Search
Filters
total: 2676
-
Catalog
- Publications 2135 available results
- Journals 62 available results
- Conferences 55 available results
- Publishing Houses 1 available results
- People 70 available results
- Projects 4 available results
- e-Learning Courses 15 available results
- Events 4 available results
- Open Research Data 330 available results
displaying 1000 best results Help
Search results for: graph neural network
-
Sathwik Prathapagiri
PeopleSathwik was born in 2000. In 2022, he completed his Master’s of Science in Biological Sciences and Bachelor’s of Engineering in Chemical Engineering in an integrated dual degree program from Birla Institute Of Technology And Science, Pilani, India. During his final year, he worked as a research intern under Dr Giri P Krishnan at Bazhenov lab, University of California San Diego school of medicine to pursue his Master’s Thesis on...
-
Pawlak's flow graph extensions for video surveillance systems
PublicationThe idea of the Pawlak's flow graphs is applicable to many problems in various fields related to decision algorithms or data mining. The flow graphs can be used also in the video surveillance systems. Especially in distributed multi-camera systems which are problematic to be handled by human operators because of their limited perception. In such systems automated video analysis needs to be implemented. Important part of this analysis...
-
Neural networks and deep learning
PublicationIn 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...
-
Interpolation properties of domination parameters of a graph
PublicationAn integer-valued graph function π is an interpolating function if a set π(T(G))={π(T): T∈TT(G)} consists of consecutive integers, where TT(G) is the set of all spanning trees of a connected graph G. We consider the interpolation properties of domination related parameters.
-
On the Characteristic Graph of a Discrete Symmetric Channel
PublicationWe present some characterizations of characteristic graphs of row and/or column symmetric channels. We also give a polynomial-time algorithm that decides whether there exists a discrete symmetric channel whose characteristic graph is equal to a given input graph. In addition, we show several applications of our results.
-
Characterizing the Scalability of Graph Convolutional Networks on Intel® PIUMA
PublicationLarge-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...
-
Fast collaborative graph exploration
PublicationWe study the following scenario of online graph exploration. A team of k agents is initially located at a distinguished vertex r of an undirected graph. At every time step, each agent can traverse an edge of the graph. All vertices have unique identifiers, and upon entering a vertex, an agent obtains the list of identifiers of all its neighbors. We ask how many time steps are required to complete exploration, i.e., to make sure...
-
Fast Collaborative Graph Exploration
PublicationWe study the following scenario of online graph exploration. A team of k agents is initially located at a distinguished vertex r of an undirected graph. At every time step, each agent can traverse an edge of the graph. All vertices have unique identifiers, and upon entering a vertex, an agent obtains the list of identifiers of all its neighbors. We ask how many time steps are required to complete exploration, i.e., to make sure...
-
Multi-agent graph searching and exploration algorithms
PublicationA team of mobile entities, which we refer to as agents or searchers interchangeably, starting from homebases needs to complete a given task in a graph.The goal is to build a strategy, which allows agents to accomplish their task. We analyze strategies for their effectiveness (e.g., the number of used agents, the total number of performed moves by the agents or the completion time).Currently, the fields of on-line (i.e., agents...
-
Applying artificial neural networks for modelling ship speed and fuel consumption
PublicationThis paper deals with modelling ship speed and fuel consumption using artificial neural network (ANN) techniques. These tools allowed us to develop ANN models that can be used for predicting both the fuel consumption and the travel time to the destination for commanded outputs (the ship driveline shaft speed and the propeller pitch) selected by the ship operator. In these cases, due to variable environmental conditions, making...
-
Graph security testing
PublicationSet S ⊂ V is called secure set iff ∀ X ⊂ S | N [ X ] ∩ S | ≥ | N ( X ) \ S | [3]. That means that every subset of a secure set has at least as many friends (neighbour vertices in S) as enemies (neighbour vertices outside S) and will be defended in case of attack. Problem of determining if given set is secure is co −NP -complete, there is no efficient algorithm solving it [3]. Property testers are algorithms that distinguish inputs...
-
Ship Resistance Prediction with Artificial Neural Networks
PublicationThe paper is dedicated to a new method of ship’s resistance prediction using Artificial Neural Network (ANN). In the initial stage selected ships parameters are prepared to be used as a training and validation sets. Next step is to verify several network structures and to determine parameters with the highest influence on the result resistance. Finally, other parameters expected to impact the resistance are proposed. The research utilizes...
-
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...
-
Constructing a map of an anonymous graph: applications of universal sequences
PublicationWe study the problem of mapping an unknown environmentrepresented as an unlabelled undirected graph. A robot (or automaton)starting at a single vertex of the graph G has to traverse the graph and return to its starting point building a map of the graph in the process. We are interested in the cost of achieving this task (whenever possible) in terms of the number of edge traversal made by the robot. Another optimization criteria...
-
Application of genetic algorithms in graph searching problem
PublicationGraph searching is a common approach to solving a problem of capturing a hostile intruder by a group of mobile agents. We assume that this task is performed in environment which we are able to model as a graph G. The question asked is how many agents are needed to capture an arbitrary fast, invisible and smart intruder. This number is called the (edge) search number of G. The strategy which must be performed by agents is called...
