Filters
total: 1851
displaying 1000 best results Help
Search results for: RECURRENT NEURAL NETWORKS
-
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...
-
Karol Flisikowski dr inż.
PeopleKarol Flisikowski works as Associate Professor at the Department of Statistics and Econometrics, Faculty of Management and Economics, Gdansk University of Technology. He is responsible for teaching descriptive and mathematical statistics (in Polish and English), as well as scientific research in the field of social statistics. He has been a participant in many national and international conferences, where he has presented the results...
-
Adrian Bekasiewicz dr hab. inż.
PeopleAdrian Bekasiewicz received the MSc, PhD, and DSc degrees in electronic engineering from Gdansk University of Technology, Poland, in 2011, 2016, and 2020, respectively. In 2014, he joined Engineering Optimization & Modeling Center where he held a Research Associate and a Postdoctoral Fellow positions, respectively. Currently, he is an Associate Professor with Gdansk University of Technology, Poland. His research interests include...
-
Overview of Scalability and Reliability Problem in SDN Networks
PublicationIn the paper an overview of scalability and reliability in the SDN (Software Defined Networks) networks has been presented. Problems and limitations for guaranteeing scalability and reliability in SDN networks have been indicated. Known methods for assuring scalability and reliability in SDN networks have been described. Projects from research communities for resolving issues with scalability and reliability in SDN networks have...
-
The reliability of tree and star networks
PublicationThis paper investigated the reliability of tree and star networks. Following measures of network reliability are assumed: the expected number of nodes, that can communicate with the central node; the expected number of node pairs, that are connected by a path through the central node; the expected number of node pairs communicating.
-
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,...
-
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...
-
Protection in elastic optical networks
PublicationIn this article, we analyze gains resulting from the use of EON architectures with special focus on transportation of cloud-ready and content-oriented traffic in the context of network resilience. EONs are a promising approach for future optical transport networks and, apart from improving the network spectral efficiency, bring such new capabilities as squeezed protection, which reduces resource requirements in failure scenarios....
-
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...
-
THE UNSUSTAINABILITY OF PUBLIC-SECTOR ORGANIZATIONAL NETWORKS: A CASE STUDY OF VOLUNTARY COURT NETWORKS
PublicationPurpose: The purpose of this study is to identify the problem of sustainability of public-sector 12 organizational networks on the example of common courts and what it implies for further 13 research. Methodology: The study used qualitative research tools in the form of structured 14 interviews. Interviews were conducted with 36 presidents and directors of common courts. 15 After conducting and transcribing each interview, their...
-
Recurrent bowel-blood translocations of Escherichia coli with the unique virulence characteristics over three-year period in the patient with acute myeloid leukaemia – case report
PublicationIn patients with haematological malignancies, the bowel remains the main source of Escherichia coli bloodstream infections. We present the clinical example of recurrent bowel-blood translocations of E. coli with the unique virulence characteristics in a 55-year-old male with the diagnosis of acute myeloid leukaemia. The virulent factors profile of examined strains confirmed that the co-existence of genes papC, sfa, usp and cnf1,...
-
Neural network agents trained by declarative programming tutors
PublicationThis paper presents an experimental study on the development of a neural network-based agent, trained using data generated using declarative programming. The focus of the study is the application of various agents to solve the classic logic task – The Wumpus World. The paper evaluates the effectiveness of neural-based agents across different map configurations, offering a comparative analysis to underline the strengths and limitations...
-
Exploiting Multi-Interface Networks: Connectivity and Cheapest Paths
PublicationRozważano zagadnienie minimalizacji energii w sieciach bezprzewodowych bez infrastruktury, w których niektóre węzły są wyposażone w więcej, niż jeden interfejs. W przyjętym modelu sieci podano nowe algorytmy przybliżone oraz wyniki dotyczące złożoności obliczeniowej dla dwóch problemów: aktywacji najtańszej spójnej podsieci spinającej oraz aktywacji ścieżki pomiędzy ustaloną parą węzłów.
-
An efficient approach to optimization of semi‐stable routing in multicommodity flow networks
Publication -
Comparison of Deep Neural Network Learning Algorithms for Mars Terrain Image Segmentation
PublicationThis paper is dedicated to the topic of terrain recognition on Mars using advanced techniques based on the convolutional neural networks (CNN). The work on the project was conducted based on the set of 18K images collected by the Curiosity, Opportunity and Spirit rovers. The data were later processed by the model operating in a Python environment, utilizing Keras and Tensorflow repositories. The model benefits from the pretrained...
