Filters
total: 9369
filtered: 6789
-
Catalog
Chosen catalog filters
displaying 1000 best results Help
Search results for: TIME SERIES CLASSIFICATIONLEARNING SYSTEMSCAPSULE NETWORKSDATA MININGMULTI-HEAD CONVOLUTIONAL NEURAL NETWORKSSIGNAL PROCESSING
-
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublicationIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
PublicationNumerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending...
-
A method of RTS noise identification in noise signals of semiconductor devices in the time domain
PublicationIn the paper a new method of Random Telegraph Signal (RTS) noise identification is presented. The method is based on a standardized histogram of instantaneous noise values and processing by Gram-Charlier series. To find a device generating RTS noise by the presented method one should count the number of significant coefficients of the Gram-Charlier series. This would allow to recognize the type of noise. There is always one (first)...
-
Material Flow Analysis in a cooked mussel processing industry
PublicationGalicia (NW Spain) is an ideal environment for mussel culture owing to its excellent natural conditions. It is the first Spanish and European mussel producer and the second worldwide after China. More than 50% of the mussel collected in Galicia is used in the processing industry, which produces different products, as cooked mussel that is canned, frozen or used in the food industry. In this paper a methodology based on Life Cycle...
-
Errors in the analysis of series resonant inverter/converter assuming sinusoidal waveforms of voltage and current
PublicationIn this paper the theory and simulation results of the series resonant inverter / converter are presented. In this work the authors carried out a detailed comparative analysis of results obtained using the method of AC analysis in the steady state for the first harmonic with the results of computer simulation. The AC analysis under certain conditions can lead to errors disqualifying this method. In particular, these errors appear...
-
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
PublicationBearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect...
-
Digital structures for high-speed signal processing
PublicationThe work covers several issues of realization of digital structures for pipelined processing of real and complex signals with the use of binary arithmetic and residue arithmetic. Basic rules of performing operations in residue arithmetic are presented along with selected residue number systems for processing of complex signals and computation of convolution. Subsequently, methods of conversion of numbers from weighted systems to...
-
Water hammer analysis in two pipes in series
PublicationW pracy przedstawiono wyniki badań laboratoryjnych przepływu nieustalonego w rurociągu skokowo zmiennej średnicy. Dokonano porównania czynników pomiarów oraz obliczeń uderzenia hydraulicznego zmodyfikowaną metodą elementów skończonych.
-
Chalcogen bonding interactions in a series of aromatic selenocyanates
PublicationSelenium atoms in aromatic selenocyanates are characterized by the occurrence of two σ-holes, a stronger one in the prolongation of the NC–Se bond and a weaker one in the prolongation of the Ar–Se bond. The crystal structures of several bis(selenocyanato) derivatives, prepared by a method originally developed for ortho bis-substituted derivatives, illustrate very well this difference, with a short NC–Se⋯NC ChB interaction organizing...
-
The Neural Knowledge DNA Based Smart Internet of Things
PublicationABSTRACT The Internet of Things (IoT) has gained significant attention from industry as well as academia during the past decade. Smartness, however, remains a substantial challenge for IoT applications. Recent advances in networked sensor technologies, computing, and machine learning have made it possible for building new smart IoT applications. In this paper, we propose a novel approach: the Neural Knowledge DNA based Smart Internet...
-
Smart Document-Centric Processing of Human Oriented Information Flows
PublicationUsually people prefer to focus on creative rather than repetitive and schematic work patterns. Still, they must spend a lot of time complying with the procedures, selecting the information they receive and repeatedly restoring the previous state of work. This paper proposes the Mobile INteractive Document architecture (MIND) - a document-centric uniform interface to provide both effective communication of content and coordination...
-
Mitigating the seismic pounding of multi-story buildings in series using linear and nonlinear fluid viscous dampers
PublicationSeismic-induced pounding between adjacent buildings may have serious consequences, ranging from minor damage up to total collapse. Therefore, researchers try to mitigate the pounding problem using different methods, such as coupling the adjacent buildings with stiff beams, connecting them by using viscoelastic links, and installing damping devices in each building individually. In the current paper, the effect of using linear and...
