Filters
total: 1355
filtered: 1266
-
Catalog
Chosen catalog filters
displaying 1000 best results Help
Search results for: ACCURACY
-
Feature Weighted Attention-Bidirectional Long Short Term Memory Model for Change Detection in Remote Sensing Images
PublicationIn remote sensing images, change detection (CD) is required in many applications, such as: resource management, urban expansion research, land management, and disaster assessment. Various deep learning-based methods were applied to satellite image analysis for change detection, yet many of them have limitations, including the overfitting problem. This research proposes the Feature Weighted Attention (FWA) in Bidirectional Long...
-
Comparative study on the effectiveness of various types of road traffic intensity detectors
PublicationVehicle detection and speed measurements are crucial tasks in traffic monitoring systems. In this work, we focus on several types of electronic sensors, operating on different physical principles in order to compare their effectiveness in real traffic conditions. Commercial solutions are based on road tubes, microwave sensors, LiDARs, and video cameras. Distributed traffic monitoring systems require a high number of monitoring...
-
Deep Learning Optimization for Edge Devices: Analysis of Training Quantization Parameters
PublicationThis paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a...
-
Flooding Extent Mapping for Synthetic Aperture Radar Time Series Using River Gauge Observations
PublicationThe flooding extent area in a river valley is related to river gauge observations such as discharge and water elevations. The higher the water elevations, or discharge, the larger the flooding area. Flooding extent maps are often derived from synthetic aperture radar (SAR) images using thresholding methods. The thresholding methods vary in complexity and number of required parameters. We proposed a simple thresholding method that...
-
Characterization of Defects Inside the Cable Dielectric With Partial Discharge Modeling
PublicationThe continuous monitoring of power system devices is an important step toward keeping such capital assets safe. Partial discharge (PD)-based measurement tools provide a reliable and accurate condition assessment of power system insulations. It is very common that voids or cavities exist in every solid dielectric insulation medium. In this article, different voids are modeled and analyzed using an advanced finite element (FE)-based...
-
A three-dimensional periodic beam for vibroacoustic isolation purposes
PublicationThis paper presents results of investigations on a three-dimensional (3-D) isotropic periodic beam. The beam can represent a vibroacoustic isolator of optimised dynamic characteristics in the case of its longitudinal, flexural and torsional behaviour. The optimisation process concerned both the widths as well as the positions of particular frequency band gaps that are present in the frequency spectrum of the beam. Since the dynamic...
-
Scoreboard Architectural Pattern and Integration of Emotion Recognition Results
PublicationThis paper proposes a new design pattern, named Scoreboard , dedicated for applications solving complex, multi-stage, non-deterministic problems. The pattern provides a computational framework for the design and implementation of systems that integrate a large number of diverse specialized modules that may vary in accuracy, solution level, and modality. The Scoreboard is an extension of Blackboard design pattern and comes under...
-
Machine learning-based prediction of preplaced aggregate concrete characteristics
PublicationPreplaced-Aggregate Concrete (PAC) is a type of preplaced concrete where coarse aggregate is placed in the mold and a Portland cement-sand grout with admixtures is injected to fill the voids. Due to the complex nature of PAC, many studies were conducted to determine the effects of admixtures and the compressive and tensile strengths of PAC. Considering that a prediction tool is needed to estimate the compressive and tensile strengths...
-
Performance Analysis and Quantification of BeiDou Navigation Satellite System (BDS-3)
PublicationPositioning, Navigation, and Timing (PNT) information play a vital role in everyday life of common persons. People greatly rely on Global Navigation Satellite System (GNSS)-enabled applications for navigation to reach their desired destination. However, GNSS navigation performance is highly degraded in urban environments due to the high probability of signal interruption, multipath (MP), and/or non-line-of-sight (NLOS) signal...
-
A non-uniform real-time speech time-scale stretching method
PublicationAn algorithm for non-uniform real-time speech stretching is presented. It provides a combination of typical SOLA algorithm (Synchronous Overlap and Add ) with the vowels, consonants and silence detectors. Based on the information about the content and the estimated value of the rate of speech (ROS), the algorithm adapts the scaling factor value. The ability of real-time speech stretching and the resultant quality of voice were...
