wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: accuracy
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublikacjaIn this paper the authors propose a decision support system for automatic blood smear analysis based on microscopic images. The images are pre-processed in order to remove irrelevant elements and to enhance the most important ones - the healthy blood cells (erythrocytes) and the pathologic (echinocytes). The separated blood cells are analyzed in terms of their most important features by the eigenfaces method. The features are the...
-
Asynchronous WAM with Irregular Pulse Repetition
PublikacjaRadiolocation systems for aviation based on Multi-Lateration (MLAT) typically use a set of synchronised ground sensors to receive radio signals broadcast by onboard transmitters. In most cases, the sensor synchronisation in Wide Area Multi-Lateration Systems (WAM) is provided by Global Navigation Satellite System (GNSS) receivers. However, in the case of synchronisation failure, there is still a possibility to estimate the coordinates...
-
An Archaeological - Architectural Documentation Based on Close Range Photogrammetry
PublikacjaWisłoujście Fortress is a historical defensive object located on the southwest coast of the Gulf of Gdańsk. Fort Carre, Eastern Sconce and Ravelin are parts of this postmediaeval fortification. In view of planned regeneration of this fortification complex, at the initiative of the Gdańsk History Museum and Institute of Archaeology and Ethnology of the University of Gdańsk it was decided to perform a documentation of one Fortress...
-
Analysis of positioning methods using Global Navigation Satellite Systems (GNSS) in Polish State Railways (PKP)
PublikacjaEach year, global navigation satellite systems (GNSS) improve their accuracy, availability, continuity, integrity, and reliability. Due to these continual improvements, the systems are increasingly used in various modes of transport, including rail transport, the subject of this publication. GNSS are used for rail passenger information, rail traffic management, and rail traffic control. These applications differ in the positioning...
-
OBTAINING FLUID FLOW PATTERN FOR TURBINE STAGE WITH NEURAL MODEL.
PublikacjaIn the paper possibility of applying neural model to obtaining patterns of proper operation for fluid flow in turbine stage for fluid-flow diagnostics is discussed. Main differences between Computational Fluid Dynamics (CFD) solvers and neural model is given, also limitations and advantages of both are considered. Time of calculations of both methods was given, also possibilities of shortening that time with preserving the accuracy...
-
ZnO ALD-Coated Microsphere-Based Sensors for Temperature Measurements
PublikacjaIn this paper, the application of a microsphere-based fiber-optic sensor with a 200 nm zinc oxide (ZnO) coating, deposited by the Atomic Layer Deposition (ALD) method, for temperature measurements between 100 and 300°C, is presented. The main advantage of integrating a fiber-optic microsphere with a sensing device is the possibility of monitoring the integrity of the sensor head in real-time, which allows for higher accuracy during...
-
Polarimetric studies of L-arginine-doped potassium dihydrogen phosphate single crystals
PublikacjaConoscopic interference patterns, channelled spectra and polarimetric techniques have been used for the characterization of pure and doped (with L-arginine amino acid) potassium dihydrogen phosphate (KDP) single crystals. Experimental polarimetric data have been obtained for the frequently used wavelength of 633 nm and for two close wavelengths of 532 and 543 nm in a high-accuracy dual-wavelength polarimeter. The measurement of...
-
Wind Turbines Modeling as the Tool for Developing Algorithms of Processing their Video Recordings
PublikacjaIn the real world, many factors exist disturbing observation of the examined phenomena and causing various noises and distortions in recorded signals. It very often makes it difficult or even impossible to optimize various signal processing algorithms, through finding appropriate parameters. In this paper, we show an application, that retrieves wind turbine rotor speed from recorded video. Next, we describe the process of reduction...
-
Selection of excitation signals for high-impedance spectroscopy
PublikacjaA method of fast impedance spectroscopy of technical objects with high impedance (|Zx| > 1 GOhm) is evaluated in this paper. An object is excited with a signal generated by a digital-to-analog converter (DAC) located on the U2531A DAQ module. Response signals proportional to current flowing through and voltage across the measured object are sampled by analog-to-digital converters (ADC) in the DAQ module. The object impedance spectrum...
