Wyszukiwarka
Wyniki wyszukiwania dla: MAGNETIC SIGNATURES, MEASUREMENT DEPTH, MODELING, NEURAL NETWORKS
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublikacjaGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Detection of the First Component of the Received LTE Signal in the OTDoA Method
PublikacjaIn a modern world there is a growing demand for localization services of various kinds. Position estimation can be realized via cellular networks, especially in the currently widely deployed LTE (Long Term Evolution) networks. However, it is not an easy task in harsh propagation conditions which often occur in dense urban environments. Recently, time-methods of terminal localization within the network have been the focus of attention,...
-
Influence of Natural Conditions on the Imaging of the Bottom of the Gdańsk Bay by Means of the Side Scan Sonar
PublikacjaThe interest in underwater resources is the reason for the development of modern hydroacoustic systems, including side sonars, which find numerous applications such as: research of seabed morphology and sediment characteristics, preparation of sea sediment maps, and even in special cases of biocenoses such as sea grass meadows, detection of specific targets at the bottom such as shipwrecks, mines, identification of suitable sites...
-
Playback detection using machine learning with spectrogram features approach
PublikacjaThis paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect...
-
MobileNet family tailored for Raspberry Pi
PublikacjaWith the advances in systems-on-a-chip technologies, there is a growing demand to deploy intelligent vision systems on low-cost microcomputers. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity of contemporary convolutional neural networks (CNNs). The state-of-the-art lightweight CNN is MobileNetV3. However, it was designed to achieve a good trade-off between...
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublikacjaIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
How to Sort Them? A Network for LEGO Bricks Classification
PublikacjaLEGO bricks are highly popular due to the ability to build almost any type of creation. This is possible thanks to availability of multiple shapes and colors of the bricks. For the smooth build process the bricks need to properly sorted and arranged. In our work we aim at creating an automated LEGO bricks sorter. With over 3700 different LEGO parts bricks classification has to be done with deep neural networks. The question arises...
-
A Miniaturized and High Optically Transparent Frequency Selective Surface for RF Shielding using Double-Glazed Glass Windows for Green Building Applications
PublikacjaThis research presents a miniaturized and high optically transparent (OT) frequency selective surface (FSS) for achieving RF shielding through glass window panels. The proposed FSS consists of a single-layered copper pattern sandwiched between two ordinary glass substrates to suppress the dual bands of sub-6 fifth generation (5G). In particular, the design effectively shields n65-downlink (2.1 GHz) and a portion of n78-band (3.5...
-
Analysis of the possibilities in railways shape assessing using GNSS mobile measurements
PublikacjaIn recent years, a dynamic development of satellite positioning techniques using both static and mobile GNSS coordinates register mode can be observed. In addition, still developing Real-time GNSS Networks, post-processing algorithms and another measurement signal analysis algorithms, make the satellite measurements increasingly used in railway industry sector. In the article the possibilities which follows from the mobile satellite...
-
Dynamic Signal Strength Mapping and Analysis by Means of Mobile Geographic Information System
PublikacjaBluetooth beacons are becoming increasingly popular for various applications such as marketing or indoor navigation. However, designing a proper beacon installation requires knowledge of the possible sources of interference in the target environment. While theoretically beacon signal strength should decay linearly with log distance, on-site measurements usually reveal that noise from objects such as Wi-Fi networks operating in...
-
System Loss Model for Body Area Networks in Room Scenarios
PublikacjaThis paper presents an analysis of system loss in Body Area Networks for room scenarios, based on a wideband measurement campaign at 5.8 GHz. The measurements were performed with a fixed antenna transmitting vertically and horizontally polarised signals, while the user wears dualpolarised antennas. The average system losses in co- and crosspolarised channels are 41.4 and 42.6 dB for vertically polarised transmitted signals and...
-
BETWEEN IDEA AND INTERPRETATION - DESIGN PROCESS AUGMENTATION
PublikacjaThe following paper investigates the idea of reducing the human digital intervention to a minimum during the advanced design process. Augmenting the outcome attributes beyond the designer's capabilities by computational design methods, data collection, data computing and digital fabrication, altogether imitating the human design process. The primary technical goal of the research was verification of restrictions and abilities used...
