Filtry
wszystkich: 981
wybranych: 837
Wyniki wyszukiwania dla: CROSS-SENSITIVITY, MULTIPLE LINEAR REGRESSION, ARTIFICIAL NEURAL NETWORKS
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublikacjaAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Investigating Feature Spaces for Isolated Word Recognition
PublikacjaMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
In silico modelling for predicting the cationic hydrophobicity and cytotoxicity of ionic liquids towards the Leukemia rat cell line, Vibrio fischeri and Scenedesmus vacuolatus based on molecular interaction potentials of ions
PublikacjaIn this study we present prediction models for estimating in silico the cationic hydrophobicity and the cytotoxicity (log [1/EC50]) of ionic liquids (ILs) towards the Leukemia rat cell line (IPC-81), the marine bacterium Vibrio fischeri and the limnic green algae Scenedesmus vacuolatus using linear free energy relationship (LFER) descriptors computed by COSMO calculations. The LFER descriptors used for the prediction model (i.e....
-
Condition-Based Monitoring of DC Motors Performed with Autoencoders
PublikacjaThis paper describes a condition-based monitoring system estimating DC motor degradation with the use of an autoencoder. Two methods of training the autoencoder are evaluated, namely backpropagation and extreme learning machines. The root mean square (RMS) error in the reconstruction of successive fragments of the measured DC motor angular-frequency signal, which is fed to the input of autoencoder, is used to determine the health...
-
Electrophoretic Deposition and Characterization of Chitosan/Eudragit E 100 Coatings on Titanium Substrate
PublikacjaCurrently, a significant problem is the production of coatings for titanium implants, which will be characterized by mechanical properties comparable to those of a human bone, high corrosion resistance, and low degradation rate in the body fluids. This paper aims to describe the properties of novel chitosan/Eudragit E 100 (chit/EE100) coatings deposited on titanium grade 2 substrate by the electrophoretic technique (EPD). The deposition...
-
Individual entrepreneurial orientation: comparison of business and STEM students
PublikacjaAbstract Purpose – The purpose of this study is to determine whether there are differences in Individual Entrepreneurial Orientation (IEO) between students who are doing their major in business studies and the ones whose areas of study are science, technology, engineering, and mathematics (STEM). Design/methodology/approach – The current research investigates which factors and components contribute to EO orientation development...
-
Wear Resistance Enhancement of Al6061 Alloy Surface Layer by Laser Dispersed Carbide Powders
PublikacjaIn this paper, results of the experimental study on improving wear resistance in sliding friction of Al-based alloy are presented. The technique used involves the formation of a metal matrix composite (MMC) in the alloy surface layer by laser dispersion of carbide powders such as WC, TiC and SiC. For WC and TiC MMC surface coatings fabricated under conditions typical for most of the technologically relevant solid-state lasers (wavelength...
-
Improving depth maps of plants by using a set of five cameras
PublikacjaObtaining high-quality depth maps and disparity maps with the use of a stereo camera is a challenging task for some kinds of objects. The quality of these maps can be improved by taking advantage of a larger number of cameras. The research on the usage of a set of five cameras to obtain disparity maps is presented. The set consists of a central camera and four side cameras. An algorithm for making disparity maps called multiple...
-
Magnetically sensitive fiber probe with nitrogen-vacancy center nanodiamonds integrated in a suspended core
PublikacjaEfficient collection of photoluminescence arising from spin dynamics of nitrogen vacancy (NV) centers in diamond is important for practical applications involving precise magnetic field or temperature mapping. These goals may be realized by the integration of nanodiamond particles with optical fibers and volumetric doping of the particles alongside the fiber core. That approach combines the advantages of robust axial fixation of...
-
Expedited Geometry Scaling of Compact Microwave Passives by Means of Inverse Surrogate Modeling
PublikacjaIn this paper, the problem of geometry scaling of compact microwave structures is investigated. As opposed to conventional structures (i.e., constructed using uniform transmission lines), re-design of miniaturized circuits (e.g., implemented with artificial transmission lines, ATSs) for different operating frequencies is far from being straightforward due to considerable cross-couplings between the circuit components. Here, we...
