Filtry
wszystkich: 19970
wybranych: 13531
-
Katalog
- Publikacje 13531 wyników po odfiltrowaniu
- Czasopisma 264 wyników po odfiltrowaniu
- Konferencje 132 wyników po odfiltrowaniu
- Wydawnictwa 1 wyników po odfiltrowaniu
- Osoby 313 wyników po odfiltrowaniu
- Wynalazki 63 wyników po odfiltrowaniu
- Projekty 71 wyników po odfiltrowaniu
- Laboratoria 5 wyników po odfiltrowaniu
- Zespoły Badawcze 2 wyników po odfiltrowaniu
- Aparatura Badawcza 8 wyników po odfiltrowaniu
- Kursy Online 977 wyników po odfiltrowaniu
- Wydarzenia 37 wyników po odfiltrowaniu
- Dane Badawcze 4566 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: VEHICLE DETECTION, CONVOLUTIONAL NEURAL NETWORK, STYLE TRANSFER, DATA AUGMENTATION, TRAFFIC MONITORING SYSTEM
-
The contactless method of chip-to-chip high-speed data transmission monitoring
PublikacjaThis paper presents a technique of decoupling differential signals transmitted in a pair of microstrip lines on a printed circuit board (PCB), using dedicated coupler for high speed data transmission monitoring in chip-to-chip interconnections. The coupler used for signal probing is overlayed on the pair of microstrip lines under test, and provides a signal to the next blocks of the measurement system without disturbing transmission...
-
New Two-center Ellipsoidal Basis Function Neural Network for Fault Diagnosis of Analog Electronic Circuits
PublikacjaIn the paper a new fault diagnosis-oriented neural network and a diagnostic method for localization of parametric faults in Analog Electronic Circuits (AECs) with tolerances is presented. The method belongs to the class of dictionary Simulation Before Test (SBT) methods. It utilizes dictionary fault signatures as a family of identification curves dispersed around nominal positions by component tolerances of the Circuit Under Test...
-
Benchmarking Deep Neural Network Training Using Multi- and Many-Core Processors
PublikacjaIn the paper we provide thorough benchmarking of deep neural network (DNN) training on modern multi- and many-core Intel processors in order to assess performance differences for various deep learning as well as parallel computing parameters. We present performance of DNN training for Alexnet, Googlenet, Googlenet_v2 as well as Resnet_50 for various engines used by the deep learning framework, for various batch sizes. Furthermore,...
-
Remote command and control capabilities for data acquisition systems provided by delay-tolerant network mechanisms
PublikacjaThe paper presents an assessment of a remote device reconfiguration service employing a Delay Tolerant Network (DTN) mechanisms. This service has been implemented as a part of a communication appliance dedicated to marine data transfer in off-shore and open sea areas. The service has been successfully deployed and validation test have been completed. The practical use-case has been defined as remote access to the equipment operating...
-
Machine Learning and Text Analysis in an Artificial Intelligent System for the Training of Air Traffic Controllers
PublikacjaThis chapter presents the application of new information technology in education for the training of air traffic controllers (ATCs). Machine learning, multi-criteria decision analysis, and text analysis as the methods of artificial intelligence for ATCs training have been described. The authors have made an analysis of the International Civil Aviation Organization documents for modern principles of ATCs education. The prototype...
-
Neural network based control system architecture proposal for underwatership hull cleaning robot.
PublikacjaPrzedstawiono model matematyczny podwodnej głowicy roboczej, oraz określono metodę jej pozycjonowania i orientacji w lokalnym środowisku. Zaproponowano architekturę układu sterowania, opartego na bazie sieci neuronowych, za pomocą którego można sterować podwodnym robotem, przeznaczonym do czyszczenia burt statku.
-
Network-aware Data Prefetching Optimization of Computations in a Heterogeneous HPC Framework
PublikacjaRapid development of diverse computer architectures and hardware accelerators caused that designing parallel systems faces new problems resulting from their heterogeneity. Our implementation of a parallel system called KernelHive allows to efficiently run applications in a heterogeneous environment consisting of multiple collections of nodes with different types of computing devices. The execution engine of the system is open for...
