Search
Filters
total: 394
filtered: 389
-
Catalog
Chosen catalog filters
Search results for: CROSS-VALIDATION
-
Obtaining a Well-Trained Artificial Intelligence Algorithm from Cross-Validation in Endoscopy
PublicationThe article shortly discusses endoscopic video analysis problems and artificial intelligence algorithms supporting it. The most common method of efficiency testing of these algorithms is to perform intensive cross-validation. This allows for accurately evaluate their performance of generalization. One of the main problems of this procedure is that there is no simple and universal way of obtaining a specific instance of a well-trained...
-
Regularized Identification of Time-Varying FIR Systems Based on Generalized Cross-Validation
PublicationA new regularization method is proposed and applied to identification of time-varying finite impulse response systems. We show, that by a careful design of the regularization constraint, one can improve estimation results, especially in the presence of strong measurement noise. We also show that the the most appropriate regularization gain can be found by direct optimization of the generalized cross-validation criterion.
-
ANYTIME POLYNOMIAL HEURISTIC ALGORITHM FOR PARTITIONING GROUPS OF DATA WITH PRESERVING CLASS PROPORTIONS FOR CROSS-VALIDATION
PublicationThe article describes a problem of splitting data for k-fold cross-validation, where class proportions must be preserved, with additional constraint that data is divided into groups that cannot be split into different cross-validation sets. This problem often occurs in e.g. medical data processing, where data samples from one patient must be included in the same cross-validation set. As this problem is NP-complete, a heuristic...
-
SDN testbed for validation of cross-layer data-centric security policies
PublicationSoftware-defined networks offer a promising framework for the implementation of cross-layer data-centric security policies in military systems. An important aspect of the design process for such advanced security solutions is the thorough experimental assessment and validation of proposed technical concepts prior to their deployment in operational military systems. In this paper, we describe an OpenFlow-based testbed, which was...
-
On the generalized model of shell structures with functional cross-sections
PublicationIn the present study, a single general formulation has been presented for the analysis of various shell-shaped structures. The proposed model is comprehensive and a variety of theories can be used based on it. The cross-section of the shell structure can be arbitrarily analyzed with the presented equations. In other words, various types of shell structures, including cylindrical, conical, spherical, elliptical, hyperbolic, parabolic,...
-
Novel Investigation of Higher Order Spectral Technologies for Fault Diagnosis of Motor-Based Rotating Machinery
PublicationIn the last decade, research centered around the fault diagnosis of rotating machinery using non-contact techniques has been significantly on the rise. For the first time worldwide, innovative techniques for the diagnosis of rotating machinery, based on electrical motors, including generic, nonlinear, higher-order cross-correlations of spectral moduli of the third and fourth order (CCSM3 and CCSM4, respectively), have been comprehensively...
-
Highly-Compact Dual-Band Bandpass Waveguide Filter Based on Cross-Shaped Frequency-Dependent Coupling
PublicationThis work reports the design of an original class of highly-compact dual-band bandpass filter based on dual-mode waveguide resonators inter-coupled through a novel type of frequency-dependent coupling (FDC). The devised FDC consists of a cross-shaped metallic structure placed in the broad wall of a rectangular waveguide. This FDC produces two additional poles and three extra transmission zeros (TZs). Specifically, each pole is...
-
Validation study on a new semi-empirical method for the prediction of added resistance in waves of arbitrary heading in analyzing ship speed trial results
PublicationThis paper describes an open and extensive validation study carried out by the Specialist Committee on Ships in Operation at Sea (SOS) of the International Towing Tank Conference (ITTC) on the newly developed SHOPERA-NTUA-NTU-MARIC (SNNM) wave-added resistance prediction method. The SNNM method aims at a simple, fast and transparent determination of the added resistance in regular waves of arbitrary encounter directions, even when...
-
Lagrangian model of an isolated dc-dc converter with a 3-phase medium frequency transformer accounting magnetic cross saturation
PublicationThis article presents a nonlinear equivalent circuit model of an isolated dc-dc converter with a 3-phase medium frequency transformer. The model takes into account the magnetic cross saturation of the 3-phase core-type magnetic circuit. The model is suitable in detailed electromagnetic transient simulations of power systems involving isolated dc-dc converters. The model is developed using the Lagrange energy method. It involves...
