displaying 1000 best results Help
Search results for: accuracy
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
Nonlinear phenomena of small-scale sound in a gas with exponential stratification
PublicationThe nonlinear dynamics of perturbations, quickly varying in space, with comparatively large characteristic wavenumbers k: k>1/H, is considered. H is the scale of density and pressure reduction in unperturbed gas, as the coordinate (H is the so-called height of the uniform equilibrium gas). Coupling nonlinear equations which govern the sound and the entropy mode in a weakly nonlinear flow are derived. They describe the dynamics...
-
Experimental and Numerical Analysis of Air Trapping in a Porous Medium with Coarse Textured Inclusions
PublicationThe paper presents a 2D upward infiltration experiment performed on a model porous medium consisting of fine sand background with two inclusions made of coarser sands. The purpose of the experiment was to investigate the effects of structural air trapping, which occurs during infiltration as a result of heterogeneous material structure. The experiment shows that a significant amount of air becomes trapped in each of the inclusions. Numerical...
-
A simplified behavioral MOSFET model based on parameters extraction for circuit simulations.
PublicationThe paper presents results on behavior modeling of general purpose Metal-Oxide Semiconductor Field-Effect Transistor (MOSFET) for simulation of power electronics systems requiring accuracy both in steady-state and in switching conditions. Methods of parameters extraction including nonlinearity of parasitic capacitances and steady-state characteristics are based on manufacturer data sheet and externally measurable characteristics....
-
Basic evaluation of limb exercises based on electromyography and classification methods
PublicationSymptoms caused by cerebral palsy or stroke deprive a person partially or even completely of his ability to move. Nowadays we can observe more technologically advanced rehabilitation devices which incorporate biofeedback into the process of rehabilitation of such people. However, there is still a lack of devices that would analyse, assess, and control (independently or with limited support) specialised movement exercises. Here...
-
An optimised placement of the hard quality sensors for a robust monitoring of the chlorine concentration in drinking water distribution systems
PublicationThe problem of an optimised placement of the hard quality sensors in drinking water distribution systemsunder several water demand scenarios for a robust monitoring of the chlorine concentration is formulatedin this paper. The optimality is understood as achieving a desired trade off between the sensors and theirmaintenance costs and the accuracy of estimation of the chlorine concentration. The contribution of thiswork is a comprehensive...
-
Representation of magnetic hysteresis in tape wound core using feedback Preisach model
PublicationThis paper presents a mathematical model for the hysteresis phenomenon in ferromagnetic tape wound core. The feedback scalar Preisach model of hysteresis is used to simulate magnetic behavior of the grain oriented silicon strip of ET114-27 type. Determination of B-H hysteretic curve is based on measurement of the initial magnetization curve and the main hysteresis loop. The Preisach distribution function (PDF) of ET114-27 material...
-
Analysis of the influence of external conditions on temperature readings in thermograms and adaptive adjustment of the measured temperature value
PublicationMeasuring human temperature is a crucial step in preventing the spread of diseases such as COVID-19. For the proper operation of an automatic body temperature measurement system throughout the year, it is necessary to consider outdoor conditions. In this paper, the effect of atmospheric factors on facial temperature readings using infrared thermography is investigated. A thorough analysis of the variation of facial temperature...
-
Comparison of three methods of EPR retrospective dosimetry in watch glass
PublicationIn this article we present results of our follow-up studies of samples of watch glass obtained and examined within a framework of international intercomparison dosimetry project RENEB ILC 2021. We present three methods of dose reconstruction based on EPR measurements of these samples: calibration method (CM), added dose method (ADM) and added dose&heating method (ADHM). The study showed that the three methods of dose reconstruction...
-
Inverse determination of sliding surface temperature based on measurements by thermocouples with account of their thermal inertia
PublicationThis study developed an inverse heat conduction algorithm to determine temperature at a sliding surface taking account of thermocouple thermal inertia. The direct heat conduction problem was solved analytically based on the Laplace integral transform approach. The inverse algorithm was applied to the problem of friction of a brake material against a steel. The experiments were conducted on a pin-on-disc tribometer for three short-time...
-
Measurement method for capacitive sensors for microcontrollers based on a phase shifter
PublicationA complete measurement method dedicated to capacitive sensors has been developed. It includes the development of hardware (an analogue interface circuit for microcontrollers with built-in times/counters and analogue comparators) and software (a measurement procedure and a systematic error calibration (correction) algorithm which is based on a calibration dictionary). The interface circuit consists of a low-pass filter and a phase...