-
Generalized adaptive notch smoothing revisited
PublicationThe problem of identification of quasi-periodically varying dynamic systems is considered. This problem can be solved using generalized adaptive notch filtering (GANF) algorithms. It is shown that the accuracy of parameter estimates can be significantly increased if the results obtained from GANF are further processed using a cascade of appropriately designed filters. The resulting generalized adaptive notch smoothing (GANS) algorithm...
-
Ab-initio study of electrical and optical properties of allylamine
PublicationThe Density functional theory is one of most promising methodology in fast and accurate calculations of electrical and optical properties from the atomic basis. In this paper, we calculate electrical and optical properties of allylamine (2-propen 1- amine) in terms of accuracy and speed of calculations obtained by selection of DFT-1/2 method with ultrasoft Vanderbilt pseudopotentials. Comparison of density of states between...
-
Enhanced voice user interface employing spatial filtration of signals from acoustic vector sensor
PublicationSpatial filtration of sound is introduced to enhance speech recognition accuracy in noisy conditions. An acoustic vector sensor (AVS) is employed. The signals from the AVS probe are processed in order to attenuate the surrounding noise. As a result the signal to noise ratio is increased. An experiment is featured in which speech signals are disturbed by babble noise. The signals before and after spatial filtration are processed...
-
KEMR-Net: A Knowledge-Enhanced Mask Refinement Network for Chromosome Instance Segmentation
PublicationThis article proposes a mask refinement method for chromosome instance segmentation. The proposed method exploits the knowledge representation capability of Neural Knowledge DNA (NK-DNA) to capture the semantics of the chromosome’s shape, texture, and key points, and then it uses the captured knowledge to improve the accuracy and smoothness of the masks. We validate the method’s effectiveness on our latest high-resolution chromosome...
-
Computational complexity and length of recorded data for fluctuation enhanced sensing method in resistive gas sensors
PublicationThis paper considers complexity and accuracy of data processing for gas detection using resistance fluctuation data observed in resistance gas sensors. A few selected methods were considered (Principal Component Analysis – PCA, Support Vector Machine – SVM). Functions like power spectral density or histogram were used to create input data vector for these algorithms from the observed resistance fluctuations. The presented considerations...
-
Elimination of impulsive disturbances from archive audio files – comparison of three noise pulse detection schemes
PublicationThe problem of elimination of impulsive disturbances (such as clicks, pops, ticks, crackles, and record scratches) from archive audio recordings is considered and solved using autoregressive modeling. Three classical noise pulse detection schemes are examined and compared: the approach based on open-loop multi-step-ahead signal prediction, the approach based on decision-feedback signal prediction, and the double threshold approach,...
-
On the instantaneous frequency smoothing for signals with quasi-linear frequency changes
PublicationThe problem of estimation of the slowly-varying instantaneous frequency of a nonstationary complex sinusoidal signal buried in noise is considered. This problem is usually solved using frequency tracking algorithms. It is shown that the accuracy of frequency estimates can be considerably increased if the results yielded by the frequency tracker are further processed using the appropriately designed filters. The resulting frequency...
-
Applying Fuzzy Logic of Expert Knowledge for Accurate Predictive Algorithms of Customer Traffic Flows in Theme Parks
PublicationThis study analyzes two forecasting models based on the application of fuzzy logic and evaluates their effectiveness in predicting visitor expenditure and length of stay at a popular theme park. The forecasting models are based on a set of more than 600 decision rules constructed in the form of a complex series of IF-THEN statements. These algorithms store expert knowledge. A descriptive instrument that records the individual visitor's...
-
System for tracking multiple trains on a test railway track
PublicationSeveral problems may arise when multiple trains are to be tracked using two IP camera streams. In this work, real-life conditions are simulated using a railway track model based on the Pomeranian Metropolitan Railway (PKM). Application of automatic clustering of optical flow is investigated. A complete tracking solution is developed using background subtraction, blob analysis, Kalman filtering, and a Hungarian algorithm. In total,...
