Filters
total: 11138
-
Catalog
- Publications 9410 available results
- Journals 90 available results
- Conferences 54 available results
- People 219 available results
- Inventions 1 available results
- Projects 22 available results
- Research Equipment 8 available results
- e-Learning Courses 152 available results
- Events 12 available results
- Open Research Data 1170 available results
displaying 1000 best results Help
Search results for: viseme · parameterization of mouth region · support vector machine · hidden markov model · pattern recognition · audiovisual speech recognition
-
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...
-
The adaptive backstepping control of PMSM supplied by current source inverter for the field weakening region
PublicationThe sensorless control system of permanent magnet synchronous motor PMSM supplied by current source inverter for field weakening operation is presented in this paper. The adaptive backstepping control system and the backstepping speed observer are presented. The control system is based on multi-scalar variables. The control variables are: dc-link voltage and the output current vector pulsation. The control system was named voltage...
-
Multiple sound sources localization in free field using acoustic vector sensor
PublicationMethod and preliminary results of multiple sound sources localization in free field using the acoustic vector sensor were presented in this study. Direction of arrival (DOA) for considered source was determined based on sound intensity method supported by Fourier analysis. Obtained spectrum components for considered signal allowed to determine the DOA value for the particular frequency independently. The accuracy of the developed...
-
Multiple sound sources localization in real time using acoustic vector sensor
PublicationMethod and preliminary results of multiple sound sources localization in real time using the acoustic vector sensor were presented in this study. Direction of arrival (DOA) for considered source was determined based on sound intensity method supported by Fourier analysis. Obtained spectrum components for considered signal allowed to determine the DOA value for the particular frequency independently. The accuracy of the developed...
-
Estimation of the short-term predictor parameters of speech under noisy conditions
Publication -
Comparative analysis of spectral and cepstral feature extraction techniques for phoneme modelling
PublicationPhoneme parameter extraction framework based on spectral and cepstral parameters is proposed. Using this framework, the phoneme signal is divided into frames and Hamming window is used. The performances are evaluated for recognition of Lithuanian vowel and semivowel phonemes. Different feature sets without noise as well as at different level of noise are considered. Two classical machine learning methods (Naive Bayes and Support...
-
Selected Problems of Machine Dynamics
e-Learning CoursesThe following set of lectures is performed: 1. LECTURE No.1 - INTRODUCTION TO SELECTED PROBLEMS OF MACHINE DYNAMICS. STRUCTURES and MACHINES 2. LECTURE No.2 - ENVIRONMENT, LOADS ON STRUCTURES and MACHINES 3. LECTURE No.3 - DYNAMICS of STRUCTURES and MACHINES 4. LECTURE No.4 - STRENGTH of STRUCTURES and MACHINES 5. LECTURE No.5 - SPECIAL PROBLEMS ASSOCIATED with DYNAMICS and STRENGTH of STRUCTURES and MACHINES
-
Performance of Vector-valued Intensity Measures for Estimating Residual Drift of Steel MRFs with Viscous Dampers
PublicationViscous Dampers (VDs) are widely used as passive energy dissipation system for improving seismic performance levels especially in retrofitting of buildings. Residual Inter-story Drift Ratio (R-IDR) is another important factor that specifies the condition of building after earthquake. The values of R-IDR illustrates the possibility of retrofitting and repairing of a building. Therefore, this study aims to explore the vector-valued...
-
Estimation of the excitation variances of speech and noise AR-models for enhanced speech coding
Publication -
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...
-
Collaborative Data Acquisition and Learning Support
PublicationWith the constant development of neural networks, traditional algorithms relying on data structures lose their significance as more and more solutions are using AI rather than traditional algorithms. This in turn requires a lot of correctly annotated and informative data samples. In this paper, we propose a crowdsourcing based approach for data acquisition and tagging with support for Active Learning where the system acts as an...
-
Macromodels for Efficient Analysis of Open-Region Problems Using the Finite Element Method
PublicationThis paper presents a local model-order reduction, called macromodeling, applied to speed-up the simulations of open-region problems, analyzed by means of finite element method. This technique is illustrated by a numerical example, which deals with a dielectric resonator antenna (DRA). The obtained results show that the proposed approach is reliable and can significantly increase the standard finite element method efficiency.
-
Novel Highly Thermostable Endolysin from Thermus scotoductus MAT2119 Bacteriophage Ph2119 with Amino Acid Sequence Similarity to Eukaryotic Peptidoglycan Recognition Proteins
Publication -
Anion–π recognition between [M(CN)6]3− complexes and HAT(CN)6: structural matching and electronic charge density modification
Publication -
Discriminating macromolecular interactions based on an impedimetric fingerprint supported by multivariate data analysis for rapid and label-free Escherichia coli recognition in human urine
PublicationThis manuscript presents a novel approach to address the challenges of electrode fouling and highly complex electrode nanoarchitecture, which are primary concerns for biosensors operating in real environments. The proposed approach utilizes multiparametric impedance discriminant analysis (MIDA) to obtain a fingerprint of the macromolecular interactions on flat glassy carbon surfaces, achieved through self-organized, drop-cast,...