-
On adaptive covariance and spectrum estimation of locally stationary multivariate processes
PublicationWhen estimating the correlation/spectral structure of a locally stationary process, one has to make two important decisions. First, one should choose the so-called estimation bandwidth, inversely proportional to the effective width of the local analysis window, in the way that complies with the degree of signal nonstationarity. Too small bandwidth may result in an excessive estimation bias, while too large bandwidth may cause excessive...
-
Monitoring of Odour Nuisance from Landfill Using Electronic Nose
PublicationThe paper presents the results of investigation on classification of atmospheric air samples collected in a vicinity of municipal landfill with respect to their odour nuisance. The research was conducted using a prototype of electronic nose instrument and a commercial electronic nose of Fast/Flash GC type –HERACLES II. The prototype was equipped with a set of six semiconductor sensors by FIGARO Co.. Classification of the air samples...
-
Comparison of Quality Evaluation of Agricultural Distillates Using Prototype of Electronic Nose and Fast/Flash GC
PublicationThe paper presents the results of investigation on quality evaluation of agricultural distillates using a prototype of electronic nose instrument and a commercial electronic nose of Fast/Flash GC type – HERACLES II. The prototype was equipped with a set of six semiconductor sensors by FIGARO Co.. In case of the prototype volatile fraction of the agricultural distillate was prepared via barbotage process. HERACLES II analysed the...
-
Comparison of different types of electronic nose instruments for evaluation of odour nuisance from landfill
PublicationThe paper presents and compares the results of investigation on classification of atmospheric air samples collected in a vicinity of municipal landfill with respect to their odour nuisance. The research was conducted using a prototype of electronic nose instrument and a commercial electronic nose of Fast/Flash GC type – HERACLES II. The prototype was equipped with six semiconductor sensors of TGS type. Classification of the air...
-
Comparison of Evaluation of Air Odour Quality in Vicinity of Petroleum Plant Using a Prototype of Electronic Nose Instrument and Fast GC Technique
PublicationThe paper presents the results of investigation on classification of the ambient air samples collected in a vicinity of the LOTOS Group S.A. petroleum plant with respect to odour. The investigations were carried out with an electronic nose prototype and a commercial electronic nose of Fast GC-type – HERACLES II. The prototype was equipped with a set of six semiconductor sensors by FIGARO Co. and a photoionization sensor of PID-type....
-
Optimally regularized local basis function approach to identification of time-varying systems
PublicationAccurate identification of stochastic systems with fast-varying parameters is a challenging task which cannot be accomplished using model-free estimation methods, such as weighted least squares, which assume only that system coefficients can be regarded as locally constant. The current state of the art solutions are based on the assumption that system parameters can be locally approximated by a linear combination of appropriately...
-
Locally Adaptive Cooperative Kalman Smoothing and Its Application to Identification of Nonstationary Stochastic Systems
PublicationOne of the central problems of the stochastic approximation theory is the proper adjustment of the smoothing algorithm to the unknown, and possibly time-varying, rate and mode of variation of the estimated signals/parameters. In this paper we propose a novel locally adaptive parallel estimation scheme which can be used to solve the problem of fixed-interval Kalman smoothing in the presence of model uncertainty. The proposed solution...
-
Quality evaluation of agricultural distillates using different types of electronic noses
PublicationThe paper presents the results of investigation on quality evaluation of agricultural distillates using a prototype of electronic nose instrument and a commercial electronic nose of Fast/Flash GC type – HERACLES II. The prototype was equipped with TGS type semiconductor sensors. HERACLES II included two chromatographic columns with different polarity of stationary phase and two FID detectors. In case of the prototype volatile fraction...
-
Estimation of the Ultimate Strength of FRP Strips-to-Masonry Substrates Bond
PublicationFiber-Reinforced Polymers (FRP) were developed as a new method over the past decades due to their many beneficial mechanical properties, and they are commonly applied to strengthen masonry structures. In this paper, the Artificial Neural Network (ANN), K-fold Cross-Validation (KFCV) technique, Multivariate Adaptive Regression Spline (MARS) method, and M5 Model Tree (M5MT) method were utilized to predict the ultimate strength of...
-
Neural network model of ship magnetic signature for different measurement depths
PublicationThis paper presents the development of a model of a corvette-type ship’s magnetic signature using an artificial neural network (ANN). The capabilities of ANNs to learn complex relationships between the vessel’s characteristics and the magnetic field at different depths are proposed as an alternative to a multi-dipole model. A training dataset, consisting of signatures prepared in finite element method (FEM) environment Simulia...
