDIC algorithm
PublicationIn this work we present computation of the magnitude of complex numbers using a modified version of the CORDIC algorithm that uses only five iterations. The relationship between the computation error and the number of CORDIC iterations are presented for floating-point and integer arithmetics. The proposed modification of CORDIC for integer arithmetic relies upon the introduction of correction once basic computations are performed...
-
Noise effect on parameters of quiet sonar with code modulation
PublicationEarlier publications of the paper authors have shown that the use of code keying mixed with the CW FM sound signal allows the significant reduction in the distance measurement error, compared to classic silent CW FM sonar. In addition to the code modulation parameters, the magnitude of this error is influenced by the received input acoustic noise. The article shows the dependence of the input signal-to-noise ratio and the sound...
-
Guido: a musical score recognition system
PublicationThis paper presents an optical music recognition system Guido that can automatically recognize the main musical symbols of music scores that were scanned or taken by a digital camera. The application is based on object model of musical notation and uses linguistic approach for symbol interpretation and error correction. The system offers musical editor with a partially automatic error correction.
-
Constrained aerodynamic shape optimization using neural networks and sequential sampling
PublicationAerodynamic shape optimization (ASO) involves computational fluid dynamics (CFD)-based search for an optimal aerodynamic shape such as airfoils and wings. Gradient-based optimization (GBO) with adjoints can be used efficiently to solve ASO problems with many design variables, but problems with many constraints can still be challenging. The recently created efficient global optimization algorithm with neural network (NN)-based prediction...
-
Sidrish Zahra
PeopleSidrish Zahra received her B.Sc. degree in Electrical (Telecommunication) Engineering from school of Electrical Engineering, Government College University Faisalabad (GCUF), Pakistan in 2016.Then, she received the M.S. degree in School of Information and Communication Engineering, University of Electronic Science & Technology of China (UESTC) in 2019. Now, She is pursuing her Ph.D. degree in Control, Electrical and Electronics...
-
Compensation of magnetic disturbances caused by sensors in a differential magnetometric system
PublicationStudy of low magnetic fields necessitates the use of precision magnetometers working in a differential system. Minimization of this error is a substantial issue in the case of magnetometers working in a differential system on a mobile platform. The compensation method of heading error consists in taking measurements of changes in magnetic induction with the use of the tested magnetometer for various locations of the sensor in relation...
-
Balance errors generated by numerical diffusion in the solution of non-linear open channel flow equations
PublicationThe paper concerns the untypical aspect of application of the dissipative numerical methods to solve nonlinear hyperbolic partial differential equations used in open channel hydraulics. It is shown that in some cases the numerical diffusion generated by the applied method of solution produces not only inaccurate solution but as well as a balance error. This error may occur even for an equation written in the conservative form not...
-
Feature Reduction Using Similarity Measure in Object Detector Learning with Haar-like Features
PublicationThis paper presents two methods of training complexity reduction by additional selection of features to check in object detector training task by AdaBoost training algorithm. In the first method, the features with weak performance at first weak classifier building process are reduced based on a list of features sorted by minimum weighted error. In the second method the feature similarity measures are used to throw away that features...
-
Dead-Time Effect Compensation Based on Additional Phase Current Measurements
PublicationThis paper proposes a new method of dead-time effect compensation. The proposed solution is based on additional phase current measurements realized by analog-to-digital converters. These measurements are carried out at the time instants specified by a pulsewidth-modulation (PWM) strategy. This makes it possible to estimate inverter currents at the commutation instants and, finally, to estimate the voltage error caused by dead time. This...
-
A Novel Iterative Decoding for Iterated Codes Using Classical and Convolutional Neural Networks
PublicationForward error correction is crucial for communication, enabling error rate or required SNR reduction. Longer codes improve correction ratio. Iterated codes offer a solution for constructing long codeswith a simple coder and decoder. However, a basic iterative code decoder cannot fully exploit the code’s potential, as some error patterns within its correction capacity remain uncorrected.We propose two neural network-assisted decoders:...
-
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...
-
Detection of impulsive disturbances in archive audio signals
PublicationIn this paper the problem of detection of impulsive disturbances in archive audio signals is considered. It is shown that semi-causal/noncausal solutions based on joint evaluation of signal prediction errors and leave-one-out signal interpolation errors, allow one to noticeably improve detection results compared to the prediction-only based solutions. The proposed approaches are evaluated on a set of clean audio signals contaminated...
-
Development of Gas Sensor Array for Methane Reforming Process Monitoring
PublicationThe article presents a new method of monitoring and assessing the course of the dry methane reforming process with the use of a gas sensor array. Nine commercially available TGS chemical gas sensors were used to construct the array (seven metal oxide sensors and two electrochemical ones). Principal Component Regression (PCR) was used as a calibration method. The developed PCR models were used to determine the quantitative parameters...