-
Massively parallel linear-scaling Hartree–Fock exchange and hybrid exchange–correlation functionals with plane wave basis set accuracy
PublikacjaWe extend our linear-scaling approach for the calculation of Hartree–Fock exchange energy using localized in situ optimized orbitals [Dziedzic et al., J. Chem. Phys. 139, 214103 (2013)] to leverage massive parallelism. Our approach has been implemented in the ONETEP (Order-N Electronic Total Energy Package) density functional theory framework, which employs a basis of non-orthogonal generalized Wannier functions (NGWFs) to achieve...
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublikacjaDeep networks have already shown a spectacular success for object classification and detection for various applications from everyday use cases to advanced medical problems. The main advantage of the classification models over the detection models is less time and effort needed for dataset preparation, because classification networks do not require bounding box annotations, but labels at the image level only. Yet, after passing...
-
Historical carpentry corner log joints—Numerical analysis within stochastic framework
PublikacjaThe paper presents the results of numerical analysis performed on historical, traditional carpentry corner logjoints of two basic topologies: the short-corner dovetail connection and the saddle notch connection. These types of carpentry joints are commonly used in currently preserved objects of wooden architecture. All connections have been modelled in pinewood, which has been defined in the Finite Element software MSC.Marc/Mentat...
-
Satellite Image Classification Using a Hierarchical Ensemble Learning and Correlation Coefficient-Based Gravitational Search Algorithm
PublikacjaSatellite image classification is widely used in various real-time applications, such as the military, geospatial surveys, surveillance and environmental monitoring. Therefore, the effective classification of satellite images is required to improve classification accuracy. In this paper, the combination of Hierarchical Framework and Ensemble Learning (HFEL) and optimal feature selection is proposed for the precise identification...
-
Systematic Literature Review for Emotion Recognition from EEG Signals
PublikacjaResearchers have recently become increasingly interested in recognizing emotions from electroencephalogram (EEG) signals and many studies utilizing different approaches have been conducted in this field. For the purposes of this work, we performed a systematic literature review including over 40 articles in order to identify the best set of methods for the emotion recognition problem. Our work collects information about the most...
-
Detecting Lombard Speech Using Deep Learning Approach
PublikacjaRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
Systematic Literature Review for Emotion Recognition from EEG Signals
PublikacjaResearchers have recently become increasingly interested in recognizing emotions from electroencephalogram (EEG) signals and many studies utilizing different approaches have been conducted in this field. For the purposes of this work, we performed a systematic literature review including over 40 articles in order to identify the best set of methods for the emotion recognition problem. Our work collects information about the most...
-
Solubility Characteristics of Acetaminophen and Phenacetin in Binary Mixtures of Aqueous Organic Solvents: Experimental and Deep Machine Learning Screening of Green Dissolution Media
PublikacjaThe solubility of active pharmaceutical ingredients is a mandatory physicochemical characteristic in pharmaceutical practice. However, the number of potential solvents and their mixtures prevents direct measurements of all possible combinations for finding environmentally friendly, operational and cost-effective solubilizers. That is why support from theoretical screening seems to be valuable. Here, a collection of acetaminophen...
-
Online sound restoration system for digital library applications.
PublikacjaAudio signal processing algorithms were introduced to the new online non-commercial service for audio restoration intended to enhance the content of digitized audio repositories. Missing or distorted audio samples are predicted using neural networks and a specific implementation of the Jannsen interpolation method based on the autoregressive model (AR) combined with the iterative restoring of missing signal samples. Since the distortion...
-
Bio-based semi-aromatic polyesters for coating applications
PublikacjaLinear and branched bio-based semi-aromatic (co)polyesters were evaluated as resins for solvent-basedand powder coatings. Dimethyl-2,5-furandicarboxylate (DMF), 2,3-butanediol and various multifunc-tional comonomers were used to synthesize amorphous hydroxyl-end-capped (co)polyesters. The resinswere cross-linked using the -caprolactam blocked trimer of isophorone diisocyanate. Both the solvent-based and powder coatings proved to...
-
Intensification of catechin extraction from the bark of Syzygium cumini using ultrasonication: Optimization, characterization, degradation analysis and kinetic studies
PublikacjaCatechin is a prominent polyphenolic component that possesses various medicinal properties. Present work communicates the intensification and optimization of catechin extraction from the bark of Syzygium cumini tree using stirred reactor, soxhlet, ultrasonic bath, and ultrasonic horn technique. The optimization of several parameters such as type of solvent, solid to solvent ratio (1:100 w/v), speed of agitation (300 RPM), extraction...
