Filters
total: 2574
filtered: 2097
-
Catalog
- Publications 2097 available results
- Journals 57 available results
- Conferences 40 available results
- Publishing Houses 1 available results
- People 67 available results
- Projects 5 available results
- e-Learning Courses 15 available results
- Events 3 available results
- Open Research Data 289 available results
Chosen catalog filters
displaying 1000 best results Help
Search results for: RESIDUAL NEURAL NETWORK
-
Heavy duty vehicle fuel consumption modelling using artificial neural networks
PublicationIn this paper an artificial neural network (ANN) approach to modelling fuel consumption of heavy duty vehicles is presented. The proposed method uses easy accessible data collected via CAN bus of the truck. As a benchmark a conventional method, which is based on polynomial regression model, is used. The fuel consumption is measured in two different tests, performed by using a unique test bench to apply the load to the engine. Firstly,...
-
Thermal and Electrodynamic Risk of Residual Current Devices in the Case of Back-Up Protection by Overcurrent Circuit Breakers
PublicationResidual current operated circuit breakers without integral overcurrent protection should be back-up protected. As back-up protection devices, overcurrent circuit breakers are used. The maximum let-through energy and let-through current of the overcurrent devices were evaluated under laboratory conditions. The thermal and electrodynamic risk of residual current devices was analyzed.
-
Analysis of Residual Stresses and Dislocation Density of AA6082 Butt Welds Produced by Friction Sir Welding
PublicationThe Friction Stir Welding (FSW) method was employed to join AA6082 sheets. The welds were produced with different tool traverse speed (200 and 250 mm/min), rotational speed (1000 and 1250 RPM) and tool tilt angle (0 and 2 deg). Based on the analysis of XRD patterns, the total precipitation volume fractions in the nugget zones and the base material were calculated. The FSW process resulted in a reduction in the fraction of precipitates...
-
Electrical safety in low-voltage DC microgrids with B-type residual current devices
PublicationResidual current devices (RCDs) are most popular devices used in low-voltage installations for protection against electric shock and fire. In cases of high risk of electric shock the application of RCDs is mandatory. Currently, the spread of local direct current (DC) microgrids is widely considered. This creates new challenges for protective systems, in particular those based on RCDs. The main purpose of the research is to test...
-
Deep neural networks for human pose estimation from a very low resolution depth image
PublicationThe work presented in the paper is dedicated to determining and evaluating the most efficient neural network architecture applied as a multiple regression network localizing human body joints in 3D space based on a single low resolution depth image. The main challenge was to deal with a noisy and coarse representation of the human body, as observed by a depth sensor from a large distance, and to achieve high localization precision....
-
Blood Pressure Estimation Based on Blood Flow, ECG and Respiratory Signals Using Recurrent Neural Networks
PublicationThe estimation of systolic and diastolic blood pressure using artificial neural network is considered in the paper. The blood pressure values are estimated using pulse arrival time, and additionally RR intervals of ECG signal together with respiration signal. A single layer recurrent neural network with hyperbolic tangent activation function was used. The average blood pressure estimation error for the data obtained from 21 subjects...
-
Architectural Modifications to Enhance Steganalysis with Convolutional Neural Networks
PublicationThis paper investigates the impact of various modifications introduced to current state-of-the-art Convolutional Neural Network (CNN) architectures specifically designed for the steganalysis of digital images. Usage of deep learning methods has consistently demonstrated improved results in this field over the past few years, primarily due to the development of newer architectures with higher classification accuracy compared to...
-
System for monitoring road slippery based on CCTV cameras and convolutional neural networks
PublicationThe slipperiness of the surface is essential for road safety. The growing number of CCTV cameras opens the possibility of using them to automatically detect the slippery surface and inform road users about it. This paper presents a system of developed intelligent road signs, including a detector based on convolutional neural networks (CNNs) and the transferlearning method employed to the processing of images acquired with video...
-
OBTAINING FLUID FLOW PATTERN FOR TURBINE STAGE WITH NEURAL MODEL.
PublicationIn 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...
-
Failure of cold-formed beam: How does residual stress affect stability?
PublicationIn machine industry, stresses are often calculated using simple linear FEM analysis. Occasional failures of elements designed in such a way require recomputation by means of more sophisticated methods, eg. including plasticity and non-linear effects. It usually leads to investigation of failure causes and improvement of an element in order to prevent its unwanted behavior in the future. The study presents the case where both linear...