-
A nine-input 1.25 mW, 34 ns CMOS analog median filter for image processing in real time
PublikacjaIn this paper an analog voltage-mode median filter, which operates on a 3 × 3 kernel is presented. The filter is implemented in a 0.35 μm CMOS technology. The proposed solution is based on voltage comparators and a bubble sort configuration. As a result, a fast (34 ns) time response with low power consumption (1.25 mW for 3.3 V) is achieved. The key advantage of the configuration is relatively high accuracy of signal processing,...
-
Wind Turbines Modeling as the Tool for Developing Algorithms of Processing their Video Recordings
PublikacjaIn the real world, many factors exist disturbing observation of the examined phenomena and causing various noises and distortions in recorded signals. It very often makes it difficult or even impossible to optimize various signal processing algorithms, through finding appropriate parameters. In this paper, we show an application, that retrieves wind turbine rotor speed from recorded video. Next, we describe the process of reduction...
-
Residual MobileNets
PublikacjaAs modern convolutional neural networks become increasingly deeper, they also become slower and require high computational resources beyond the capabilities of many mobile and embedded platforms. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity. In this paper, we propose a novel residual depth-separable convolution block, which is an improvement of the basic...
-
Classification of objects in the LIDAR point clouds using Deep Neural Networks based on the PointNet model
PublikacjaThis work attempts to meet the challenges associated with the classification of LIDAR point clouds by means of deep learning. In addition to achieving high accuracy, the designed system should allow the classification of point clouds covering an area of several dozen square kilometers within a reasonable time interval. Therefore, it must be characterized by fast processing and efficient use of memory. Thus, the most popular approaches...
-
Comparative Study of Self-Organizing Maps vs. Subjective Evaluation of Quality of Allophone Pronunciation for Nonnative English Speakers
PublikacjaThe purpose of this study was to apply Self-Organizing Maps to differentiate between the correct and the incorrect allophone pronunciations and to compare the results with subjective evaluation. Recordings of a list of target words, containing selected allophones of English plosive consonants, the velar nasal and the lateral consonant, were made twice. First, the target words were read from the list by 9 non-native speakers and...
-
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublikacjaRecently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening...
-
Positron collisions with molecular hydrogen: cross sections and annihilation parameters calculated using theR-matrix with pseudo-states method
PublikacjaThe molecular R-matrix with pseudo-states (MRMPS) method is employed to study positron collisions with H2. The calculations employ pseudo-continuum orbital sets containing up to h (l = 5) functions. Use of these high l functions is found to give converged eigenphase sums. Below the positronium formation threshold, the calculated cross sections agree with other high-accuracy theories and generally with the measurements. Calculation...
-
Big Data i 5V – nowe wyzwania w świecie danych (Big Data and 5V – New Challenges in the World of Data)
PublikacjaRodzaje danych, składające się na zbiory typu Big Data, to m.in. dane generowane przez użytkowników portali internetowych, dane opisujące transakcje dokonywane poprzez Internet, dane naukowe (biologiczne, astronomiczne, pomiary fizyczne itp.), dane generowane przez roboty w wyniku automatycznego przeszukiwania przez nie Internetu (Web mining, Web crawling), dane grafowe obrazujące powiązania pomiędzy stronami WWW itd. Zazwyczaj,...
-
Computer-Aided Diagnosis of COVID-19 from Chest X-ray Images Using Hybrid-Features and Random Forest Classifier
PublikacjaIn recent years, a lot of attention has been paid to using radiology imaging to automatically find COVID-19. (1) Background: There are now a number of computer-aided diagnostic schemes that help radiologists and doctors perform diagnostic COVID-19 tests quickly, accurately, and consistently. (2) Methods: Using chest X-ray images, this study proposed a cutting-edge scheme for the automatic recognition of COVID-19 and pneumonia....
-
Uncertainty Quantification of Additive Manufacturing Post-Fabrication Tuning of Resonator-Based Microwave Sensors
PublikacjaReconfigurability, especially in terms of the ability of adjusting the operating frequency, has become an important prerequisite in the design of modern microwave components and systems. It is also pertinent to microwave sensors developed for a variety of applications such as characterization of material properties of solids or liquids. This paper discusses uncertainty quantification of additive-manufacturing-based post-fabrication...
