Search
Filters
total: 12212
-
Catalog
- Publications 9874 available results
- Journals 219 available results
- Conferences 149 available results
- Publishing Houses 2 available results
- People 228 available results
- Inventions 1 available results
- Projects 12 available results
- e-Learning Courses 170 available results
- Events 19 available results
- Open Research Data 1538 available results
displaying 1000 best results Help
Search results for: ARTIFICIAL INTELLIGENCE, BURIED OBJECT CHARACTERIZATION, DEEP REGRESSION NETWORK, GROUND PENETRATING RADAR (GPR), SURROGATE MODELING, TIME FREQUENCY SPECTROGRAM
-
Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models
PublicationThis 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...
-
Buried Object Characterization by Data-Driven Surrogates and Regression-Enabled Hyperbolic Signature Extraction
PublicationThis work addresses artificial-intelligence-based buried object characterization using FDTD-based electromagnetic simulation toolbox of a Ground Penetrating Radar (GPR) to generate B-scan data. In data collection, FDTD-based simulation tool, gprMax is used. The task is to estimate geophysical parameters of a cylindrical shape object of various radii, buried at different positions in the dry soil medium simultaneously and independently...
-
Variable Data Structures and Customized Deep Learning Surrogates for Computationally Efficient and Reliable Characterization of Buried Objects
PublicationIn this study, in order to characterize the buried object via deep-learning-based surrogate modeling approach, 3-D full-wave electromagnetic simulations of a GPR model has been used. The task is to predict simultaneously and independent of each characteristic parameters of a buried object of several radii at different positions (depth and lateral position) in various dispersive subsurface media. This study has analyzed variable...
-
High frequency impulse ground penetrating radar application in assessment of interlayer connections
PublicationGround Penetrating Radar (GPR) technique is commonly used in the nondestructive evaluation of pavement structures. In particular, this method is used to estimate thicknesses of pavement layers as well as it can be utilized in advanced studies of pavement structures. The device presented in this paper comprise the high frequency impulse antennas that allow for investigating the interlayer zones in terms of their electromagnetic...
-
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...
-
A novel heterogeneous model of concrete for numerical modelling of ground penetrating radar
PublicationThe ground penetrating radar (GPR) method has increasingly been applied in the non-destructive testing of reinforced concrete structures. The most common approach to the modelling of radar waves is to consider concrete as a homogeneous material. This paper proposes a novel, heterogeneous, numerical model of concrete for exhaustive interpretation of GPR data. An algorithm for determining the substitute values of the material constants...
-
3-D finite-difference time-domain modelling of ground penetrating radar for identification of rebars in complex reinforced concrete structures
PublicationThis paper presents numerical and experimental investigations to identify reinforcing bars using the ground penetrating radar (GPR) method. A novel element of the paper is the inspection of different arrangements of reinforcement bars. Two particular problems, i.e. detection of few adjacent transverse bars and detection of a longitudinal bar located over or under transverse reinforcement, have been raised. An attention was also...
-
A novel method of time-frequency analysis: an essential spectrogram
PublicationA novel precise method of time-frequency analysis is presented. In the algorithm, a new energy distribution is estimated by simultaneously discard or displacement of the classical spec- trogram energy. A channelized instantaneous frequency and a local group delay are used in order to replacement in the same manner as formulated by Kodera et al. [1, 2]. Additionally, new representations: a channelized instantaneous bandwidth and...
-
Numerical modeling of GPR field in damage detection of a reinforced concrete footbridge
PublicationThe paper presents a study on the use of the ground penetrating radar (GPR) method in diagnostics of a footbridge. It contains experimental investigations and numerical analyses of the electromagnetic field propagation using the finite difference time domain method (FDTD). The object of research was a reinforced concrete footbridge over a railway line. The calculations of the GPR field propagation were performed on a selected cross-section...
-
Applying ground penetrating radar to tracking of ancient architectural transformations: the case of the monastery St. Peter on the Island of Rab (Croatia)
PublicationThe ground-penetrating radar (GPR) method has been used for many years in archaeological research. However, thismethod is still not widely used in studies of past architecture. The biggest problem with the implementation of the GPRmethod at such sites is usually connected with extensive debris layers, plant cover and standing relics of walls and otherfeatures that restrict the available measurement area. Despite of these, properly...
