Filters
total: 2673
-
Catalog
- Publications 1877 available results
- Journals 94 available results
- Conferences 38 available results
- People 265 available results
- Projects 4 available results
- Laboratories 1 available results
- Research Teams 1 available results
- e-Learning Courses 91 available results
- Events 3 available results
- Open Research Data 299 available results
displaying 1000 best results Help
Search results for: neural architecture search
-
Search for the fundamental solution to the vector acoustic wave equations
PublicationCzasowo-przestrzenna funkcja Greena pola swobodnego jest dobrze znanym rozwiązaniem podsta-wowym skalarnego niejednorodnego równania falowego. Wyraża ona odpowiedź ośrodka płynnego na punktowe zaburzenie o symetrii sferycznej. Odpowiedź ośrodka na zaburzenie wektorowe nie jest tak oczywista. Artykuł przedstawia oryginalne podejście do problemu, polegające na systematycznej, szcze-gółowej weryfikacji hipotetycznych rozwiązań skalarnych...
-
A Backtracking Search Algorithm for Distribution Network Reconfiguration Problem
Publication -
Pi of the sky: search for optical flashes of extragalactic origin
Publication -
Search for Ultimate Throughput in Ultra-Broadband Photonic Internet
Publication -
The iterative method in search for the state of equilibrium in anchor lines.
PublicationPrzedstawiono iteracyjną metodę rozwiązywania równań równowagi lin kotwicznych. Metoda jest szczególnie łatwa do zaprogramowania obliczeń numerycznych, ponieważ w każdym kroku iteracyjnym wymaga jedynie obliczania całek oznaczonych znanych funkcji. Wynikiem obliczeń są wartości sił podłużnych w linie i jej kształt, który na skutek oddziaływania prądu oceanicznego na linę może być krzywą przestrzenną. Przytoczone przykłady...
-
Extended neighborhood in local search paradigm for school timetabling
Publication.
-
Search for the most useful geometry of an acoustic journal bearing
PublicationComputer simulations of a number of journal bearing’s geometries utilising acoustic levitation were carried out. The choice of the best geometry depended on the ability of a deformed shape, created by piezo-electric elements, to facilitate squeeze film ultrasonic levitation, and also to create three evenly distributed diverging aerodynamic gaps. Deformations of analysed variants of the bearing’s shape were generated by numerical...
-
Neural Network-Based Sequential Global Sensitivity Analysis Algorithm
PublicationPerforming global sensitivity analysis (GSA) can be challenging due to the combined effect of the high computational cost, but it is also essential for engineering decision making. To reduce this cost, surrogate modeling such as neural networks (NNs) are used to replace the expensive simulation model in the GSA process, which introduces the additional challenge of finding the minimum number of training data samples required to...
-
Co w architekturze piszczy? Dźwiękowy wymiar przestrzeni / What’s the buzz in architecture? – The sonic aspect of space
PublicationThe article presents a debate on the dividing line between architecture and the sound sciences. It sketches out the theoretical and practical aspects of space development in the context of its sonic reception. The analysis is based on examples of projects combining architecture and art in public space and their consequences for the reception of this space. The projects relate to the use of art in urban space with special emphasis...
-
How to teach architecture? – Remarks on the edge of Polish transformation processes after 1989
PublicationThe political changes in Poland after 1989 have resulted in a whole range of dynamic processes including the transformation of space. Until that time the established institutional framework for spatial, urban and architectural planning policy was based on uniform provisions of the so-called planned economy. The same applied to the training of architects, which was based on a unified profile of education provided at the state’s...
-
“ARTIFICIAL INTELLIGENCE – IN SEARCH FOR SYNERGY
EventsKonferencja poświęcona jest omówieniu stanu badań i zastosowań sztucznej inteligencji AI z wykorzystaniem technologii satelitarnych
-
International Journal of Neural Networks
Journals -
IEEE TRANSACTIONS ON NEURAL NETWORKS
Journals -
JOURNAL OF NEURAL TRANSMISSION-SUPPLEMENT
Journals -
NETWORK-COMPUTATION IN NEURAL SYSTEMS
Journals -
International Journal of Neural Systems
Journals -
Monika Arczyńska dr inż. arch.
PeopleArchitect and researcher with over 10 years of international experience in cultural projects. She has been working on the designs of Grand Egyptian Museum in Cairo, Palestinian Museum in East Bank, Giant’s Causeway Visitor Centre and National Centre for Contemporary Art in Moscow (with Heneghan Peng Architects). As a founder of A2P2 architecture & planning she runs architecture department of the company. In 2018 together with...