-
A review on analytical models of brushless permanent magnet machines
PublikacjaThis study provides an in-depth investigation of the use of analytical and numerical methods in analyzing electrical machines. Although numerical models such as the finite-element method (FEM) can handle complex geometries and saturation effects, they have significant computational burdens, are time-consuming, and are inflexible when it comes to changing machine geometries or input values. Analytical models based on magnetic equivalent...
-
DEEP LEARNING BASED ON X-RAY IMAGING IMPROVES COXARTHROSIS DETECTION
PublikacjaObjective: The purpose of the study was to create an Artificial Neural Network (ANN) based on X-ray images of the pelvis, as an additional tool to automate and improve the diagnosis of coxarthrosis. The research is focused on joint space narrowing, which is a radiological symptom showing the thinning of the articular cartilage layer, which is translucent to X-rays. It is the first and the most important of the radiological signs...
-
Automatic localization and continous tracking of mobile sound source using passive acoustic radar
PublikacjaA concept, practical realization and applications of the passive acoustic radar for localization and continuous tracking of fixed and mobile sound sources such as: cars, trucks, aircrafts and sources of shooting, explosions were presented in the paper. The device consists of the new kind of multi-channel miniature three dimensional sound intensity sensors invented by the Microflown company and a group of digital signal processing...
-
Application of the Msplitmethod for filtering airborne laser scanning data-sets to estimate digital terrain models
PublikacjaALS point cloud filtering involves the separation of observations representing the physical terrain surface from those representing terrain details. A digital terrain model (DTM) is created from a subset of points representing the ground surface. The accuracy of the generated DTM is influenced by several factors, including the survey method used, the accuracy of the source data, the applied DTM generation algorithm, and the survey...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublikacjaThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
Application of Msplit method for filtering airborne laser scanning data sets to estimate digital terrain models
PublikacjaALS point cloud filtering involves the separation of observations representing the physical terrain surface from those representing terrain details. A digital terrain model (DTM) is created from a subset of points representing the ground surface. The accuracy of the generated DTM is influenced by several factors, including the survey method used, the accuracy of the source data, the applied DTM generation algorithm, and the survey...
-
The Impact of Material Selection on Durability of Exhaust Valve Faces of a Ship Engine – A Case Study
Publikacjawo alloys were used in order to extend the service life of marine engine exhaust valve head. Layers of cobalt base alloys were made of the powders with with chemical composition as follow: the layer marked L12; C-1,55%; Si-1,21%; Cr-29,7%; W-9%; Ni-2%; Mo<0,01%; Fe-1,7%; Co-54,83% and the layer marked N; C-1,45%; Co-38,9%; Cr-24,13%; Ni-10,43%; W-8,75%; Fe-7,64%; Mo-7,56%; Si-2,59%. Base metal was valve steel after heat treatment....
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublikacjaThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
Multibeam Echosounder and LiDAR in Process of 360-Degree Numerical Map Production for Restricted Waters with HydroDron
PublikacjaIn order to increase the safety of inland navigation and facilitate the monitoring of the coastal zone of restricted waters, a model of multi-sensory fusion of data from hydroacoustic and optoelectronic systems mounted on the autonomous survey vessel HydroDron will be developed. In the research will be used the LiDAR laser scanner and multibeam echosounder. To increase the visual quality and map accuracy, additionally side scan...
-
Optimal placement of IMU sensor for the detection of children activity
PublikacjaIn this paper an investigation to determine the optimal placement of IMU sensors for the purpose of children characteristic activity detection is presented. The article compares four different placement of two IMU sensors on human body. Ten healthy volunteers participated within the study. Data were collected firstly from two wireless 9-axial IMU sensors placed at the left and right wrists, then sensors were placed at lower back...
-
Toward Human Chromosome Knowledge Engine
PublikacjaHuman chromosomes carry genetic information about our life. Chromosome classification is crucial for karyotype analysis. Existing chromosome classification methods do not take into account reasoning, such as: analyzing the relationship between variables, modeling uncertainty, and performing causal reasoning. In this paper, we introduce a knowledge engine for reasoning-based human chromosome classification that stores knowledge...