-
System for tracking multiple trains on a test railway track
PublicationSeveral problems may arise when multiple trains are to be tracked using two IP camera streams. In this work, real-life conditions are simulated using a railway track model based on the Pomeranian Metropolitan Railway (PKM). Application of automatic clustering of optical flow is investigated. A complete tracking solution is developed using background subtraction, blob analysis, Kalman filtering, and a Hungarian algorithm. In total,...
-
Ab-initio study of electrical and optical properties of allylamine
PublicationThe Density functional theory is one of most promising methodology in fast and accurate calculations of electrical and optical properties from the atomic basis. In this paper, we calculate electrical and optical properties of allylamine (2-propen 1- amine) in terms of accuracy and speed of calculations obtained by selection of DFT-1/2 method with ultrasoft Vanderbilt pseudopotentials. Comparison of density of states between molecule...
-
Automatic system for optical parameters measurements of biological tissues
PublicationIn this paper a system allowing execution of automatic measurements of optical parameters of scattering materials in an efficient and accurate manner is proposed and described. The system is designed especially for measurements of biological tissues including phantoms, which closely imitate optical characteristics of real tissue. The system has modular construction and is based on the ISEL system, luminance and color meter and...
-
Compressed Projection Bases for Model-Order Reduction of Multiport Microwave Components Using FEM
PublicationThis paper presents a projection basis compression technique for generating compact reduced-order models (ROM) in the FE analysis of microwave devices. In this approach redundancy is removed from the projection basis by means of the proper orthogonal decomposition technique applied to the projected system of linear equations. Compression allows for keeping the size of a reduced-order model as small as possible without compromising...
-
Maturity curve for estimating the in-place strength of high performance concrete
PublicationThe paper presents the maturity curve for estimating the in-place early-age compressive strength of concrete. The development of appropriate maturity curve is a complex process. It is important to correctly determine the datum temperature and activation energy, which can be obtained in mortar tests. This paper describes an investigation of the accuracy of the maturity method to estimate the strength when different way to rate constant...
-
Zastosowanie sygnałów o projektowanych kształtach do diagnostyki obiektów wysoko-impedancyjnych metodą spektroskopii impedancyjnej
PublicationW artykule przedstawiono metodę szybkiej spektroskopii impedancyjnej obiektów o wysokich impedancjach (|Zx| > 1 GOhm) z zastosowaniem sygnałów o projektowanych kształtach. Sygnał pobudzenia wytwarzany jest w module DAQ U2531A i doprowadzany na wejście badanego obiektu za pośrednictwem przetwornika cyfrowo-analogowego (CA). Sygnały odpowiedzi proporcjonalne do napięcia na mierzonej impedancji Zx oraz prądu płynącego przez Zx są...
-
Rozpoznawanie oraz lokalizacja w obrazie przewodów linii wysokiego napięcia
PublicationW pracy przedstawiono opracowany algorytm rozpoznawania oraz lokalizacji przewodów linii wysokiego napięcia na podstawie obrazu horyzontalnego. Procedura detekcji przewodu została podzielona na trzy etapy. Pierwszy etap zawiera algorytm wykrywania krawędzi wykazujący największą czułość na krawędzie poziome, a jednocześnie brak czułości na krawędzie pionowe. Efektem jest znaczna redukcja liczby wykrytych krawędzi w porównaniu do...
-
Addressing the Weaknesses of Multi-Criteria Decision-Making Methods using Python
PublicationThe book aims to draw attention to the weaknesses in Multi-Criteria Decision-Making (MCDM) methods and provide insights to improve the decision-making process. By addressing these weaknesses, it seeks to enhance the accuracy and effectiveness of MCDM methods in selecting the best alternatives in various fields. The book covers popular MCDM methods such as TOPSIS, ELECTRE, VIKOR, and PROMETHEE. It compares traditional methods with...
-
Optical method supported by machine learning for urinary tract infection detection and urosepsis risk assessment
PublicationThe study presents an optical method supported by machine learning for discriminating urinary tract infections from an infection capable of causing urosepsis. The method comprises spectra of spectroscopy measurement of artificial urine samples with bacteria from solid cultures of clinical E. coli strains. To provide a reliable classification of results assistance of 27 algorithms was tested. We proved that is possible to obtain...
