Filtry
wszystkich: 981
wybranych: 837
Wyniki wyszukiwania dla: CROSS-SENSITIVITY, MULTIPLE LINEAR REGRESSION, ARTIFICIAL NEURAL NETWORKS
-
Novel Nonlinear High Order Technologies for Damage Diagnosis of Complex Assets
PublikacjaFor the first time worldwide, innovative techniques, generic non-linear higher-order unnormalized cross-correlations of spectral moduli, for the diagnosis of complex assets, are proposed. The normalization of the proposed techniques is based on the absolute central moments, that have been proposed and widely investigated in mathematical works. The existing higher-order, crosscovariances of complex spectral components are not sufficiently...
-
Deep Learning-Based LOS and NLOS Identification in Wireless Body Area Networks
PublikacjaIn this article, the usage of deep learning (DL) in ultra-wideband (UWB) Wireless Body Area Networks (WBANs) is presented. The developed approach, using channel impulse response, allows higher efficiency in identifying the direct visibility conditions between nodes in off-body communication with comparison to the methods described in the literature. The effectiveness of the proposed deep feedforward neural network was checked on...
-
Monitoring the gas turbine start-up phase on the platform using a hierarchical model based on Multi-Layer Perceptron networks
PublikacjaVery often, the operation of diagnostic systems is related to the evaluation of process functionality, where the diagnostics is carried out using reference models prepared on the basis of the process description in the nominal state. The main goal of the work is to develop a hierarchical gas turbine reference model for the estimation of start-up parameters based on multi-layer perceptron neural networks. A functional decomposition...
-
Multiple jets impingement – numerical analysis by the ζ-f and hybrid VLES turbulence models
PublikacjaPresented paper summarizes the Authors findings referring to the numerical analyses of the jet impinging phenomena in the case of complex jets configurations in various applications e.g. in the heat exchangers. Multiple jets interference resulting in the cross-flow and the surface curvature are the factors which impose the need of advanced turbulence models utilization. The outcome of the research based on the ζ-f turbulence model...
-
5G Millimeter Wave Network Optimization: Dual Connectivity and Power Allocation Strategy
PublikacjaThe fifth generation (5G) of mobile networks utilizing millimeter Wave (mmWave) bands can be considered the leading player in meeting the continuously increasing hunger of the end user demands in the near future. However, 5G networks are characterized by high power consumption, which poses a significant challenge to the efficient management of base stations (BSs) and user association. Implementing new power consumption and user...
-
Musical Instrument Identification Using Deep Learning Approach
PublikacjaThe work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata...
-
STABILITY AND LOAD BEARING CAPACITY OF A BARS WITH BUILT UP CROSS SECTION AND ELASTIC SUPPORTS
PublikacjaThe present paper is devoted to the numerical analysis and experimental tests of compressed bars with built–up cross section which are commonly used as a top chord of the roof trusses. The significant impact on carrying capacity for that kind of elements in case of out-of-plane buckling is appropriate choice of battens which are used to provide interaction between separate members. Linear buckling analysis results and nonlinear static...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublikacjaTo effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches...
-
High Isolation Metamaterial-based Dual-band MIMO Antenna for 5G Millimeter-wave Applications
PublikacjaThis article presents a high-isolation metamaterial-based dual-band multiple-input multiple-output (MIMO) antenna for 5G millimeter-wave communication networks. The proposed antenna is a pentagon-shaped monopole that provides a dual-band response with a wide operating bandwidth at 5G 28/28 bands. The antenna is printed on 0.508-mm-thick Rogers RT5880 substrate of relative permittivity ɛr =2.2. It exhibits a small physical size...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublikacjaBreast 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...
-
Towards rainfall interception capacity estimation using ALS LiDAR data
PublikacjaIn this study we develop a spatial model for interception capacity of vegetation based on LiDAR data. The study is conducted in the natural wetland river valley dominated meadows, reeds and small bushes. The multiple regression model was chosen to relate the field measurements of interception capacity and LiDAR statistics at 2m grid. The optimal model was chosen by stepwise selection and further manual variables selection resulting...