-
Prediction of maximum tensile stress in plain-weave composite laminates with interacting holes via stacked machine learning algorithms: A comparative study
PublikacjaPlain weave composite is a long-lasting type of fabric composite that is stable enough when being handled. Open-hole composites have been widely used in industry, though they have weak structural performance and complex design processes. An extensive number of material/geometry parameters have been utilized for designing these composites, thereby an efficient computational tool is essential for that purpose. Different Machine Learning...
-
An Off-Body Channel Model for Body Area Networks in Indoor Environments
PublikacjaThis paper presents an off-body channel model for body area networks (BANs) in indoor environments. The proposed model, which is based on both simulations and measurements in a realistic environment, consists of three components: mean path loss, body shadowing, and multipath fading. Seven scenarios in a realistic indoor office environment containing typical scatterers have been measured: five were static (three standing and two...
-
ReFlexeNN - the Wearable EMG Interface with Neural Network Based Gesture Classification
PublikacjaThe electromyographic activity of muscles was measured using a wireless biofeedback device. The aim of the study was to examine the possibility of creating an automatic muscle tension classifier. Several measurement series were conducted and the participant performed simple physical exercises - forcing the muscle to increase its activity accordingly to the selected scale. A small wireless device was attached to the electrodes placed...
-
Prediction of the Biogenic Amines Index of Poultry Meat Using an Electronic Nose
PublikacjaThe biogenic amines index of fresh chicken meat samples during refrigerated storage was predicted based on the headspace analysis using an electronic nose equipped with an array of electrochemical sensors. The reference biogenic amines index values were obtained using dispersive liquid–liquid microextraction–gas chromatography–mass spectrometry. A prototype electronic nose with modular construction and a dedicated sample chamber...
-
A comparative analysis of the effectiveness of corporate bankruptcy prediction models based on financial ratios: Evidence from Colombia, 2008 to 2015
PublikacjaLogit and discriminant analyses have been used for corporate bankruptcy prediction in several studies since the last century. In recent years there have been dozens of studies comparing the several models available, including the ones mentioned above and also probit, artificial neural networks, support vector machines, among others. For the first time for Colombia, this paper presents a comparative analysis of the effectiveness...
-
Performance Analysis of the OpenCL Environment on Mobile Platforms
PublikacjaToday’s smartphones have more and more features that so far were only assigned to personal computers. Every year these devices are composed of better and more efficient components. Everything indicates that modern smartphones are replacing ordinary computers in various activities. High computing power is required for tasks such as image processing, speech recognition and object detection. This paper analyses the performance of...
-
Automatic Emotion Recognition in Children with Autism: A Systematic Literature Review
PublikacjaThe automatic emotion recognition domain brings new methods and technologies that might be used to enhance therapy of children with autism. The paper aims at the exploration of methods and tools used to recognize emotions in children. It presents a literature review study that was performed using a systematic approach and PRISMA methodology for reporting quantitative and qualitative results. Diverse observation channels and modalities...
-
Rapid Surrogate-Aided Multi-Criterial Optimization of Compact Microwave Passives Employing Machine Learning and ANNs
PublikacjaThis article introduces an innovative method for achieving low-cost and reliable multi-objective optimization (MO) of microwave passive circuits. The technique capitalizes on the attributes of surrogate models, specifically artificial neural networks (ANNs), and multi-resolution electromagnetic (EM) analysis. We integrate the search process into a machine learning (ML) framework, where each iteration produces multiple infill points...
-
Magnetic superhydrophobic melamine sponges for crude oil removal from water
PublikacjaThis paper proposes the preparation of a new sorbent material based on melamine sponges (MS) with superhydrophobic, superoleophilic, and magnetic properties. This study involved impregnating the surface of commercially available MS with eco-friendly deep eutectic solvents (DES) and Fe3O4 nanoparticles. The DES selection was based on the screening of 105 eutectic mixtures using COSMO-RS modeling. Other parameters affecting the efficiency...
-
A fast procedure of stress state evaluation in magnetically anisotropic steels with the help of a probe with adjustable magnetizing field direction
PublikacjaThe paper presents a novel approach to the stress state evaluation issue. It deals with a strongly (magnetically) anisotropic materials for which a direct interpretation of the Barkhausen effect (BE) intensity would lead to erroneous results. In such a case one has to take into account both the measured BE intensity and the orientation of the magnetisation direction relative to the magnetic easy axis. For the in plane stress distribution...