-
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...
-
Neural networks and deep learning
PublikacjaIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
Experimental bases for the rail track surface damage detection system
PublikacjaA diagnosis of rail surface is generally based on the classical method of direct assessment and track geometry measurements. Identification and qualification of inequality and damage on the surface rails is depend on the skills and experience person who conducting inspection. In times of increasing exploitation of railways, infrastructure managers decide to use systems supporting the assessment of technical condition of the railways....
-
Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA data
Publikacja -
On Cointegration Analysis for Condition Monitoring and Fault Detection of Wind Turbines Using SCADA Data
Publikacja -
Comparative Evaluation of Multicoil Inductive Power Transfer Approaches Based on Z-source Network
PublikacjaThis paper describes comparative evaluation between wireless power transfer topologies with utilization of Z-source network. Paper describes components calculation method. List of open-loop, close-loop simulations were conducted to compare both topologies. Spectrum of signals is also researched.
-
Integrated multiscale 3d imaging geographic information system using acoustic data
PublikacjaW artykule zaprezentowano prototyp zintegrowanego systemu informacji geograficznej do trójwymiarowej wizualizacji danych uzyskanych metodami akustycznymi. System wykorzystuje dane pochodzące z systemów wielowiązkowych, sonarów bocznych oraz echosond jednowiązkowych. Otrzymane wyniki zostały zaprezentowane w postaci trójwymiarowych interaktywnych scen obszaru Zatoki Gdańskiej.
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublikacjaIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
Coastal zone monitoring using Sentinel-1 SAR polarymetry data
PublikacjaIn recent years the role of the surveillance and security of Polish boundaries has significantly increased. Polish coastal zone monitoring requires various approaches using various technological means in order to ensure the protection of Polish boundaries. In this paper, the authors discuss and present alternatives to underwater surveillance methods of coastal area analysis and monitoring using data retrieved from the newly developed...
-
Automatic detection of abandoned luggage employing a dual camera system
PublikacjaA system for automatic detection of events using a system of fixed and PTZ (pan-tilt-zoom) cameras is described. Images from the fixed camera are analyzed by means of object detection and tracking. Event detection system uses a set of rules to analyze data on the tracked moving objects and to detect defined events. A PTZ camera is used to obtain a detailed view of a selected object. A procedure for conversion between the pixel...
-
Multi-Camera Vehicle Tracking Using Local Image Features and Neural Networks
PublikacjaA method for tracking moving objects crossing fields of view of multiple cameras is presented. The algorithm utilizes Artificial Neural Networks (ANNs). Each ANN is trained to recognize images of one moving object acquired by a single camera. Local image features calculated in the vicinity of automatically detected interest points are used as object image parameters. Next, ANNs are employed to identify the same objects captured...
-
Analysing the impact of traffic incidents on express road traffic flow using FREEVAL
PublikacjaTraffic incidents occurring on motorways or express roads cause disruptions and deteriorate traffic conditions. The impact will differ depending on the type of incident, its duration and space blocked on the roadway and can be measured with e.g. average speed reduction, extension of travel time, time lost or overall costs of traffic disruptions. The aim of the paper is to analyse this impact, based on data from the Tri-City Ring...
-
The application of microscopic models in the study of pedestrian traffic
PublikacjaCities (especially in Central and Eastern Europe) focus on improving the road network, which aims to improve the efficiency of motor traffic and minimize congestion. Most of existing tools for analysing the effectiveness of urban transport networks do not assume to analyse the impact of walking and cycling on efficiency of transport systems. It is therefore necessary to develop solutions...
-
Fault detection in the marine engine using a support vector data description method
PublikacjaFast detection and correct diagnosis of any engine condition changes are essential elements of safety andenvironmental protection. Many diagnostic algorithms significantly improve the detection of malfunctions.Studies on diagnostic methods are rarely reported and even less implemented in the marine engine industry.To fill this gap, this paper presents the Support Vector Data Description (SVDD) method as applied to thefault detection...
