Filters
total: 13289
-
Catalog
- Publications 11466 available results
- Journals 490 available results
- Conferences 109 available results
- Publishing Houses 1 available results
- People 273 available results
- Projects 9 available results
- e-Learning Courses 203 available results
- Events 11 available results
- Open Research Data 727 available results
displaying 1000 best results Help
Search results for: GLOBAL SENSITIVITY ANALYSIS · SURROGATE MODELING · NEURAL NETWORKS · SOBOL’ INDICES · TERMINATION CRITERIA
-
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...
-
Neural Network-Based Sequential Global Sensitivity Analysis Algorithm
PublicationPerforming global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate modeling such as neural networks (NNs) are used to replace the expensive simulation model in the GSA process, which introduces the additional challenge of finding the minimum number of training data samples required to...
-
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...
-
Deep neural networks for data analysis
e-Learning CoursesThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Global sensitivity analysis of membrane model of abdominal wall with surgical mesh
PublicationThe paper addresses the issue of ventral hernia repair. Finite Element simulations can be helpful in the optimization of hernia parameters. A membrane abdominal wall model is proposed in two variants: a healthy one and including hernia defect repaired by implant. The models include many uncertainties, e.g. due to variability of abdominal wall, intraabdominal pressure value etc. Measuring mechanical properties with high accuracy...
-
Improved Efficacy Behavioral Modeling of Microwave Circuits through Dimensionality Reduction and Fast Global Sensitivity Analysis
PublicationBehavioral models have garnered significant interest in the realm of high-frequency electronics. Their primary function is to substitute costly computational tools, notably electromagnetic (EM) analysis, for repetitive evaluations of the structure under consideration. These evaluations are often necessary for tasks like parameter tuning, statistical analysis, or multi-criterial design. However, constructing reliable surrogate models...
-
Sławomir Jerzy Ambroziak dr hab. inż.
PeopleSławomir J. Ambroziak was born in Poland, in 1982. He received the M.Sc., Ph.D. and D.Sc. degrees in radio communication from Gdańsk University of Technology (Gdańsk Tech), Poland, in 2008, 2013, and 2020 respectively. Since 2008 he is with the Department of Radiocommunication Systems and Networks of the Gdańsk Tech: 2008-2013 as Research Assistant, 2013-2020 as Assistant Professor, and since 2020 as Associate Professor. He is...
-
Neural networks and deep learning
PublicationIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
Performance Analysis of Convolutional Neural Networks on Embedded Systems
PublicationMachine learning is no longer confined to cloud and high-end server systems and has been successfully deployed on devices that are part of Internet of Things. This paper presents the analysis of performance of convolutional neural networks deployed on an ARM microcontroller. Inference time is measured for different core frequencies, with and without DSP instructions and disabled access to cache. Networks use both real-valued and...
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe 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...
-
Results of implementation of Feed Forward Neural Networks for modeling of heat transfer coefficient during flow condensation for low and high values of saturation temperature
Open Research DataThis database present results of implementation of Feed Forward Neural Networks for modeling of heat transfer coefficient during flow condensation for low and high values of saturation temperature. Databse contain one table and 7 figures.
-
Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks
PublicationThe importance of surrogate modeling techniques has been gradually increasing in the design of antenna structures over the recent years. Perhaps the most important reason is a high cost of full-wave electromagnetic (EM) analysis of antenna systems. Although imperative in ensuring evaluation reliability, it entails considerable computational expenses. These are especially pronounced when carrying out EM-driven design tasks such...
-
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...
-
Adrian Bekasiewicz dr hab. inż.
PeopleAdrian Bekasiewicz received the MSc, PhD, and DSc degrees in electronic engineering from Gdansk University of Technology, Poland, in 2011, 2016, and 2020, respectively. In 2014, he joined Engineering Optimization & Modeling Center where he held a Research Associate and a Postdoctoral Fellow positions, respectively. Currently, he is an Associate Professor with Gdansk University of Technology, Poland. His research interests include...
-
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...
-
Modeling of Surface Roughness in Honing Processes by UsingFuzzy Artificial Neural Networks
PublicationHoning processes are abrasive machining processes which are commonly employed to improve the surface of manufactured parts such as hydraulic or combustion engine cylinders. These processes can be employed to obtain a cross-hatched pattern on the internal surfaces of cylinders. In this present study, fuzzy artificial neural networks are employed for modeling surface roughness parameters obtained in finishing honing operations. As...
-
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,...
-
Comparative study of neural networks used in modeling and control of dynamic systems
PublicationIn this paper, a diagonal recurrent neural network that contains two recurrent weights in the hidden layer is proposed for the designing of a synchronous generator control system. To demonstrate the superiority of the proposed neural network, a comparative study of performances, with two other neural network (1_DRNN) and the proposed second-order diagonal recurrent neural network (2_DRNN). Moreover, to confirm the superiority...
