Search
Filters
total: 24346
-
Catalog
- Publications 2623 available results
- Journals 368 available results
- Conferences 214 available results
- Publishing Houses 1 available results
- People 209 available results
- Projects 12 available results
- Research Teams 1 available results
- e-Learning Courses 101 available results
- Events 2 available results
- Open Research Data 20815 available results
displaying 1000 best results Help
Search results for: NEURAL INFORMATION RETRIEVAL
-
Semantic technologies based method of collection, processing and sharing information along food chain
PublicationIn the paper the method of collecting, processing and sharing information along food chain is presented. Innovative features of that method result from advantages of data engineering based on semantic technologies. The source to build ontology are standards and regulations related to food production, and data collected in databases owned by food chain participants. It allows food chain information resources can be represented in...
-
Information Theory and Coding 2023/2024
e-Learning CoursesThe course is an auxiliary tool for completing the subject Information Theory and Coding.
-
Neural Architecture Search for Skin Lesion Classification
PublicationDeep 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...
-
Information content of systems as a physical principle
PublicationTo explain the conceptual gap between classical and quantum and other, hypothetical descriptions of the world, several principles have been proposed. So far, all these principles have not explicitly included the uncertainty relation. Here we introduce an information content principle ( ICP ) which represents a constrained uncertainty principle. The principle, by taking into account the encoding and decoding properties of a single physical...
-
The Diffusion of Information and Communication Technologies
PublicationThis book provides extensive evidence on information and communication technologies development patterns and dynamics of this process across developed economies over the period 1980 to the present day. It adopts newly developed methodology to identification of the ‘critical mass’ and isolation of technological takeoff intervals, which are intimately related to the process of technology diffusion. The statistically robust analysis...
-
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...
-
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...
-
Security Information Sharing for the Polish Power System
PublicationThe Polish Power System is becoming increasingly more dependent on Information and Communication Technologies which results in its exposure to cyberattacks, including the evolved and highly sophisticated threats such as Advanced Persistent Threats or Distributed Denial of Service attacks. The most exposed components are SCADA systems in substations and Distributed Control Systems in power plants. When addressing this situation...
-
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublicationIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Information Systems Security 2023/2024
e-Learning CoursesThe e-learning course for the Information Systems Security, in the field of Electronics and Telecommunications in the II degree studies (2nd year of studies, 3rd semester).
-
Dynamic Semantic Visual Information Management
PublicationDominant Internet search engines use keywords and therefore are not suited for exploration of new domains of knowledge, when the user does not know specific vocabulary. Browsing through articles in a large encyclopedia, each presenting a small fragment of knowledge, it is hard to map the whole domain, see relevant concepts and their relations. In Wikipedia for example some highly relevant articles are not linked with each other....
-
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...
-
System information propagation for composite structures
PublicationWe study in details decoherence process of a spin register, coupled to a spin environment. We use recently developed methods of information transfer study in open quantum systems to analyze information flow between the register and its environment. We show that there are regimes when not only the register decoheres effectively to a classical bit string, but this bit string is redundantly encoded in the environment, making it available...
-
Comparative study of neural networks used in modeling and control of dynamic systems
PublicationIn this paper, a diagonal recurrent neural network that contains two recurrent weights in the hidden layer is proposed for the designing of a synchronous generator control system. To demonstrate the superiority of the proposed neural network, a comparative study of performances, with two other neural network (1_DRNN) and the proposed second-order diagonal recurrent neural network (2_DRNN). Moreover, to confirm the superiority...
-
Information meeting for PhD students 23
e-Learning CoursesInformation meeting on 18.12.2023 1st-year PhD students
-
Deep neural network architecture search using network morphism
PublicationThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Social Aspects of Information Technology - Nowy
e-Learning CoursesSubject of the course includes history of science and technics as well as social, economic, medical, health and legal aspects of Information Technology and related fields of science and technology.
-
Different sources of market information and product innovativeness
PublicationThe purpose of this study is to identify whether the gathering of market information from different sources – i.e. from customers, competitors and other entities – is related to product innovativeness. The relationships proposed so far have not been empirically investigated but they can have important theoretical and practical implications for product innovation. To achieve the purpose of the paper data concerning 287 new products...
-
Query by Shape for Image Retrieval from Multimedia Databases
Publication -
Query-by-Shape interface for Content Based Image Retrieval
Publication -
A systematic retrieval of international competitiveness literature: a bibliometric study
PublicationOver the last three decades there has been growing interest in international competitiveness research. However, as evidenced by the academic literature, there is a lack of systematic chronological studies synthesizing how this field has evolved over time. The main aim of this paper is to consolidate the state of the art of academic research on international competitiveness in the discipline of economics by using a new method: a...