-
Discussion of Derivability of Local Residual Stress Level from Magnetic Stray Field Measurement
PublicationThe NDT procedure dubbed ‘metal magnetic memory’ method and the related ISO 24497 standard has found wide industrial acceptance in some countries, mainly in Russia and China. The method has been claimed by some researchers (Roskosz and Bieniek in NDT&E Int 45:55–62, 2012; Wilson et al. in Sens Actuators A 135:381–387, 2007) as having potential for quantitative determination of local residual stress state in engineering structures,...
-
Predicting the impact of traffic–induced vibrations on buildings using artificial neural networks
PublicationTraffic–induced vibrations may constitute a considerable load to a building, cause cracking of plaster, cracks in load–bearing elements or even a global structural collapse of the whole structure [1-4]. Vibrations measurements of real structures are costly and laborious, not justified in all cases. The aim of the paper is to create an original algorithm, to predict the negative dynamic impact on the examined residential building...
-
Collision-Free Network Exploration
PublicationA set of mobile agents is placed at different nodes of a n-node network. The agents synchronously move along the network edges in a collision-free way, i.e., in no round may two agents occupy the same node. In each round, an agent may choose to stay at its currently occupied node or to move to one of its neighbors. An agent has no knowledge of the number and initial positions of other agents. We are looking for the shortest possible...
-
Collision-free network exploration
PublicationMobile agents start at different nodes of an n-node network. The agents synchronously move along the network edges in a collision-free way, i.e., in no round two agents may occupy the same node. An agent has no knowledge of the number and initial positions of other agents. We are looking for the shortest time required to reach a configuration in which each agent has visited all nodes and returned to its starting location. In...
-
Bees Detection on Images: Study of Different Color Models for Neural Networks
PublicationThis paper presents an approach to bee detection in video streams using a neural network classifier. We describe the motivation for our research and the methodology of data acquisition. The main contribution to this work is a comparison of different color models used as an input format for a feedforward convolutional architecture applied to bee detection. The detection process has is based on a neural binary classifier that classifies...
-
Analytical procedures for quality control of pharmaceuticals in terms of residual solvents content: Challenges and recent developments
PublicationResidual solvents play an important role in the synthesis of drugs and in product formulations. In addition, they pose a serious problem, that is toxicity, as many of them exhibit toxic or environmentally hazardous properties. Therefore, constant monitoring of quality control is needed. In this study, we present an overview of regulatory and general methods described by various pharmacopoeias. Then, the most commonly used methodologies...
-
Adding Intelligence to Cars Using the Neural Knowledge DNA
PublicationIn this paper we propose a Neural Knowledge DNA based framework that is capable of learning from the car’s daily operation. The Neural Knowledge DNA is a novel knowledge representation and reasoning approach designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing devices. We examine our framework for drivers' classification based on their driving behaviour. The experimental...
-
EMULACJA ŚRODOWISKA DLA ZASTOSOWANIA PROTOKOŁU IN-BAND NETWORK TELEMETRY
PublicationOkreślenie jakości obsługi strumieni pakietów w sieci przełączników wymaga odpowiedniego środowiska badawczego w którym prowadzi się doświadczenia i pomiary wybranych wielkości. Protokół In-band Network Telemetry jest jednym z narzędzi, które można wykorzystać do realizacji tych zadań. W pracy zaproponowano zwirtualizowane środowisko badawcze w którym można emulować sieć przełączników programowalnych w języku P4 wraz z implementacją...
-
Toward Intelligent Recommendations Using the Neural Knowledge DNA
PublicationIn this paper we propose a novel recommendation approach using past news click data and the Neural Knowledge DNA (NK-DNA). The Neural Knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for news recommendation tasks on the MIND benchmark dataset. By taking advantages of NK-DNA, deep...
-
Diagnosis of damages in family buildings using neural networks
PublicationThe article concerns a problem of damages in family buildings, which result from traffic-induced vibrations. These vibrations arise from various causes and their size is influenced by many factors. The most important is the type of a road, type and weight of vehicles that run on the road, type and condition of the road surface, the distance from the house to the source of vibrations and many others which should be taken into account....
-
Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
PublicationNumerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending...
-
Residual stress evaluation in oil pipeline.
PublicationPrzedstawiono metodę pomiaru rozkładu naprężeń w ropociągu z wykorzystaniem efektu Barkhausena. Opisano procedurę pomiaru oraz kalibracji metody. Wynik potwierdzono w jednym punkcie metodą Mathar´a
-
Application 2D Descriptors and Artificial Neural Networks for Beta-Glucosidase Inhibitors Screening
PublicationBeta-glucosidase inhibitors play important medical and biological roles. In this study, simple two-variable artificial neural network (ANN) classification models were developed for beta-glucosidase inhibitors screening. All bioassay data were obtained from the ChEMBL database. The classifiers were generated using 2D molecular descriptors and the data miner tool available in the STATISTICA package (STATISTICA Automated Neural...