-
Real-time speech streching for supporting hearing impaired schoolchildren
PublicationA study of time scale modification algorithms applied to support hearing impaired schoolchildren is presented. Variety of algorithms are considered, namely: overlap-and add, two variations of synchronous overlapand- add, and the phase vocoder. Their effectiveness as well as real-time processing capabilities are examined.
-
Journal of Pattern Intelligence
Journals -
PATTERN ANALYSIS AND APPLICATIONS
Journals -
The Matter of Decision-Making Control Over Operation Processes of Marine Power Plant Systems with the Use of their Models in the form of Semi-Markov Decision-Making Processes
PublicationThe article presents the possibility to control the real operation process of an arbitrary device installed in the marine power plant based on the four-state semi-Markov process, being the model of the process, which describes the transition process of operational states of the device and the transition process of its technical states. All these states are precisely defined for the ship main engine (SG). A hypothesis is proposed...
-
Broadband interference in speech reinforcement systems
PublicationArtykuł podejmuje niedoceniany problem wpływu liczby i rozkładu głośników w systemach nagłośnienia, na jakość przekazu głosowego, czyli na zrozumiałość mowy w audytoriach. Superpozycji przesuniętych w czasie szerokopasmowych sygnałów o tym samym kształcie i lekko różnych wielkościach, które docierają do słuchacza z licznych spójnych źródeł, towarzyszy zjawisko interferencji prowadzące do głębokiej modyfikacji odbieranych sygnałów...
-
Application of theory of semi-Markov processes to determining distribution of probabilistic process of marine accidents resulting from colission of ships
PublicationIn this paper is presented possible application of the theory of semi-Markov processes to elaborating an eight-state model of the process of occurrence of serviceability state and unserviceability states of sea-going ships making critical manoeuvres during their entering and leaving the ports. In the analysis it was taken into account that sea-going ships are in service for a very long time t (t → ∞). The model was elaborated to...
-
International Conference on Advances in Pattern Recognition and Digital Techniques
Conferences -
Stochastic model of the process of starting piston combustion engines and the practical use of the process
PublicationW artykule zaproponowano model procesu rozruchu silników o zapłonie samoczynnym, w formie procesu semimarkowskiego, dyskretnego w stanach i ciągłego w czasie eksploatacji. Stanami tego procesu są: stan zimny silnika (s1), stan ciepły silnika (s2) i stan gorący silnika (s3). Zaproponowano również koncepcję zastosowania opracowanego modelu do określenia ilości substancji szkodliwych, jakie emitowane są w spalinach podczas rozruchu...
-
Predictions of cervical cancer identification by photonic method combined with machine learning
PublicationCervical cancer is one of the most commonly appearing cancers, which early diagnosis is of greatest importance. Unfortunately, many diagnoses are based on subjective opinions of doctors—to date, there is no general measurement method with a calibrated standard. The problem can be solved with the measurement system being a fusion of an optoelectronic sensor and machine learning algorithm to provide reliable assistance for doctors...
-
A memory efficient and fast sparse matrix vector product on a Gpu
PublicationThis paper proposes a new sparse matrix storage format which allows an efficient implementation of a sparse matrix vector product on a Fermi Graphics Processing Unit (GPU). Unlike previous formats it has both low memory footprint and good throughput. The new format, which we call Sliced ELLR-T has been designed specifically for accelerating the iterative solution of a large sparse and complex-valued system of linear equations arising...
-
Stochastic model of the load spectrum for main engines of sea-going ships
PublicationW artykule przedstawiono możliwość zastosowania procesów semimarkowskich do probabilistycznego opisu widma obciążeń silników o zapłonie samoczynnym, zastosowanych do napędu statków - czyli silników głównych. W rozważaniach uwzględnione zostały charakterystyki zewnętrzne mocy tego rodzaju silników. Umożliwiły one sformułowanie czteroelementowego zbioru stanów procesu obciążeń tego rodzaju silników. Do opisu rzeczywistego procesu...
-
Viscoelastic model of waterhammer in single pipeline - problems and questions
PublicationW artykule dokonano analizy zastosowania lepkosprężystego modelu uderzenia hydraulicznego w pojedynczym przewodzie. Przedstawiono teoretyczne podstawy lepkosprężystego zachowania się materiału przewodu oraz matematyczny opis modelu uderzenia hydraulicznego w rurociągu z tworzywa sztucznego. Przedyskutowano główne problemy pojawiające się przy aplikacji takiego modelu. Nacisk położono na identyfikację parametrów modelu. Przeanalizowano...
