Filters
total: 4205
filtered: 3328
-
Catalog
Chosen catalog filters
displaying 1000 best results Help
Search results for: HEARING IMPAIRED
-
INVESTIGATION OF THE LOMBARD EFFECT BASED ON A MACHINE LEARNING APPROACH
PublicationThe Lombard effect is an involuntary increase in the speaker’s pitch, intensity, and duration in the presence of noise. It makes it possible to communicate in noisy environments more effectively. This study aims to investigate an efficient method for detecting the Lombard effect in uttered speech. The influence of interfering noise, room type, and the gender of the person on the detection process is examined. First, acoustic parameters...
-
The Cultures of Knowledge Organizations: Knowledge, Learning, Collaboration (KLC)
PublicationThis book focuses on seeing, understanding, and learning to shape an organization’s essential cultures. The book is grounded on a fundamental assumption that every organization has a de facto culture. These “de facto cultures” appear at first glance to be serendipitous, vague, invisible, and unmanaged. An invisible and unrecognized de facto culture can undermine business goals and strategies and lead to business failures. The authors...
-
Assessing the attractiveness of human face based on machine learning
PublicationThe attractiveness of the face plays an important role in everyday life, especially in the modern world where social media and the Internet surround us. In this study, an attempt to assess the attractiveness of a face by machine learning is shown. Attractiveness is determined by three deep models whose sum of predictions is the final score. Two annotated datasets available in the literature are employed for training and testing...
-
Federated Learning in Healthcare Industry: Mammography Case Study
PublicationThe paper focuses on the role of federated learning in a healthcare environment. The experimental setup involved different healthcare providers, each with their datasets. A comparison was made between training a deep learning model using traditional methods, where all the data is stored in one place, and using federated learning, where the data is distributed among the workers. The experiment aimed to identify possible challenges...
-
Robust and Efficient Machine Learning Algorithms for Visual Recognition
PublicationIn visual recognition, the task is to identify and localize all objects of interest in the input image. With the ubiquitous presence of visual data in modern days, the role of object recognition algorithms is becoming more significant than ever and ranges from autonomous driving to computer-aided diagnosis in medicine. Current models for visual recognition are dominated by models based on Convolutional Neural Networks (CNNs), which...
-
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...
-
Detecting Lombard Speech Using Deep Learning Approach
PublicationRobust 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...
-
Edge-Computing based Secure E-learning Platforms
PublicationImplementation of Information and Communication Technologies (ICT) in E-Learning environments have brought up dramatic changes in the current educational sector. Distance learning, online learning, and networked learning are few examples that promote educational interaction between students, lecturers and learning communities. Although being an efficient form of real learning resource, online electronic resources are subject to...
-
Social Learning in Cluster Organizations and Accumulation of Technological Capability
PublicationThe purpose of the paper is to present how members of cluster organizations perceive their role in the accumulation of technological capability through social learning. The paper presents the results of a qualitative study of four cluster organizations. The theoretical foundation of the study are the communities of practice and the organizational inertia theories. The study indicates that the dynamics of technological capability...
-
Multimedia industrial and medical applications supported by machine learning
PublicationThis article outlines a keynote paper presented at the Intelligent DecisionTechnologies conference providing a part of the KES Multi-theme Conference “Smart Digital Futures” organized in Rome on June 14–16, 2023. It briefly discusses projects related to traffic control using developed intelligent traffic signs and diagnosing the health of wind turbine mechanisms and multimodal biometric authentication for banking branches to provide...
-
The use of machine learning for face regions detection in thermograms
PublicationThe aim of this study is to analyse the methods of detecting characteristic points of the face in thermographic images. As part of the implementation an extensive analysis of scientific publications covering similar issues both for the analysis of images made in visible light and thermographic images was carried out. On the basis of this analysis, 3 models were selected and then they were implemented and tested on the basis of...
-
Transfer learning in imagined speech EEG-based BCIs
PublicationThe Brain–Computer Interfaces (BCI) based on electroencephalograms (EEG) are systems which aim is to provide a communication channel to any person with a computer, initially it was proposed to aid people with disabilities, but actually wider applications have been proposed. These devices allow to send messages or to control devices using the brain signals. There are different neuro-paradigms which evoke brain signals of interest...