-
Corrigendum to “An investigation on residual stress and fatigue life assessment of T-shape welded joints” [Eng. Fail. Anal. 141 (2022) 106685]
PublicationThis paper aims to quantitatively evaluate the residual stress and fatigue life of T-type welded joints with a multi-pass weld in different direction. The main research objectives of the experimental test were to test the residual stress by changing direction along with multiple wielding passes and determine the fatigue life of the welded joints. The result shows that compressive residual stress increases in the sample gradually...
-
Advanced numerical modelling for predicting residual compressive strength of corroded stiffened plates
PublicationAn advanced methodology for predicting the residual compressive strength of corroded stiffened plates is developed here using the non-linear finite element method. The non-uniform loss of a plate thickness is accounted for on a macro-scale. In contrast, mechanical properties are changed using the constitutive model to reflect the corrosion degradation impact on a micro-scale. Three different stiffened plate thicknesses are considered,...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
Tripping of F-type RCDs for sinusoidal residual current with superimposed smooth DC component
PublicationRecent trends in green energy development make that photovoltaics and electric vehicles are applied on an increasing scale. In both photovoltaic and electric vehicle charging installations, a significant value of DC component of the earth fault current may appear, which is a challenge, in particular, for commonly used residual current devices (RCDs). This paper presents results of the laboratory test on the operation of F-type...
-
Performance of Vector-valued Intensity Measures for Estimating Residual Drift of Steel MRFs with Viscous Dampers
PublicationViscous Dampers (VDs) are widely used as passive energy dissipation system for improving seismic performance levels especially in retrofitting of buildings. Residual Inter-story Drift Ratio (R-IDR) is another important factor that specifies the condition of building after earthquake. The values of R-IDR illustrates the possibility of retrofitting and repairing of a building. Therefore, this study aims to explore the vector-valued...
-
Application tool for IP QoS network design
PublicationDespite the fact that differentiated-service-aware network implementation has been a widely discussed topic for quite some time, network design still proofs nontrivial. Well developed software could put an end to network designer's problems. This chapter describes work, which has been aimed at creating a comprehensive network design tool, offering a fair range of functionality and high reliability. The presented tool is able to...
-
Progress in the post weld residual stress evaluation using Barkhausen effect meter with a novel rotating magnetic field probe
PublicationWe report the progress in post weld residual stress evaluation using Barkhausen effect (BE) meter with rotating magnetic field probe. The novel probe of the BE meter contains two C-core electromagnets and searching coil with ferrite antenna. This meter allows automatic measurements of BE intensity envelopes at different angles of magnetizing field. The full process of measurement at given position of the probe takes about only...
-
Testing sensitivity of A-type residual current devices to earth fault currents with harmonics
PublicationIn many applications, modern current-using equipment utilizes power electronic converters to control the consumed power and to adjust the motor speed. Such equipment is used both in industrial and domestic installations. A characteristic feature of the converters is producing distorted earth fault currents, which contain a wide spectrum of harmonics, including high-order harmonics. Nowadays, protection against electric shock in...
-
Towards bees detection on images: study of different color models for neural networks
PublicationThis paper presents an approach to bee detection in videostreams using a neural network classifier. We describe the motivationfor our research and the methodology of data acquisition. The maincontribution to this work is a comparison of different color models usedas an input format for a feedforward convolutional architecture appliedto bee detection. The detection process has is based on a neural...
-
How to Sort Them? A Network for LEGO Bricks Classification
PublicationLEGO 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...
-
Artificial Neural Networks as an architectural design tool- generating new detail forms based on the Roman Corinthian order capital
PublicationThe following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital....
-
Efficient uncertainty quantification using sequential sampling-based neural networks
PublicationUncertainty quantification (UQ) of an engineered system involves the identification of uncertainties, modeling of the uncertainties, and the forward propagation of the uncertainties through a system analysis model. In this work, a novel surrogate-based forward propagation algorithm for UQ is proposed. The proposed algorithm is a new and unique extension of the recent efficient global optimization using neural network (NN)-based...
-
Constrained aerodynamic shape optimization using neural networks and sequential sampling
PublicationAerodynamic shape optimization (ASO) involves computational fluid dynamics (CFD)-based search for an optimal aerodynamic shape such as airfoils and wings. Gradient-based optimization (GBO) with adjoints can be used efficiently to solve ASO problems with many design variables, but problems with many constraints can still be challenging. The recently created efficient global optimization algorithm with neural network (NN)-based prediction...
