Search
Search results for: MAGNETIC SIGNATURES, MEASUREMENT DEPTH, MODELING, NEURAL NETWORKS
-
Multidipoles model of ship's magnetic field
PublicationShips made of ferromagnetic metals interfere with Earth's magnetic field in their surrounding. The disturbance of the magnetic field makes possible localization and even identification of the ship, which could determine a threat to the ship. The measurement of the magnetic field around the ship enables to determine its magnetic signature. The paper presents a multidipoles model of the ship magnetic field, which allows to determine...
-
Identyfikacja instrumentu muzycznego z nagrania fonicznego za pomocą sztucznych sieci neuronowych
PublicationCelem rozprawy jest zbadanie algorytmów do identyfikacji instrumentów występujących w sygnale polifonicznym z wykorzystaniem sztucznych sieci neuronowych. W części teoretycznej przywołano podstawy przetwarzania sygnałów fonicznych w kontekście ekstrakcji parametrów sygnałów wykorzystywanych w treningu sieci neuronowych. Dodatkowo dokonano analizy rozwoju metod uczenia maszynowego z uwzględnieniem podziału na sieci neuronowe pierwszej,...
-
Evaluation of Facial Pulse Signals Using Deep Neural Net Models
PublicationThe reliable measurement of the pulse rate using remote photoplethysmography (PPG) is very important for many medical applications. In this paper we present how deep neural networks (DNNs) models can be used in the problem of PPG signal classification and pulse rate estimation. In particular, we show that the DNN-based classification results correspond to parameters describing the PPG signals (e.g. peak energy in the frequency...
-
Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings
PublicationThe paper proposes an approach for extending deep neural networks-based solutions to closed-set speaker identification toward the open-set problem. The idea is built on the characteristics of deep neural networks trained for the classification tasks, where there is a layer consisting of a set of deep features extracted from the analyzed inputs. By extracting this vector and performing anomaly detection against the set of known...
-
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...
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublicationThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
Predictions of cervical cancer identification by photonic method combined with machine learning
PublicationCervical cancer is one of the most commonly appearing cancers, which early diagnosis is of greatest importance. Unfortunately, many diagnoses are based on subjective opinions of doctors—to date, there is no general measurement method with a calibrated standard. The problem can be solved with the measurement system being a fusion of an optoelectronic sensor and machine learning algorithm to provide reliable assistance for doctors...
-
Abdominal Aortic Aneurysm segmentation from contrast-enhanced computed tomography angiography using deep convolutional networks
PublicationOne of the most common imaging methods for diagnosing an abdominal aortic aneurysm, and an endoleak detection is computed tomography angiography. In this paper, we address the problem of aorta and thrombus semantic segmentation, what is a mandatory step to estimate aortic aneurysm diameter. Three end-to-end convolutional neural networks were trained and evaluated. Finally, we proposed an ensemble of deep neural networks with underlying...
-
Minimization of a ship's magnetic signature under external field conditions using a multi-dipole model
PublicationThe paper addresses the innovative issue of minimizing the ship's magnetic signature under any external field conditions, i.e., for arbitrary values of ambient field modulus and magnetic inclination. Varying values of the external field, depending on the current geographical location, affect only the induced part of ship's magnetization. A practical problem in minimizing the ship signature is separating permanent magnetization...
-
The influence of the geographic positioning system error on the quality of ship magnetic signature reproduction based on measurements in sea conditions
PublicationIn previous studies, the authors performed the magnetic signature reconstruction of the marine ship Zodiak as part of the measurement campaign focused on recording magnetic data and the relative position of a ship during its passage over a magnetometer immersed on the testing ground. A high degree of representation of the magnetic signature was obtained. However, the recorded measurement data revealed new patterns of the multidipole model...
-
The decay of quantum correlations between quantum dot spin qubits and the characteristics of its magnetic-field dependence
PublicationWe address the question of the role of quantum correlations beyond entanglement in the context of quantum magnetometry. We study the evolution of the rescaled variant of the geometric quantum discord of two electron-spin qubits interacting with an environment of nuclear spins via the hyperfine interaction. We have found that quantum correlations display a strong magnetic-field sensitivity which can be utilized for decoherence-driven...
-
Magnetic disturbances caused by magnetic contamination of plastics
PublicationIn the study of low magnetic fields precision magnetometers working in a differential system are used. Two optically pumped magnetometers working in a differential system allow for precise measuring of disturbances in the magnetic field. In order to attain high accuracy of magnetic field measurement, it is necessary to use appropriate materials for the construction of a magnetometric system, particularly of those located closely...
-
OBTAINING FLUID FLOW PATTERN FOR TURBINE STAGE WITH NEURAL MODEL.