-
First recurrent large genomic rearrangement in the BRCA1 gene found in Poland
Publication -
292. Cisplatin and 5-fluorouracil in recurrent, persistent or metastatic cervical carcinoma
Publication -
A Novel Method for the Deblurring of Photogrammetric Images Using Conditional Generative Adversarial Networks
PublicationThe visual data acquisition from small unmanned aerial vehicles (UAVs) may encounter a situation in which blur appears on the images. Image blurring caused by camera motion during exposure significantly impacts the images interpretation quality and consequently the quality of photogrammetric products. On blurred images, it is difficult to visually locate ground control points, and the number of identified feature points decreases...
-
Rearrangeability in multicast Clos networks is NP-complete
PublicationPrzestrajalność w polach Closa z połączeniami jeden do jeden jest problemem wielomianowym. W pracy pokazano, że w polach z połączeniami jeden do wiele problem ten jest NP zupełny.Three-stage elos networks are commutation networks with circuit switching. So far, graph theory has been very useful tool for solving issues related to these networks with unicast connections. This is so because if elos network is represented as a bipartite...
-
Towards Designing an Innovative Industrial Fan: Developing Regression and Neural Models Based on Remote Mass Measurements
PublicationThis article presents the process of the construction and testing a remote, fully autonomous system for measuring the operational parameters of fans. The measurement results obtained made it possible to create and verify mathematical models using linear regression and neural networks. The process was implemented as part of the first stage of an innovative project. The article presents detailed steps of constructing a system to...
-
Controlling computer by lip gestures employing neural network
PublicationResults of experiments regarding lip gesture recognition with an artificial neural network are discussed. The neural network module forms the core element of a multimodal human-computer interface called LipMouse. This solution allows a user to work on a computer using lip movements and gestures. A user face is detected in a video stream from a standard web camera using a cascade of boosted classifiers working with Haar-like features....
-
Cooperative Data Transmission in Wireless Vehicular Networks
PublicationThe paper presents issues related to the cooperative transmission in wireless vehicular networks. Cooperative transmission involves the use of mobile terminals as relay stations to improve the transmission quality, improve network performance and reduce energy consumption. The paper presents the methods used to implement cooperative transmission and the types of cooperative networks.
-
DIAGNOSIS OF MALIGNANT MELANOMA BY NEURAL NETWORK ENSEMBLE-BASED SYSTEM UTILISING HAND-CRAFTED SKIN LESION FEATURES
PublicationMalignant melanomas are the most deadly type of skin cancer but detected early have high chances for successful treatment. In the last twenty years, the interest of automated melanoma recognition detection and classification dynamically increased partially because of public datasets appearing with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task...
-
Deep Learning-Based LOS and NLOS Identification in Wireless Body Area Networks
PublicationIn this article, the usage of deep learning (DL) in ultra-wideband (UWB) Wireless Body Area Networks (WBANs) is presented. The developed approach, using channel impulse response, allows higher efficiency in identifying the direct visibility conditions between nodes in off-body communication with comparison to the methods described in the literature. The effectiveness of the proposed deep feedforward neural network was checked on...
-
IET Networks
Journals -
SOCIAL NETWORKS
Journals -
Optimization of Wireless Networks for Resilience to Adverse Weather Conditions
PublicationIn this chapter, we consider how adverse weather conditions such as rain or fog affect the performance of wireless networks, and how to optimize these networks so as to make them robust to these conditions. We first show how to analyze the weather conditions in order to make them useful for network optimization modelling. Using an example realistic network, we show how to optimize two types of wireless networks: free-space optical...
-
Topology recognition and leader election in colored networks
PublicationTopology recognition and leader election are fundamental tasks in distributed computing in networks. The first of them requires each node to find a labeled isomorphic copy of the network, while the result of the second one consists in a single node adopting the label 1 (leader), with all other nodes adopting the label 0 and learning a path to the leader. We consider both these problems in networks whose nodes are equipped with...
-
CRVG - a new model for wireless networks topology generation
PublicationThis paper presents a new model of wireless network topology generator. Its main advantage is the possibility of relatively sparse networks generation. Because no iteration is needed, the model can be used for massive generation of networks for testing. The topological properties of produced graphs place them in the class of scale free networks, resembling real ones.