-
Supply current signal and artificial neural networks in the induction motor bearings diagnostics
PublicationThis paper contains research results of the diagnostics of induction motor bearings based on measurement of the supply current with usage of artificial neural networks. Bearing failure amount is greater than 40% of all engine failures, which makes their damage-free operation crucial. Tests were performed on motors with intentionally made bearings defects. Chapter 2 introduces the concept of artificial neural networks. It presents...
-
Accuracy Investigations of Turbine Blading Neural Models Applied to Thermal and Flow Diagnostics
PublicationPossibility of replacing computional fluid dynamics simulations by a neural model for fluid flow and thermal diagnostics of steam turbines is investigated. Results of calculations of velocity magnitude of steam for 3D model of the stator of steam turbine is presented.
-
Call processing performance in multidomain IMS/NGN architecture
PublicationThe Next Generation Network (NGN) architecture, which bases on the IP Multimedia Subsystem (IMS) concept, is a proposition of a telecommunication network dedicated to the needs of the modern information society. The main goal of NGN is to provide Quality of Service (QoS), for which proper network design and dimensioning are necessary. This also requires appropriate traffic models, which should be efficient and not excessively complicated...
-
Investigation of Parallel Data Processing Using Hybrid High Performance CPU + GPU Systems and CUDA Streams
PublicationThe paper investigates parallel data processing in a hybrid CPU+GPU(s) system using multiple CUDA streams for overlapping communication and computations. This is crucial for efficient processing of data, in particular incoming data stream processing that would naturally be forwarded using multiple CUDA streams to GPUs. Performance is evaluated for various compute time to host-device communication time ratios, numbers of CUDA streams,...
-
Novel bio-based thermoplastic poly(ether-urethane)s. Correlations between the structure, processing and properties
PublicationThe main purpose of this work was to analyze the effect of the number of unreacted isocyanate groups and the [NCO]/[OH] molar ratio during the chain extension of a prepolymer during the polymerization process on the structure, processing and selected properties of thermoplastic poly(ether-urethane)s. Three series of novel thermoplastic polyurethanes were obtained via a prepolymer route. Three prepolymers were synthesized from diisocyanate...
-
Neural Networks, Support Vector Machine and Genetic Algorithms for Autonomous Underwater Robot Support
PublicationIn this paper, artificial neural networks, a classification technique called support vector machine and meta-heuristics genetic algorithm have been considered for development in autonomous underwater robots. Artificial neural networks have been used for seabed modelling as well as support vector machine has been applied for the obstacles classification to avoid some collision problems. Moreover, genetic algorithm has been applied...
-
Hybrid of Neural Networks and Hidden Markov Models as a modern approach to speech recognition systems
PublicationThe aim of this paper is to present a hybrid algorithm that combines the advantages ofartificial neural networks and hidden Markov models in speech recognition for control purpos-es. The scope of the paper includes review of currently used solutions, description and analysis of implementation of selected artificial neural network (NN) structures and hidden Markov mod-els (HMM). The main part of the paper consists of a description...
-
Artificial Neural Network in Forecasting the Churn Phenomena Among Costumers of IT and Power Supply Services
PublicationThis paper presents an attempt to use an artificial neural network to investigate the churn phenomenon among the customers of a telecommunications operator. An attempt was made to create a data model based on the customer lifetime value (CLV) rather than on activity alone. A multilayered artificial neural network was used for the experiments. The results yielded a 99% successful identification rate for customers in no danger of...
-
Digital signal processing applied to the modernization of Polish Navy sonars
PublicationThe article presents the equipment and digital signal processing methods used for modernizing the Polish Navy’s sonars. With the rapid advancement of electronic technologies and digital signal processing methods, electronic systems, including sonars, become obsolete very quickly. In the late 1990s a team of researchers of the Department of Marine Electronics Systems, Faculty of Electronics, Telecommunications and Informatics, Gdansk...