-
Intra-subject class-incremental deep learning approach for EEG-based imagined speech recognition
PublikacjaBrain–computer interfaces (BCIs) aim to decode brain signals and transform them into commands for device operation. The present study aimed to decode the brain activity during imagined speech. The BCI must identify imagined words within a given vocabulary and thus perform the requested action. A possible scenario when using this approach is the gradual addition of new words to the vocabulary using incremental learning methods....
-
Bending and buckling formulation of graphene sheets based on nonlocal simple first-order shear deformation theory
PublikacjaThis paper presents a formulation based on simple first-order shear deformation theory (S-FSDT) for large deflection and buckling of orthotropic single-layered graphene sheets (SLGSs). The S-FSDT has many advantages compared to the classical plate theory (CPT) and conventional FSDT such as needless of shear correction factor, containing less number of unknowns than the existing FSDT and strong similarities with the CPT. Governing...
-
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
PublikacjaA problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and...
-
OVERALL SET OF BANDSAW TEETH VERSUS METHODS OF MEASUREMENTS
PublikacjaThis article deals with the impact of the manual methods of measurement on the overall set measurement results. It describes the results of the measurement of bandsaw teeth kerf with the use of a micrometer and a digital calliper. It is commonly known that the cutting process causes the wear of cutting tools. The wear of the cutting edge depends on the cutting conditions as well as on the mechanical properties of the processed...
-
Multi-domain and Context-Aware Recommendations Using Contextual Ontological User Profile
PublikacjaRecommender Systems (RS) became popular tools in many Web services like Netflix, Amazon, or YouTube, because they help a~user to avoid an information overload problem. One of the types of RS are Context-Aware RS (CARS) which exploit contextual information to provide more adequate recommendations. Cross-Domain RS (CDRS) were created as a response to the data sparsity problem which occurs when only few users can provide reviews or...
-
TEMPERATURE INFLUENCE ON TIRE ROLLING RESISTANCE MEASUREMENTS QUALITY
PublikacjaGlobal warming makes it necessary to reduce energy consumption, which in the case of motor vehicles, is connected, among other things, with reduction of resistive forces acting on a vehicle during its motion. One of the most important components of those forces is rolling resistance, which is very difficult to measure, especially in road conditions. The article deals with issues related to the influence of the thermal state of...
-
Autonomous Ship Utility Model Parameter Estimation Utilising Extended Kalman Filter
PublikacjaIn this paper, a problem of autonomous ship utility model identification for control purposes is considered. In particular, the problem is formulated in terms of model parameter estimation (one-step-ahead prediction). This is a complex task due to lack of measurements of the parameter values, their time-variability and structural uncertainty introduced by the available models. In this work, authors consider and compare two utility...
-
A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification
PublikacjaThe article concerns the automation of vessel movement anomaly detection for maritime and coastal traffic safety services. Deep Learning techniques, specifically Convolutional Neural Networks (CNNs), were used to solve this problem. Three variants of the datasets, containing samples of vessel traffic routes in relation to the prohibited area in the form of a grayscale image, were generated. 1458 convolutional neural networks with...
-
Towards Improving Optimised Ship Weather Routing
PublikacjaThe aim of the paper is to outline a project focusing on the development of a new type of ship weather routing solution with improved uncertainty handling, through better estimation of ship performance and responses to sea conditions. Ensemble forecasting is considered to take into account the uncertainty levels that are typical of operations in a stochastic environment. Increased accuracy of weather prediction is achieved through...
-
Performance Evaluation of GAM in Off-Body Path Loss Modelling for Body Area Networks
PublikacjaThis paper addresses the performance evaluation of an off-body path loss model, based on measurements at 2.45 GHz, which has been developed with the use of the Generalised Additive Model, allowing to model a non-linear dependence on different predictor variables. The model formulates path loss as a function of distance, antennas’ heights, antenna orientation angle and polarisation, results showing that performance is very sensitive...
-
Automatic recognition of therapy progress among children with autism
PublikacjaThe article presents a research study on recognizing therapy progress among children with autism spectrum disorder. The progress is recognized on the basis of behavioural data gathered via five specially designed tablet games. Over 180 distinct parameters are calculated on the basis of raw data delivered via the game flow and tablet sensors - i.e. touch screen, accelerometer and gyroscope. The results obtained confirm the possibility...