-
Development of a tropical disease diagnosis system using artificial neural network and GIS
PublicationExpert systems for diagnosis of tropical diseases have been developed and implemented for over a decade with varying degrees of success. While the recent introduction of artificial neural networks has helped to improve the diagnosis accuracy of such systems, this aspect is still negatively affected by the number of supported diseases. A large number of supported diseases usually corresponds to a high number of overlapping symptoms,...
-
Borders of Digital Art in the Context of the Information Society
PublicationThe article shows the relationship between the development of information technologies, the characteristics of the information society and digital art. The broad possibilities of the digital world related to recording, storing and processing data (cyber text, big data, smart services) and the creation of virtual worlds are pointed out. The influence of the development of information technologies on the character of the works of...
-
Transmitting Alarm Information in DAB+ Broadcasting System
PublicationThe main goal of digital broadcasting is to deliver high-quality content with the lowest possible bitrate. This paper is focused on transmitting alarm information, such as emergency warning and alerting, in the DAB+ (Digital Audio Broadcasting plus) broadcasting system. These additional services should be available at the lowest possible bitrate, in order to provide a clear and understandable voice message to people. Furthermore, additional...
-
Information transfer during the universal gravitational decoherence
PublicationRecently Pikovski et al. (Nat Phys 11:668, 2015) have proposed in an intriguing universal decoherence mechanism, suggesting that gravitation may play a conceptually important role in the quantum-to-classical transition, albeit vanishingly small in everyday situations. Here we analyze information transfer induced by this mechanism. We show that generically on short time-scales, gravitational decoherence leads to a redundant information...
-
Aspects of multistation quantum information broadcasting
PublicationWe study quantum information transmission over multiparty quantum channel. In particular, we show an equivalence of different capacity notions and provide a multiletter characterization of a capacity region for a general quantum channel with k senders and m receivers. We point out natural generalizations to the case of two-way classical communication capacity. (C) 2010 Elsevier B.V. All rights reserved.
-
Computational collective intelligence for enterprise information systems
PublicationCollective intelligence is most often understood as a kind of intelligence which arises on the basis of a group (collective) of autonomous unites (people, systems) which is taskoriented. There are two important aspects of an intelligent collective: The cooperation aspect and the competition aspect (Levy 1997). The first of them means the possibility for integrating the decisions made by the collective members for creating the decision of...
-
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...
-
From Linear Classifier to Convolutional Neural Network for Hand Pose Recognition
PublicationRecently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening...
-
Monitoring of the Process of System Information Broadcasting in Time
PublicationOne of the problems of quantum physics is how a measurement turns quantum, noncopyable data, towards copyable classical knowledge. We use the quantum state discrimination in a central system model to show how its evolution leads to the broadcasting of the information, and how orthogonalization and decoherence factors allow us to monitor the distance of the state in question to the one perfectly broadcasting information, in any...
-
Diagnosing wind turbine condition employing a neural network to the analysis of vibroacoustic signals
PublicationIt is important from the economic point of view to detect damage early in the wind turbines before failures occur. For this purpose, a monitoring device was built that analyzes both acoustic signals acquired from the built-in non-contact acoustic intensity probe, as well as from the accelerometers, mounted on the internal devices in the nacelle. The signals collected in this way are used for long-term training of the autoencoder...
-
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....
-
Neural Approximators for Variable-Order Fractional Calculus Operators (VO-FC)
PublicationThe paper presents research on the approximation of variable-order fractional operators by recurrent neural networks. The research focuses on two basic variable-order fractional operators, i.e., integrator and differentiator. The study includes variations of the order of each fractional operator. The recurrent neural network architecture based on GRU (Gated Recurrent Unit) cells functioned as a neural approximation for selected...
-
Software Tools to Measure the Duplication of Information
PublicationData stored in average computer system usually is not unique, portions of stored data are duplicated. When duplicated data are stored in separate files containing source code of computer program of student homework, a possibility of cheating should be seriously considered. This paper presents software tools built, in order to detect re-use of pieces of code in supplied text files. Three aspects of information atching are considered:...
-
Ontology-based text convolution neural network (TextCNN) for prediction of construction accidents
PublicationThe construction industry suffers from workplace accidents, including injuries and fatalities, which represent a significant economic and social burden for employers, workers, and society as a whole.The existing research on construction accidents heavily relies on expert evaluations,which often suffer from issues such as low efficiency, insufficient intelligence, and subjectivity.However, expert opinions provided in construction...