-
Improved Modeling of Microwave Structures Using Performance-Driven Fully-Connected Regression Surrogate
PublicationFast replacement models (or surrogates) have been widely applied in the recent years to accelerate simulation-driven design procedures in microwave engineering. The fundamental reason is a considerable—and often prohibitive—CPU cost of massive full-wave electromagnetic (EM) analyses related to solving common tasks such as parametric optimization or uncertainty quantification. The most popular class of surrogates are data-driven...
-
Ridged horn antenna for ground penetrating radar
PublicationOmówiono modyfikację tuby grzbietowej polegającą na jej wypełnieniu dielektrykiem, w celu wykorzystania do układu pozwalającego na poszukiwanie obiektów znajdujących się pod ziemią. Omówiono badania, które doprowadziły do opracowania konstrukcji anteny z wypełnieniem dielektrycznym. Przedstawiono wyniki testu takiej anteny w układzie do detekcji obiektu metalowego umieszczonego pod ziemią.
-
Non-destructive Diagnostics of the Floor in the Gdańsk Crane Using Ground Penetrating Radar = Diagnostyka nieniszcząca posadzki w gdańskim Żurawiu z zastosowaniem metody georadarowej
PublicationThis paper presents the results of a ground penetrating radar (GPR) survey carried out at the Crane in Gdańsk. The measurements were conducted on the floor of the southern and northern towers. The aim of the experiment is to assess the possibility of detecting anomalies beneath the floor. The surveys were carried out in a non-destructive manner, using a georadar unit with 2 GHz and 400/900 MHz antennas. This paper compares the...
-
Deep-Learning-Based Precise Characterization of Microwave Transistors Using Fully-Automated Regression Surrogates
PublicationAccurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning...
-
Global Surrogate Modeling by Neural Network-Based Model Uncertainty
PublicationThis work proposes a novel adaptive global surrogate modeling algorithm which uses two neural networks, one for prediction and the other for the model uncertainty. Specifically, the algorithm proceeds in cycles and adaptively enhances the neural network-based surrogate model by selecting the next sampling points guided by an auxiliary neural network approximation of the spatial error. The proposed algorithm is tested numerically...
-
Detection and time/frequency analysis of electric fields in the ground
PublicationThis paper sets out to detect and characterize electric fields in the ground (such as stray current fields) using a tandem time/frequency method of signal analysis. Results were obtained from investigations performed in the presence of a generated electric field with controlled variable characteristics, and in the presence of an electric field generated by a tramline. The analysis of measurement registers was performed using Short‐Time...
-
Time-frequency analysis of acoustic signals using concentrated spectrogram
PublicationThe paper presents improved method of time-frequency (TF) analysis of discrete-time signals. The method involves signal's local group delay (LGD) and channelized instantaneous frequency (CIF) to purposely redistribute all Short-time Fourier transform (STFT) lines. Additionally, the energy concentration index (ECI) and some histogram-like statistics are used to evaluate readability of estimated TF distributions of the energy. Recorded...
-
Performance-Driven Surrogate Modeling of High-Frequency Structures
PublicationThe development of modern high-frequency structures, including microwave and antenna components, heavily relies on full-wave electromagnetic (EM) simulation models. Notwithstanding, EM-driven design entails considerable computational expenses. This is especially troublesome when solving tasks that require massive EM analyzes, parametric optimization and uncertainty quantification be-ing representative examples. The employment of...
-
GPR simulations for diagnostics of a reinforced concrete beam
PublicationThe most popular technique for modelling of an electromagnetic field, the finite difference time domain (FDTD) method, has recently become a popular technique as an interpretation tool for ground penetrating radar (GPR) measurements. The aim of this study is to detect the size and the position of damage in a reinforced concrete beam using GPR maps. Numerical simulations were carried out using the finite differ-ence time domain...