-
MACHINE LEARNING APPLICATIONS IN RECOGNIZING HUMAN EMOTIONS BASED ON THE EEG
PublicationThis study examined the machine learning-based approach allowing the recognition of human emotional states with the use of EEG signals. After a short introduction to the fundamentals of electroencephalography and neural oscillations, the two-dimensional valence-arousal Russell’s model of emotion was described. Next, we present the assumptions of the performed EEG experiment. Detail aspects of the data sanitization including preprocessing,...
-
Fast Calibration-Free Single-Anchor Indoor Localization Based on Limited Number of ESPAR Antenna Radiation Patterns
Publication— In this article, we investigate how the calibrationfree single-anchor indoor localization algorithm developed for base stations equipped with electronically steerable parasitic array radiator (ESPAR) antennas can further be improved. By reducing the total number of ESPAR antenna radiation patterns used in localization process, one can significantly reduce the time needed for an object localization. Performed localization measurements...
-
Combined Close Range Photogrammetry and Terrestrial Laser Scanning for Ship Hull Modelling
PublicationThe paper addresses the fields of combined close-range photogrammetry and terrestrial laser scanning in the light of ship modelling. The authors pointed out precision and measurement accuracy due to their possible complex application for ship hulls inventories. Due to prescribed vitality of every ship structure, it is crucial to prepare documentation to support the vessel processes. The presented methods are directed, combined...
-
On the Usefulness of the Generalised Additive Model for Mean Path Loss Estimation in Body Area Networks
PublicationIn this article, the usefulness of the Generalised Additive Model for mean path loss estimation in Body Area Networks is investigated. The research concerns a narrow-band indoor off-body network operating at 2.45 GHz, being based on measurements performed with four different users. The mean path loss is modelled as a sum of four components that depend on path length, antenna orientation angle, absolute difference between transmitting...
-
The Use of Unmanned Surface Vessels in Bathymetric Measurements of Waterbodies with Highly Dynamic Seafloor Relief
PublicationThe early 21st century is a time when unmanned surface vessels (USV) are used in various measurement applications. Modern autonomous and unmanned vessels are increasingly often used in bathymetric measurements whose aim is to measure the seafloor with the sufficient positioning accuracy. Therefore, the use of USVs in hydrography can be seen as the beginning of a new era in this regard. This paper presents bathymetric measurements...
-
Reliability and types of diagnosis in the process of diesel engine operation
PublicationThe article presents complexity of the problem concerning development of diagnosis with defined reliability by a diagnosing system (SDG) on technical condition of marine combustion engines, especially main engines. It was shown that development of the final diagnosis, the so-called initial operation diagnosis, on the operational usability (fDG on PEx) of a main engine in particular, is not possible without prior development of...
-
Seismic gap between buildings founded on different soil types experiencing pounding during earthquakes
PublicationSeveral formulas have been suggested in the literature to evaluate the minimum seismic gap that would prevent collisions between adjacent buildings during earthquakes, including those based on the absolute sum of the peak displacements (ABS), square root of the sum of the squares (SRSS), the double difference method (DDC), Australian code, and approach proposed by Naderpour et al. The aim of the present study is to evaluate the...
-
Accurate and continuous adhesive fracture energy determination using an instrumented wedge test
PublicationThe wedge test and the related double cantilever beam test are practical methods of assessing structural adhesive fracture energy. In the former, and to a lesser extent the latter, a recognised problem is the difficulty of following the length of the growing crack, required to calculate fracture energy with any accuracy. We present a novel method of measurement of crack length that has the advantages of being accurate and allowing...
-
Visual Object Tracking System Employing Fixed and PTZ Cameras
PublicationThe paper presents a video monitoring system utilizing fixed and PTZ cameras for tracking of moving objects. First type of camera provides image for background modelling, being employed for foreground objects localization. Estimated objects locations are then utilised for steering of PTZ cameras when observing targeted objects with high close-ups. Objects are classified into several classes, then basic event detection is being...
-
Monitoring of CRT by means of impedance multiple measurements - simulation studies
PublicationCardiac resynchronization therapy (CRT) is a very promising treatment for patients with congestive heart failure. An Impedance Cardiography (ICG) is used for evaluation of heart mechanical activity. A simulation study with the use of a FEM model was performed. The developed realistic model of the thorax, based on CT data obtained from examination of a 68-year-old man, consisted of 212 000 tetrahedral elements. Different configurations...