PublicationIn the paper possibility of applying neural model to obtaining patterns of proper operation for fluid flow in turbine stage for fluid-flow diagnostics is discussed. Main differences between Computational Fluid Dynamics (CFD) solvers and neural model is given, also limitations and advantages of both are considered. Time of calculations of both methods was given, also possibilities of shortening that time with preserving the accuracy...
-
Analyzing the Effectiveness of the Brain–Computer Interface for Task Discerning Based on Machine Learning
PublicationThe 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...
-
Towards neural knowledge DNA
PublicationIn this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing,...
-
Method of determining the residual fluxes in transformer core
PublicationThe article presents the method of calculating the residual induction in transformer columns. The method is based on measurement of the magnetic induction in selected points around the transformer core. The values of residual induction are calculated as linear combination of the results of measurement.
-
Prognostic and diagnostic capabilities of OOBN in assessing investment risk of complex construction projects
PublicationModelling decision problems using Bayesian networks is extremely valuable especially in case of issues related to uncertainty; it is also very helpful in constructing and understanding visual representation of the elements and their relations. This approach facilitates subsequent application of Bayesian networks, however there can be situations where using simple Bayesian networks is impractical or even ineffective. The aim of...
-
TOXIC GASES IDENTIFICATION USING SINGLE ELECTROCATALYTIC SENSOR RESPONSES AND ARTIFICIAL NEURAL NETWORK
PublicationThe need for precise detection of toxic gases drives development of new gas sensors structures and methods of processing the output signals from the sensors. In literature, artificial neural networks are considered as one of the most effective tool for the analysis of gas sensors or sensors arrays responses. In this paper a method of toxic gas components identification using a electrocatalytic gas sensor as a detector and an artificial...
-
Developing Methodology for Model Tests of Floating Platforms in Low -Depth Towing Tank
PublicationThe paper presents two different methods of physical modeling of semi-submersible platform mooring system for research in low depth towing tank. The tested model was made in the scale of 1:100 resembling the "Thunder Horse" platform moored in the Gulf of Mexico at a depth of 1,920 m. Its mooring system consisted of 16 semi-taut mooring lines (chain-wire-chain) spaced starshape and attached at the bottom to suction piles. The tests...
-
Machine Learning Applied to Aspirated and Non-Aspirated Allophone Classification—An Approach Based on Audio "Fingerprinting"
PublicationThe purpose of this study is to involve both Convolutional Neural Networks and a typical learning algorithm in the allophone classification process. A list of words including aspirated and non-aspirated allophones pronounced by native and non-native English speakers is recorded and then edited and analyzed. Allophones extracted from English speakers’ recordings are presented in the form of two-dimensional spectrogram images and...
-
Neural network training with limited precision and asymmetric exponent
PublicationAlong with an extremely increasing number of mobile devices, sensors and other smart utilities, an unprecedented growth of data can be observed in today’s world. In order to address multiple challenges facing the big data domain, machine learning techniques are often leveraged for data analysis, filtering and classification. Wide usage of artificial intelligence with large amounts of data creates growing demand not only for storage...
-
Super-resolved Thermal Imagery for High-accuracy Facial Areas Detection and Analysis
PublicationIn this study, we evaluate various Convolutional Neural Networks based Super-Resolution (SR) models to improve facial areas detection in thermal images. In particular, we analyze the influence of selected spatiotemporal properties of thermal image sequences on detection accuracy. For this purpose, a thermal face database was acquired for 40 volunteers. Contrary to most of existing thermal databases of faces, we publish our dataset...
-
Charge density wave, enhanced mobility, and large nonsaturating magnetoresistance across the magnetic states of HoNiC2 and ErNiC2
PublicationWe report on magnetotransport and thermoelectric properties of two ternary carbides HoNiC2 and ErNiC2 hosting both charge density wave and long-range magnetic order. In the charge density wave state, both compounds show relatively large magnetoresistance MR ≈ 150% in HoNiC2 and ≈ 70%in ErNiC2 at a magnetic field of 9 T and temperature as low as 2 K. This positive field-linear magnetoresistance shows no signatures of saturation....
-
Electric field maps of an astable multivibrator in frequency range from 30 MHz to 3 GHz
Open Research DataThe data presents a result of near field measurements of electromagnetic emissions radiated from the PCB of a small electronic device. An efficient method of modelling the magnetic and electric field emissions is the measurements in the near field using electric and magnetic probes. The attached files contain electric field maps created on based measurements...
