Search
Search results for: knowledge representation
-
An Analysis of Neural Word Representations for Wikipedia Articles Classification
PublicationOne of the current popular methods of generating word representations is an approach based on the analysis of large document collections with neural networks. It creates so-called word-embeddings that attempt to learn relationships between words and encode this information in the form of a low-dimensional vector. The goal of this paper is to examine the differences between the most popular embedding models and the typical bag-of-words...
-
Combined spline wavelet decomposition for 3d seafloor imaging from multibeam sonar echoes
PublicationThe paper proposes combined spline-wavelet approach to the raw echoes seaflor imaging from Multibeam Sonar System (MBSS) records. Wavelet representation is closely related to image representation, due to its unique approximations properties. Splines have the best approximation properties among all known wavelets of a given order, so they are best suited for approximating of smooth seafloor surface. Additionaly, wavelet bases have...
-
A note on a Wiener-Wintner theorem for mean ergodic Markov amenable semigroups
PublicationWe prove a Wiener-Wintner ergodic type theorem for a Markov representation of a right amenable semitopological semigroup.
-
Convergence to equilibrium under a random Hamiltonian
PublicationWe analyze equilibration times of subsystems of a larger system under a random total Hamiltonian, in which the basis of the Hamiltonian is drawn from the Haar measure. We obtain that the time of equilibration is of the order of the inverse of the arithmetic average of the Bohr frequencies. To compute the average over a random basis, we compute the inverse of a matrix of overlaps of operators which permute four systems. We first...
-
MULTI-CRITERIA MODEL IN MULTIFUNCTIONAL BUILDING SYSTEM DESIGN PROCESS
PublicationThe paper presents a multi-criteria approach in multifunctional building system design process. The aim is to develop a theory relative to the engineering system of multifunctional with a mathematical representation defined by a holistic network for the lifecycle of the designed object. The idea of work was to define the structure of a complex system. Background for the presented field is to develop a design strategy for multifunctional...
-
Modeling emotions for affect-aware applications
PublicationThe chapter concerns emotional states representation and modeling for software systems, that deal with human affect. A review of emotion representation models is provided, including discrete, dimensional and componential models. The paper provides also analysis of emotion models used in diverse types of affect-aware applications: games, mood trackers or tutoring systems. The analysis is supported with two design cases. The study...
-
Embedded Representations of Wikipedia Categories
PublicationIn this paper, we present an approach to building neural representations of the Wikipedia category graph. We test four different methods and examine the neural embeddings in terms of preservation of graphs edges, neighborhood coverage in representation space, and their influence on the results of a task predicting parent of two categories. The main contribution of this paper is application of neural representations for improving the...
-
Geometric Algebra Model of Distributed Representations
PublicationFormalism based on GA is an alternative to distributed representation models developed so far-Smolensky's tensor product, Holographic Reduced Representations (HRR) and Binary Spatter Code (BSC). Convolutions are replaced by geometric products, interpretable in terms of geometry which seems to be the most natural language for visualization of higher concepts. This paper recalls the main ideas behind the GA model and investigates...
-
Teleportation of geometric structures in 3D
PublicationThe simplest quantum teleportation algorithms can be represented in geometric terms in spaces of dimensions 3 (for real state vectors) and 4 (for complex state vectors). The geometric representation is based on geometric-algebra coding, a geometric alternative to the tensor-product coding typical of quantum mechanics. We discuss all the elementary ingredients of the geometric version of the algorithm: geometric analogs of states...
-
Visualization of short-term heart period variability with network tools as a method for quantifying autonomic drive
PublicationWe argue that network methods are successful in detecting nonlinear properties in the dynamics of autonomic nocturnal regulation in short-term variability. Two modes of visualization of networks constructed from RR-increments are proposed. The first is based on the handling of a state space. The state space of RR-increments can be modified by a bin size used to code a signal and by the role of a given vertex as the representation...
-
A Hopf type theorem for equivariant local maps
PublicationWe study otopy classes of equivariant local maps and prove a Hopf type theorem for such maps in the case of a real finite-dimensional orthogonal representation of a compact Lie group.
-
A Quasi-2D MOSFET Model — 2D-to-Quasi-2D Transformation
PublicationA quasi-two-dimensional (quasi-2D) representation of the MOSFET channel is proposed in this work. The representation lays the foundations for a quasi 2D MOSFET model. The quasi 2D model is a result of a 2D into quasi 2D transformation. The basis for the transformation are an analysis of a current density vector field and such phenomena as Gradual Channel Detachment Effect (GCDE), Channel Thickness Modulation Effect (CTME), and...
