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
-
History of World Architecture I 2021/22
e-Learning CoursesThe course History of World Architecture (HWA I) is obligatory on the first semester of study at the Faculty of Architecture at Gdańsk University ofTechnology. It lasts 15 weeks, finishes with the exam, and consists of 15 two-hour lectures and 15 two-hour exercises. The merit of the course includes Western World architecture, beginning from Prehistory and Antiquity (Sumer, Egypt, Greece, Rome), up to the end of the Middle Ages....
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is not uncommon for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected...
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is common for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected as...
-
Process: Architecture
Journals -
Architecture Today
Journals -
Journal of Architecture (The)
Journals -
Architecture d'Aujourdui
Journals -
Vernacular Architecture
Journals -
Architecture and Culture
Journals -
Architecture and Engineering
Journals -
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
A novel architecture of Web-GIS for mapping and analysis of echinococcosis in Poland
PublicationEchinococcosis is an infectious disease transferred through ingestion of food or water which have been contaminated with eggs of the Echinococcus tapeworm, which are spread by intermediate parasite hosts. Because the latter are primarily territorial, research related to diagnosis and prevention of echinococcosis requires investigation of environmental factors, which can be supported with the use of a Geographical Information System...
-
COMBINING FUNCTIONAL AND AESTHETIC ASPECTS OF DAYLIGHTING IN SUSTAINABLE ARCHITECTURE WITH THE USE OF DIGITAL DESIGN METHODS
PublicationThe aesthetics of modern architecture should relate to its origins and goals - the environment, function, sustainability and its users. One of the conditions that meet the criteria is the presence of daylight and the use of its potential. The contemporary digital tools that support the design process allow to controlling the use of difficult and capricious materials, such as daylight. They also combine daylighting aspects with...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublicationThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
The influence of the development of private air communication on the architecture and urban planning of the 21st century
PublicationIn the first part, the article describes the stages of the development of gyroplanes and the influence of wartime policy on the interest in light aircraft. Also presented are links and the possibilities of using gyroplanes in various sectors of the economy. The authors, based on source texts, present the current position of the aviation industry in the Polish economy and attempt to diagnose its development capabilities. As a result,...
-
Visual Features for Improving Endoscopic Bleeding Detection Using Convolutional Neural Networks
PublicationThe presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods....
-
Outlier detection method by using deep neural networks
PublicationDetecting outliers in the data set is quite important for building effective predictive models. Consistent prediction can not be made through models created with data sets containing outliers, or robust models can not be created. In such cases, it may be possible to exclude observations that are determined to be outlier from the data set, or to assign less weight to these points of observation than to other points of observation....
-
A Highly Scalable, Modular Architecture for Computer Aided Assessment e-Learning Systems
PublicationIn this chapter, the authors propose a novel e-learning system, dedicated strictly to knowledge assessment tasks. In its functioning it utilizes web-based technologies, but its design differs radically from currently popular e-learning solutions which rely mostly on thin-client architecture. The authors' research proved that such architecture, while well suited for didactic content distribution systems is ill-suited for knowledge...
-
A heterogenous wireless system for maritime communication - the netBaltic system architecture
PublicationIn the article, the concept of a heterogeneous wireless maritime mesh network offering transmission for e.g., e-navigation services is presented. The constrains of existing and competitive solutions are discussed showing the need for a new system. The authors present detailed information about a netBaltic node's architecture and networking mechanisms offering different transmission capabilities and proposed for use on different...
-
Mobile Cloud computing architecture for massively parallelizablegeometric computation
PublicationCloud Computing is one of the most disruptive technologies of this century. This technology has been widely adopted in many areas of the society. In the field of manufacturing industry, it can be used to provide advantages in the execution of the complex geometric computation algorithms involved on CAD/CAM processes. The idea proposed in this research consists in outsourcing part of the load to be com- puted in the client machines...
-
Automatic singing quality recognition employing artificial neural networks
PublicationCelem artykułu jest udowodnienie możliwości automatycznej oceny jakości technicznej głosów śpiewaczych. Pokrótce zaprezentowano w nim stworzoną bazę danych głosów śpiewaczych oraz zaimplementowane parametry. Przy pomocy sztucznych sieci neuronowych zaprojektowano system decyzyjny, który oceniono w pięciostopniowej skali jakość techniczną głosu. Przy pomocy metod statystycznych udowodniono, że wyniki generowane przez ten system...
-
A Selection of Starting Points for Iterative Position Estimation Algorithms Using Feedforward Neural Networks
PublicationThis article proposes the use of a feedforward neural network (FNN) to select the starting point for the first iteration in well-known iterative location estimation algorithms, with the research objective of finding the minimum size of a neural network that allows iterative position estimation algorithms to converge in an example positioning network. The selected algorithms for iterative position estimation, the structure of the...