-
A Bayesian regularization-backpropagation neural network model for peeling computations
PublicationA Bayesian regularization-backpropagation neural network (BRBPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network...
-
Experimental investigation of joint with positive eccentricity in CFS truss
PublicationDue to technological restrictions, in the case of trusses made of CFS open cross-sections, positive eccentricities in the truss joints have become very frequent. Therefore studies concerning the load-bearing capacity of truss joints with positive eccentricity were undertaken. It was assumed that the resistance of cold-formed steel (CFS) open cross-section truss joints located on compression chords and with positive eccentricity...
-
Modelling of residential sales price with kriging using different distance metrics in different correlation functions
PublicationThe modelling and estimation of sales prices based on economical conditions are important for housing sector especially in developing countries. Analysts are focused on the subject to analyze price movements and estimate the future trend of the sales prices for housing sector. In this study, we tried to generate a robust and efficient model related to the subject. Firstly, we investigated economic variables affecting housing sales...
-
Dynamic tests of composite footbridge segment – experimental and numerical studies
PublicationExperimental dynamic tests and numerical simulations of a 3 meters long segment of a footbridge made of polymer composites are presented in the paper. The span-length is reduced, however dimensions of cross-section are the same as the target footbridge. The segment structure is made of sandwich panels, which consist of fibre reinforced polymer (GFRP) laminates (skins) and a PET foam (core). The first part of the paper contains...
-
Fast surrogate-assisted simulation-driven design of compact microwave hybrid couplers
PublicationThis work presents a robust methodology for expedited simulation-driven design optimization of compact microwave hybrid couplers. The technique relies on problem decomposition, and a bot-tom–up design strategy, starting from the level of basic building blocks of the coupler, and finishing with a tuning procedure that exploits a fast surrogate model of the entire structure. The latter is constructed by cascading local response surface...
-
Isolation of the relative decrease in magnetic permeability contribution to reluctance of an open magnetic circuit based on stray field measurements
PublicationThe goal of the study was to evaluate a relative decrease in magnetic permeability in open magnetic circuits based on stray magnetic field measurements. The boundary element method was used to simulate magnetic circuits with variable geometry and variable magnetic permeability. The simulated magnetic circuits were rectangular or bone-shaped flat samples. Reluctance was increased in the middle of the samples resulting in leakage...
-
APPLICATION OF ULTRAFAST GAS CHROMATOGRAPHY TO RECOGNIZE ODOR NUISANCE
PublicationPotentialities of ultrafast gas chromatography applied to periodical monitoring of odor nuisance originating from a municipal landfill have been examined. The results of investigation on classification of the atmospheric air samples collected in a vicinity of the landfill during winter and summer season have been presented. The investigation was performed using ultrafast gas chromatography of Fast/Flash GC type HERACLES II by Alpha...
-
Comparison of the Measurement Techniques Employed for Evaluation of Ambient Air Odour Quality Influenced by Operation of Industrial Sewage Treatment Plant
PublicationThe paper presents the results of investigation on ambient air quality evaluation with respect to concentration of odorants in a vicinity of a sewage treatment plant of the LOTOS Group S.A. petroleum plant. The investigation was performed during winter season using a prototype of electronic nose and the Nasal Ranger field olfactometers. The prototype was equipped with a set of six semiconductor sensors by FIGARO Co. and one PID-type...
-
Monitoring of odour nuisance in the Tricity Agglomeration
PublicationThe paper describes a principle of operation of odour nuisance monitoring network, which is being designed in the Tricity Agglomeration. Moreover, it presents the preliminary results of an investigation on ambient air quality with respect to odour nuisance in a vicinity of the municipal landfill. The investigation was performed during spring-winter season using a prototype of electronic nose and the Nasal Ranger field olfactometers. The...
-
Comparison of the measurement techniques employed for evaluation of ambient air odour quality
PublicationThe paper presents the results of investigation on ambient air odour quality in a vicinity of the industrial sewage treatment plant being a part of the crude oil processing plant. The investigation was performed during spring-winter season using a prototype of electronic nose and the Nasal Ranger field olfactometers. The prototype was equipped with a set of six semiconductor sensors by FIGARO Co. and one PID-type sensor. The field...