-
A Task-Scheduling Approach for Efficient Sparse Symmetric Matrix-Vector Multiplication on a GPU
PublicationIn this paper, a task-scheduling approach to efficiently calculating sparse symmetric matrix-vector products and designed to run on Graphics Processing Units (GPUs) is presented. The main premise is that, for many sparse symmetric matrices occurring in common applications, it is possible to obtain significant reductions in memory usage and improvements in performance when the matrix is prepared in certain ways prior to computation....
-
Strength analysis of the support structure of the offshore wind turbine
PublicationThe global power demand from renewable sources is growing. One of a very favorable solution which meets severe environmental protection requirements are the offshore wind turbines. The offshore wind energy sector has experienced very fast development over last decade. Offshore wind farms, in comparison with onshore applications, can provide increased efficiency with reduced noise, visual, transportation and installation con-flicts....
-
Model Assisted Statistics and Applications
Journals -
3D Sound Intensity Measurement Around Organ Pipes Using Acoustic Vector Sensors
PublicationThe aim of the presented paper was to obtain and visualize sound intensity distribution of radiated acoustic energy around the organ pipes. The experimental setup consisted of the multichannel acoustic vector sensor and the specialized Cartesian robot. Measurements were performed in free field with spatial resolution of 0.1 [m]. Two organ pipes, i.e. wooden and metal were measured during the ex-periment. The organ pipes were activated...
-
Analysis of muscles behaviour. Part II. The computational model of muscles group acting on the elbow joint
PublicationThe purpose of this paper is to present the computational model of muscles' group describing the movements of flexion/extension at the elbow joint in the sagittal plane of the body when the forearm is being kept in the fixed state of supination/pronation. The method ofevaluating the muscle forces is discussed in detail. This method is the basis for the quantitative and qualitative verification of the proposed computational model...
-
How Machine Learning Contributes to Solve Acoustical Problems
PublicationMachine learning is the process of learning functional relationships between measured signals (called percepts in the artificial intelligence literature) and some output of interest. In some cases, we wish to learn very specific relationships from signals such as identifying the language of a speaker (e.g. Zissman, 1996) which has direct applications such as in call center routing or performing a music information retrieval task...
-
Analiza stanu nawierzchni i klas pojazdów na podstawie parametrów ekstrahowanych z sygnału fonicznego
PublicationCelem badań jest poszukiwanie parametrów wektora cech ekstrahowanego z sygnału fonicznego w kontekście automatycznego rozpoznawania stanu nawierzchni jezdni oraz typu pojazdów. W pierwszej kolejności przedstawiono wpływ warunków pogodowych na charakterystykę widmową sygnału fonicznego rejestrowanego przy przejeżdżających pojazdach. Następnie, dokonano parametryzacji sygnału fonicznego oraz przeprowadzano analizę korelacyjną w celu...
-
Subjective Quality Evaluation of Speech Signals Transmitted via BPL-PLC Wired System
PublicationThe broadband over power line – power line communication (BPL-PLC) cable is resistant to electricity stoppage and partial damage of phase conductors. It maintains continuity of transmission in case of an emergency. These features make it an ideal solution for delivering data, e.g. in an underground mine environment, especially clear and easily understandable voice messages. This paper describes a subjective quality evaluation of...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublicationThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...
-
Verification of agent system for it project management support
PublicationThis article is a continuation of article series telling about research about possibility of using agent system to information technology evaluation. Following article presents full conception of exploiting agent system and shows how it can support some managers works, especially in taking correct management method and information tool for project management. In this article the agent system that based on knowledge and can process...
-
Diagnostic model of compression-ignition engine slide bearings for controlling the changes of their state
PublicationW artykule przedstawiono koncepcję umożliwiającą sterowanie procesami zmian stanów eksploatacyjnych silnika na podstawie modelu diagnostycznego łożysk ślizgowych. Jako model łożyska ślizgowego przyjęty został topologiczny model diagnostyczny, pozwalający na pełne i dokładne wykorzystanie oleju smarowego jako jednego z nośników informacji o stanie technicznym łożyska. Przedstawiona została przykładowa interpretacja stanów eksploatacyjnych...
-
Analysis of odour interactions in model gas mixtures using electronic nose and fuzzy logic
PublicationMeasurement and monitoring of air quality in terms of odour nuisance is an important problem. Although the source of these nuisances is different (e.g. wastewater treatment plants, municipal landfills), their common feature is that they are a complex mixture of odorants with different odour thresholds. An additional problem is occurrence of the odour interactions between mixture components. From a practical point of view, it would...