-
Comparison of reproduction strategies in genetic algorithm approach to graph searching
Publicationgenetic algorithms (ga) are a well-known tool used to obtain approximate solutions to optimization problems. successful application of genetic algorithm in solving given problem is largely dependant on selecting appropriate genetic operators. selection, mutation and crossover techniques play a fundamental role in both time needed to obtain results and their accuracy. in this paper we focus on applying genetic algorithms in calculating...
-
A subdomain model for armature reaction field and open‐circuit field prediction in consequent pole permanent magnet machines
PublicationIn this paper, the machine quantity, such as electromagnetic torque, self and mutual inductances, and electromotive force, is analytically calculated for non-overlapping winding consequent pole slotted machine for open-circuit field and armature reaction. The sub-domain approach of (2-D) analytical model is developed using Maxwell's equations and divide the problem into slots, slot-openings, airgap and magnets region, the magnet...
-
Mathematical modelling of implant in an operated hernia for estimation of the repair persistence
PublicationThis paper presents mathematical modelling of an implanted surgical mesh used in the repair process of the abdominal hernia. The synthetic implant is simulated by a membrane structure. The author provides a material modelling of the implant based on the dense net model appropriate for technical fabrics. The accuracy of the proposed solution is evaluated by comparing the simulations of the dynamic behaviour of the system with the...
-
Experimental verification of a new method of loop resistance testing in low voltage systems with residual current devices
PublicationA periodical verification of the effectiveness of protection against electric shock shall be performed in low voltage systems. The scope of this verification includes loop impedance/resistance testing. If a residual current device is installed in a tested circuit, this testing is problematic. A residual current device trips out during the test, because of the high value of measurement current. This precludes the execution of the...
-
Fiber optic displacement sensor with signal analysis in spectral domain
PublicationIn this paper, a study of a low-coherence fiber optic displacement sensor is presented. The sensor consisted of a broadband source whose central wavelength was either at 1310 nm or 1550 nm, a sensing Fabry-Pérot interferometer operating in reflective mode and an optical spectrum analyzer acting as the detection setup. All these components were connected by a single-mode fiber coupler. Metrological parameters of the sensor were...
-
Response of a fiber-optic Fabry-Pérot interferometer to refractive index and absorption changes – modelling and experiments
PublicationThis paper describes how the refractive index and the absorption of investigated substances change the spectrum of the optical radiation at the output of the fiber-optic Fabry-Pérot interferometer. The modeling of the operation of the interferometer takes into account not only the spectra of the refractive index and the absorption of the medium that is inside the cavity, but also spectra of the refractive indices of the core and...
-
Examining Quality of Hand Segmentation Based on Gaussian Mixture Models
PublicationResults of examination of various implementations of Gaussian mix-ture models are presented in the paper. Two of the implementations belonged to the Intel’s OpenCV 2.4.3 library and utilized Background Subtractor MOG and Background Subtractor MOG2 classes. The third implementation presented in the paper was created by the authors and extended Background Subtractor MOG2 with the possibility of operating on the scaled version of...
-
Analysis of Positioning Error and Its Impact on High Frequency Performance Parameters of Differential Signal Coupler of Differential Signal Coupler
PublicationThis paper presents the analysis of the effect of differential signal coupler positioning accuracy on its high frequency performance parameters for contact-less high speed chip-to-chip data transmission on PCB application. Our considerations are continuation of the previous works on differential signal coupler concept, design methodology and analysis for high speed data transmission monitoring presented in [1, 2]. The theoretical...
-
Accurate design of pseudoelliptic inline SIW filters with frequency-dependent couplings
PublicationThis paper presents an accurate synthesis method for inline SIW (Substrate Integrated Waveguide) generalized Chebyshev bandpass filters with frequency-dependent couplings. The technique is based on the synthesis of a coupling matrix that takes into account the impedance of the frequency-dependent stub. Thus, a loading effect compensation in adjacent resonators (via resonant frequency adjustment) and coupling elements (via coupling-value...
-
Indirect Measurement of Motor Current Derivatives in PMSM Sensorless Drives
PublicationMotor current derivatives contain useful information for control algorithms, especially in sensorless electric drives. The measurement of motor current derivatives in electric motors supplied by voltage source inverter can be performed using di/dt transducers. However, in such a solution additional sensors have to be installed, e.g. Rogowski coils. Another approach is to measure current derivatives indirectly – by oversampling...