-
Space-Time Conservation Method applied to numerical solution of water hammer equations
PublikacjaArtykuł poświęcony jest metodzie czasoprzestrzennych objętości skończonych (STC) zastosowanej do przypadku uderzenia hydraulicznego w stalowym przewodzie pracującym pod ciśnieniem. Metoda STC ze względu na swoje własności numeryczne - m.in. wysoką dokładność - może być interesującą alternatywą dla tradycyjnych metod numerycznych, szczególnie w przypadku, gdy efekty numeryczne mają bardzo silny wpływ na rozwiązanie, tym samym utrudniając...
-
Isotope-labeled substances in analysis of persistent organicpollutants in environmental samples
PublikacjaUltratrace analysis of persistent organic pollutants (POPs) in environmental samples requires very sophisticated methods for both sample preparation and instrumental analysis. The complex matrix requires a multi-stage procedure. Each stage is a potential source of error, as a consequence of which the final result of analysis could be a source of misinformation rather than information. The individual stages and the procedure as...
-
Controlling computer by lip gestures employing neural network
PublikacjaResults of experiments regarding lip gesture recognition with an artificial neural network are discussed. The neural network module forms the core element of a multimodal human-computer interface called LipMouse. This solution allows a user to work on a computer using lip movements and gestures. A user face is detected in a video stream from a standard web camera using a cascade of boosted classifiers working with Haar-like features....
-
Application of hybrid finite-difference mode-matching method to analysis of structures loaded with axially-symmetrical posts
PublikacjaW artykule przedstawiono nową metodę hybrydową do analizy układów falowodowych zawierających dowolne konfiguracje obiektów osiowo-symetrycznych. Metoda oparta jest na połączeniu metody różnic skończonych, metody dopasowania rodzajów oraz iteracyjnej procedury rozpraszania. W pracy przedstawiono badania zbieżności metody. Uzyskane wyniki numeryczne porównano z wynikami odniesienia. Duża zgodność wyników potwierdziła poprawność opracowanego...
-
Thermo-resonance analysis of an excited graphene sheet using a new approach
PublikacjaForced vibration of graphene nanoplate based on a refined plate theory in conjunction with higher-order nonlocal strain gradient theory in the thermal environment has been investigated. Regarding the higher-order nonlocal strain gradient theory, both stress nonlocality and size-dependent effects are taken into account, so the equilibrium equations which are governing on the graphene sheet have been formulated by the theory....
-
Nonlinear Model of Synchronous Generator for Autonomous Electrical Power Systems Analysis
PublikacjaThis paper presents the nonlinear lookup table model for synchronous generator (SG) analysis. The saturation effects of the SG magnetic circuit have been considered. The saturated characteristic of the SG magnetic circuit are based on the open circuit saturation curve for magnetizing inductances. The model has been implemented into the Synopsys/Saber software using the MAST modelling language. To implement the no-load voltage characteristic...
-
Analysis of the applicability of laser scanning to making an inventory of swimming pool facilities
Publikacja3D scanning can be used in many branches of economy, e.g. reverse and prototype engineering, industrial design, quality control, pros-thetics, orthodontics, archiving of historic objects and archeological findings, examination of a scene of crime, making films and comput-er games. The technology of terrestrial laser scanning has a bright fu-ture as we are living in the time of blooming measurement tech-niques, which can provide...
-
SHEAR YIELD STRESSES AND FRACTURE TOUGHNESS OF SCOTS PINE (PINUS SYLVESTRIS L.) ACCORDING TO THE RAW MATERIAL PROVENANCE
PublikacjaIn this paper values of the fracture toughness and of shear yield stress in the shear zone of Scots pine are presented. Tests of cutting were carried on samples of Scotch pine (Pinus sylvestris L.) wood of five provenances from Poland. These experimentally cutting tests were carried on the sash gang saw PRW-15M and the values of cutting power were obtained. The values of fracture toughness and shear yield stress based on Atkins’s...
-
Modeling energy consumption of parallel applications
PublikacjaThe paper presents modeling and simulation of energy consumption of two types of parallel applications: geometric Single Program Multiple Data (SPMD) and divide-and-conquer (DAC). Simulation is performed in a new MERPSYS environment. Model of an application uses the Java language with extension representing message exchange between processes working in parallel. Simulation is performed by running threads representing distinct process...