-
Research and applications of active bearings: A state-of-the-art review
PublicationControllable/active bearings are mainly associated with active magnetic bearings (AMBs), whereas active bearing control is also found in many types of bearings, e.g. fluid, gas and hybrid bearings. The article presents a review of the literature describing the structure and results of studies of active bearings. Active control brings a number of benefits resulting in the fact that their use as a support for rotors becomes increasingly...
-
E-learning course "International comparative studies on SMEs"
PublicationProjekt Leonardo da Vinci "International comparative studies and course development on SMEs" został zainspirowany poprzednim projektem LdV "A European Diploma in SME Management". Bazując na poprzednich doświadczeniach projektowych zaproponowano opracowanie struktur dla opisania narodowych systemów małych i średnich przedsiębiorstw (ang. SME Small Media Enterprises) przy wykorzystaniu dostępnych krajowych danych. Udowodniono, że...
-
Unique performance aspects of PTFE-Lined thrust bearings
PublicationW pracy przedstawiono korzyści płynące z zastępowania tradycyjnych stopów łożyskowych przez warstwy ślizgowe wykonane z kompozytów na bazie PTFE. Kompozytowe warstwy ślizgowe są coraz częściej stosowane w dużych łożyskach hydrogeneratorów o pionowych wałach. W pracy omówiono także aspekty stosowania takich łożysk związane z ich charakterystycznymi cechami.
-
Trees having many minimal dominating sets
PublicationWe provide an algorithm for listing all minimal dominating sets of a tree of order n in time O(1.4656^n). This leads to that every tree has at most 1.4656^n minimal dominating sets. We also give an infinite family of trees of odd and even order for which the number of minimal dominating sets exceeds 1.4167^n, thus exceeding 2^{n/2}. This establishes a lower bound on the running time of an algorithm for listing all minimal dominating...
-
Analysis of pavement structure sensitivity to passage of oversized heavy duty vehicle in terms of bearing capacity
PublicationOversized heavy duty vehicles occur in traffic very rarely but they reach extremely high weights, even up to 800 tonne. The detrimental impact of these vehicles on pavement structure is much higher than in case of commercial vehicles that comprise typical traffic, thus it is necessary to assess the sensitivity of pavement structure to passage of oversized vehicles. The paper presents results of sample calculations of load equivalency factor...
-
Technical Aspects and Energy Effects of Waste Heat Recovery from District Heating Boiler Slag
Publication -
“Fearing your own queer self”: Depictions of Diasporic Queer Experience in Grace Lau’s Poetry
Publication -
Serial depletion of Baltic herring since the Viking Age revealed by ancient DNA and population genomics
Publication -
Current knowledge about self-healing polymers in the aspect of application for full-rubber protective gloves
Publication -
Influence of hydrostatic pump operation period on performance of a thrust bearing of a 125 MW pump-turbine
Publication -
Evaluation of water turbine hydrodynamic thrust bearing performance on the basis of thermoelastohydrodynamic calculations and operational data
Publication -
Vibration-Based Diagnostics of Radial Clearances and Bolts Loosening in the Bearing Supports of the Heavy-Duty Gearboxes
Publication -
KABA Subject Heading Language as the Main Resource Subject Organization Tool in a Semantic Knowledge Base
Publication -
The features of steel surface hardening with high energy heating by high frequency currents and shower cooling
Publication -
Numerical Modeling of Steel Surface Hardening in the Process of High Energy Heating by High Frequency Currents
Publication -
The influence of strain on the Verwey transition as a function of dopant concentration: towards a geobarometer for magnetite-bearing rocks
Publication -
High-precision bearing estimation for active sonar with cylindrical array performed by interpolated array transformation
PublicationThe article presents a method for improving the accuracy of bearing in multibeam sonar with a cylindrical array. The antenna’s non-linear shape and the resulting non-uniform sampling of the signal in space, mean that known methods of high-resolution spectral analysis cannot be used. In order to apply an algorithm from this group, a linear virtual antenna must be produced. The paper presents a technique of mapping a cylindrical...