-
Automatic labeling of traffic sound recordings using autoencoder-derived features
PublikacjaAn approach to detection of events occurring in road traffic using autoencoders is presented. Extensions of existing algorithms of acoustic road events detection employing Mel Frequency Cepstral Coefficients combined with classifiers based on k nearest neighbors, Support Vector Machines, and random forests are used. In our research, the acoustic signal gathered from the microphone placed near the road is split into frames and converted...
-
Design of Microstrip UWB Balun Using Quasi-TEM Approach Aided by the Artificial Neural Network
PublikacjaThe design procedure for UWB balun realized in the microstrip technology is proposed in the paper. The procedure applies Artificial Neural Network which corrects the dimensions of the approximate design found by appropriate scaling of the dimensions of the prototype. The scale coefficients for longitudinal and transverse dimensions of microstrip lines are determined from electromagnetic modeling based on transmission line equations....
-
Spectral Finite Element Method in Condition Monitoring and Damage Detection
PublikacjaIt is well known that the dynamic behaviour of engineering structures may carry very important and crucial information that can be further used for the assessment of their condition as well as detection of any damage induced. The current interest in monitoring techniques based on the propagation of guided elastic waves requires that numerical techniques used for modelling the phenomena associated must shift into the realm of high...
-
Design and Analysis of Artificial Neural Network (ANN) Models for Achieving Self-Sustainability in Sanitation
PublikacjaThe present study investigates the potential of using fecal ash as an adsorbent and demonstrates a self-sustaining, optimized approach for urea recovery from wastewater streams. Fecal ash was prepared by heating synthetic feces to 500 °C and then processing it as an adsorbent for urea adsorption from synthetic urine. Since this adsorption approach based on fecal ash is a promising alternative for wastewater treatment, it increases...
-
3D Machine Vision System for Inspection of Contact Strips in Railway Vehicle Current Collectors
PublikacjaConstruction and technical condition of current collectors is crucial to reliability and safety of railway transportation. According to the Technical Specifications for Interoperability railway vehicles in the European Union should be equipped with carbon contact strips. Excessive wear or defects of contact strips degrade the capability of undisturbed power transmission, cause faster wear of contact wire, and can even result in...
-
The system for remote monitoring of a vertical axis wind farm
PublikacjaThe article presents a system for remote monitoring of working parameters of a wind turbine with a vertical axis. The monitoring system was built using a Raspberry PI 3 microcomputer with the Raspbian operating system and a MicroDAQ E2000 measuring card. The developed system enables monitoring the power output of the generator, torque on the turbine shaft, turbine speed and wind speed. The values of the monitored parameters are...
-
Mutual Coupling Reduction in Antenna Arrays Using Artificial Intelligence Approach and Inverse Neural Network Surrogates
PublikacjaThis paper presents a novel approach to reduce undesirable coupling in antenna arrays using custom-designed resonators and inverse surrogate modeling. To illustrate the concept, two stand-ard patch antenna cells with 0.07λ edge-to-edge distance are designed and fabricated to operate at 2.45 GHz. A stepped-impedance resonator is applied between the antennas to suppress their mutual coupling. For the first time, the optimum values...
-
Integration of inertial sensors and GPS system data for underwater navigation
PublikacjaThe Inertial Navigation System (INS) is usually employed to determine the position of an underwater vehicles, like Remotely Operated Vehicles (ROV) and, more recently, Autonomous Underwater Vehicle (AUV). The accuracy of the position provided by the INS, which uses accelerometers and gyroscopes, deteriorates with time. An external aiding sources such as the Global Positioning System (GPS) can be employed to reduce the error growth...
-
System of monitoring of the Forest Opera in Sopot structure and roofing
PublikacjaThe authors present a solution realized in Forest Opera (name in Polish: Opera Leśna) in Sopot (Poland) in connection with the modernization and construction of a new roof. The complicated structure of the roof of the facility and the used covering in form of membrane made of technical fabric required (for security reasons) to install the unit of devices allowing for the continuous geodetic monitoring of the facility. Monitoring...