-
Modeling the impact of rotor movement on non-linearity of motor currents waveforms in high-speed PMSM drives
PublikacjaMotor current measurement techniques as well as predictive control algorithms for electric drives rely on an assumption of linear motor currents changes resulting from constant inverter output voltages. Recent research has reported that this assumption does not hold in motors with short electrical time constant, and in drives whose rotor position advances substantially during a control period. This paper proposes a simulation model...
-
Combining Road Network Data from OpenStreetMap with an Authoritative Database
PublikacjaComputer modeling of road networks requires detailed and up-to-date dataset. This paper proposes a method of combining authoritative databases with OpenStreetMap (OSM) system. The complete route is established by finding paths in the graph constructed from partial data obtained from OSM. In order to correlate data from both sources, a method of coordinate conversion is proposed. The algorithm queries road data from OSM and provides...
-
Dynamics of fault arc traveling along busbars in high voltage switchboards = Dynamika łuku zwarciowego przemieszczającego się wzdłuż szyn rozdziel-nic wysokiego napięcia
PublikacjaThe paper presents the results of magnetic induction and electrodynamic force calculations acting on arc column during short-circuit in medium voltage air-insulated bus-bars. The gap between the bars was 120 mm and the prospective short-circuit currents ranged from 4 kA to 8 kA. The paper also shows the measurement results of average velocity fault arc depending on currents arc diameter and arc current was established and described....
-
Improvement of opipramol base solubility by complexation with β-cyclodextrin
PublikacjaOpipramol (OPI), a tricyclic antidepressant and anxiolytic compound, is administered orally in the form of a dihydrochloride. Salt form of the drug has a higher solubility in water and hence bioavailability and stability. A similar effect can be achieved by closing the hydrophobic part of the drug molecule in the cyclodextrin cavity. The paper presents opipramol inclusion complexes with beta-cyclodextrin (β-CD) in 1:1 molar ratio....
-
Novel MNZ-type microwave sensor for testing magnetodielectric materials
PublikacjaA novel microwave sensor with the mu-near-zero (MNZ) property is proposed for testing magnetodielectric material at 4.5 GHz. The sensor has a double-layer design consisting of a microstrip line and a metal strip with vias on layers 1 and 2, respectively. The proposed sensor can detect a unit change in relative permittivity and relative permeability with a difference in the operating frequency of 45 MHz and 78 MHz, respectively....
-
Experimental study on ice drift under the wind effect
PublikacjaThis study aims at wind and free ice drift interaction, which is an important aspect in sea ice, and low flow inland waters. Ice drift is caused by dynamic balance of water drag, gravitational acceleration, resistance force and wind drag. To have a clear point of view on wind to ice interaction, the external forces for this experimental study were limited to wind effect. The experiments were conducted in the Institute of Hydro-Engineering...
-
High Frequency Conducted Emission in AC Motor Drives Fed By Frequency Converters: Sources and Propagation Paths
PublikacjaProvides a concise and thorough reference for designing electrical and electronic systems that employ adjustable speed drives Electrical and electronic systems that employ adjustable speed drives are being increasingly used in present-day automation applications. They are considered by many application engineers as one of the most interfering components, especially in a contemporarily faced industrial environment. This book fills...
-
QUASI-DISTRIBUTED NETWORK OF LOW-COHERENCE FIBER-OPTIC FABRY-PÉROT SENSORS WITH CAVITY LENGTH-BASED ADDRESSING
PublikacjaDistributed measurement often relies on sensor networks. In this paper, we present the construction of low coherent fiber-optic Fabry-Pérot sensors connected into a quasi-distributed network. We discuss the mechanism of spectrum modulation in this type of sensor and the constraints of assembly of such sensors in the network. Particular attention was paid to separate the signals from individual sensors, which can be achieved by...
-
Predicting Ice Phenomena in a River Using the Artificial Neural Network and Extreme Gradient Boosting
PublikacjaForecasting ice phenomena in river systems is of great importance because these phenomena are a fundamental part of the hydrological regime. Due to the stochasticity of ice phenomena, their prediction is a difficult process, especially when data sets are sparse or incomplete. In this study, two machine learning models—Multilayer Perceptron Neural Network (MLPNN) and Extreme Gradient Boosting (XGBoost)—were developed to predict...
-
Zaawansowane Metody Pomiarowe i Diagnostyczne 2022/2023
Kursy Online{mlang en} 1. Introduction/Guide for the use of the International System of Units2. Rules and style conventions for expressing values of quantities.3. The role of measurement uncertainty in conformity assessment. 4. Probabilistic model for measurement processes, estimation theory5. Analog-digital conversion methods6. Selected structures of classical analog-digital converters7. New techniques of analog-digital conversion: sigma-delta...