-
Machine Learning Techniques in Concrete Mix Design
PublicationConcrete mix design is a complex and multistage process in which we try to find the best composition of ingredients to create good performing concrete. In contemporary literature, as well as in state-of-the-art corporate practice, there are some methods of concrete mix design, from which the most popular are methods derived from The Three Equation Method. One of the most important features of concrete is compressive strength, which...
-
Impact response of novel layered two stage fibrous composite slabs with different support type
PublicationThe performance of novel Layered Two Stage Fibrous Composite slabs (LTSFC) was pioneered under falling mass collisions using a combined experimental and numerical study. Such LTSFC slabs consist of three layers with and without the insertion of glass fibre mesh between the layers. LTSFC techniques were used to fabricate the composite slabs with three layers including 3%, 1.5%, and 3% of fibre content for the top, middle, and...
-
Simulation of influence of the air gap asymmetryon voltage waveforms of a synchronous machine
PublicationResults of simulation of a synchronous generator with the air gap asymmetry characterised by eccentricity are presented in the paper. The Lagrange's energy method has been used in derivation of the model equations. Analysis of influence of the air gap asymmetry on characteristics of self and mutual inductances of windings, as well as analysis of induced voltage waveforms as a function of the air gap asymmetry have been performed....
-
Application of the theory of semi-markov processes to the development of a reliability model of an automotiv vrhicle = Zastosowanie teorii procesów semi-Markowa do opracowania modelu niezawodnościowego samochodu
PublicationW artykule przedstawiono możliwość zastosowania teorii procesów semi-Markowa (semimarkowskich) do opisu niezawodności samochodu, na przykładzie samochodu osobowego. W rozważaniach uwzględniony został samochód, w którym wyróżniono takie węzły konstrukcyjne (zespoły funkcjonalne) jak: silnik z układami zasilania czynnikami energetycznymi (paliwem, olejem smarowym i cieczą chłodzącą), sprzęgło, skrzynia biegów, wał napędowy, most...
-
Primary role identification in e-mail networks using pattern subgraphs and sequence diagrams
PublicationSocial networks often forms very complex structures that additionally change over time. Description of actors' roles in such structures requires to take into account this dynamics reflecting behavioral characteristics of the actors. A role can be defined as a sequence of different types of activities. Various types of activities are modeled by pattern subgraphs, whereas sequences of these activities are modeled by sequence diagrams....
-
On the mixing property and the ergodic principle for nonhomogeneous Markov chains
PublicationW pracy rozważane są różne typy zachowania granicznego nieskończenie wymiarowych niejednorodnych łańcuchów Markowa z czasem dyskretnym. Badana jest struktura geometryczna zbioru łańcuchów Markowa w normowej i mocnej topologii operatorowej.
-
Optimal asynchronous estimation of 2D Gaussian-Markov processes
PublicationW artykule rozważa się problem estymacji trajektorii dwuwymiarowych ciągłoczasowych procesów Gaussa-Markowa na podstawie zaszumionych pomiarów wykonywanych w nierównomiernie rozłożonych chwilach czasu. W przypadku takiego problemu, w każdym cyklu pracy algorytmu należy dokonać dyskretnoczasowej predykcji (analogicznie jak w przypadku filtru Kalmana). Niestety zadanie to może być złożone obliczeniowo. Aby rozwiązać ten problem,...
-
Challenges in providing support for management of evidence-based arguments
PublicationThe paper considers selected challenges related to the application of evidence based arguments and maps them on the tool support level. In particular, we consider: communication and teamwork, handling large arguments, evidence management and integration, argument assessment and communication, change control and reporting, evidence reuse, user data security and argument portfolio management. Then we explain how these challenges...
-
Deep eutectic solvents – Ideal solution for clean air or hidden danger?
PublicationThe industrial sector is one of the fastest-growing sources of greenhouse gases, due to its excessive energy consumption to meet the rapidly growing demand for energy-intensive products. The use of deep eutectic solvents (DESs) has been studied extensively in order to cope with these harmful gases, but their usage can be an issue in respect to ecological reasons. Do deep eutectic solvents harm the atmosphere? Yes, these solvents...
-
Gaze pattern lock for elders and disabled
Publication...
-
MODEL OF MULTILEVEL STOCHASTIC ANALYSIS OF ROAD SAFETY ON REGIONAL LEVEL
PublicationIn this paper multilevel approach to the issue of road safety level on the road network of European regions, classified as NUTS 2 in statistical databases of the European Union, has been presented. Following the pattern of many publications on road safety it has been assumed that the risk calculated as the number of death casualties in road accidents per 100,000 inhabitants of a given region has Poisson distribution. Therefore,...