-
Graph Decomposition for Memoryless Periodic Exploration
PublicationWe consider a general framework in which a memoryless robot periodically explores all the nodes of a connected anonymous graph by following local information available at each vertex. For each vertex v, the endpoints of all edges adjacent to v are assigned unique labels within the range 1 to deg (v) (the degree of v). The generic exploration strategy is implemented using a right-hand-rule transition function: after entering vertex...
-
Exploring Neural Networks for Musical Instrument Identification in Polyphonic Audio
PublicationThe purpose of this paper is to introduce neural network-based methods that surpass state-of-the-art (SOTA) models, either by training faster or having simpler architecture, while maintaining comparable effectiveness in musical instrument identification in polyphonic music. Several approaches are presented, including two authors’ proposals, i.e., spiking neural networks (SNN) and a modular deep learning model named FMCNN (Fully...
-
Parallel tabu search for graph coloring problem
PublicationTabu search is a simple, yet powerful meta-heuristic based on local search that has been often used to solve combinatorial optimization problems like the graph coloring problem. This paper presents current taxonomy of patallel tabu search algorithms and compares three parallelization techniques applied to Tabucol, a sequential TS algorithm for graph coloring. The experimental results are based on graphs available from the DIMACS...
-
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...
-
Coronas and Domination Subdivision Number of a Graph
PublicationIn this paper, for a graph G and a family of partitions P of vertex neighborhoods of G, we define the general corona G ◦P of G. Among several properties of this new operation, we focus on application general coronas to a new kind of characterization of trees with the domination subdivision number equal to 3.
-
A survey of neural networks usage for intrusion detection systems
PublicationIn recent years, advancements in the field of the artificial intelligence (AI) gained a huge momentum due to the worldwide appliance of this technology by the industry. One of the crucial areas of AI are neural networks (NN), which enable commer‐ cial utilization of functionalities previously not accessible by usage of computers. Intrusion detection system (IDS) presents one of the domains in which neural networks are widely tested...
-
Zero-visibility cops and robber and the pathwidth of a graph
PublicationWe examine the zero-visibility cops and robber graph searching model, which differs from the classical cops and robber game in one way: the robber is invisible. We show that this model is not monotonic. We show that the zero-visibility copnumber of a graph is bounded above by its pathwidth and cannot be bounded below by any nontrivial function of the pathwidth. As well, we define a monotonic version of this game and show that the...
-
On Tradeoffs Between Width- and Fill-like Graph Parameters
PublicationIn this work we consider two two-criteria optimization problems: given an input graph, the goal is to find its interval (or chordal) supergraph that minimizes the number of edges and its clique number simultaneously. For the interval supergraph, the problem can be restated as simultaneous minimization of the path width pw(G) and the profile p(G) of the input graph G. We prove that for an arbitrary graph G and an integer t ∈ {1,...
-
The convex domination subdivision number of a graph
PublicationLet G = (V;E) be a simple graph. A set D\subset V is a dominating set of G if every vertex in V - D has at least one neighbor in D. The distance d_G(u, v) between two vertices u and v is the length of a shortest (u, v)-path in G. An (u, v)-path of length d_G(u; v) is called an (u, v)-geodesic. A set X\subset V is convex in G if vertices from all (a, b)-geodesics belong to X for any two vertices a, b \in X. A set X is a convex dominating...
-
Parallel immune system for graph coloring
PublicationThis paper presents a parallel artificial immune system designed forgraph coloring. The algorithm is based on the clonal selection principle. Each processor operates on its own pool of antibodies and amigration mechanism is used to allow processors to exchange information. Experimental results show that migration improves the performance of the algorithm. The experiments were performed using a high performance cluster on a set...
-
Deep neural networks for data analysis
e-Learning CoursesThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Non-monotone graph searching models
PublicationGraph searching encompasses a variety of different models, many of which share a property that in optimal strategies fugitive can never access once searched regions. Monotonicity, as it is called, is vital in many established results in the field however its absence significantly impedes the analysis of a given problem. This survey attempts to gather non-monotone models, that are less researched in effort of summarizing the results...
-
Adding Interpretability to Neural Knowledge DNA
PublicationThis paper proposes a novel approach that adds the interpretability to Neural Knowledge DNA (NK-DNA) via generating a decision tree. The NK-DNA is a promising knowledge representation approach for acquiring, storing, sharing, and reusing knowledge among machines and computing systems. We introduce the decision tree-based generative method for knowledge extraction and representation to make the NK-DNA more explainable. We examine...
-
A Novel Iterative Decoding for Iterated Codes Using Classical and Convolutional Neural Networks
PublicationForward error correction is crucial for communication, enabling error rate or required SNR reduction. Longer codes improve correction ratio. Iterated codes offer a solution for constructing long codeswith a simple coder and decoder. However, a basic iterative code decoder cannot fully exploit the code’s potential, as some error patterns within its correction capacity remain uncorrected.We propose two neural network-assisted decoders:...