-
Zaawansowane Metody Pomiarowe i Diagnostyczne 2023/2024
Kursy Online{mlang en} 1. Introduction/Guide for the use of the International System of Units2. Rules and style conventions for expressing values of quantities.3. The role of measurement uncertainty in conformity assessment. 4. Probabilistic model for measurement processes, estimation theory5. Analog-digital conversion methods6. Selected structures of classical analog-digital converters7. New techniques of analog-digital conversion: sigma-delta...
-
Zaawansowane Metody Pomiarowe i Diagnostyczne 2024/2025
Kursy Online{mlang en} 1. Introduction/Guide for the use of the International System of Units2. Rules and style conventions for expressing values of quantities.3. The role of measurement uncertainty in conformity assessment. 4. Probabilistic model for measurement processes, estimation theory5. Analog-digital conversion methods6. Selected structures of classical analog-digital converters7. New techniques of analog-digital conversion: sigma-delta...
-
THE 3D MODEL OF WATER SUPPLY NETWORK WITH APPLICATION OF THE ELEVATION DATA
Publikacja3D visualization is a key element of research and analysis and as the source used by experts in various fields e.g.: experts from water and sewage systems. The aim of this study was to visualize in three-dimensional space model of water supply network with relief. The path of technological development of GESUT data (Geodezyjna Ewidencja Sieci Uzbrojenia Terenu – geodetic records of public utilities) for water supply and measurement...
-
The Influence of Selecting Regions from Endoscopic Video Frames on The Efficiency of Large Bowel Disease Recognition Algorithms
PublikacjaThe article presents our research in the field of the automatic diagnosis of large intestine diseases on endoscopic video. It focuses on the methods of selecting regions of interest from endoscopic video frames for further analysis by specialized disease recognition algorithms. Four methods of selecting regions of interest have been discussed: a. trivial, b. with the deletion of characteristic, endoscope specific additions to the...
-
Online sound restoration system for digital library applications
PublikacjaAudio signal processing algorithms were introduced to the new online non-commercial service for audio restoration intended to enhance the content of digitized audio repositories. Missing or distorted audio samples are predicted using neural networks and a specific implementation of the Jannsen interpolation method based on the autoregressive model (AR) combined with the iterative restoring of missing signal samples. Since the distortion...
-
Computed aided system for separation and classification of the abnormal erythrocytes in human blood
PublikacjaThe human peripheral blood consists of cells (red cells, white cells, and platelets) suspended in plasma. In the following research the team assessed an influence of nanodiamond particles on blood elements over various periods of time. The material used in the study consisted of samples taken from ten healthy humans of various age, different blood types and both sexes. The markings were leaded by adding to the blood unmodified...
-
Data governance: Organizing data for trustworthy Artificial Intelligence
PublikacjaThe rise of Big, Open and Linked Data (BOLD) enables Big Data Algorithmic Systems (BDAS) which are often based on machine learning, neural networks and other forms of Artificial Intelligence (AI). As such systems are increasingly requested to make decisions that are consequential to individuals, communities and society at large, their failures cannot be tolerated, and they are subject to stringent regulatory and ethical requirements....
-
A new multi-process collaborative architecture for time series classification
PublikacjaTime series classification (TSC) is the problem of categorizing time series data by using machine learning techniques. Its applications vary from cybersecurity and health care to remote sensing and human activity recognition. In this paper, we propose a novel multi-process collaborative architecture for TSC. The propositioned method amalgamates multi-head convolutional neural networks and capsule mechanism. In addition to the discovery...
-
Utilising AI Models to Analyse the Relationship between Battlefield Developments in the Russian-Ukrainian War and Fluctuations in Stock Market Values
PublikacjaThis study examines the impact of battlefield developments in the ongoing Russian–Ukrainian war, which to date has lasted over 1000 days, on the stock prices of defence corporations such as BAE Systems, Booz Allen Hamilton, Huntington Ingalls, and Rheinmetall AG. Stock prices were analysed alongside sentiment data extracted from news articles, and processed using machine learning models leveraging natural...