-
Massive surveillance data processing with supercomputing cluster
PublicationIn recent years, increasingly complex algorithms for automated analysis of surveillance data are being developed. The rapid growth in the number of monitoring installations and higher expectations of the quality parameters of the captured data result in an enormous computational cost of analyzing the massive volume of data. In this paper a new model of online processing of surveillance data streams is proposed, which assumes the...
-
Reactive Processing and Functionalization of Ground Tire Rubber
PublicationThe dynamic development of the automotive industry resulted in a sig- nificant increase in rubber wastes, especially end-of-life tires, which are a serious threat to the natural environment and human health. This situation has enforced the industry and academic research groups to search new and cost-effective methods for recycling waste tires. In this field of research, reactive processing and functionaliza- tion seem to be a...
-
Determination of time delay between ventricles contraction using impedance measurements
PublicationThe paper presents a novel approach to assessment of ventricular dyssynchrony basing on multichannel electrical impedance measurements. Using a proper placement of electrodes, the sensitivity approach allows estimating time difference between chambers contraction from over determined nonlinear system of equations. The theoretical considerations which include Finite Element Method simulations were verified using measurements on...
-
Zastosowanie analizy szeregów czasowych do oceny zanieczyszczenia powietrza atmosferycznego w rejonie Trójmiasta. Application of time series analysis on air quality assessment in the region of Tricity
PublicationNa podstawie analizy wyników pomiarów poziomów stężenia: NO3-, SO42-, F- ,Cl-, NH4+, PO43-, Ca2+, K+, Mg2+ oraz pomiarów pH i przewodności elektrolitycznej próbek wód opadowych na terenie Trójmiasta z zastosowaniem techniki analizy szeregów czasowych wykazano, że cykliczne wahania poziomów depozycji SO42-, F-, NO3- i Ca2+ w próbkach są skorelowane z cyklicznymi 9 zmianami przeważających kierunków wiatrów. Analiza struktury szeregów...
-
A Model-Driven Solution for Development of Multimedia Stream Processing Applications
PublicationThis paper presents results of action research related to model-driven solutions in the area of multimedia stream processing. The practical problem to be solved was the need to support application developers who make their multimedia stream processing applications in a supercomputer environment. The solution consists of a domain-specific visual language for composing complex services from simple services called Multimedia Stream...
-
Emotion Recognition from Physiological Channels Using Graph Neural Network
PublicationIn recent years, a number of new research papers have emerged on the application of neural networks in affective computing. One of the newest trends observed is the utilization of graph neural networks (GNNs) to recognize emotions. The study presented in the paper follows this trend. Within the work, GraphSleepNet (a GNN for classifying the stages of sleep) was adjusted for emotion recognition and validated for this purpose. The...
-
Sound Field Intensity Measurements and Visualization around the Human Head Model . Rozkłąd natężenia pola akustycznego w komorze bezechowej obecności sztucznej głowy i w przypadku braku jej obecności
PublicationThe main goal of this research study was to measure and visualize sound field intensity distribution in and without presence of the human head model. Measurements were performed in the anechoic chamber with the 5 cm grid. Experimental setup consisted of a multitone generator, two loudspeakers, human head model, intensimetric probe, the Cartesian robot applied for precise positioning of the acoustic sensor, and an analyzer. Based...
-
Optimization algorithm and filtration using the adaptive TIN model at the stage of initial processing of the ALS point cloud
PublicationAirborne laser scanning (ALS) provides survey results in the form of a point cloud. The ALS point cloud is a source of data used primarily for constructing a digital terrain model (DTM). To generate a DTM, the set of ALS observations must be first subjected to the point cloud processing methodology. A standard methodology is composed of the following stages: acquisition of the ALS data, initial processing (including filtration),...