-
AUTOMATYCZNA KLASYFIKACJA MOWY PATOLOGICZNEJ
PublikacjaAplikacja przedstawiona w niniejszym rozdziale służy do automatycznego wykrywania mowy patologicznej na podstawie bazy nagrań. W pierwszej kolejności przedstawiono założenia leżące u podstaw przeprowadzonych badan wraz z wyborem bazy mowy patologicznej. Zaprezentowano również zastosowane algorytmy oraz cechy sygnału mowy, które pozwalają odróżnić mowę niezaburzoną od mowy patologicznej. Wytrenowane sieci neuronowe zostały następnie...
-
Electromagnetic Simulation with 3D FEM for Design Automation in 5G Era
PublikacjaElectromagnetic simulation and electronic design automation (EDA) play an important role in the design of 5G antennas and radio chips. The simulation challenges include electromagnetic effects and long simulation time and this paper focuses on simulation software based on finite-element method (FEM). The state-of-the-art EDA software using novel computational techniques based on FEM can not only accelerate numerical analysis, but...
-
Bio-inspired Decisional DNA in Machinas and other Man-made Systems: The Way Forward
PublikacjaArtificial bio-inspired intelligent techniques and systems supporting smart, knowledge-based solutions of real world problems which are currently researched very extensively by research teams around the world, have enormous potential to enhance automation of decision making and problem solving for a number of diverse areas including design, manufacturing, Information Technology (IT), social communities of practice, and economics...
-
Neural Architecture Search for Skin Lesion Classification
PublikacjaDeep neural networks have achieved great success in many domains. However, successful deployment of such systems is determined by proper manual selection of the neural architecture. This is a tedious and time-consuming process that requires expert knowledge. Different tasks need very different architectures to obtain satisfactory results. The group of methods called the neural architecture search (NAS) helps to find effective architecture...
-
Parametric optimization of sandwich composite footbridge with U-shaped cross-section
PublikacjaParametric optimization of sandwich composite footbridge was presented in the paper. Composite footbridge has 14,5 m long and has U-shaped cross-section with inner dimensions 2,6 × 1,3 m. The sandwich structure in made from GFRP laminate as a faces and PET foam as a core. The aim of analysis was to minimize the mass of the new footbridge that can lead to minimize the cost of structure. After optimization was conducted, the new...
-
Automatic labeling of traffic sound recordings using autoencoder-derived features
PublikacjaAn approach to detection of events occurring in road traffic using autoencoders is presented. Extensions of existing algorithms of acoustic road events detection employing Mel Frequency Cepstral Coefficients combined with classifiers based on k nearest neighbors, Support Vector Machines, and random forests are used. In our research, the acoustic signal gathered from the microphone placed near the road is split into frames and converted...
-
Artificial intelligence support for disease detection in wireless capsule endoscopy images of human large bowel
PublikacjaIn the work the chosen algorithms of disease recognition in endoscopy images were described and compared for theirs efficiency. The algorithms were estimated with regard to utility for application in computer system's support for digestive system's diagnostics. Estimations were achieved in an advanced testing environment, which was built with use of the large collection of endoscopy movies received from Medical University in Gdańsk....
-
Influence of Escherichia coli on Expression of Selected Human Drug Addiction Genes
PublikacjaThe impact of enteric microflora on the expression of genes associated with cocaine and amphetamine addiction was described. Human genome-wide experiments on RNA transcripts expressed in response to three selected Escherichia coli strains allowed for significant alteration (p > 0.05) of the linear regression model between HT-29 RNA transcripts associated with the KEGG pathway:hsa05030:Cocaine addiction after 3 h stimulation with...
-
Special techniques and future perspectives: Simultaneous macro- and micro-electrode recordings
PublikacjaThere are many approaches to studying the inner workings of the brain and its highly interconnected circuits. One can look at the global activity in different brain structures using non-invasive technologies like positron emission tomography (PET) or functional magnetic resonance imaging (fMRI), which measure physiological changes, e.g. in the glucose uptake or blood flow. These can be very effectively used to localize active patches...
-
Fundamental Schemes to Determine Disjoint Paths for Multiple Failure Scenarios
PublikacjaDisjoint path routing approaches can be used to cope with multiple failure scenarios. This can be achieved using a set of k (k> 2) link- (or node-) disjoint path pairs (in single-cost and multi-cost networks). Alternatively, if Shared Risk Link Groups (SRLGs) information is available, the calculation of an SRLG-disjoint path pair (or of a set of such paths) can protect a connection against the joint failure of the set of links...