-
Wiktoria Wojnicz dr hab. inż.
PeopleDSc in Mechanics (in the field of Biomechanics) - Lodz Univeristy of Technology, 2019 PhD in Mechanics (in the field of Biomechanics) - Lodz Univeristy of Technology, 2009 (with distinction) List of papers (2009 - ) Wojnicz W., Wittbrodt E., Analysis of muscles' behaviour. Part I. The computational model of muscle. Acta of Bioengineering and Biomechanics, Vol. 11, No.4, 2009, p. 15-21 Wojnicz W., Wittbrodt E., Analysis of...
-
Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
PublicationNumerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending...
-
Modeling the Networks - ed. 2021/2022
e-Learning CoursesThe goal of this course is to present optimization problems for road networks, where the road network is a set of n distinct lines, or n distinct (open or closed) line segments, in the plane, such that their union is a connected region.
-
An advanced tool integrating failure and sensitivity analysis into novel modeling of the stormwater flood volume
PublicationAn innovative tool for modeling the specific flood volume was presented that can be applied to assess the need for stormwater network modernization as well as for advanced flood risk assessment. Field measurements for a catchment area in Kielce, Poland, were used to apply the model and demonstrate its usefulness. This model extends the capability of recently developed statistical and machine learning hydrodynamic models developed...
-
Sylwester Kaczmarek dr hab. inż.
PeopleSylwester Kaczmarek received his M.Sc in electronics engineering, Ph.D. and D.Sc. in switching and teletraffic science from the Gdansk University of Technology, Gdansk, Poland, in 1972, 1981 and 1994, respectively. His research interests include: IP QoS and GMPLS and SDN networks, switching, QoS routing, teletraffic, multimedia services and quality of services. Currently, his research is focused on developing and applicability...
-
On Reduced-Cost Design-Oriented Constrained Surrogate Modeling of Antenna Structures
PublicationDesign of contemporary antenna structures heavily relies on full-wave electromagnetic (EM) simulation models. Such models are essential to ensure reliability of evaluating antenna characteristics, yet, they are computationally expensive and therefore unsuitable for handling tasks that require multiple analyses, e.g., parametric optimization. The cost issue can be alleviated by using fast surrogate models. Conventional data-driven...
-
Performance-Based Nested Surrogate Modeling of Antenna Input Characteristics
PublicationUtilization of electromagnetic (EM) simulation tools is mandatory in the design of contemporary antenna structures. At the same time, conducting designs procedures that require multiple evaluations of the antenna at hand, such as parametric optimization or yield-driven design, is hindered by a high cost of accurate EM analysis. To certain extent, this issue can be addressed by utilization of fast replacement models (also referred...
-
An annotated timeline of sensitivity analysis
PublicationThe last half a century has seen spectacular progresses in computing and modelling in a variety of fields, applications, and methodologies. Over the same period, a cross-disciplinary field known as sensitivity analysis has been making its first steps, evolving from the design of experiments for laboratory or field studies, also called ‘in-vivo’, to the so-called experiments ‘in-silico’. Some disciplines were quick to realize the...
-
NEURAL NETWORKS
Journals -
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is not uncommon for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected...
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is common for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected as...
-
Triangulation-based Constrained Surrogate Modeling of Antennas
PublicationDesign of contemporary antenna structures is heavily based on full-wave electromagnetic (EM) simulation tools. They provide accuracy but are CPU-intensive. Reduction of EM-driven design procedure cost can be achieved by using fast replacement models (surrogates). Unfortunately, standard modeling techniques are unable to ensure sufficient predictive power for real-world antenna structures (multiple parameters, wide parameter ranges,...
-
Termination functions for evolutionary path planning algorithm
PublicationIn this paper a study of termination functions (stop criterion) for evolutionary path planning algorithm is presented. Tested algorithm is used to determine close to optimal ship paths in collision avoidance situation. For this purpose a path planning problem is defined. A specific structure of the individual path and fitness function is presented. For the simulation purposes a close to real tested environment is created. Five...
-
Artificial Neural Networks in Microwave Components and Circuits Modeling
PublicationArtykuł dotyczy wykorzystania sztucznych sieci neuronowych (SNN) w projektowaniu i optymalizacji układów mikrofalowych.Zaprezentowano podstawowe zasady i założenia modelowania z użyciem SNN. Możliwości opisywanej metody opisano wykorzystując przykładowyprojekt anteny łatowej. Przedstawiono różne strategie modelowania układów, które wykorzystują możliwości opisywanej metody w połączeniu zwiedzą mikrofalową. Porównano również dokładność...