-
Application of the neural networks for developing new parametrization of the Tersoff potential for carbon
PublicationPenta-graphene (PG) is a 2D carbon allotrope composed of a layer of pentagons having sp2- and sp3-bonded carbon atoms. A study carried out in 2018 has shown that the parameterization of the Tersoff potential proposed in 2005 by Ehrhart and Able (T05 potential) performs better than other potentials available for carbon, being able to reproduce structural and mechanical properties of the PG. In this work, we tried to improve the...
-
Decisional-DNA-Based Digital Twin Implementation Architecture for Virtual Engineering Objects
PublicationDigital twin (DT) is an enabling technology that integrates cyber and physical spaces. It is well-fitted for manufacturing setup since it can support digitalized assets and data analytics for product and process control. Conventional manufacturing setups are still widely used all around the world for the fabrication of large-scale production. This article proposes a general DT implementation architecture for engineering objects/artifacts...
-
Dynamically positioned ship steering making use of backstepping method and artificial neural networks
PublicationThe article discusses the issue of designing a dynamic ship positioning system making use of the adaptive vectorial backstepping method and RBF type arti cial neural networks. In the article, the backstepping controller is used to determine control laws and neural network weight adaptation laws. e arti cial neural network is applied at each time instant to approximate nonlinear functions containing parametric uncertainties....
-
An Improved Convolutional Neural Network for Steganalysis in the Scenario of Reuse of the Stego-Key
PublicationThe topic of this paper is the use of deep learning techniques, more specifically convolutional neural networks, for steganalysis of digital images. The steganalysis scenario of the repeated use of the stego-key is considered. Firstly, a study of the influence of the depth and width of the convolution layers on the effectiveness of classification was conducted. Next, a study on the influence of depth and width of fully connected...
-
Joanna Kabrońska dr inż. arch.
PeoplePhD with honours: Forma architektoniczna jako droga realizacji idei biblioteki przyszłości (Form of Architectural Solutions as a Means of Implementing the idea of Libraries of the Future), 1994 IV International Biennale of Architecture in Cracow Prize winner, 1991 DAAD post-doctoral scholarship, Berlin, 2002 Author of publications on architecture, art and memory, including the monograph Architektura jako forma pamięci. Rola architektury...
-
Developing students' spatial skills and teaching the history of architecture through structural drawing
PublicationThe method of “structural drawing" is used in teaching history of architecture in the Architectural Faculty of Gdańsk University of Technology. It is addressed to students of the first semester of study – so to the architectural beginners. There are three main goals of the structural drawing method used in that educational course: (1) developing the students’ spatial skills; (2) training architectural drawing ability; (3) teaching...
-
Designing of an effective structure of system for the maintenance of a technical object with the using information from an artificial neural network
Publication -
[AiU] Contemporary research methodology, evaluation and preservation of historic architecture
e-Learning CoursesThis course is compulsory for PhD students assigned to Architecture and Urbanism tracks at Doctoral School at Gdańsk University of Technology. The course is conducted by prof. Sandro Parrinello, Department of Civil Engineering and Architecture of University of Pavia Course type: workshops Total hours of training: 30 teaching hours Classes in hybrid mode (classes conducted online and at the GdańskTech)
-
Civil Engineering and Architecture
Journals -
ENVIRONMENTALLY FRIENDLY MATERIALS IN ARCHITECTURE � MODERN TRENDS AND DEVELOPMENT DIRECTIONS
PublicationFor a long time the interest in environmentally friendly materials in architecture is no longer limited to the use of renewable and natural substances such as wood, stone, straw, or reusable materials, such as metals or glass. Today the so-called naturals and the materials compatible with the idea of sustainability constantly appear on the market in new forms. Increasing awareness of the necessity to limit the building sector’s...
-
A universal IT system architecture for servicing, collecting, storing, processing and presenting data from wireless devices
PublicationIn the article we present a universal IT system architecture, which allows one to develop, based on mobile and multiplatform JAVA language, applications capable of working with many different wireless systems in an easy and effective way. Modular system architecture supports efficient data processing and enables convenient presentation of chosen parameters. Additionally, proposed IT system architecture provides easy adoption to...
-
[AiU]20232024_Challenges and Perspectives in Contemporary Architecture and Urbanism
e-Learning CoursesThis course is compulsory for PhD students assigned to Architecture and Urbanism tracks at Doctoral School at Gdańsk University of Technology. The course is conducted by Prof. Marichela Sepe, DICEA / Sapienza University Rome Course type: workshops Total hours of training: 15 teaching hours Classes in online mode (classes conducted online)
-
Evolving neural network as a decision support system — Controller for a game of “2048” case study
PublicationThe paper proposes an approach to designing the neuro-genetic self-learning decision support system. The system is based on neural networks being adaptively learned by evolutionary mechanism, forming an evolved neural network. Presented learning algorithm enables for a selection of the neural network structure by establishing or removing of connections between the neurons, and then for a finding the beast suited values of the network...