-
Prediction of the Biogenic Amines Index of Poultry Meat Using an Electronic Nose
PublicationThe biogenic amines index of fresh chicken meat samples during refrigerated storage was predicted based on the headspace analysis using an electronic nose equipped with an array of electrochemical sensors. The reference biogenic amines index values were obtained using dispersive liquid–liquid microextraction–gas chromatography–mass spectrometry. A prototype electronic nose with modular construction and a dedicated sample chamber...
-
Playback detection using machine learning with spectrogram features approach
PublicationThis paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect...
-
Finger Vein Presentation Attack Detection Method Using a Hybridized Gray-Level Co-Occurrence Matrix Feature with Light-Gradient Boosting Machine Model
PublicationPresentation Attack Detection (PAD) is crucial in biometric finger vein recognition. The susceptibility of these systems to forged finger vein images is a significant challenge. Existing approaches to mitigate presentation attacks have computational complexity limitations and limited data availability. This study proposed a novel method for identifying presentation attacks in finger vein biometric systems. We have used optimal...
-
A Novel Spatio–Temporal Deep Learning Vehicle Turns Detection Scheme Using GPS-Only Data
PublicationWhether the computer is driving your car or you are, advanced driver assistance systems (ADAS) come into play on all levels, from weather monitoring to safety. These modern-day ADASs use various assisting tools for drivers to keep the journey safe; these sophisticated tools provide early signals of numerous events, such as road conditions, emerging traffic scenarios, and weather warnings. Many urban applications, such as car-sharing...
-
RF Multi-Functional Input-Reflectionless Dispersive-Delay Structure With Sharp-Rejection Filtering Using Channelization Techniques
PublicationA class of RF multi-functional input-reflectionless dispersive-delay structure (DDS) with linear-type in-band groupdelay variation and sharp-rejection bandpass-filtering capability is reported. It exploits a two-branch-channelized/balanced-type circuit with similar low-order reflective DDS units inside its channels, which are connected through input/output 3-dB quadrature wideband couplers. The adopted DDS unit is based on a coupledresonator...
-
Analysis of Failure Mechanism in Joints with Positive Eccentricity in CFS Truss
PublicationThe paper presents studies concerning the load-bearing capacity of truss joints with a positive eccentricity resulting from the arrangement of geometric members and the failure mechanisms observed in the joints. Based on the previously conducted experimental study, a numerical model of the tested fragment of the CFS truss with eccentricity in the joint was created and validated. All structural details of the tested truss and the...
-
The Influence of Selecting Regions from Endoscopic Video Frames on The Efficiency of Large Bowel Disease Recognition Algorithms
PublicationThe article presents our research in the field of the automatic diagnosis of large intestine diseases on endoscopic video. It focuses on the methods of selecting regions of interest from endoscopic video frames for further analysis by specialized disease recognition algorithms. Four methods of selecting regions of interest have been discussed: a. trivial, b. with the deletion of characteristic, endoscope specific additions to the...
-
Detection of propofol concentrations in blood by Raman spectroscopy
PublicationIn this paper we present a proof-of-concept of a Raman spectroscopy-based approach for measuring the content of propofol, a common anesthesia drug, in whole human blood, and plasma, which is intended for use during clinical procedures. This method utilizes the Raman spectroscopy as a chemically–sensitive method for qualitative detection of the presence of a drug and a quantitative determination of its concentration. A number of...
-
Rapid Simulation-Driven Multiobjective Design Optimization of Decomposable Compact Microwave Passives
PublicationIn this paper, a methodology for fast multiobjective optimization of the miniaturized microwave passives has been presented. Our approach is applicable to circuits that can be decomposed into individual cells [e.g., compact microstrip resonant cells (CMRCs)]. The structures are individually modeled using their corresponding equivalent circuits and aligned with their accurate, EM simulated...
-
Investigation of Air Quality beside a Municipal Landfill: The Fate of Malodour Compounds as a Model VOC
PublicationThis paper presents the results of an investigation on ambient air odour quality in the vicinity of a municipal landfill. The investigations were carried out during the spring–winter and the spring seasons using two types of the electronic nose instrument. The field olfactometers were employed to determine the mean odour concentration, which was from 2.1 to 32.2 ou/m3 depending on the measurement site and season of the year. In...
-
Machine-aided detection of SARS-CoV-2 from complete blood count
PublicationThe current gold standard for SARS-CoV-2 detection methods lacks the functionality to perform population screening. Complete blood count (CBC) tests are a cost-effective way to reach a wide range of people – e.g. according to the data of the Central Statistical Office of Poland from 2016, there are 3,000 blood diagnostic laboratories in Poland, and 46% of Polish people have at least one CBC test per year. In our work, we show...