-
Frontiers in Neural Circuits
Journals -
NEURAL COMPUTING & APPLICATIONS
Journals -
Neural Regeneration Research
Journals -
Neural Network World
Journals -
NEUROREHABILITATION AND NEURAL REPAIR
Journals -
NEURAL PROCESSING LETTERS
Journals -
The networking of the justice system as part of public court networks
PublicationThe goal of this paper is to look at the organizational structure of the justice system and provide the answer to the basic question of the possible network relations, their force, and imapct. As part od the paper, I have defined public inetrorganisational court network, dividing them into regulatory inter-organisational networks nad voluntary inetrorganisational networks. Emphasis has also been placed on the benefits and threats...
-
Statistical significance of displacements in heterogeneous control networks
PublicationThis paper proposes a modification of the classical process for evaluating the statistical significance of displacements in the case of heterogeneous (e.g. linear-angular) control networks established to deformation measurements and analysis. The basis for the proposed solution is the idea of local variance factors. The theoretical discussion was complemented with an example of its application on a simulated horizontal control...
-
Electrical and noise responses of carbon nanotube networks enhanced by UV light for nitrogen dioxide sensing
Open Research DataNetworks consisting of randomly oriented carbon nanotubes (CNN) were investigated toward nitrogen dioxide detection by means of electrical and low-frequency noise measurements. UV-activation of CNN layers improved gas sensitivity and reduced the limit of detection, especially by employing 275 nm-LED. This data set includes DC resistance measurements...
-
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...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublicationThe 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...
-
A Bayesian regularization-backpropagation neural network model for peeling computations
PublicationA Bayesian regularization-backpropagation neural network (BRBPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network...
-
Trust Management Method for Wireless Sensor Networks
PublicationA Wireless Sensor Network (WSN) is a network of spatially distributed autonomous sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. and to cooperatively pass their data to the main location. The first wireless network that bore any real resemblance to a modern WSN is the Sound Surveillance System (SOSUS), developed by the United States Military in the 1950s to detect and track Soviet...
-
Application of wavelength division multiplexing in sensor networks
PublicationOver the past few years the need to acquire data on various parameters from a number of sensors grew. The need that led to the development of a network of sensors which enables simultaneous control and measurement in a wide range of applications. The aim of this article is to discuss a possibility of connecting a variety of sensors in a network that would utilize WDM technology. Wavelength Division Multiplexing is commonly used...
-
Jarosław Sadowski dr hab. inż.
People -
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
PublicationA problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and...
-
Traffic Remapping Attacks in Ad Hoc Networks
PublicationAd 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...
-
User Orientation Detection in Relation to Antenna Geometry in Ultra-Wideband Wireless Body Area Networks Using Deep Learning
PublicationIn this paper, the issue of detecting a user’s position in relation to the antenna geometry in ultra-wideband (UWB) off-body wireless body area network (WBAN) communication using deep learning methods is presented. To measure the impulse response of the channel, a measurement stand consisting of EVB1000 devices and DW1000 radio modules was developed and indoor static measurement scenarios were performed. It was proven that for...
-
Intelligent turbogenerator controller based on artifical neural network
PublicationThe paper presents a desing of an intelligent controller based on neural network (ICNN). The ICNN ensures at the same time two fundamental functions : the maintaining of generator voltage at the desired value and the damping of the electromechanical oscillations. Its performance is evaluted on a single machine infinite bus power system through computer simulations. The dynamic and transient operation of the proposed controller...
-
The impact of institutions on innovation networks: empirical evidence from Poland
PublicationInnovation networks may accelerate and improve the innovation process, while institutional pathologies may hamper it. This study employs the Kruskal-Wallis H test and regression analysis to determine if the relationship between institutions and innovation networks does exist among the investigated variables. The purpose of the study was to find out whether cooperation with special local institutions influences the innovative behaviour...
-
Traffic Modeling in IMS-based NGN Networks
PublicationIn the modern world the need for accurate and quickly delivered information is becoming more and more essential. In order to fulfill these requirements, next generation telecommunication networks should be fast introduced and correctly dimensioned. For this reason proper traffic models must be identified, which is the subject of this paper. In the paper standardization of IMS (IP Multimedia Subsystem) concept and IMS-based NGN...