-
Efficiency of Biomass Energy used for Heating Purposes in a Residential Building in Comparison with other Energy Sources
PublicationThis paper discusses the results of analyses investigating the energy efficiency of biomass in comparison with other popular energy carriers used for heating, ventilation and water heating in residential buildings. The compared energy sources were lignite, natural gas, heating oil and electricity produced by conventional and integrated power generation plants. The most efficient variant relying on biomass and the least efficient...
-
Transcriptional profile of in vitro expanded human epidermal progenitor cells for the treatment of non-healing wounds
PublicationBackground Epidermal progenitor cells (EPCs) have been under extensive investigation due to their increasing potential of application in medicine and biotechnology. Cultured human EPCs are used in the treatment of chronic wounds and have recently became a target for gene therapy and toxicological studies. One of the challenges in EPCs culture is to provide a high number of undifferentiated, progenitor cells displaying high viability...
-
Assessment of possible application of water lubricated sintered brass slide bearing for marine propeller shaft
PublicationW artykule przedstawiono wyniki badań eksperymentalnych smarowanego wodą łożyska poprzecznego z panwią wykonaną ze spieku brązu.Przedstawiono wyniki pomiarów rozkładu ciśnienia w filmie smarnym, trajektorie osi wału oraz oporów ruchu.Przeprowadzono ocenę przydatności tego typu łożyska do łożyskowania okrętowych wałów śrubowych.
-
Comparison of induction motor bearing diagnostic test results through vibration and stator current measurement
PublicationThe paper discusses results of tests performed by authors, related to the angine bearings diagnostic using vibration and stator current measurements. The paper contains the description of an automatic measurement system, developed for measurement of those harmonics and processing that to obtain bearing diagnostic information. System was tested on objects with intentionally made defects in bearings, results of this test was also...
-
Evaluation of water turbine hydrodynamic thrust bearing performance on the basis of thermoelastohydrodynamic calculations and operational data.
PublicationW pracy przedstawiono analizę konstrukcji łożyska wzdłużnego turbiny wodnej. Łożysko zostało skonstruowane około 50 lat temu, a jego konstrukcja przewiduje kompensację termicznych odkształceń klocków. W analizie uwzględniono odkształcenia łożyska i wymianę ciepła w filmie smarowym i klockach łożyskowych. Poza obecną konstrukcją łożyska przeprowadzono również studium wpływu podstawowych parametrów konstrukcyjnych: grubości klocka...
-
Influence of hydrostatic pump operation period on performance of a thrust bearing of a 125 MW pump-turbine.
PublicationW pracy przedstawiono wyniki badań eksploatacyjnych łożysk wzdłużnych pompoturbin 125 MW elektrowni szczytowo pompowej (esp) Żar. W celu oceny warunków pracy łożysk wyposażono je w segmenty pomiarowe umożliwiające pomiary temperatury i położenia segmentu. W pracy omówiono konstrukcję i wyposażenie segmentu badawczego, metodykę wyznaczania charakterystycznych wielkości. Omówiono także wyniki badań wpływu czasu pracy pompy hydrostatycznego...
-
Bacterial cellulose in the field of wound healing and regenerative medicine of skin: recent trends and future prospectives
PublicationIn this overview, we focused on the bacterial cellulose (BC) applications, described in recently published scientific papers, in the field of skin regenerative medicine and wound care industry. Bacterial cellulose was proven to be biocompatible with living tissues. Moreover, its mechanical properties and porous structure are considered to be suitable for biomedical applications. It is due to the fact that porous structure of bacterial...
-
Justifying the prolongation of the service life of the bearing structure of a tank car when using Y25 bogies
PublicationThis paper substantiates the use of Y25 bogies under tank cars in order to prolong their service life. The reported study has been carried out for a tank car with rated parameters, as well as the actual ones, registered during full-scale research. Mathematical modeling was performed to determine the basic indicators of the tank car dynamics. The differential equations of motion were solved by a Runge-Kutta method using the Mathcad...