-
Implementation of Time-Averaged Restraints with UNRES Coarse-Grained Model of Polypeptide Chains
PublikacjaTime-averaged restraints from nuclear magnetic resonance (NMR) measurements have been implemented in the UNRES coarse-grained model of polypeptide chains in order to develop a tool for data-assisted modeling of the conformational ensembles of multistate proteins, intrinsically disordered proteins (IDPs) and proteins with intrinsically disordered regions (IDRs), many of which are essential in cell biology. A numerically stable variant...
-
Modeling the Effects of Slowly Biodegradable Substrate at Large WWTP in Northern Poland
PublikacjaThe essential study was divided into two parts: experimental investigation and mathematical modeling using special platform to computer simulations. In the first part of research an innovative measurement procedure for an indirect determination of the effect of biodegradable particulate and colloidal Xs substrate was developed and implemented. The results of laboratory tests were used futher to verify the mechanism of the hydrolysis...
-
An Example of Using Low-Cost LiDAR Technology for 3D Modeling and Assessment of Degradation of Heritage Structures and Buildings
PublikacjaThis article examines the potential of low-cost LiDAR technology for 3D modeling and assessment of the degradation of historic buildings, using a section of the Koszalin city walls in Poland as a case study. Traditional terrestrial laser scanning (TLS) offers high accuracy but is expensive. The study assessed whether more accessible LiDAR options, such as those integrated with mobile devices such as the Apple iPad Pro, can serve...
-
Open extensive IoT research and measurement infrastructure for remote collection and automatic analysis of environmental data.
PublikacjaInternet of Things devices that send small amounts of data do not need high bit rates as it is the range that is more crucial for them. The use of popular, unlicensed 2.4 GHz and 5 GHz bands is fairly legally enforced (transmission power above power limits cannot be increased). In addition, waves of this length are very diffiult to propagate under field conditions (e.g. in urban areas). The market response to these needs are the...
-
Diagnostyka łożysk silnika indukcyjnego na podstawie prądu zasilającego przy użyciu sztucznych sieci neuronowych
PublikacjaW artykule zawarto wyniki badań dotyczące diagnostyki łożysk silnika indukcyjnego na podstawie pomiarów prądu zasilającego z wyko-rzystaniem sztucznych sieci neuronowych. Zaprezentowano wyniki uczenia sieci oraz rezultaty testów przeprowadzonych na danych spoza zbioru uczącego. Badania wykonane zostały na obiektach z celowo wprowadzonymi uszkodzeniami łożysk. Przedstawiona nowa koncepcja zakłada użycie zestawu sieci neuronowych...
-
Prognozowanie wpływu drgań komunikacyjnych na budynki mieszkalne za pomocą sztucznych sieci neuronowych i maszyn wektorów wspierających
PublikacjaDrgania komunikacyjne mogą stanowić duże obciążenie eksploatacyjne budynku, powodując zarysowania i spękania tynków, odpadanie wypraw, zarysowania konstrukcji, pękanie elementów konstrukcji lub nawet zawalenie się budynku. Pomiary drgań na rzeczywistych konstrukcjach są pracochłonne i kosztowne, a co ważne nie w każdym przypadku są one uzasadnione. Celem pracy jest analiza autorskiego algorytmu, dzięki któremu z dużym prawdopodobieństwem...
-
New method to monitor changes in the subarachnoid width and pial artery pulsation for physiological and clinical research
PublikacjaThere are several medical conditions associated with brain oedema such as traumatic brain injury, intoxication or tumors. Brain edema and related brain parenchyma expansion may lead to compression and subsequent injury of several brain structures. So far, the only method enabling detection and monitoring of the progress a cerebral oedema in a patient, has been monitoring of intracranial pressure (ICP) with a pressure probe inserted...
-
Pt-rich intermetallic APt8P2 (A = Ca and La)
PublikacjaThe combination of experimental and theoretical investigation of two new Pt-rich intermetallic compounds: APt8P2 (A = Ca and La) is presented, including solid-state synthesis, crystal structure determination, physical properties characterization and chemical bonding analysis. APt8P2 was obtained through the high-temperature pellet synthesis. According to both single crystal and powder X-ray diffraction results, APt8P2 crystallize...
-
Risk Assessment at Unsignalized Intersections Based on Human-Road-Environment-Vehicle System Applying Fuzzy Logic
PublikacjaThe constant increase in motorization level and traffic density increases risks due to dangerous situations for road participants. Therefore, assessing the accident level of road network elements has been an urgent task over the past decades. However, existing approaches mainly rely on traffic flow parameters and account for dynamic vehicle characteristics. The research aims to design a model accounting for uncertain factors (weather...