-
Multibeam Sonar Data Processing for Seafloor Classification
PublicationDespite many years of the development of methodology for sensing the seafloor by means of underwater acoustics, the currently used techniques are still not mature enough and not ready to be utilised in numerous different (i.e. with respect to a water region character, used equipment type etc.) tasks. Therefore the hydroacoustic methods, both utilising vertical observations (e.g. by singlebeam echosounders), as well as those relying...
-
Foundations of Grid Processing Architecture for the Comcute System
PublicationFundamental system algorithms and structures implemented in the Comcute system are described and analysed in detail. Layered architecture of the system model is highlighted. System tasks of the layers are elaborated, presented and described. Operational details of communication interfaces among layers are worked out and examined. The focus is put onto implemented system components with regard to their operability and efficiency....
-
Big Data Processing by Volunteer Computing Supported by Intelligent Agents
PublicationIn this paper, volunteer computing systems have been proposed for big data processing. Moreover, intelligent agents have been developed to efficiency improvement of a grid middleware layer. In consequence, an intelligent volunteer grid has been equipped with agents that belong to five sets. The first one consists of some user tasks. Furthermore, two kinds of semi-intelligent tasks have been introduced to implement a middleware...
-
Application of spatial neural simulators of turbine blade rows to fluid flow diagnostics
PublicationThis chapter presents the results of neural modelling of fluid flow in steam turbine row. In modelling working conditions of the flow channel varied, thus the aim of the work was to reconstruct the reference state - distributions of velocity, pressure, and losses in flow channel - with high accuracy for fluid flow diagnostics.
-
Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks
PublicationTraffic–induced vibrations may constitute a considerable load to a building, cause cracking of plaster, cracks in load–bearing elements or even a global structural collapse of the whole structure [1-4]. Vibrations measurements of real structures are costly and laborious, not justified in all cases. The aim of the paper is to create an original algorithm, to predict the negative dynamic impact on the examined residential building...
-
A New Approach of Solidification Analysis in Modular Latent Thermal Energy Storage Unit Based on Image Processing
PublicationThe solidification process of RT18HC in a cylindrical shell and tube storage unit has been studied using a new methodology based on image processing. The main idea of the algorithm is to label the region of solidification and use statistical functions to calculate the dimensions of the solidification front over time. Said analysis includes two methods. The first method is to measure the solid fraction changes during solidification....
-
Using Rule-Based System for Monitoring Marine Navigation Data Processing
PublicationProcessing marine navigational data requires sophisticated software solutions. Typically, specialized tools called processors are analyzing raw data from different sensors. It becomes important to create the monitoring software that is able to validate and verify processing components integrated into the final system. Drools®business rule management platform provides a core business rules engine, web authoring and rules management...
-
Krylov Space Iterative Solvers on Graphics Processing Units
PublicationCUDA architecture was introduced by Nvidia three years ago and since then there have been many promising publications demonstrating a huge potential of Graphics Processing Units (GPUs) in scientific computations. In this paper, we investigate the performance of iterative methods such as cg, minres, gmres, bicg that may be used to solve large sparse real and complex systems of equations arising in computational electromagnetics.
-
Numerical simulation of temperature distribution of heat flow on reservoir tanks connected in a series
PublicationThe flow of temperature distribution through a medium in thermodynamic studies plays an important role in understanding physical phenomena in chemical science and petroleum engineering, while temperature distribution indicates the degree of reaction that must be undergone to obtain the final product. Therefore, this paper aims to present and apply the exponential matrix algorithm (EMA), differential transformation algorithm (DTA),...
-
Full wavefield processing by using FCN for delamination detection
Publication -
Processing of Hydroacoustic and LiDAR Data for Three-dimensional Surface Reconstruction
PublicationThe technologies of sonar and laser scanning are commonly used for obtaining spatial information about underwater and over ground environments in the form of point clouds. Since this data model has known disadvantages, a more practical solution of visualising such data involves the creation of solid three-dimensional meshes composed of edges and facets. In this paper, several methods for 3D shape reconstruction of data obtained...