-
History of contemporary architecture and urbanism
e-Learning Courseslectures: PhD Małgorzata Kostrzewska PhD Bartosz Macikowski exercises: PhD Łukasz Bugalski
-
History of Architecture and Urbanism_23/24
e-Learning Courses -
Computationally-efficient design optimisation of antennas by accelerated gradient search with sensitivity and design change monitoring
PublicationElectromagnetic (EM) simulation tools are of primary importance in the design of contemporary antennas. The necessity of accurate performance evaluation of complex structures is a reason why the final tuning of antenna dimensions, aimed at improvement of electrical and field characteristics, needs to be based on EM analysis. Design automation is highly desirable and can be achieved by coupling EM solvers with numerical optimisation...
-
Use of Modified Cuckoo Search algorithm in the design process of integrated power systems for modern and energy self-sufficient farms
PublicationIn the face of increasingly stringent pollutant emission regulations, designing an agricultural holding becomes a difficult challenge of connecting a large number of coefficients that describe an energy system of a farm in regard to its ecological and economic efficiency. One way to cope with this issue is to design an energy self-sufficient farm that integrates various technologies, including renewable energy. However, the selection...
-
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...
-
USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTING SHIP FUEL CONSUMPTION
PublicationIn marine vessel operations, fuel costs are major operating costs which affect the overall profitability of the maritime transport industry. The effective enhancement of using ship fuel will increase ship operation efficiency. Since ship fuel consumption depends on different factors, such as weather, cruising condition, cargo load, and engine condition, it is difficult to assess the fuel consumption pattern for various types...
-
Neural Graph Collaborative Filtering: Analysis of Possibilities on Diverse Datasets
PublicationThis paper continues the work by Wang et al. [17]. Its goal is to verify the robustness of the NGCF (Neural Graph Collaborative Filtering) technique by assessing its ability to generalize across different datasets. To achieve this, we first replicated the experiments conducted by Wang et al. [17] to ensure that their replication package is functional. We received sligthly better results for ndcg@20 and somewhat poorer results for...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublicationSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
Timber - material of the future. Examples of small wooden architecture structures.
PublicationThe aim of this article is to present various types of wood-based products, classified as engineered timber, while specifying the implications of their structural properties for their forms. Timber is used as a construction material due to its fire resistance, good structural characteristics and insulating properties. The advent of new technologies of wood processing and wood-based materials production has converted timber into...
-
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublicationIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Architecture supporting security of agent systems
PublicationW rozprawie zaproponowano nową architekturę bezpieczeństwa wspomagającą anonimowość w systemach agentowych. Moduł I architektury zapewnia funkcjonalność protokołu ochrony przed tropieniem (ang. untraceability), z tą zaletą, że nie wprowadza ograniczeń wobec agentów samodzielnie ustalających trasę własnej wędrówki. Stanowi rdzeń architektury, który zaimplementowano jako rozszerzenie platformy agentowej JADE, udostępniane publicznie...
-
Architektura i światło / Architecture and light
PublicationArtykuł dotyczy wpływu naturalnego oświetlenia na kreację współczesnej architektury. Światło słoneczne uwidaczniając architekturę, podkreśla jej walory estetyczno-przestrzenne oraz stanowi źródło energii. Od najdawniejszych czasów miało wpływ na powstające budowle. Postęp w nauce i technologii poszerzył możliwości i zakres wykorzystania światła. Wzrastające oczekiwania i wymagania wobec architektury sprawiają, że jego wpływ na...
-
Rural architecture and landscape - problem of continuity
Publication.
-
KASKADA - multimedia processing platform architecture
PublicationPrzedstawiono architekturę platformy KASKADA (skrót od: Kontekstowa Analiza Strumieni Danych z Kamer do Aplikacji Definiujących Alarmy), będącą częścią projektu MAYDAY EURO 2012. Opisano nowy wielowarstwowy model przetwarzania strumieni multimedialnych. Zaproponowano następujące warstwy: usług - prostych i złożonych, zadań obliczeniowych i procesów. Przedstawiono przykładowy scenariusz wraz ze szczegółami jego wykonania, jak również...
-
Lightweight structures in architecture: scenarios for the future
PublicationLightweight structures - structures with a reduced weight, which otherwise retain the qualities necessary for the building performance, ensuring a proper durability and strength, safety, indoor environmental quality and energy efficiency; stuctures which strive for the optimization of structural systems - are in tune with current trends and socio-economic, environmental and technological factors. The growing interest in the lightweight...
-
The application of neural networks in forecasting the influence of traffic-induced vibrations on residential buildings
PublicationTraffic-induced vibrations may cause the cracking of plaster, damage to structural elements and, in extreme cases, may even lead to the structural collapse of residential buildings. The aim of this article is to analyse the effectiveness of a method of forecasting the impact of vibrations on residential buildings using the concept of artificial intelligence. The article presents several alternative forecasting systems for which...