-
Occurrence of antimicrobial resistant bacteria in environment and the statistical analysis of this phenomenon
PublikacjaIntroduction: In this study the occurrence of antimicrobial resistance patterns among fecal indicators (Escherichia coli and Enterococcus spp.) was analyzed in water and wastewater samples. The trends in antimicrobial resistance were analyzed using basic statistical methods. Methods: Samples were obtained from two local watercourses (Oliwski Stream and Reda River) as well as from the wastewater treatment plant (WWTP) Gdansk - Wschod....
-
Belief in the importance of socially responsible behaviors – the significance of trust and personal experiences with COVID-19
PublikacjaA vast number of studies have shown that trust is related to socially desirable traits and behaviors. In the present research we have investigated the relationship between generalized trust and beliefs about the importance of socially responsible behaviors (SRB) during the pandemic – namely, following the sanitary regime and getting vaccinated. Basing on the previous findings we assumed that trustful people...
-
Dependent self-employed individuals: are they different from paid employees?
PublikacjaThis study focuses on dependent self-employment, which covers a situation where a person works for the same employer as a typical worker while on a self-employment contractual basis, i.e., without a traditional employment contract and without certain rights granted to "regular" employees. The research exploits the individual-level dataset of 35 European countries extracted from the 2017 edition of the European Labour Force Survey...
-
Fighting Administrative Corruption with Digital Government in Sub-Saharan Africa
PublikacjaAdministrative corruption is a pervasive problem and a major threat to economic and social development around the world, especially in Sub-Saharan Africa which lags behind other regions in various development indicators and is seen as one of the most corrupt regions globally. This paper examines a hypothesis that digital government – the use of digital technology to transform public administration organizations and their relationships...
-
Quality Expectations of Mobile Subscribers
PublikacjaMobile systems, by nature, have finite resources. Radio spectrum is limited, expensive and shared between many users and services. Mobile broadband networks must support multiple applications of voice, video and data on a single IP-based infrastructure. These converged services each have unique traffic holding and quality requirements. A positive user experience must be obtained through efficient partitioning of the available wireless...
-
Changing Attitudes in Cross Cultural Diversity through International Senior Capstone Projects
PublikacjaIn this global world, today’s engineer is likely to have to work in global international teams with colleagues from other nationalities. The challenge for many engineering curricula is how to include, in a realistic way, this global dimension and increase the student’s awareness of the issues that are encountered. In the Purdue University Engineering Technology program, an international capstone project was created to increase...
-
Data-driven, probabilistic model for attainable speed for ships approaching Gdańsk harbour
PublikacjaThe growing demand for maritime transportation leads to increased traffic in ports. From this arises the need to observe the consequences of the specific speed ships reach when approaching seaports. However, usually the analyzed cases refer only to the statistical evaluation of the studied phenomenon or to the empirical modelling, ignoring the mutual influence of variables such as ship type, length or weather conditions. In this...
-
Thermal Image Processing for Respiratory Estimation from Cubical Data with Expandable Depth
PublikacjaAs healthcare costs continue to rise, finding affordable and non-invasive ways to monitor vital signs is increasingly important. One of the key metrics for assessing overall health and identifying potential issues early on is respiratory rate (RR). Most of the existing methods require multiple steps that consist of image and signal processing. This might be difficult to deploy on edge devices that often do not have specialized...
-
Maxillary sinus aeration analysis using computational fluid dynamics
PublikacjaThe maxillary sinus aeration using the computational fluid dynamics (CFD) method based on individual adult patients’ computed tomography (CT) scans were analyzed. The analysis was based on CT images of 4 patients: one with normal nose anatomy and three with nasal septal deviation (NSD) and concha bullosa (CB). The CFD simulation was performed using the Reynolds-Average Simulation approach and turbulence closure based on linear...
-
Optimal Design of Transmitarray Antennas via Low-Cost Surrogate Modelling
PublikacjaOver the recent years, reflectarrays and transmitarrays have been drawing a considerable attention due to their attractive features, including a possibility of realizing high gain and pencil-like radiation patterns without the employment of complex feeding networks. Among the two, transmitarrays seem to be superior over reflectarrays in terms of achieving high radiation efficiency without the feed blockage. Notwithstanding, the...