-
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublicationIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Deep Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Breast MRI segmentation by deep learning: key gaps and challenges
PublicationBreast MRI segmentation plays a vital role in early diagnosis and treatment planning of breast anomalies. Convolutional neural networks with deep learning have indicated promise in automating this process, but significant gaps and challenges remain to address. This PubMed-based review provides a comprehensive literature overview of the latest deep learning models used for breast segmentation. The article categorizes the literature...
-
Deep neural network architecture search using network morphism
PublicationThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Influence of User Mobility on System Loss and Depolarization in a BAN Indoor Scenario
PublicationIn this article, an analysis of system loss and depolarization in body area networks (BANs) for body-toinfrastructure (B2I) communications based on a measurement campaign in the 5.8 GHz band in an indoor environment is performed. Measurements were performed with an off-body antenna transmitting linearly polarized signals and dual-polarized receiving antennas carried by the user on the body. A normal distribution with a mean of...
-
Aleksandra Parteka dr hab. inż.
PeopleAbout me: I am an associate professor and head of doctoral studies at the Faculty of Management and Economics, Gdansk University of Technology (GdanskTech, Poland). I got my MSc degree in Economics from Gdansk University of Technology (2003) and Universita’ Politecnica delle Marche (2005), as well as MA degree in Contemporary European Studies from Sussex University (2006, with distinction). I received my PhD in Economics...
-
The conducted immunity test of a power supply unit in accordance with EMC standards
Open Research DataThe dataset presents a result of measurements that are a part of immunity tests to conducted disturbances, induced by radio-frequency fields. The immunity tests were carried out on the mains cable of the DF1723003TC NDN power supply. Tests of immunity of electronic systems to conducted disturbances in the frequency range from 150 kHz to 230 MHz are...
-
Analysis of magnetic disturbances of air platform caused by induced magnetisation
PublicationMagnetometric systems installed on air platforms like airplanes or helicopters are equipped in compensators of magnetic disturbances. Time changes of the platform's position caused generation of magnetic disturbances. The permanent and induced magnetization of ferromagnetic elements and eddy currents induced in conducting parts of the platform are sources of these disturbances. The linear model of magnetic disturbances of platforms...
-
Enhanced Mobility and Large Linear Nonsaturating Magnetoresistance in the Magnetically Ordered States of TmNiC2
PublicationWe have studied the magnetic, magnetotransport, and galvanomagnetic properties of TmNiC2. We find that the antiferromagnetic and field induced metamagnetic and ferromagnetic orderings do not suppress the charge density wave. The persistence of Fermi surface pockets, open as a result of imperfect nesting accompanying the Peierls transition, results in an electronic carriers mobility of the order of 4 × 103 cm2 V−1 s−1 in ferromagnetic...
-
Modelowanie przepływu pary przez okołodźwiękowe wieńce turbinowe z użyciem sztucznych sieci neuronoych
PublicationNiniejszy artykuł stanowi opis modelu przepływu pary przez okołodźwiękowe stopnie turbinowe, stworzonego w oparciu o sztuczne sieci neuronowe (SSN). Przedstawiony model neuronowy pozwala na wyznaczenie rozkładu wybranych parametrów w analizowanym przekroju kanału przepływowego turbiny dla rozpatrywanego zakresu wartości ciśnienia wlotowego.
-
Influence of plastic deformation on stray magnetic field distribution of soft magnetic steel sample
PublicationThe effect of various combinations of conditions, i.e., presence of the Earth’s magnetic field during and after deformation on the distribution of stray magnetic field of S355 steel sample, which is locally deformed, was investigated. Some of the stages of the experiment were carried out in zero magnetic field. Compensation of the Earth’s magnetic field was obtained by the application of a pair of Helmholtz coils. These coils are...
-
Study of various machine learning approaches for Sentinel-2 derived bathymetry
PublicationIn recent years precise and up-to-date information regarding seabed depth has become more and more important for companies and institutions that operate on coastlines. While direct, in-situ measurements are performed regularly, they are expensive, time-consuming and impractical to be performed in short time intervals. At the same time, an ever-increasing amount of satellite imaging data becomes available. With these images, it...
-
Computational intelligence methods in production management
PublicationThis chapter presents a survey of selected computational intelligence methods used in production management. This group of methods includes, among others, approaches based on the artificial neural networks, the evolutionary algorithms, the fuzzy logic systems and the particle swarm optimization mechanisms. From the abovementioned methods particularly noteworthy are the evolutionary and the particle swarm algorithms, which are successfully...
-
Optymalizacja treningu i wnioskowania sieci neuronowych
PublicationSieci neuronowe są jedną z najpopularniejszych i najszybciej rozwijających się dziedzin sztucznej inteligencji. Ich praktyczne wykorzystanie umożliwiło szersze użycie komputerów w wielu obszarach komunikacji, przemysłu i transportu. Dowody tego są widoczne w elektronice użytkowej, medycynie, a nawet w zastosowaniach militarnych. Wykorzystanie sztucznej inteligencji w wielu przypadkach wymaga jednak znacznej mocy obliczeniowej,...