-
Impact of Low Switching-to-Fundamental Frequency Ratio on Predictive Current Control of PMSM: A simulation study
PublicationPredictive current control algorithms for permanent magnet synchronous (PMSM) drives rely on an assumption that within short intervals motor currents can be approximated with linear functions. This approximation may result either from discretizing the motor model or from simplifications applied to the continuous-time model. As the linear current approximation has been recognized as inaccurate in case when the drive operates with...
-
Determination of changes in viscosity of refined oil depending on the temperature (19-96 Celsius degrees).
Open Research DataThe rheological characteristics of the refined oil were made on the basis of the viscosity assessment using a Brookfield viscometer with an LV SC4 - 18 spindle and a shear rate of 52.8 s-1 in from temperature 19-96 °C.
-
Katarzyna Mazur mgr inż.
PeopleKatarzyna Mazur is a graduate of the interdisciplinary Faculty of Mechanical and Medical Engineering, jointly conducted by Gdańsk University of Technology and Medical University of Gdańsk. In 2012, she received the Gold Medal of Gdansk University of Technology for the final result of her studies and placed herself among the 5% of the Best Graduates of Gdansk University of Technology in the academic year 2011/2012.
-
Identification of ship’s hull mathematical model with numerical methods
PublicationThe modern maritime industry is moving toward the development of technology that will allow for full or partial autonomy of ship operation. This innovation places high demands on ship performance prediction techniques at the design stage. The researchwork presented in the article is related to the design stage of the ship and concerns methods for prognosis and evaluation of the specific operational condition of the ship, namely...
-
Wireless intelligent audio-video surveillance prototyping system
PublicationThe presented system is based on the Virtex6 FPGA and several supporting devices like a fast DDR3 memory, small HD camera, microphone with A/D converter, WiFi radio communication module, etc. The system is controlled by the Linux operating system. The Linux drivers for devices implemented in the system have been prepared. The system has been successfully verified in a H.264 compression accelerator prototype in which the most demanding...
-
Reliable Greedy Multipoint Model-Order Reduction Techniques for Finite-Element Analysis
PublicationA new greedy multipoint model-order reduction algorithm for fast frequency-domain finite-element method simulations of electromagnetic problems is proposed. The location of the expansion points and the size of the projection basis are determined based on a rigorous error estimator. Compared to previous multipoint methods, the quality of the error estimator is significantly improved by ensuring the orthogonality of the projection...
-
Electronic transition dipole moment functions of the first singlet Delta gerade and first triplet Delta ungerade states of the Lithium dimer
Open Research DataElectronic transition dipole moment functions (ETDMF) of the first singlet Delta gerade (1sDg) and first triplet Delta ungerade (1tDu) states have been calculated for the Lithium dimer. ETDMFs are needed in understanding processes like photodissociation, photoassociation, cooling, and trapping of molecules. The results of the four ETDMFs have been obtained...
-
Electronic transition dipole moment functions of the second triplet Sigma ungerade plus state of the Lithium dimer
Open Research DataElectronic transition dipole moment functions (ETDMF) of the second triplet Sigma ungerade plus (2tSu+) state have been calculated for the Lithium dimer. ETDMFs are needed in understanding processes like photodissociation, photoassociation, cooling, and trapping of molecules. The results of the five ETDMFs have been obtained by the nonrelativistic multireference...
-
Electronic transition dipole moment functions of the second singlet Sigma ungerade plus and second triplet Sigma gerade plus states of the Lithium dimer
Open Research DataElectronic transition dipole moment functions (ETDMF) of the second singlet Sigma ungerade plus (2sSu+) and second triplet Sigma gerade plus (2tSg+) states have been calculated for the Lithium dimer. ETDMFs are needed in understanding processes like photodissociation, photoassociation, cooling, and trapping of molecules. The results of the four ETDMFs...
-
Electronic transition dipole moment functions of the third singlet Sigma gerade plus state of the Lithium dimer
Open Research DataElectronic transition dipole moment functions (ETDMF) of the third singlet Sigma gerade plus (3sSg+) state have been calculated for the Lithium dimer. ETDMFs are needed in understanding processes like photodissociation, photoassociation, cooling, and trapping of molecules. The results of the five ETDMFs have been obtained by the nonrelativistic multireference...
-
Electronic transition dipole moment functions of the first singlet Sigma ungerade plus and first triplet Sigma gerade plus states of the Lithium dimer
Open Research DataElectronic transition dipole moment functions (ETDMF) of the first singlet Sigma ungerade plus (1sSu+) and first triplet Sigma gerade plus (1tSg+) states have been calculated for the Lithium dimer. ETDMFs are needed in understanding processes like photodissociation, photoassociation, cooling, and trapping of molecules. The results of the four ETDMFs...