-
Forecasting energy consumption and carbon dioxide emission of Vietnam by prognostic models based on explainable machine learning and time series
PublikacjaThis study assessed the usefulness of algorithms in estimating energy consumption and carbon dioxide emissions in Viet- nam, in which the training dataset was used to train the models linear regression, random forest, XGBoost, and AdaBoost, allowing them to comprehend the patterns and relationships between population, GDP, and carbon dioxide emissions, energy consumption. The results revealed that random forest, XGBoost, and AdaBoost...
-
INVESTIGATION OF SOUR SUBSTANCES BY FIVE-CHANNEL POTENTIOMETRIC TASTE SENSOR CONTAINING ALL-SOLID-STATE- ELECTRODES (ASSEs)
PublikacjaAn elaboration of taste sensor for discrimination of different food products is of great importance for food industry. Potentiometric taste sensor containing ion selective electrodes with lipid/polymer membranes has already been applied commercially in food industry. However, time-consuming and demanding preconditioning method of ions selective electrodes as well as maintenance of electrodes’ bodies are disadvantages of this taste...
-
Investigation of sour substances by five-channel potentiometric taste sensor containing all-solid-state-electrodes ( ASSEs)
PublikacjaAn elaboration of taste sensor for discrimination of different food products is of great importance for food industry. Potentiometric taste sensor containing ion selective electrodes with lipid/polymer membranes has already been applied commercially in food industry. However, time-consuming and demanding preconditioning method of ions selective electrodes as well as maintenance of electrodes’ bodies are disadvantages of this taste...
-
Electron Scattering on X(CH3)4 Molecules: Applicability of Simple Additivity Rule and Role of Methylation
PublikacjaTo investigate influence of target methylation (substitution of a hydrogen atom by methyl group) on electron-collision processes we compare absolute total cross sections for XH4 and X(CH3)4 molecules, where X is Si and Ge, respectively. We also compare experimental TCSs energy dependencies with estimated data obtained using simple formula and TCSs for methyl group and those for SiH4 and GeH4. Electron-scattering TCSs for mentioned...
-
Basic sensitivity analysis of a telecommunication tower complementing standard reinforcement design process
PublikacjaThis paper presents straightforward sensitivity assessment of a telecommunication tower. The analysis is set toidentify the elements of the tower which may be reinforced with the greatest structural advantage. As current expertopin ions on structural redesign of similar structures due to a planned addition of extra loads are mainly based ondeterministic computations or engineering intuition,...
-
Dynamic Bankruptcy Prediction Models for European Enterprises
PublikacjaThis manuscript is devoted to the issue of forecasting corporate bankruptcy. Determining a firm’s bankruptcy risk is one of the most interesting topics for investors and decision-makers. The aim of the paper is to develop and to evaluate dynamic bankruptcy prediction models for European enterprises. To conduct this objective, four forecasting models are developed with the use of four different methods—fuzzy sets, recurrent and...
-
System for automatic singing voice recognition
PublikacjaW artykule przedstawiono system automatycznego rozpoznawania jakości i typu głosu śpiewaczego. Przedstawiono bazę danych oraz zaimplementowane parametry. Algorytmem decyzyjnym jest algorytm sztucznych sieci neuronowych. Wytrenowany system decyzyjny osiąga skuteczność ok. 90% w obydwu kategoriach rozpoznawania. Dodatkowo wykazano przy pomocy metod statystycznych, że wyniki działania systemu automatycznej oceny jakości technicznej...
-
Machine learning-based seismic response and performance assessment of reinforced concrete buildings
PublikacjaComplexity and unpredictability nature of earthquakes makes them unique external loads that there is no unique formula used for the prediction of seismic responses. Hence, this research aims to implement the most well-known Machine Learning (ML) methods in Python software to propose a prediction model for seismic response and performance assessment of Reinforced Concrete Moment-Resisting Frames (RC MRFs). To prepare 92,400 data...
-
On Memory-Based Precise Calibration of Cost-Efficient NO2 Sensor Using Artificial Intelligence and Global Response Correction
PublikacjaNitrogen dioxide (NO2) is a prevalent air pollutant, particularly abundant in densely populated urban regions. Given its harmful impact on health and the environment, precise real-time monitoring of NO2 concentration is crucial, particularly for devising and executing risk mitigation strategies. However, achieving precise measurements of NO2 is challenging due to the need for expensive and cumbersome equipment. This has spurred...