-
Data fusion of sparse, heterogeneous, and mobile sensor devices using adaptive distance attention
PublicationIn environmental science, where information from sensor devices are sparse, data fusion for mapping purposes is often based on geostatistical approaches. We propose a methodology called adaptive distance attention that enables us to fuse sparse, heterogeneous, and mobile sensor devices and predict values at locations with no previous measurement. The approach allows for automatically weighting the measurements according to a priori...
-
Stress anisotropy characterisation with the help of Barkhausen effect detector with adjustable magnetic field direction
PublicationIn the paper we describe a novel apparatus for the measurement of the Barkhausen noise (BN) angular dependence, which in turn may be indicative of the stress induced anisotropy of magnetic properties. Such dependence can be further used for the stress distribution evaluation. The change of magnetization direction in the material is obtained by varying the magnetic flux density in two perpendicular yokes of the apparatus. We present...
-
BADANIE WPŁYWU INDUKCJI REMANENCJI NA STAN PRZEJŚCIOWY JEDNOFAZOWEGO UKŁADU TRANSFORMATOROWEGO
PublicationW referacie przedstawiono wyniki badań eksperymentalnych i symulacyjnych wpływu indukcji remanencji w rdzeniu transformatora jednofazowego na jego stan przejściowy przy jego pracy jałowej. Badany obiekt jest układem transformatorowym o dwóch uzwojeniach nawiniętych na zwijanym z blachy anizotropowej rdzeniu w kształcie toroidu. Doświadczenia eksperymentalne polegały na rozładowywaniu kondensatora przez uzwojenie strony pierwotnej...
-
Three-dimensional mapping for data collected using variable stereo baseline
PublicationThe paper describes a system of 3D mapping of data collected with due regard for variable baseline. This solution constitute an extension to a VisRobot sub-system developed as a subsystem, necessary for implementing the generic idea of using mobile robots to explore an indoor static environment. This subsystem is to acquire stereo images, calculate the depth in the images and construct the sought 3D map. Stereo images are obtained...
-
Training of Deep Learning Models Using Synthetic Datasets
PublicationIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Analysis of Methods for Determining Shallow Waterbody Depths Based on Images Taken by Unmanned Aerial Vehicles
PublicationHydrographic surveys enable the acquisition and processing of bathymetric data, which after being plotted onto nautical charts, can help to ensure safety of navigation, monitor changes in the coastal zone, and assess hydro-engineering structure conditions. This study involves the measurement of waterbody depth, identification of the seabed shape and geomorphology, the coastline course, and the location of underwater obstacles....
-
Methods of Artificial Intelligence for Prediction and Prevention Crisis Situations in Banking Systems
PublicationIn this paper, a support vector machine has been studied due to prediction of bank crisis. To prevent outcomes of crisis situations, artificial neural networks have been characterized as applied to stock market investments, as well as to test the credibility of the bank's customers. Finally, some numerical experiments have been presented.
-
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...
-
Inspection of Gas Pipelines Using Magnetic Flux Leakage Technology
PublicationMagnetic non-destructive testing methods can be classified into the earliest methods developed for assessment of steel constructions. One of them is the magnetic flux leakage technology. A measurement of the magnetic flux leakage is quite commonly used for examination of large objects such as tanks and pipelines. Construction of a magnetic flux leakage tool is relatively simple, but a quantitative analysis of recorded data is a...
-
Path Loss Analysis for the IoT Applications in the Urban and Indoor Environments
PublicationThe Internet of Things (IoT) networks concept implies their presence in a various and untypical locations, usually with a disturbed radio signals propagation. In the presented paper an investigation of an additional path loss observed in an underground environment was described. The proposed measurement locations correspond to the operation areas of rapidly growing narrowband IoT (NBIoT) networks, the ones using the Long Term Evolution...
-
Projektowanie i eksploatacja dróg szynowych z wykorzystaniem mobilnych pomiarów satelitarnych
PublicationNiniejsza monografia zawiera szczegółowy opis aktywnych sieci geodezyjnych GNSS oraz modelowania dokładności określania pozycji w pomiarach satelitarnych. Omówiono również opracowaną technikę mobilnych pomiarów satelitarnych toru kolejowego oraz aplikacje związane z jej zastosowaniem w projektowaniu i eksploatacji dróg szynowych. Autorzy zawarli w pracy wyniki swoich badań, wykonywanych na przestrzeni lat 2009–2015. Badania przeprowadzono...