-
Product Graph Invariants with Applications in the Theory of Information
PublicationThere are a large number of graph invariants. In the paper, we consider some of them, e.g. the independence and chromatic numbers. It is well know that we cannot efficiently calculate these numbers for arbitrary graphs. In the paper we present relations between these invariants and concepts from the theory of information. Concepts such as source coding and transmission over a noisy channel with zero probability of error are modeled...
-
A construction for the hat problem on a directed graph
PublicationA team of n players plays the following game. After a strategy session, each player is randomly fitted with a blue or red hat. Then, without further communication, everybody can try to guess simultaneously his own hat color by looking at the hat colors of the other players. Visibility is defined by a directed graph; that is, vertices correspond to players, and a player can see each player to whom he is connected by an arc. The...
-
An Automated Method for Biometric Handwritten Signature Authentication Employing Neural Networks
PublicationHandwriting biometrics applications in e-Security and e-Health are addressed in the course of the conducted research. An automated graphomotor analysis method for the dynamic electronic representation of the handwritten signature authentication was researched. The developed algorithms are based on dynamic analysis of electronically handwritten signatures employing neural networks. The signatures were acquired with the use of the...
-
Zero-Visibility Cops and Robber Game on a Graph
PublicationWe examine the zero-visibility cops and robber graph searching model, which differs from the classical cops & robber game in one way: the robber is invisible. We show that this model is not monotonic. We also provide bounds on both the zero-visibility copnumber and monotonic zero-visibility copnumber in terms of the pathwidth.
-
Modeling the impact of surface currents in a harbor using graph theory
PublicationEnsuring security in a harbor requires research into its infrastructure using spatial environmental data. This paper presents a methodology that defines the design of a graph for modeling the interactions between surface currents and moving objects. Combining this graph with port charts that integrate electronic navigation charts with coastal orthophotographs allows us to perform a multidimensional analysis. In addition, the complete...
-
Collision-Free Network Exploration
PublicationA set of mobile agents is placed at different nodes of a n-node network. The agents synchronously move along the network edges in a collision-free way, i.e., in no round may two agents occupy the same node. In each round, an agent may choose to stay at its currently occupied node or to move to one of its neighbors. An agent has no knowledge of the number and initial positions of other agents. We are looking for the shortest possible...
-
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...
-
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...
-
Maritime Communications Network Development Using Virtualised Network Slicing of 5G Network
PublicationThe paper presents the review on perspectives of maritime systems development at the context of 5G systems implementation and their main properties. Firstly, 5G systems requirements and principles are discussed, which can be important for maritime applications. Secondly, the problems of network softwarisation, virtualisation and slicing, and possible types of services for potential implementation in 5G marine applications are described....
-
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...
-
Linear game non-contextuality and Bell inequalities—a graph-theoretic approach
PublicationWe study the classical and quantum values of a class of one-and two-party unique games, that generalizes the well-known XOR games to the case of non-binary outcomes. In the bipartite case the generalized XOR(XOR-d) games we study are a subclass of the well-known linear games. We introduce a 'constraint graph' associated to such a game, with the constraints defining the game represented by an edge-coloring of the graph. We use the...
-
Towards neural knowledge DNA
PublicationIn this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing,...
-
Weakly convex domination subdivision number of a graph
PublicationA set X is weakly convex in G if for any two vertices a; b \in X there exists an ab–geodesic such that all of its vertices belong to X. A set X \subset V is a weakly convex dominating set if X is weakly convex and dominating. The weakly convex domination number \gamma_wcon(G) of a graph G equals the minimum cardinality of a weakly convex dominating set in G. The weakly convex domination subdivision number sd_wcon (G) is the minimum...
-
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....
-
Distributed graph searching with a sense of direction
PublicationIn this work we consider the edge searching problem for vertex-weighted graphs with arbitrarily fast and invisible fugitive. The weight function w provides for each vertex v the minimum number of searchers required to guard v, i.e., the fugitive may not pass through v without being detected only if at least w(v) searchers are present at v. This problem is a generalization of the classical edge searching problem, in which one has...
-
A MODEL FOR FORECASTING PM10 LEVELS WITH THE USE OF ARTIFICIAL NEURAL NETWORKS
PublicationThis work presents a method of forecasting the level of PM10 with the use of artificial neural networks. Current level of particulate matter and meteorological data was taken into account in the construction of the model (checked the correlation of each variable and the future level of PM10), and unidirectional networks were used to implement it due to their ease of learning. Then, the configuration of the network (built on the...
-
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....
-
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...
-
Marzena Starnawska dr
People -
Graph Representation Integrating Signals for Emotion Recognition and Analysis
PublicationData reusability is an important feature of current research, just in every field of science. Modern research in Affective Computing, often rely on datasets containing experiments-originated data such as biosignals, video clips, or images. Moreover, conducting experiments with a vast number of participants to build datasets for Affective Computing research is time-consuming and expensive. Therefore, it is extremely important to...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublicationIn 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...