-
Mutual Coupling Reduction in Antenna Arrays Using Artificial Intelligence Approach and Inverse Neural Network Surrogates
PublicationThis paper presents a novel approach to reduce undesirable coupling in antenna arrays using custom-designed resonators and inverse surrogate modeling. To illustrate the concept, two stand-ard patch antenna cells with 0.07λ edge-to-edge distance are designed and fabricated to operate at 2.45 GHz. A stepped-impedance resonator is applied between the antennas to suppress their mutual coupling. For the first time, the optimum values...
-
Application of gpr method in diagnostics of reinforced concrete structures
PublicationThis paper presents an application of the ground penetration method (GPR) for diagnostics of reinforced concrete structures. In situ measurements were conducted for three civil engineering structures: the ground floor structure, the abutment of the railway viaduct and the concrete well. The dual polarized ground penetrating radar with the antenna operating at a center frequency of 2 GHz was used for GPR surveys. Three different...
-
Modeling and Simulation for Exploring Power/Time Trade-off of Parallel Deep Neural Network Training
PublicationIn the paper we tackle bi-objective execution time and power consumption optimization problem concerning execution of parallel applications. We propose using a discrete-event simulation environment for exploring this power/time trade-off in the form of a Pareto front. The solution is verified by a case study based on a real deep neural network training application for automatic speech recognition. A simulation lasting over 2 hours...
-
Usage of parametric echosounder with emphasis on buried object searching.
PublicationThe purpose of this article is to present the results of investigation to search for buried objects. The paper will contain echograms and other means of visualization from buried pipe placed between area of W?adys?awowo and gas platform and interesting in terms of the number of small and medium-sized unidentified objects found in the muddy bottom at different depths localized in the Gulf of Puck - results will be presented also...
-
Recent Advances in Performance-Driven Surrogate Modeling of High-Frequency Structures
PublicationDesign of high‐frequency structures, including microwave and antenna components, heavily relies on full‐wave electromagnetic (EM) simulation models. Their reliability comes at a price of a considerable computational cost. This may lead to practical issues whenever numerous EM analyses are to be executed, e.g., in the case of parametric optimization. The difficulties entailed by massive simulations may be mitigated by the use of...
-
Radar Signal Parameters Estimation Using Phase Accelerogram in the Time-Frequency Domain
PublicationRadar signal parameter estimation, in the context of the reconstruction of the received signal in a passive radar utilizing other radars as a source of illumination, is one of the fundamental steps in the signal processing chain in such a device. The task is also a crucial one in electronic reconnaissance systems, e.g. ELINT (Electronic Intelligence) systems. In order to obtain accurate results it is important to measure, estimate...
-
PRINCIPLES OF ARTIFICIAL INTELLIGENCE APPLICATION IN CONTROL OF THE ENTERPRISE
PublicationThe implementation of the tasks of evaluating historical financial information, the control or audit of business activities are based primarily on professional judgments about the object of study of a professional accountant or auditor. Their findings are drawn on the basis of the study of documents, the use of audit evidence, risk assessment, etc. There is always a probability (and rather high) that professional judgment will...
-
Electromagnetic Modeling of Microstrip Elements Aided with Artificial Neural Network
PublicationThe electromagnetic modeling principle aided withartificial neural network to designing the microwave widebandelements/networks prepared in microstrip technology is proposedin the paper. It is assumed that the complete information is knownfor the prototype design which is prepared on certain substratewith certain thickness and electric permittivity. The longitudinaland transversal dimensions of new design...
-
Fundamentals of Data-Driven Surrogate Modeling
PublicationThe primary topic of the book is surrogate modeling and surrogate-based design of high-frequency structures. The purpose of the first two chapters is to provide the reader with an overview of the two most important classes of modeling methods, data-driven (or approx-imation), as well as physics-based ones. These are covered in Chap-ters 1 and 2, respectively. The remaining parts of the book give an exposition of the specific aspects...
-
Interpolation methods in GPR tomographic imaging of linear and volume anomalies for cultural heritage diagnostics
PublicationThis paper presents results of a ground penetrating radar (GPR) survey conducted in St. Joseph’s Church in Gdańsk, Poland. The aim of the study was to produce tomographic imaging of a renovated floor as well as the objects buried under the floor to detect linear and volume inclusions. The assumed track spacing was meaningfully greater than the single signal spacing in each track, which induced the need for interpolation methods...