-
Approximation of Fractional Order Dynamic Systems Using Elman, GRU and LSTM Neural Networks
PublicationIn the paper, authors explore the possibility of using the recurrent neural networks (RNN) - Elman, GRU and LSTM - for an approximation of the solution of the fractional-orders differential equations. The RNN network parameters are estimated via optimisation with the second order L-BFGS algorithm. It is done based on data from four systems: simple first and second fractional order LTI systems, a system of fractional-order point...
-
An Intelligent Approach to Short-Term Wind Power Prediction Using Deep Neural Networks
PublicationIn this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent...
-
Adjusted SpikeProp algorithm for recurrent spiking neural networks with LIF neurons
PublicationA problem related to the development of a supervised learning method for recurrent spiking neural networks is addressed in the paper. The widely used Leaky-Integrate-and-Fire model has been adopted as a spike neuron model. The proposed method is based on a known SpikeProp algorithm. In detail, the developed method enables gradient descent learning of recurrent or multi-layer feedforward spiking neural networks. The research included...
-
Software Agents for Computer Network Security
PublicationThe chapter presents applications of multi-agent technology for design and implementation of agent-based systems intended to cooperatively solve several critical tasks in the area of computer network security. These systems are Agent-based Generator of Computer Attacks (AGCA), Multi-agent Intrusion Detection and Protection System (MIDPS), Agent-based Environment for Simulation of DDoS Attacks and Defense (AESAD) and Mobile Agent...
-
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...
-
Direct electrical stimulation of the human brain has inverse effects on the theta and gamma neural activities
PublicationObjective: Our goal was to analyze the electrophysiological response to direct electrical stimulation (DES) systematically applied at a wide range of parameters and anatomical sites, with particular focus on neural activities associated with memory and cognition. Methods: We used a large set of intracranial EEG (iEEG) recordings with DES from 45 subjects with electrodes...
-
Model of control plane of ASON/GMPLS network
PublicationASON (Automatic Switched Optical Network) is a concept of optical network recommended in G.8080/Y.1304 by ITU-T. Control Plane of this network could be based on GMPLS (Generalized Multi-Protocol Label Switching) protocols. This solution, an ASON control plane built on GMPLS protocols is named ASON/GMPLS. In the paper, we decompose the control plane problem and show the main concepts of ASON network. We propose a hierarchical architecture...
-
Toward Intelligent Vehicle Intrusion Detection Using the Neural Knowledge DNA
PublicationIn this paper, we propose a novel intrusion detection approach using past driving experience and the neural knowledge DNA for in-vehicle information system security. The neural knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for classifying malicious vehicle control commands...
-
Simulator for Performance Evaluation of ASON/GMPLS Network
PublicationThe hierarchical control plane network architecture of Automatically Switched Optical Network with utilization of Generalized Multi-Protocol Label Switching protocols is compliant to next generation networks requirements and can supply connections with required quality of service, even with incomplete domain information. Considering connection control, connection management and network management, the controllers of this architecture...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublicationTo effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches...
-
Corrigendum to “Fatigue life improvement using low transformation temperature weld material with measurement of residual stress” [Int. J. Fatigue 164 (2022) 107137]
PublicationWelding processes often produce high levels of tensile residual stress. Low transformation temperature (LTT) welding wires utilise phase transformation strains to overcome the thermal contraction of a cooling weld. In this paper, the residual stress within each weld was quantified using the milling/strain gauge method, being the strain change measured as the weldment was milled away. The fatigue tests were conducted under uniaxial...
-
Performance Analysis of Convolutional Neural Networks on Embedded Systems
PublicationMachine learning is no longer confined to cloud and high-end server systems and has been successfully deployed on devices that are part of Internet of Things. This paper presents the analysis of performance of convolutional neural networks deployed on an ARM microcontroller. Inference time is measured for different core frequencies, with and without DSP instructions and disabled access to cache. Networks use both real-valued and...
-
An Analysis of Neural Word Representations for Wikipedia Articles Classification
PublicationOne of the current popular methods of generating word representations is an approach based on the analysis of large document collections with neural networks. It creates so-called word-embeddings that attempt to learn relationships between words and encode this information in the form of a low-dimensional vector. The goal of this paper is to examine the differences between the most popular embedding models and the typical bag-of-words...
-
Security level estimation as a function of residual risks
PublicationArtykuł przedstawia sposób oceny poziomu bezpieczeństwa organizacji IT w oparciu o metodę oceny ryzyka. Opisane są podstawowe kroki wspomnianej metody, proponowane rozwiązania i zastosowania. Zaproponowano prosty sposób oceny bezpieczeństwa systemów informatycznych organizacji w oparciu o wielkość wyznaczoną na podstawie wyliczonego ryzyka rezydualnego tychże systemów.