-
Engendering responsibility in architecture students through real planning for a tram depot in Gdańsk
PublicationApart from technical competencies, the profession of architect requires specific social competencies: understanding the user’s needs, ability to diagnose social problems, negotiating and understanding the impact of construction investments on society and the environment. The architect plays a significant role in the collective effort to create spatial order. This is why it is important to include these social competencies in the...
-
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...
-
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...
-
ReFlexeNN - the Wearable EMG Interface with Neural Network Based Gesture Classification
PublicationThe 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...
-
MEDIA ARCHITECTURE AND INTERACTIVE ART INSTALLATIONS STIMULATING HUMAN INVOLVEMENT AND ACTIVITIES IN PUBLIC SPACES
PublicationThis paper examines the potential for media architecture and interactive art installations to stimulate human involvement and activities in public spaces. On the basis of theoretical approaches, case studies and interdisciplinary surveys, the paper provides insight into how screens projecting media and interactive installations in city spaces can inspire people to become active on many levels. The research is focused, both on temporary...
-
The Eastern Battery in Świnoujście, Poland - history and architecture of a Prussian coastal fort from the 19th century
PublicationThe article describes the history, architecture and development of the Eastern Battery (also known as the Gerhard Fort) – one of three remaining coastal forts in Świnoujście (former Swinemünde) located in northern Poland, by the Baltic Sea. The research is mostly based on historical cartographic material and architectural plans verified during field studies. This data served to create a digital model – one of the results of the...
-
Reduced-cost constrained miniaturization of wideband antennas using improved trust-region gradient search with repair step
PublicationIn the letter, an improved algorithm for electromagnetic (EM)-driven size reduction of wideband antennas is proposed. Our methodology utilizes variable-fidelity EM simulation models, auxiliary polynomial regression surrogates, as well as multi-point response correction. The constraint handling is implicit, using penalty functions. The core optimization algorithm is a trust-region gradient search with a repair step added in order...
-
Comparison of single best artificial neural network and neural network ensemble in modeling of palladium microextraction
Publication -
Creating neural models using an adaptive algorithm for optimal size of neural network and training set.
PublicationZaprezentowano adaptacyjny algorytm generujący modele neuronowe liniowych układów mikrofalowych, zdolny do oszacowania optymalnego rozmiaru zbiory uczącego i sieci neuronowej. Stworzono kilka modeli nieciągłości falowodowych i mokropaskowych, a następnie zweryfikowano ich poprawność porównując wyniki analiz metodą dopasowania rodzajów i metodą momentów filtrów pasmowo-przepustowych.
-
Optical Sensor Based Gestures Inference Using Recurrent Neural Network in Mobile Conditions
PublicationIn this paper the implementation of recurrent neural network models for hand gesture recognition on edge devices was performed. The models were trained with 27 hand gestures recorded with the use of a linear optical sensor consisting of 8 photodiodes and 4 LEDs. Different models, trained off-line, were tested in terms of different network topologies (different number of neurons and layers) and different effective sampling frequency...
-
Message Inter-Arrival and Inter-Departure Time Distributions in IMS/NGN Architecture
PublicationCurrently is it assumed that requirements of the information society for delivering multimedia services will be satisfied by the Next Generation Network (NGN) architecture, which includes elements of the IP Multimedia Subsystem (IMS) solution. In order to guarantee Quality of Service (QoS), NGN has to be appropriately designed and dimensioned. Therefore, proper traffic models should be proposed and applied. This requires determination...
-
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...
-
Benchmarking Deep Neural Network Training Using Multi- and Many-Core Processors
PublicationIn 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,...
-
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...
-
‘The Urban Walk Architecture Talk’— Bridging Socially Engaged Art, Urban Processes and Cultural Development
Publication“Urban Walk—Architecture Talk” is a project based on an elective seminar under the same title organized at the Faculty of Architecture of Gdańsk University of Technology. It aims at getting familiar with the topic of multi-layer and multi-sensory reception of public space, mainly by recognizing the needs of its users. Additionally, it deals with the consequences of such perception and the use of space in order to build more complete...
-
Using Convolutional Neural Networks for Corneal Arcus Detection Towards Familial Hypercholesterolemia Screening
PublicationFamilial hypercholesterolemia (FH) is a highly undiagnosed disease. Among FH patients, the onset of premature coronary artery disease is 13 times higher than in the general population. Early diagnosis and treatment is essential to prevent cardiovascular diseases and their complications, and to prolong life. One of the clinical criteria of FH is the occurrence of a corneal arcus (CA) among patients, especially those under 45 years...
-
Multi-Camera Vehicle Tracking Using Local Image Features and Neural Networks
PublicationA 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...