-
Concept of the agent system for the information technology evaluation
PublicationIn this paper the concept of the agent system for the information technology evaluation has been presented. This article includes the concept description and shows abilities of using software tools which can be applicable to implementation and verification of proposed solution. The article is the part of common researches over creation solutions for information technology evaluation which range over using expert's evaluation and...
-
The Use of Information and Communication Technologies in Cluster Organizations
PublicationThe purpose of the paper is to explore how cluster organizations (COs) take advantage of Information and Communication Technologies (ICT). The paper addresses the research question: “How do cluster organizations take advantage of ICT in fulfilling their main roles?”. The research was carried out in the first half of 2016 in four purposefully selected cluster organizations. The main research strategy involved Grounded Theory; the...
-
Normalization of face illumination using basic knowledge and information extracted from a single image
PublicationThis paper presents a method for face image normalization that can be applied to the extraction of illumination invariant facial features or used to remove bad lighting effects and produce high-quality, photorealistic results. Most of the existing approaches concentrate on separating the constant albedo from the variable light intensity; that concept, however, is based on the Lambertian model, which fails in the presence of specularities...
-
Advanced Modeling of Management Processes in Information Technology
PublicationThis book deals with the issues of modeling management processes of information technology and IT projects while its core is the model of information technology management and its component models (contextual, local) describing initial processing and the maturity capsule as well as a decision-making system represented by a multi-level sequential model of IT technology selection, which acquires a fuzzy rule-based implementation...
-
[19.11.2020] Information meeting for PhD students
e-Learning CoursesInformation meeting on 19.11.2020 1st and 2nd-year PhD students
-
[08.04.2024] Information meeting for Doctoral School candidates
e-Learning CoursesInformation meeting on 08.04.2024 Doctoral School candidates
-
[03.04.2023]Information meeting for Doctoral School candidates
e-Learning CoursesInformation meeting on 03.04.2023 Doctoral School candidates
-
What is information?
PublicationPrzedstawiono zarys metodologii konstrukcji miar informacyjnych opartej na sterowaniu zdarzeniowym. Podejście takie umożliwia jawne uwzględnianie wpływu kontekstu, kryterium użyteczności i protokołu postępowania na ilość informacji. Podano szereg przykładów obejmujących systemy rozproszone, transmisję danych, środowiska niekooperacyjne i in. wraz z oceną wynikowej przepustowości. Wskazano dalsze kierunki badań, m. in. w kierunku...
-
What is information?
PublicationPojęcie informacji było dotąd kwantyfikowane głównie w terminach statystycznych, dając początek shannonowskiej teorii informacji i zasad cyfrowej transmisji danych. Współczesne systemy komunikacyjne łączące skomplikowane, inteligentne i autonomiczne podmioty wymagają nowego spojrzenia na miary informacji, uwzględniającego kontekst i semantykę przekazu oraz racjonalne działania podmiotów. W niniejszym eseju zaproponowano podejście...
-
A Simple Neural Network for Collision Detection of Collaborative Robots
PublicationDue to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents...
-
Wykorzystanie Web 2.0 oraz architektury informacji w pracy brokera informacji = TAKING ADVANTAGE OF WEB 2.0 AND THE INFORMATION ARCHITECTURE IN THE INFORMATION BROKER’S WORK
PublicationThe development of information and communication technologies, dissemination of access as well as unlimited increase of publications result in the uncontrolled growth of knowledge resources. Looking up for the relevant information becomes increasingly difficult, especially when time plays a role. Such process requires vast knowledge, practical experience in obtaining and providing information and also analytical...
-
Software Modeling from the Perspective of Intuitive Information Processing
PublicationThere is psychological evidence that humans process information not only consciously but also intuitively. Intuitive information processing is present also during the activities related to software modeling. The goal of this paper is to analyze software modeling from the perspective of theories which describe intuitive (nonconscious, implicit) information processing. The paper includes presentation of relevant psychological theories,...
-
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...
-
Automatic evaluation of information credibility in Semantic Web and Knowledge Grid
PublicationThis article presents a novel algorithm for automatic estimation of information credibility. It concerns information collected in Knowledge Grid and Semantic Web. Possibilities to evaluate the credibility of information in such structures are much greater than those available for WWW sites which use natural language. The rating system presented in this paper estimates credibility automatically on the basis of the following metrics:...
-
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,...