-
Implementation of Weigh-in-Motion System in Freight Traffic Management in Urban Areas
PublikacjaThe article presents how the Weigh-in-Motion system can be used for managing Gdynia’s freight traffic. Potential sites for weight pre-selection were identified in an analysis of the technical and location conditions. Situated directly in the east part of the Port of Gdynia a site was selected for a pilot implementation. Theoretical scenarios were simulated using an extended WIM system as a tool for controlling access to selected...
-
Automatic Detection and Monitoring of Cyanobacterial Blooms in the Context of the Marine Cadastre
PublikacjaIn the wake of the European and global spatial data infrastructures (SDI) it is important to build information systems which use and serve thematic data in compliance with the INSPIRE Directive. In the context of hydrographic data, the Directive requires EU member states to collect and share information on maritime areas divided into regions and sub-regions, as well as coastal zone management areas. These data are part of recently...
-
Radar data fusion in the STRADAR system
PublikacjaThe main task of the Polish Border Guard is protection of the country’s border which requires utilization of multimedia surveillance systems automatically gathering, processing and sharing various data. The paper presents such a system developed for the Maritime Division of the Polish Border Guard within the STRADAR project and the problem of fusion of radar data in this system. The system, apart from providing communication means,...
-
Deep Learning-Based Intrusion System for Vehicular Ad Hoc Networks
PublikacjaThe increasing use of the Internet with vehicles has made travel more convenient. However, hackers can attack intelligent vehicles through various technical loopholes, resulting in a range of security issues. Due to these security issues, the safety protection technology of the in-vehicle system has become a focus of research. Using the advanced autoencoder network and recurrent neural network in deep learning, we investigated...
-
Analysis of the regenerative braking process for the urban traffic conditions
PublikacjaIn a regular drive system, with an internal combustion engine, vehicle braking is connected with the unproductive dissipation of kinetic and potential energy accumulated in the mass of the vehicle into the environment. This energy can constitute up to 70% of the energy used to drive a vehicle under urban conditions. Its recovery and reuse is one of the basic advantages of hybrid and electric vehicles. Modern traffic management...
-
Data Compression in Ultrasonic Network Communication via Sparse Signal Processing
PublikacjaThis document presents the approach of using compressed sensing in signal encoding and information transferring within a guided wave sensor network, comprised of specially designed frequency steerable acoustic transducers (FSATs). Wave propagation in a damaged plate was simulated using commercial FEM-based software COMSOL. Guided waves were excited by means of FSATs, characterized by the special shape of its electrodes, and modeled...
-
Traffic Remapping Attacks in Ad Hoc Networks
PublikacjaAd hoc networks rely on the mutual cooperation of stations. As such, they are susceptible to selfish attacks that abuse network mechanisms. Class-based QoS provisioning mechanisms, such as the EDCA function of IEEE 802.11, are particularly prone to traffic remapping attacks, which may bring an attacker better QoS without exposing it to easy detection. Such attacks have been studied in wireless LANs, whereas their impact in multihop...
-
Use of Data from Satellite Navigation System in Operational and Strategic Management of Transport in Cities
PublikacjaThe article presents the possibilities of using data from the Global Positioning System for the development of traffic models and examples of use this data in the transport management. Traffic models are useful tools in planning and evaluation of transport solutions, but also can be used for current, operational transport management.
-
Iterative Global Sensitivity Analysis Algorithm with Neural Network Surrogate Modeling
PublikacjaGlobal sensitivity analysis (GSA) is a method to quantify the effect of the input parameters on outputs of physics-based systems. Performing GSA can be challenging due to the combined effect of the high computational cost of each individual physics-based model, a large number of input parameters, and the need to perform repetitive model evaluations. To reduce this cost, neural networks (NNs) are used to replace the expensive physics-based...
-
Optoelectronic system for monitoring of thin diamond layers growth
PublikacjaDevelopment of the optoelectronic system for monitoring of diamond/DLC (Diamond-Like-Carbon) thin films growth during mu PA ECR CVD (Microwave Plasma Assisted Electron Cyclotron Resonance Chemical Vapour Deposition) process is described. The multi-point Optical Emission Spectroscopy (OES) and Raman spectroscopy were employed as non-invasive optoelectronic tools. Dissociation of H-2 molecules, excitation and ionization of hydrogen...