-
Speed estimation of a car at impact with a W-beam guardrail using numerical simulations and machine learning
PublicationThis paper aimed at developing a new method of estimating the impact speed of a passenger car at the moment of a crash into a W-beam road safety barrier. The determination of such a speed based on the accident outcomes is demanding, because often there is no access to full accident data. However, accurate determination of the impact speed is one of the key elements in the reconstruction of road accidents. A machine learning algorithm...
-
Highly Miniaturized Self-Diplexed U-Shaped Slot Antenna Based on Shielded QMSIW
PublicationThis article presents an efficient yet simple design approach to highly miniaturized cavity-backed self-diplexing antenna (SDA) with high-isolation. The structure employs a shielded quarter-mode substrate integrated waveguide (QMSIW). Two U-shaped slots are engraved on the top conducting plane, which realize two frequency bands and significant size reduction. The slots are excited by two independent 50Ω orthogonal feed-lines to...
-
Validation Process for Computational Model of Full-Scale Segment for Design of Composite Footbridge
PublicationExperimental tests and numerical simulations of a full-scale segment of a foot and cycle bridge made of polymer composites are presented in the paper. The analysed structure is made of sandwich panels, which consist of glass fibre reinforced polymer (GFRP) multi-layered laminate faces and a PET foam (obtained from recycling) core. The dimensions of the segment cross-section are the same as for the target footbridge; however, span...
-
Machine learning-based seismic fragility and seismic vulnerability assessment of reinforced concrete structures
PublicationMany studies have been performed to put quantifying uncertainties into the seismic risk assessment of reinforced concrete (RC) buildings. This paper provides a risk-assessment support tool for purpose of retrofitting and potential design strategies of RC buildings. Machine Learning (ML) algorithms were developed in Python software by innovative methods of hyperparameter optimization, such as halving search, grid search, random...
-
Assessment of Electronic Sensing Techniques for the Rapid Identification of Alveolar Echinococcosis through Exhaled Breath Analysis
PublicationHere we present a proof-of-concept study showing the potential of a chemical gas sensors system to identify the patients with alveolar echinococcosis disease through exhaled breath analysis. The sensors system employed comprised an array of three commercial gas sensors and a custom gas sensor based on WO3 nanowires doped with gold nanoparticles, optimized for the measurement of common breath volatile organic compounds. The measurement...
-
Electrical Tree Growth Behavior Under AC and DC High Voltage in Power Cables
PublicationThis work investigates the impact of an applied AC and DC high voltage on the electrical tree behavior in extruded cross-linked polyethylene (XLPE) insulation based on simulation and experimental validation. Extensive partial discharge (PD) testing methods are being implemented for high voltage cables under AC voltage for monitoring their condition. However, these PD testing methods cannot be utilized for power cables under DC...
-
Magnetic Signature Description of Ellipsoid-Shape Vessel Using 3D Multi-Dipole Model Fitted on Cardinal Directions
PublicationThe article presents a continuation of the research on the 3D multi-dipole model applied to the reproduction of magnetic signatures of ferromagnetic objects. The model structure has been modified to improve its flexibility - model parameters determined by optimization can now be located in the cuboid contour representing the object's hull. To stiffen the model, the training dataset was expanded to data collected from all four cardinal...
-
Load Testing of GFRP Composite U-Shape Footbridge
PublicationThe paper presents the scope of load tests carried out on an innovative shell composite footbridge. The tested footbridge was manufactured in one production cycle and has no components made from materials other than GFRP laminates and PET foam. The load tests, performed on a 14-m long structure, were the final stage of a research program in the Fobridge project carried out in cooperation with: Gdańsk University of Technology (leader),...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Inverse Nonlinear Eigenvalue Problem Framework for the Synthesis of Coupled-Resonator Filters With Nonresonant Nodes and Arbitrary Frequency-Variant Reactive Couplings
PublicationA novel, general circuit-level description of coupledresonator microwave filters is introduced in this article. Unlike well-established coupling-matrix models based on frequency-invariant couplings or linear frequency-variant couplings (LFVCs), a model with arbitrary reactive frequencyvariant coupling (AFVC) networks is proposed. The engineered formulation is more general than prior-art ones—with the only restriction that the coupling...