-
Efficient uncertainty quantification using sequential sampling-based neural networks
PublicationUncertainty quantification (UQ) of an engineered system involves the identification of uncertainties, modeling of the uncertainties, and the forward propagation of the uncertainties through a system analysis model. In this work, a novel surrogate-based forward propagation algorithm for UQ is proposed. The proposed algorithm is a new and unique extension of the recent efficient global optimization using neural network (NN)-based...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
A survey of neural networks usage for intrusion detection systems
PublicationIn recent years, advancements in the field of the artificial intelligence (AI) gained a huge momentum due to the worldwide appliance of this technology by the industry. One of the crucial areas of AI are neural networks (NN), which enable commer‐ cial utilization of functionalities previously not accessible by usage of computers. Intrusion detection system (IDS) presents one of the domains in which neural networks are widely tested...
-
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...
-
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...
-
Sensitivity analysis based on non-intrusive regression-based polynomial chaos expansion for surgical mesh modelling
PublicationThe modelling of a system containing implants used in ventral hernia repair and human tissue suffers from many uncertainties. Thus, a probabilistic approach is needed. The goal of this study is to define an efficient numerical method to solve non-linear biomechanical models supporting the surgeon in decisions about ventral hernia repair. The model parameters are subject to substantial variability owing to, e.g., abdominal wall...
-
Modeling the global atmospheric transport and deposition of mercury to the Great Lakes
PublicationMercury contamination in the Great Lakes continues to have important public health and wildlife ecotoxicology impacts, and atmospheric deposition is a significant ongoing loading pathway. The objective of this study was to estimate the amount and source-attribution for atmospheric mercury deposition to each lake, information needed to prioritize amelioration efforts. A new global, Eulerian version of the HYSPLIT-Hg model was used...
-
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...
-
Expedited Variable-Resolution Surrogate Modeling of Miniaturized Microwave Passives in Confined Domains
PublicationDesign of miniaturized microwave components is largely based on computational models, primarily, full-wave electromagnetic (EM) simulations. EM analysis is capable of giving an accurate account for cross-coupling effects, substrate and radiation losses, or interactions with environmental components (e.g., connectors). Unfortunately, direct execution of EM-based design tasks such as parametric optimization or uncertainty quantification,...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Rapid Design of 3D Reflectarray Antennas by Inverse Surrogate Modeling and Regularization
PublicationReflectarrays (RAs) exhibit important advantages over conventional antenna arrays, especially in terms of realizing pencil-beam patterns without the employment of the feeding networks. Unfortunately, microstrip RA implementations feature narrow bandwidths, and are severely affected by losses. A considerably improved performance can be achieved for RAs involving grounded dielectric layers, which are also easy to manufacture using...
-
Inverse surrogate modeling for low-cost geometry scaling of microwave and antenna structures
PublicationPurpose–The purpose of this paper is to investigate strategies for expedited dimension scaling ofelectromagnetic (EM)-simulated microwave and antenna structures, exploiting the concept of variable-fidelity inverse surrogate modeling.Design/methodology/approach–A fast inverse surrogate modeling technique is described fordimension scaling of microwave and antenna structures. The model is established using referencedesigns obtained...
-
Reliable Surrogate Modeling of Antenna Input Characteristics by Means of Domain Confinement and Principal Components
PublicationA reliable design of contemporary antenna structures necessarily involves full-wave electromagnetic (EM) analysis which is the only tool capable of accounting, for example, for element coupling or the effects of connectors. As EM simulations tend to be CPU-intensive, surrogate modeling allows for relieving the computational overhead of design tasks that require numerous analyses, for example, parametric optimization or uncertainty...
-
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...
-
Sensitivity analysis of a composite footbridge
PublicationThis work include an example of sensitivity analysis for the design of a composite footbridge. A sandwich structure is used, consisting two high-strength skins separated by a core material. The analysis was conducted for two numerical models. The first one is a simple, single-span beam of a composite cross-section (laminate and foam), with different Young’s modulus for each material. Calculations were made by means of a MATLAB-based...
-
Rapid dimension scaling of triple-band antennas by means of inverse surrogate modeling
PublicationGeometry scaling of antennas, i.e., finding optimum dimensions of the structure for given operating conditions and material parameters is an important yet challenging problem. In this paper, we discuss fast dimension scaling of triple-band antennas with respect to operating frequencies. We adopt the inverse surrogate modeling approach where the surrogate model is a function of the three operating frequencies of the antenna and...
-
Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks
PublicationTraffic–induced vibrations may constitute a considerable load to a building, cause cracking of plaster, cracks in load–bearing elements or even a global structural collapse of the whole structure [1-4]. Vibrations measurements of real structures are costly and laborious, not justified in all cases. The aim of the paper is to create an original algorithm, to predict the negative dynamic impact on the examined residential building...
-
Low-Cost Surrogate Modeling of Miniaturized Microwave Components Using Nested Kriging
PublicationIn the paper, a recently reported nested kriging methodology is employed for modeling of miniaturized microwave components. The approach is based on identifying the parameter space region that contains high-quality designs, and, subsequently, rendering the surrogate in this subset. The results obtained for a miniaturized unequal-power-split rat-race coupler and a compact three-section impedance transformer demonstrate reliability...