-
Condition monitoring and fault diagnosis of wind turbines based on structural break detection in SCADA data
Publikacja -
Measurement of engine and vehicle parameters using onboard CAN network
PublikacjaWspółczesne samochody wyposażane są w dużą liczbę układów elektronicznych, które wymagają wzajemnej wymiany informacji. Techniczne problemy niezależnego łączenia ze sobą dużej liczby sterowników doprowadziły do powstania pokładowych sieci wymiany danych. Do najpopularniejszych z nich zalicza się obecnie system CAN. W pracy przedstawiono metodę rozpoznawania ramek wiadomości transmitowanych w pokładowej sieci CAN pojazdu przez sterowniki....
-
Microseismic Monitoring of Hydraulic Fracturing - Data Interpretation Methodology With an Example from Pomerania
PublikacjaMicroseismic monitoring is a method for localizing fractures induced by hydraulic fracturing in search for shell gas. The data is collected from an array of geophones deployed on the surface or underground. Ground vibrations are recorded and analysed for fracture location, magnitude and breakage mechanism. For successful microseismic monitoring one need a velocity model of underlying formations. The model is further tuned with...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublikacjaThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Implementation of DEIS for reliable fault monitoring and detection in PEMFC single cells and stacks
PublikacjaDynamic Electrochemical Impedance Spectroscopy (DEIS) was presented as novel method for diagnostic and monitoring of PEMFC stack and single cells operation. Impedance characteristics were obtained simultaneously with current - voltage characteristics for stack and each individual cell. Impedance measurements were performed in galvanodynamic mode. It allowed to compare performance of each cell and identification of faulty cell operation...
-
Application of a fuzzy neural network for river water quality prediction
PublikacjaMonitoring i modelowanie zmian w jakości wód powierzchniowych stanowią jeden z kluczowych elementów monitoringu i zarządzania ochroną środowiska na skalę globalną. Kontrolowanie tak złożonych i nieliniowych w swojej charakterystyce obiektów, jakimi są rzeki, jest trudnym zadaniem. Zazwyczaj do tego celu wykorzystuje się modele matematyczne, jednak czasem wymagają one bardzo dużej ilości danych, lub czas oczekiwania na odpowiedź...
-
Characterizing the Scalability of Graph Convolutional Networks on Intel® PIUMA
PublikacjaLarge-scale Graph Convolutional Network (GCN) inference on traditional CPU/GPU systems is challenging due to a large memory footprint, sparse computational patterns, and irregular memory accesses with poor locality. Intel’s Programmable Integrated Unffied Memory Architecture (PIUMA) is designed to address these challenges for graph analytics. In this paper, a detailed characterization of GCNs is presented using the Open-Graph Benchmark...
-
Adaptive Hyperparameter Tuning within Neural Network-based Efficient Global Optimization
PublikacjaIn this paper, adaptive hyperparameter optimization (HPO) strategies within the efficient global optimization (EGO) with neural network (NN)-based prediction and uncertainty (EGONN) algorithm are proposed. These strategies utilize Bayesian optimization and multiarmed bandit optimization to tune HPs during the sequential sampling process either every iteration (HPO-1itr) or every five iterations (HPO-5itr). Through experiments using...
-
Neural Architecture Search for Skin Lesion Classification
PublikacjaDeep neural networks have achieved great success in many domains. However, successful deployment of such systems is determined by proper manual selection of the neural architecture. This is a tedious and time-consuming process that requires expert knowledge. Different tasks need very different architectures to obtain satisfactory results. The group of methods called the neural architecture search (NAS) helps to find effective architecture...
-
Compressive Sensing Approach to Harmonics Detection in the Ship Electrical Network
PublikacjaThe contribution of this paper is to show the opportunities for using the compressive sensing (CS) technique for detecting harmonics in a frequency sparse signal. The signal in a ship’s electrical network, polluted by harmonic distortions, can be modeled as a superposition of a small number of sinusoids and the discrete Fourier transform (DFT) basis forms its sparse domain. According to the theory of CS, a signal may be reconstructed...