-
Development and evaluation of RADA-PDGF2 self-assembling peptide hydrogel for enhanced skin wound healing
PublicationBackground: Wound healing complications affect numerous patients each year, creating significant economic and medical challenges. Currently, available methods are not fully effective in the treatment of chronic or complicated wounds; thus, new methods are constantly sought. Our previous studies showed that a peptide designated as PDGF2 derived from PDGF-BB could be a promising drug candidate for wound treatment and that RADA16-I...
-
Improved energy management technique in pipe-embedded wall heating/cooling system in residential buildings
PublicationEffective and environmentally responsive techniques of energy management in residential buildings are desirable for the resulting reduction of energy costs and consumption. In this paper, an improved and efficient technique of energy management in pipe-embedded wall heating/cooling systems, called the Thermal Barrier, is described. Specifically, the Thermal Barrier is a technique focused on the management and control of heat...
-
Deterministic and statistical size effect during shearing of granular layer within a micro-polar hypoplasticity
PublicationArtykuł omawia deterministyczny i statystyczny efekt skali w materiałach granulowanych podczas ścinania cienkiej warstwy piasku między dwoma bardzo szorstkimi ścianami. Obliczenia wykonano metodą elementów skończonych na bazie mikropolarnego prawa hipoplastycznego. Przyjęto różne metody redukujące ilość realizacji pól losowych dla początkowego wskaźnika porowatości..
-
Improved energy management technique in pipe-embedded wall heating/cooling system in residential buildings
PublicationEffective and environmentally responsive techniques of energy management in residential buildings are desirable for the resulting reduction of energy costs and consumption. In this paper, an improved and efficient technique of energy management in pipe-embedded wall heating/cooling systems, called the Thermal Barrier, is described. Specifically, the Thermal Barrier is a technique focused on the management and control of heat supply...
-
Tacit knowledge awareness and sharing as a focal part of knowledge production, Polish-US view on IT, healthcare, and construction industry
PublicationIn the knowledge economy era, knowledge production and dissemination are of key interest to individuals, organizations, and economies. Tacit knowledge results from experience, leading to innovation. The learning culture can facilitate the transformation of errors into experiences. This study explores whether mistake acceptance facilitates tacit knowledge awareness and sharing in the information technology, healthcare, and construction...
-
Machine Learning in Multi-Agent Systems using Associative Arrays
PublicationIn this paper, a new machine learning algorithm for multi-agent systems is introduced. The algorithm is based on associative arrays, thus it becomes less complex and more efficient substitute of artificial neural networks and Bayesian networks, which is confirmed by performance measurements. Implementation of machine learning algorithm in multi-agent system for aided design of selected control systems allowed to improve the performance...
-
Data augmentation for improving deep learning in image classification problem
PublicationThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
Security of export transactions in the offer of leading banks on the Polish market
PublicationThe following article presents the so-called conditioned payment methods, i.e. instruments for securing export transactions, such as letter of credit, documentary collection, bank guarantees, factoring and forfaiting. The characteristics of each particular method are presented as well as the transactions using them are described. In the following paper, the author included also the leading Polish banks, which offer the above- mentioned...
-
Becoming a Learning Organization Through Dynamic Business Process Management
Publication -
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
Discovering Rule-Based Learning Systems for the Purpose of Music Analysis
PublicationMusic analysis and processing aims at understanding information retrieved from music (Music Information Retrieval). For the purpose of music data mining, machine learning (ML) methods or statistical approach are employed. Their primary task is recognition of musical instrument sounds, music genre or emotion contained in music, identification of audio, assessment of audio content, etc. In terms of computational approach, music databases...
-
Selected Problems of Experimental Testing Marine Stern Tube Bearings
PublicationThis paper presents typical methods for conducting experimental tests on main shaft slide bearings. There are described their possible testing capabilities, advantages, drawbacks and limitations. Various testing methods were analyzed to find a solution able of providing a wide range of possible investigations at possibly acceptable limitations.
-
Digital competence learning in secondary adult education in Finland and Poland
Publication