-
Interannual Variability of the GNSS Precipitable Water Vapor in the Global Tropics
PublikacjaThis paper addresses the subject of inter-annual variability of the tropical precipitable water vapor (PWV) derived from 18 years of global navigation satellite system (GNSS) observations. Non-linear trends of retrieved GNSS PWV were investigated using the singular spectrum analysis (SSA) along with various climate indices. For most of the analyzed stations (~49%) the GNSS PWV anomaly was related to the El Niño Southern Oscillation...
-
Statistical Data Pre-Processing and Time Series Incorporation for High-Efficacy Calibration of Low-Cost NO2 Sensor Using Machine Learning
PublikacjaAir pollution stands as a significant modern-day challenge impacting life quality, the environment, and the economy. It comprises various pollutants like gases, particulate matter, biological molecules, and more, stemming from sources such as vehicle emissions, industrial operations, agriculture, and natural events. Nitrogen dioxide (NO2), among these harmful gases, is notably prevalent in densely populated urban regions. Given...
-
Deep learning approach on surface EEG based Brain Computer Interface
PublikacjaIn this work we analysed the application of con-volutional neural networks in motor imagery classification for the Brain Computer Interface (BCI) purposes. To increase the accuracy of classification we proposed the solution that combines the Common Spatial Pattern (CSP) with convolutional network (ConvNet). The electroencephalography (EEG) is one of the modalities we try to use for controlling the prosthetic arm. Therefor in this...
-
Using deep learning to increase accuracy of gaze controlled prosthetic arm
PublikacjaThis paper presents how neural networks can be utilized to improve the accuracy of reach and grab functionality of hybrid prosthetic arm with eye tracing interface. The LSTM based Autoencoder was introduced to overcome the problem of lack of accuracy of the gaze tracking modality in this hybrid interface. The gaze based interaction strongly depends on the eye tracking hardware. In this paper it was presented how the overall the...
-
SDN testbed for validation of cross-layer data-centric security policies
PublikacjaSoftware-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...
-
Artificial Thermal Ageing of Polyester Reinforced and Polyvinyl Chloride Coated Technical Fabric
PublikacjaArchitectural fabric AF9032 has been subjected to artificial thermal ageing to determine changes of the material parameters of the fabric. The proposed method is based on the accelerated ageing approach proposed by Arrhenius. 300 mm x 50 mm samples were cut in the warp and fill directions and placed in a thermal chamber at 80 °C for up to 12 weeks or at 90 °C for up to 6 weeks. Then after one week of conditioning at ambient temperature,...
-
Assessment of wastewater quality indicators for wastewater treatment influent using an advanced logistic regression model
PublikacjaInfluent quality indicators play a significant role in wastewater treatment plant performance due to their correlation with reactor operations and effluent quality. However, selecting a specific/best parameter indicator for predicting influent wastewater quality is one of the challenges in wastewa- ter treatment. This study, therefore, focused on determining suitable variables as influent quality indicators. For this purpose, a...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublikacjaW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
Positivity and job burnout in emergency personnel: examining linear and curvilinear relationship
PublikacjaThe aim of this study was to examine whether the relationship between the ratio of job-related positive to negative emotions (positivity ratio) and job burnout is best described as linear or curvilinear. Participants were 89 police officers (12% women) and 86 firefighters. The positivity ratio was evaluated using the Job-related Affective Wellbeing Scale (Van Katwyk, Fox, Spector, & Kelloway, 2000). Exhaustion and disengagement,...
-
Predicting Value of Binding Constants of Organic Ligands to Beta-Cyclodextrin: Application of MARSplines and Descriptors Encoded in SMILES String
PublikacjaThe quantitative structure–activity relationship (QSPR) model was formulated to quantify values of the binding constant (lnK) of a series of ligands to beta–cyclodextrin (β-CD). For this purpose, the multivariate adaptive regression splines (MARSplines) methodology was adopted with molecular descriptors derived from the simplified molecular input line entry specification (SMILES) strings. This approach allows discovery of regression...