-
TOXIC GASES IDENTIFICATION USING SINGLE ELECTROCATALYTIC SENSOR RESPONSES AND ARTIFICIAL NEURAL NETWORK
PublicationThe need for precise detection of toxic gases drives development of new gas sensors structures and methods of processing the output signals from the sensors. In literature, artificial neural networks are considered as one of the most effective tool for the analysis of gas sensors or sensors arrays responses. In this paper a method of toxic gas components identification using a electrocatalytic gas sensor as a detector and an artificial...
-
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...
-
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
PublicationBearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect...
-
Structural analysis as a supporting method for the research of the medieval brick architecture
PublicationChronology of brick historical buildings might be established much more precisely than the chronology of stone ones due to the architectural and metrical analysis of bricks, mortars and brickworks. Comparison of historical sources allows to reconstruct the previous stages of constructing monuments. Causations between transformations and developments of monuments are usually interpreted as the results of artistic or ideological...
-
The Neural Knowledge DNA Based Smart Internet of Things
PublicationABSTRACT The Internet of Things (IoT) has gained significant attention from industry as well as academia during the past decade. Smartness, however, remains a substantial challenge for IoT applications. Recent advances in networked sensor technologies, computing, and machine learning have made it possible for building new smart IoT applications. In this paper, we propose a novel approach: the Neural Knowledge DNA based Smart Internet...
-
Apparatus to search for optical flashes of extragalactic origin
Publication -
Focused crawler for trustworthy healthcare information search
PublicationArtykuł zawiera opis prac wykonanych w projekcie 6 Programu Ramowego Unii Europejskiej: Personalised Information Platform for life and health Services (PIPS). Głównym celem projektu jest zapewnienie obywatelowi Unii kompleksowego wspomagania w zakresie zagadnień ochrony zdrowia oraz odżywiania. Do realizacji tego celu konieczne jest pozyskanie i dostarczenie obywatelowi wiarygodnej, prawdziwej i aktualnej informacji z tych dziedzin....
-
A Population-Based Method with Selection of a Search Operator
PublicationThis paper presents a method based on a population in which the parameters of individuals can be processed by operators from various population-based algorithms. The mechanism of selecting operators is based on the introduction of an additional binary parameters vector located in each individual, on the basis of which it is decided which operators are to be used to modify individuals’ parameters. Thus, in the proposed approach,...
-
Ocena poprawności działania algorytmu proof-number search na strukturze digrafu acyklicznego
PublicationAlgorytm proof-number search jest znanym algorytmem służącym do rozwiązywania gier logicznych. Rozwiązanie gry jest jednoznaczne ze znalezieniem optymalnej strategii i pozwala przeprowadzić rozgrywkę w sposób pozwalający na osiągnięcie najlepszego możliwego wyniku. Jedną z największych wad tego algorytmu, naturalnie pracującego na strukturze drzewa, jest wielokrotne rozwijanie identycznych poddrzew gry co prowadzi do nadmiarowego...
-
Development of Local IDF-formula Using Controlled Random Search Method for Global Optimization
PublicationThe aim of the study is to present the effective and relatively simple empirical approach to rainfall Intensity-Duration-Frequency-formulas development, based on Controlled Random Search (CRS) for global optimization. The approach is mainly dedicated to the cases in which the commonly used IDF-relationships do not provide satisfactory fit between simulations and observations, and more complex formulas with higher number of parameters...
-
Reduced-cost design closure of antennas by means of gradient search with restricted sensitivity update
PublicationDesign closure, i.e., adjustment of geometry parameters to boost the performance, is a challenging stage of antenna design process. Given complexity of contemporary structures, reliable parameter tuning requires numerical optimization and can be executed using local algorithms. Yet, EM-driven optimization is a computationally expensive endeavour and reducing its cost is highly desirable. In this paper, a modification of the trust-region...
-
Supply current signal and artificial neural networks in the induction motor bearings diagnostics
PublicationThis paper contains research results of the diagnostics of induction motor bearings based on measurement of the supply current with usage of artificial neural networks. Bearing failure amount is greater than 40% of all engine failures, which makes their damage-free operation crucial. Tests were performed on motors with intentionally made bearings defects. Chapter 2 introduces the concept of artificial neural networks. It presents...
-
Accuracy Investigations of Turbine Blading Neural Models Applied to Thermal and Flow Diagnostics
PublicationPossibility of replacing computional fluid dynamics simulations by a neural model for fluid flow and thermal diagnostics of steam turbines is investigated. Results of calculations of velocity magnitude of steam for 3D model of the stator of steam turbine is presented.
-
Weather Routing System Architecture Using Onboard Data Collection and Route Optimisation
PublicationThis paper describes the architecture of a weather routing system consisting of two key elements: onboard monitoring and route optimiser sub-systems. The former is responsible for collecting various onboard measurements, such as current ship position or ship motion variables. These data, when gathered and processed, are then used for fine-tuning a ship model. The model, together with weather forecasts, is utilised by a multi-objective...