-
Determination of refractive index dispersion using fiber-optic low-coherence Fabry–Perot interferometer: implementation and validation
PublicationWe present the implementation and validation of low-coherence Fabry–Perot interferometer for refractive index dispersion measurements of liquids. A measurement system has been created with the use of four superluminescent diodes with different optical parameters, a fiber-optic coupler and an optical spectrum analyzer. The Fabry–Perot interferometer cavity has been formed by the fiber-optic end and mirror surfaces mounted on a micromechanical...
-
An Archaeological - Architectural Documentation Based on Close Range Photogrammetry
PublicationWisłoujście 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...
-
Global sensitivity analysis of membrane model of abdominal wall with surgical mesh
PublicationThe paper addresses the issue of ventral hernia repair. Finite Element simulations can be helpful in the optimization of hernia parameters. A membrane abdominal wall model is proposed in two variants: a healthy one and including hernia defect repaired by implant. The models include many uncertainties, e.g. due to variability of abdominal wall, intraabdominal pressure value etc. Measuring mechanical properties with high accuracy...
-
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublicationRecently 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...
-
Comparative Study of Self-Organizing Maps vs. Subjective Evaluation of Quality of Allophone Pronunciation for Nonnative English Speakers
PublicationThe 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...
-
Electricity demand prediction by multi-agent system with history-based weighting
PublicationEnergy and load demand forecasting in short-horizons, over an interval ranging from one hour to one week, is crucial for on-line scheduling and security functions of power system. Many load forecasting methods have been developed in recent years which are usually complex solutions with many adjustable parameters. Best-matching models and their relevant parameters have to be determined in a search procedure. We propose a hybrid...
-
Rating Prediction with Contextual Conditional Preferences
PublicationExploiting contextual information is considered a good solution to improve the quality of recommendations, aiming at suggesting more relevant items for a specific context. On the other hand, recommender systems research still strive for solving the cold-start problem, namely where not enough information about users and their ratings is available. In this paper we propose a new rating prediction algorithm to face the cold-start...
-
One-Dimensional Modeling of Flows in Open Channels
PublicationIn this chapter, modeling of the unsteady open channel flow using one-dimensional approach is considered. As this question belongs to the well-known and standard problems of open channel hydraulic engineering, comprehensively presented and described in many books and publications, our attention is focused on some selected aspects only. As far as the numerical solution of the governing equations is considered, one can find out that...
-
The idea of a robotic single-sided lapping system
PublicationThis paper reviews the idea of a robotic lapping system. Robot’s assistance automates the lap-ping process and supports the development of a flexible lapping system. However, the main aim behind the idea of a robotic lapping system is to provide improved means for controlling the posi-tion of conditioning rings on a lapping plate. Due to the kinematics of lapping process, the profile wear of the tool is not constant along the radius....
-
Facial emotion recognition using depth data
PublicationIn this paper an original approach is presented for facial expression and emotion recognition based only on depth channel from Microsoft Kinect sensor. The emotional user model contains nine emotions including the neutral one. The proposed recognition algorithm uses local movements detection within the face area in order to recognize actual facial expression. This approach has been validated on Facial Expressions and Emotions Database...
-
Wind Turbines Modeling as the Tool for Developing Algorithms of Processing their Video Recordings
PublicationIn 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
PublicationAs 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
PublicationThis 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...
-
Wind Turbines Modeling as the Tool for Developing Algorithms of Processing their Video Recordings
PublicationIn 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...
-
Positron collisions with molecular hydrogen: cross sections and annihilation parameters calculated using theR-matrix with pseudo-states method
PublicationThe 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...
-
Selection of excitation signals for high-impedance spectroscopy
PublicationA 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
PublicationIn 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,...
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublicationIn 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...
-
ADAPTIVE BACKSTEPPING TRACKING CONTROL FOR OVER-ACTUATED DP MARINE VESSEL WITH INERTIA UNCERTAINTIES
PublicationDesigning a tracking control system for an over-actuated dynamic positioning marine vessel in the case of insufficient information on environmental disturbances, hydrodynamic damping, Coriolis forces and vessel inertia characteristics is considered. The designed adaptive MIMO backstepping control law with control allocation is based on Lyapunov control theory for cascaded systems to guarantee stabilization of the marine vessel...