-
Macromodeling techniques for accelerated finite element analysis
PublicationThis paper deals with the Model Order Reduction applied locally in the Finite Element Method (FEM) analysis. Due to the reduction process, blocks of FEM system matrices associated with selected subregions of the computational domain are projected onto the subspaces spanned by the vectors of suited orthogonal projection basis. In effect, large and sparse FEM matrices are replaced with small and dense ones, called macromodels. This...
-
When Neural Networks Meet Decisional DNA: A Promising New Perspective for Knowledge Representation and Sharing
PublicationABSTRACT In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domain’s past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest...
-
Accelerating Video Frames Classification With Metric Based Scene Segmentation
PublicationThis paper addresses the problem of the efficient classification of images in a video stream in cases, where all of the video has to be labeled. Realizing the similarity of consecutive frames, we introduce a set of simple metrics to measure that similarity. To use these observations for decreasing the number of necessary classifications, we propose a scene segmentation algorithm. Performed experiments have evaluated the acquired...
-
RF Indoor Positioning System Supported by Wireless Computer Vision Sensors
PublicationIn this paper the possibility of increase the accuracy of RF fingerprinting indoor tracking system by the use of additional information from simple vision system is examined. As the distances in signal space differs from ones in real environment the ambiguity in decision process of fingerprinting algorithm can occur when set of closest distances between tag and map points in signal space corresponds to big distances differences...
-
Exact modal absorbing boundary condition for waveguide simulations - discrete Green's function approach
PublicationA modal absorbing boundary condition (ABC) based on the discrete Green's function (DGF) is introduced and applied for termination of waveguides simulated by means of the finite-difference time-domain (FDTD) method. The differences between the developed approach and implementations already demonstrated in the literature are presented. By applying DGF, a consistent theoretical approach to modal ABC in the FDTD method is obtained....
-
Melody Harmonization with Interpolated Probabilistic Models
PublicationMost melody harmonization systems use the generative hidden Markov model (HMM), which model the relation between the hidden chords and the observed melody. Relations to other variables, such as the tonality or the metric structure, are handled by training multiple HMMs or are ignored. In this paper, we propose a discriminative means of combining multiple probabilistic models of various musical variables by means of model interpolation....
-
Analyzing the Geometry of the Turnouts and Their Adjustment Basing on the Tacheometer Measurements
PublicationThe article presents the results of tacheometric measurements of a station throat, as well as the method of data preparation and analysis. The calculations covered the verification of the geometry and the location of railway turnouts and crossings. The analyses were performed for the selected parameters of the turnout geometry, including their lengths and track gauge in main sections. In addition, the data were analyzed to confirm...
-
Voltage Harmonic Distortion Measurement Issue in Smart-Grid Distribution System
PublicationThis paper presents the investigation results ofvoltage harmonic transfer accuracy problems through voltagetransformers which are widely used in power quality monitoringsystems in medium and high voltage grids. A simplified lumpedparameters circuit model of the voltage transformer is presentedand verified by simulation and experimental investigations. Anumber voltage transformers typically used in medium voltagegrid has been tested...
-
New Simple and Robust Method for Determination of Polarity of Deep Eutectic Solvents (DESs) by Means of Contact Angle Measurement
PublicationThe paper presents a new method for evaluating the polarity and hydrophobicity of deep eutectic solvents (DESs) based on the measurement of the DES contact angle on glass. DESs consisting of benzoic acid derivatives and quaternary ammonium chlorides–tetrabutylammonium chloride (TBAC) and benzyldimethylhexadecylammonium chloride (16-BAC)—in selected molar ratios were chosen for the study. To investigate the DESs polarity, an optical...
-
A method of earth fault loop impedance measurement without unwanted tripping of RCDs
PublicationIn low-voltage networks, earth fault loop impedance (EFLI) measurement is the basis for assessing the effectiveness of automatic disconnection of supply. Such a measurement is performed during initial and periodical verification, especially in a TN low-voltage network. Nowadays, due to widespread application of residual current devices (RCDs), such test is difficult in many circuits because RCDs operate during the test. In this...