-
A Microwave Sensor with Operating Band Selection to Detect Rotation and Proximity in the Rapid Prototyping Industry
PublikacjaThis paper presents a novel sensor for detecting and measuring angular rotation and proximity, intended for rapid prototyping machines. The sensor is based on a complementary split-ring resonator (CSRR) driven by a conductor-backed coplanar waveguide. The sensor has a planar topology, which makes it simple and cost-effective to produce and accurate in measuring both physical quantities. The sensor has two components, a rotor, and...
-
Light4Health eLearning Course: health research for interior lighting design. Re-thinking design approaches based on science
PublikacjaThis paper presents the results of 'Light4Health' (L4H), a three-year EU Erasmus+ Strategic Partnership grant project (2019-2021), which investigated, systematized and taught health-related research on the impact of natural and artificial light on human health and well-being relevant to indoor lighting design. The objective was to re-think evidence-based lighting design approaches for residential, working/educational, and healthcare...
-
Application of a hybrid mechanistic/machine learning model for prediction of nitrous oxide (N2O) production in a nitrifying sequencing batch reactor
PublikacjaNitrous oxide (N2O) is a key parameter for evaluating the greenhouse gas emissions from wastewater treatment plants. In this study, a new method for predicting liquid N2O production during nitrification was developed based on a mechanistic model and machine learning (ML) algorithm. The mechanistic model was first used for simulation of two 15-day experimental trials in a nitrifying sequencing batch reactor. Then, model predictions...
-
An ANN-Based Approach for Prediction of Sufficient Seismic Gap between Adjacent Buildings Prone to Earthquake-Induced Pounding
PublikacjaEarthquake-induced structural pounding may cause major damages to structures, and therefore it should be prevented. This study is focused on using an artificial neural network (ANN) method to determine the sufficient seismic gap in order to avoid collisions between two adjacent buildings during seismic excitations. Six lumped mass models of structures with a different number of stories (from one to six) have been considered in...
-
Determination of benzodiazepines and Z-hypnotic drugs in whole blood samples by GC–MS/MS: Method development, validation and application
PublikacjaBenzodiazepines (BZDs) and Z-drugs are widely used as anxiolytics, sedative hypnotics, anticonvulsants and muscle relaxants. “Designer benzodiazepines” (DBZDs) are a new psychoactive substance class consisting of benzodiazepine derivatives that are not allowed for medical use and are known for being used recreationally. From a toxicologist standpoint, the huge number of such substances implicate a necessity for developing fast...
-
Physical crosslinking of hyaluronic acid in the presence of phospholipids in an aqueous nano-environment
PublikacjaHyaluronic acid and phospholipids are two components in the synovial joint cavity that contribute to joint lubrication synergistically. Molecular dynamics simulations were performed and hydrogen bonds in hyaluronic acid were analyzed to identify specific sites that are responsible for its physical cross-linking. Two molecular masses of hyaluronic acid, 10 kDa and 160 kDa, were considered. We use molecular dynamics simulations and...
-
Application of gas chromatography–tandem mass spectrometry for the determination of amphetamine-type stimulants in blood and urine
PublikacjaAmphetamine, methamphetamine, phentermine, 3,4-methylenedioxyamphetamine (MDA), 3,4-methylenedioxymethamphetamine (MDMA), and 3,4-methylenedioxy-N-ethylamphetamine (MDEA) are the most popular amphetamine-type stimulants. The use of these substances is a serious societal problem worldwide. In this study, a method based on gas chromatography-tandem mass spectrometry (GC-MS/MS) with simple and rapid liquid-liquid extraction (LLE)...
-
Application of multi-criteria methods to compare different solutions of supplying buildings in electricity from photovoltaic systems
PublikacjaNowadays, the technologies of electricity generation in distributed systems are usually associated with Renewable Energy Sources (RES). The choice of the construction site depends mainly on the availability of the power system. However, energy planning, especially in case of RES, is a complex process involving multiple and often conflicting objectives. The complexity of the selection of the electricity system is typically addressed...