-
Efficient Multi-Fidelity Design Optimization of Microwave Filters Using Adjoint Sensitivity
PublikacjaA simple and robust algorithm for computationally efficient design optimiza-tion of microwave filters is presented. Our approach exploits a trust-region (TR)-based algorithm that utilizes linear approximation of the filter response obtained using adjoint sensitivity. The algorithm is sequentially executed on a family of electromagnetic (EM)-simulated models of different fidelities, starting from a coarse-discretization one, and...
-
Numerical Analysis of Steady Gradually Varied Flow in Open Channel Networks with Hydraulic Structures
PublikacjaIn this paper, a method for numerical analysis of steady gradually varied fl ow in channel networks with hydraulic structures is considered. For this purpose, a boundary problem for the system of ordinary differential equations consisting of energy equation and mass conservation equations is formulated. The boundary problem is solved using fi nite difference technique which leads to the system of non-linear algebraic equations....
-
Scattering of electrons by a 1,2-butadiene (C4H6) molecule: measurements and calculations
PublikacjaWe present the results of experimental and theoretical study on electron collisions with a 1,2-butadiene (H2C=C=CHCH3) molecule. Absolute grand-total cross sections (TCSs) were measured using a linear electron-transmission method for collision energies in the 0.5–300 eV range. Two distinct features in the TCS energy curve were detected: a narrow peak located at 2.3 eV and a broad enhancement centered around 9 eV. We attributed...
-
Processing, Mechanical and Morphological Properties of GTR Modified by SBS Copolymers
PublikacjaIn this work, ground tire rubber (GTR) was thermo-mechanically treated in the presence of styrene-butadiene-styrene (SBS) copolymers. During preliminary investigation, the effects of different SBS copolymer grades, the variable content of SBS copolymer on the Mooney viscosity, and the thermal and mechanical properties of modified GTR were determined. Subsequently, GTR modified by SBS copolymer and cross-linking agents (sulfur-based...
-
Torsion of restrained thin-walled bars of open constant bisymmetric cross-section
PublikacjaElastic and geometric stiffness matrices were derived using Castigliano's first theorem, for the case of torsion of restrained thin-walled bars of open constant bisymmetric cross-section. Functions which describe the angles of torsion were adopted from the solutions of thedifferential equation for restrained torsion. The exact solutions were simplified by expanding them in a power series. Numerical examples were taken from Kujawa...
-
Thermal Images Analysis Methods using Deep Learning Techniques for the Needs of Remote Medical Diagnostics
PublikacjaRemote medical diagnostic solutions have recently gained more importance due to global demographic shifts and play a key role in evaluation of health status during epidemic. Contactless estimation of vital signs with image processing techniques is especially important since it allows for obtaining health status without the use of additional sensors. Thermography enables us to reveal additional details, imperceptible in images acquired...
-
Service-based Resilience via Shared Protection in Mission-critical Embedded Networks
PublikacjaMission-critical networks, which for example can be found in autonomous cars and avionics, are complex systems with a multitude of interconnected embedded nodes and various service demands. Their resilience against failures and attacks is a crucial property and has to be already considered in their design phase. In this paper, we introduce a novel approach for optimal joint service allocation and routing, leveraging virtualized...
-
System for tracking multiple trains on a test railway track
PublikacjaSeveral problems may arise when multiple trains are to be tracked using two IP camera streams. In this work, real-life conditions are simulated using a railway track model based on the Pomeranian Metropolitan Railway (PKM). Application of automatic clustering of optical flow is investigated. A complete tracking solution is developed using background subtraction, blob analysis, Kalman filtering, and a Hungarian algorithm. In total,...
-
System for tracking multiple trains on a test railway track
PublikacjaSeveral problems may arise when multiple trains are to be tracked using two IP camera streams. In this work, real-life conditions are simulated using a railway track model based on the Pomeranian Metropolitan Railway (PKM). Application of automatic clustering of optical flow is investigated. A complete tracking solution is developed using background subtraction, blob analysis, Kalman filtering, and a Hungarian algorithm. In total,...
-
Application of a Gas Sensor Array to Effectiveness Monitoring of Air Contaminated with Toluene Vapors Absorption Process
PublikacjaThis article demonstrates the application of a gas sensor array to monitor the effectiveness of the absorption process of air stream purification from odorous compounds (toluene vapors). A self-constructed matrix consisting of five commercially available gas sensors was used. Multiple linear regression (MLR) was selected as the statistical technique used to calibrate the matrice. Gas chromatography coupled with a flame ionization...