-
Comments on “Closed Form Variable Fractional Time Delay Using FFT”
PublicationIn this letter drawbacks of the aforementioned paper are pointed out. The proposed approach is improved with minor modifications of the discrete frequency response. This allows for design of fractional delay filters which are close to optimal and can be efficiently implemented in the frequency domain using the sliding DFT based structure. Alternatively, the derived equivalent closed form formulae for offset windows can be used...
-
A MODEL FOR FORECASTING PM10 LEVELS WITH THE USE OF ARTIFICIAL NEURAL NETWORKS
PublicationThis work presents a method of forecasting the level of PM10 with the use of artificial neural networks. Current level of particulate matter and meteorological data was taken into account in the construction of the model (checked the correlation of each variable and the future level of PM10), and unidirectional networks were used to implement it due to their ease of learning. Then, the configuration of the network (built on the...
-
EPILEPTIC BEHAVIOR WITH A DISTINGUISHED PREICTAL PERIOD IN A LARGE-SCALE NEURAL NETWORK MODEL
PublicationWe present a neural network model capable of reproducing focal epileptic behavior. An important property of our model is the distinguished preictal state. This novel feature may shed light on the pathologi-cal mechanisms of seizure generation and, in perspective, help develop new therapeutic strategies to manage refractory partial epilepsy.
-
Seismic pounding behavior of multi-story buildings in series considering the effect of infill panels
PublicationThe aim of the present paper is to study the influence of the infill panels on the seismic pounding response of adjacent structures in series. The contribution of the masonry infill has been simulated using equivalent diagonal compression struts. Steel frames have been assumed to have elastic-plastic behavior with 1% linear strain hardening. The dynamic contact analysis has been utilized where contact surface model (target and...
-
An automated, low-latency environment for studying the neural basis of behavior in freely moving rats
PublicationBackground Behavior consists of the interaction between an organism and its environment, and is controlled by the brain. Brain activity varies at sub-second time scales, but behavioral measures are usually coarse (often consisting of only binary trial outcomes). Results To overcome this mismatch, we developed the Rat Interactive Foraging Facility (RIFF): a programmable interactive arena for freely moving rats with multiple feeding...
-
Integration, Processing and Dissemination of LiDAR Data in a 3D Web-GIS
PublicationThe rapid increase in applications of Light Detection and Ranging (LiDAR) scanners, followed by the development of various methods that are dedicated for survey data processing, visualization, and dissemination constituted the need of new open standards for storage and online distribution of collected three-dimensional data. However, over a decade of research in the area has resulted in a number of incompatible solutions that offer...
-
Selection of an artificial pre-training neural network for the classification of inland vessels based on their images
PublicationArtificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained...
-
Suppression of Supply Current Harmonics of 18-Pulse Diode Rectifier by Series Active Power Filter with LC Coupling
PublicationThe reported research aims at improving the quality of three-phase rectifier supply currents. An effective method consists of adding properly formed booster voltages to the fundamental supply voltages using a series active filter. In the proposed solution, the booster voltages are generated by three single-phase systems consisting of inverters, LC filters, and single-phase transformers. The application of LC couplings ensures low...
-
Impact of high-pressure processing on the bioactive compounds of milk - A comprehensive review
PublicationHigh-pressure processing (HPP) is a promising alternative to thermal pasteurization. Recent studies highlighted the effectivity of HPP (400–600 MPa and exposure times of 1–5 min) in reducing pathogenic microflora for up to 5 logs. Analysis of modern scientific sources has shown that pressure affects the main components of milk including fat globules, lactose, casein micelles. The behavior of whey proteins under HPP is very important...
-
Analogue CMOS ASICs in Image Processing Systems
PublicationIn this paper a survey of analog application specific integrated circuits (ASICs) for low-level image processing, called vision chips, is presented. Due to the specific requirements, the vision chips are designed using different architectures best suited to their functions. The main types of the vision chip architectures and their properties are presented and characterized on selected examples of prototype integrated circuits (ICs)...