-
The Imaging of Gdansk Bay Seabed by Using Side Sonar
PublicationThis paper is mainly aimed at presentation of an impact of environmental conditions on imaging accuracy by using hydro-acoustic systems in waters of a high non-uniformity of spatial distribution of hydrological parameters. Impact of refraction on erroneous estimation of range, in case of wave radiation into water under a large angle, like in side sonars or multi-beam echo-sounders, is especially important. In this paper seasonal...
-
Investigation of educational processes with affective computing methods
PublicationThis paper concerns the monitoring of educational processes with the use of new technologies for the recognition of human emotions. This paper summarizes results from three experiments, aimed at the validation of applying emotion recognition to e-learning. An analysis of the experiments’ executions provides an evaluation of the emotion elicitation methods used to monitor learners. The comparison of affect recognition algorithms...
-
Accurate electrothermal modelling of high frequency DC-DC converters with discrete IGBTs in PLECS software
PublicationIn the paper, a novel, improved method of the IGBT junction temperature computations in the PLECS simulation software is presented. The developed method aims at accuracy of the junction temperature computations in PLECS by utilising a more sophisticated model of transistor losses, and by taking into account variability of transistor thermal resistance as a function of its temperature. A detailed description of the proposed method,...
-
Azimuth estimator for a rotating array radar with wide beam
PublicationThe problem of estimating azimuth in rotating array radar with a beam, wide in the azimuth plane, is considered. Under such setup the echo signal usually has a very low signal to noise ratio, but the number of observations is large, because of long dwell times. The proposed solution is based on the maximum likelihood approach, but it employs simplifications which facilitate its implementation in real time systems. Results, obtained...
-
Regression points in non-intrusive polynomial chaos expansion method and D-optimal design
PublicationThe paper addresses selected issues of uncertainty quantification in the modelling of a system containing surgical mesh used in ventral hernia repair. Uncertainties in the models occur e.g. due to variability of abdominal wall properties among others. In order to include them, a non-intrusive regression-based polynomial chaos expansion method is employed. Its accuracy depends on the choice of regression points. In the study a relation...
-
Estimators of covariance matrices in Msplit(q) estimation
PublicationThis paper proposes methods for the determination of covariance matrices of Msplit(q) estimators. The solutions presented here allow Msplit(q) estimation to be supplemented by the operations from the domain of accuracy analysis (especially that concerning estimators of parameters). Theoretical forms of covariance matrices of Msplit(q) estimators were established using the empirical influence functions and the equivalent covariance...
-
Neural network based algorithm for hand gesture detection in a low-cost microprocessor applications
PublicationIn this paper the simple architecture of neural network for hand gesture classification was presented. The network classifies the previously calculated parameters of EMG signals. The main goal of this project was to develop simple solution that is not computationally complex and can be implemented on microprocessors in low-cost 3D printed prosthetic arms. As the part of conducted research the data set EMG signals corresponding...
-
OrphaGPT: An Adapted Large Language Model for Orphan Diseases Classification
PublicationOrphan diseases (OD) represent a category of rare conditions that affect only a relatively small number of individuals. These conditions are often neglected in research due to the challenges posed by their scarcity, making medical advancements difficult. Then, the ever-evolving medical research and diagnosis landscape calls for more attention and innovative approaches to address the complex challenges of rare diseases and OD. Pre-trained...
-
An automated learning model for twitter sentiment analysis using Ranger AdaBelief optimizer based Bidirectional Long Short Term Memory
PublicationSentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day-to-day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi-LSTM RAO)...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Enhancing Renal Tumor Detection: Leveraging Artificial Neural Networks in Computed Tomography Analysis
PublicationRenal cell carcinoma is one of the most common cancers in Europe, with a total incidence rate of 18.4 cases per 100 000 population. There is currently significant overdiagnosis (11% to 30.9%) at times of planned surgery based on radiological studies. The purpose of this study was to create an artificial neural network (ANN) solution based on computed tomography (CT) images as an additional tool to improve the differentiation of...
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublicationHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...