-
Non-enzymatic flexible glucose sensing platform based on nanostructured TiO2–Au composite
PublikacjaAll over the world the number of people suffering from diabetes and related complications is drastically growing. Therefore, the need for accurate, reliable and stable sensor for monitoring of glucose in human body fluids is becoming highly desirable. In this work we show that material composed of gold layers deposited onto TiO2 nanotubes (NTs) formed onto the flexible Ti foil exhibits great response toward glucose oxidation and...
-
Energy efficiency of electric multiple units in suburban operation
PublikacjaThis thesis presents approach to analysis of energy efficiency of a suburban rail network, using novel models developed on the Matlab/Simulink basis. Necessary features and requirements for such models were determined thru in-depth review of the source literature in all applicable fields: electrified transportation systems, electric multiple units construction, vehicle drivetrains and finally, existing simulation methods. Existing...
-
Platelet RNA Sequencing Data Through the Lens of Machine Learning
PublikacjaLiquid biopsies offer minimally invasive diagnosis and monitoring of cancer disease. This biosource is often analyzed using sequencing, which generates highly complex data that can be used using machine learning tools. Nevertheless, validating the clinical applications of such methods is challenging. It requires: (a) using data from many patients; (b) verifying potential bias concerning sample collection; and (c) adding interpretability...
-
Super-resolved Thermal Imagery for High-accuracy Facial Areas Detection and Analysis
PublikacjaIn 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...
-
Comparative study on the effectiveness of various types of road traffic intensity detectors
PublikacjaVehicle detection and speed measurements are crucial tasks in traffic monitoring systems. In this work, we focus on several types of electronic sensors, operating on different physical principles in order to compare their effectiveness in real traffic conditions. Commercial solutions are based on road tubes, microwave sensors, LiDARs, and video cameras. Distributed traffic monitoring systems require a high number of monitoring...
-
Channel State Estimation in LTE-Based Heterogenous Networks Using Deep Learning
PublikacjaFollowing the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides...
-
High-Power Jamming Attack Mitigation Techniques in Spectrally-Spatially Flexible Optical Networks
PublikacjaThis work presents efficient connection provisioning techniques mitigating high-power jamming attacks in spectrally-spatially flexible optical networks (SS-FONs) utilizing multicore fibers. High-power jamming attacks are modeled based on their impact on the lightpaths’ quality of transmission (QoT) through inter-core crosstalk. Based on a desired threshold on a lightpath’s QoT, the modulation format used, the length of the path,...
-
Simulation of the number of storm overflows considering changes in precipitation dynamics and the urbanisation of the catchment area: a probabilistic approach
PublikacjaThis paper presents a probabilistic methodology that allows the study of the interactions between changes in rainfall dynamics and impervious areas in urban catchment on a long- and short-term basis. The proposed probabilistic model predict future storm overflows while taking into account the dynamics of changes in impervious areas and rainfall. In this model, a logistic regression method was used to simulate overflow resulting...
-
Determinants of the incidence of non-academic staff in European and US HEIs
PublikacjaIn this article, we contribute to the scant literature covering quantitative studies on the determinants of the non-academic staff incidence in higher education institutions by analysing how the proportion of non-academic staff is related to key features such as size, prestige, year of foundation and financial structure of universities. We apply nonlinear regression analysis to compare HEIs across Europe and the USA, taking into...
-
Application of Wavelet Transform and Fractal Analysis for Esophageal pH-Metry to Determine a New Method to Diagnose Gastroesophageal Reflux Disease
PublikacjaIn this paper, a new method for analysing gastroesophageal reflux disease (GERD) is shown. This novel method uses wavelet transform (WT) and wavelet-based fractal analysis (WBFA) on esophageal pH-metry measurements. The esophageal pH-metry is an important diagnostic tool supporting the physician’s work in diagnosing some forms of reflux diseases. Interpreting the results of 24-h pH-metry monitoring is time-consuming, and the conclusions...
-
Electrical Stimulation Modulates High Gamma Activity and Human Memory Performance
PublikacjaDirect electrical stimulation of the brain has emerged as a powerful treatment for multiple neurological diseases, and as a potential technique to enhance human cognition. Despite its application in a range of brain disorders, it remains unclear how stimulation of discrete brain areas affects memory performance and the underlying electrophysiological activities. Here, we investigated the effect of direct electrical stimulation...