-
Ireneusz Czarnowski Prof.
PeopleIRENEUSZ CZARNOWSKI is a graduate of the Faculty of Electrical Engineering at Gdynia Maritime University. He gained a doctoral degree in the field of computer science at Poznan University of Technology and a postdoctoral degree in the field of computer science at Wroclaw University of Science and Technology. Since 1998 is associated with Gdynia Maritime University, currently is a professor of computer science in the Department...
-
Artificial Intelligence
e-Learning Courses -
Artificial intelligence
e-Learning Courses -
Accurate Modeling of Frequency Selective Surfaces Using Fully-Connected Regression Model with Automated Architecture Determination and Parameter Selection Based on Bayesian Optimization
PublicationSurrogate modeling has become an important tool in the design of high-frequency structures. Although full-wave electromagnetic (EM) simulation tools provide an accurate account for the circuit characteristics and performance, they entail considerable computational expenditures. Replacing EM analysis by fast surrogates provides a way to accelerate the design procedures. Unfortunately, modeling of microwave passives is a challenging...
-
Fundamentals of Physics-Based Surrogate Modeling
PublicationChapter 1 was focused on data-driven (or approximation-based) modeling methods. The second major class of surrogates are physics-based models outlined in this chapter. Although they are not as popular, their importance is growing because of the challenges related to construction and handling of approximation surrogates for many real-world problems. The high cost of evaluating computational models, nonlinearity of system responses,...
-
A concept of heterogeneous numerical model of concrete for GPR simulations
PublicationThe Ground Penetrating Radar (GPR) method, which is increasingly being used in the non-destructive diagnostics of reinforced concrete structures, often needs more accurate interpretation tools for analysis of experimental data. Recently, there has been growing interest in developing of various numerical models for exhaustive understanding of GPR data. This paper presents the concept of a heterogeneous numerical model of concrete,...
-
Solving the Problem of Dynamic Adaptability of Artificial Intelligence Systems that Control Dynamic Technical Objects
PublicationThis paper investigates the increase in the response speed and stability of artificial intelligence systems that control dynamic technical objects. The problem of calculating the optimal time of switching an artificial intelligence system between software classes by the criterion of the rigidity degree of the model of a control object is considered. The solution of this problem is proposed for the general case of the control object...
-
Piotr Szczuko dr hab. inż.
PeoplePiotr Szczuko received his M.Sc. degree in 2002. His thesis was dedicated to examination of correlation phenomena between perception of sound and vision for surround sound and digital image. He finished Ph.D. studies in 2007 and one year later completed a dissertation "Application of Fuzzy Rules in Computer Character Animation" that received award of Prime Minister of Poland. His interests include: processing of audio and video, computer...
-
Artificial Intelligence Aided Architectural Design
PublicationTools and methods used by architects always had an impact on the way building were designed. With the change in design methods and new approaches towards creation process, they became more than ever before crucial elements of the creation process. The automation of architects work has started with computational functions that were introduced to traditional computer-aided design tools. Nowadays architects tend to use specified tools...
-
Diagnostics of pillars in St. Mary’s Church (Gdańsk, Poland) using the GPR method
PublicationThe main goal of this study was non-destructive evaluation of pillars in the St. Mary’s Church (Gdańsk, Poland) using the ground penetrating radar (GPR) technique. The GPR inspection was conducted on four brick masonry pillars and five pillars strengthened by reinforced concrete jacketing. Data were acquired with a 2 GHz antenna along longitudinal and transverse profiles. The study involved the estimation of the electromagnetic...
-
Iterative Global Sensitivity Analysis Algorithm with Neural Network Surrogate Modeling
PublicationGlobal sensitivity analysis (GSA) is a method to quantify the effect of the input parameters on outputs of physics-based systems. Performing GSA can be challenging due to the combined effect of the high computational cost of each individual physics-based model, a large number of input parameters, and the need to perform repetitive model evaluations. To reduce this cost, neural networks (NNs) are used to replace the expensive physics-based...
-
Is Artificial Intelligence Ready to Assess an Enterprise’s Financial Security?
PublicationThis study contributes to the literature on financial security by highlighting the relevance of the perceptions and resulting professional judgment of stakeholders. Assessing a company’s financial security using only economic indicators—as suggested in the existing literature—would be inaccurate when undertaking a comprehensive study of financial security. Specifically, indices and indicators based on financial or managerial reporting...
-
Integrated Application of GPR and Ultrasonic Testing in the Diagnostics of a Historical Floor
PublicationThe paper presents the results of integrated ground penetrating radar (GPR) and ultrasonic testing (UT) measurements conducted on a historical floor in St. Nicholas’ Church, Gdańsk, Poland. The described inspection was the first stage of the technical state assessment of the building. The aim of the study was the detection of underfloor air gaps, which were observed in a few trial pits. The condition of the ground under the floor...
-
Integration of natural and artificial intelligence in production systems
PublicationIntegration processes play an increasingly important role in modern economy, and seriously co-decide about the effectiveness of the company. Integration phase occurs in the system life cycle by preceding the final stages of its implementation and activation. In turn, used in software engineering (SE) iteration-evolutionary models, such as spiral model make that the integration activities can occur in varying degrees in all phases...
-
TIME SERIES MODELING (PG_00063724)
e-Learning CoursesEffectively uses in-depth knowledge of economic time series analysis methods, applying the results of analyzes to formulate forecasts. Subject contents: 1. Classical time series analysis (trend, cyclical fluctuations) 2. Exponential smoothing models 3. Holt and Winters model 4. Stochastic processes and time series 5. Characteristics of stochastic processes 6. Process spectrum autocorrelation functions 7. Study of the stationarity...
-
Variable‐fidelity modeling of antenna input characteristics using domain confinement and two‐stage Gaussian process regression surrogates
PublicationThe major bottleneck of electromagnetic (EM)-driven antenna design is the high CPU cost of massive simulations required by parametric optimization, uncertainty quantification, or robust design procedures. Fast surrogate models may be employed to mitigate this issue to a certain extent. Unfortunately, the curse of dimensionality is a serious limiting factor, hindering the construction of conventional data-driven models valid over...
-
Editorial for the special issue on advances in forward and inverse surrogate modeling for high-frequency design
PublicationThe design of modern‐day high‐frequency devices and circuits, including microwave/RF, antenna and photonic components, historically has relied on full‐wave electromagnetic (EM) simulation tools. Initially used for design verification, EM simulations are nowadays used in the design process itself, for example, for finding optimum values of geometry and/or material parameters of the structures of interest. In a growing number of...
-
Application of artificial intelligence into/for control of flexible manufacturing cell
PublicationThe application of artificial intelligence in technological processes control is usually limited. One problem is how to respond to changes in the environment of manufacturing system. A way to overcome the above shortcoming is to use fuzzy logic for representation of the inexact information. In this paper fundamentals of artificial intelligence and fuzzy logic are introduced from a theoretical point of view. Still more the fuzzy...
-
Surrogate-Assisted Design of Checkerboard Metasurface for Broadband Radar Cross-Section Reduction
PublicationMetasurfaces have been extensively exploited in stealth applications to reduce radar cross section (RCS). They rely on the manipulation of backward scattering of electromagnetic (EM) waves into various oblique angles. However, arbitrary control of the scattering properties poses a significant challenge as a design task. Yet it is a principal requirement for making RCS reduction possible. This article introduces a surrogate-based...
-
Cost-Efficient Surrogate Modeling of High-Frequency Structures Using Nested Kriging with Automated Adjustment of Model Domain Lateral Dimensions
PublicationSurrogate models are becoming popular tools of choice in mitigating issues related to the excessive cost of electromagnetic (EM)-driven design of high-frequency structures. Among available techniques, approximation modeling is by far the most popular due to its versatility. In particular, the surrogates are exclusively based on the sampled simulation data with no need to involve engineering insight or problem-specific knowledge....
-
Artificial Intelligence Technologies in Education: Benefits, Challenges and Strategies of Implementation
PublicationSince the education sector is associated with highly dynamic business environments which are controlled and maintained by information systems, recent technological advancements and the increasing pace of adopting artificial intelligence (AI) technologies constitute a need to identify and analyze the issues regarding their implementation in education sector. However, a study of the contemporary literature reveled that relatively...