-
Non-linear circuit model of a single doubly-fed induction machine formulated in natural axes for drive systems simulation purposes
PublicationMathematical modelling and a circuit model formulated in natural axes of a single doubly-fed induction machine, with the account of magnetic circuit nonlinearity are presented in the paper. Derivation of the model differential equations was based on Lagrange's energy method. State functions of magnetic elements in the model are non-linear and depend on all currents flowing in the machine windings and on the angle of rotor position....
-
Theory versus experiment for vacuum Rabi oscillations in lossy cavities. II. Direct test of uniqueness of vacuum
PublicationThe paper continues the analysis of vacuum Rabi oscillations we started in part I [Phys. Rev. A 79, 033836 (2009)]. Here we concentrate on experimental consequences for cavity QED of two different classes of representations of harmonic-oscillator Lie algebras. The zero-temperature master equation, derived in part I for irreducible representations of the algebra, is reformulated in a reducible representation that models electromagnetic...
-
GRAPHICAL REPRESENTATION OF MUSIC SET BASED ON MOOD OF MUSIC. GRAFICZNA PREZENTACJA ZBIORU MUZYCZNEGO OPARTA NA ANOTACJI NASTROJU MUZYKI
PublicationOne of the features for music recommendation, which is useful and intuitive for music listen-ers, is “mood”. The paper presents an approach to graphical representation of mood of music pieces. Subjective evaluation based on listening tests is performed for assigning mood labels of 150 pieces of music and placing them on the 2D mood plane. As a result, a map of songs is created, where music excerpts with similar mood are organized...
-
GROUP COMPOSER - System for Modeling Agents’ Team Building for Tasks
PublicationMulti-agent systems consist of many autonomous units, called agents, that can interact when trying to achieve their goals. The selection of interaction partners is called team formation. Three basic approaches can be considered to match multi-agent system resources to the problem at hand. To research the properties of different approaches, a software for modeling team formation in multi-agent systems has been created and is presented...
-
Sparse autoregressive modeling
PublicationIn the paper the comparison of the popular pitch determination (PD) algorithms for thepurpose of elimination of clicks from archive audio signals using sparse autoregressive (SAR)modeling is presented. The SAR signal representation has been widely used in code-excitedlinear prediction (CELP) systems. The appropriate construction of the SAR model is requiredto guarantee model stability. For this reason the signal representation...
-
Text Categorization Improvement via User Interaction
PublicationIn this paper, we propose an approach to improvement of text categorization using interaction with the user. The quality of categorization has been defined in terms of a distribution of objects related to the classes and projected on the self-organizing maps. For the experiments, we use the articles and categories from the subset of Simple Wikipedia. We test three different approaches for text representation. As a baseline we use...
-
Rapid Design Tuning of Miniaturized Rat-Race Couplers Using Regression-Based Equivalent Network Surrogates
PublicationA simple technique for fast design tuning of compact rat-race couplers is presented. Our approach involves equivalent circuit representation, corrected by nonlinear functions of frequency with coefficients extracted through nonlinear regression. At the same time, the tuning process connects two levels of coupler representation: EM simulation of the entire circuit and re-optimization of the coupler building blocks (slow-wave cells...
-
TF-IDF weighted bag-of-words preprocessed text documents from Simple English Wikipedia
Open Research DataThe SimpleWiki2K-scores dataset contains TF-IDF weighted bag-of-words preprocessed text documents (raw strings are not available) [feature matrix] and their multi-label assignments [label-matrix]. Label scores for each document are also provided for an enhanced multi-label KNN [1] and LEML [2] classifiers. The aim of the dataset is to establish a benchmark...
-
Text classifiers for automatic articles categorization
PublicationThe article concerns the problem of automatic classification of textual content. We present selected methods for generation of documents representation and we evaluate them in classification tasks. The experiments have been performed on Wikipedia articles classified automatically to their categories made by Wikipedia editors.
-
Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
PublicationMy doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.
-
Semantic rules representation in controlled natural language in FluentEditor
PublicationThis paper presents a way of representation of semantic rules (SWRL) in controlled English in order to facilitate understanding the rules by humans interacting with a machine. This approach (implemented in FluentEditor) may be applied in many domains, where the understandability of the rules used to support a decision process is of great importance.
-
Wikipedia Articles Representation with Matrix'u
PublicationIn the article we evaluate different text representation methods used for a task of Wikipedia articles categorization. We present the Matrix’u application used for creating computational datasets ofWikipedia articles. The representations have been evaluated with SVM classifiers used for reconstruction human made categories.
-
Equivariant Morse equation
PublicationThe paper is concerned with the Morse equation for flows in a representation of a compact Lie group. As a consequence of this equation we give a relationship between the equivariant Conley index of an isolated invariant set of the flow given by x˙ = − ∇f(x) and the gradient equivariant degree of ∇f. Some multiplicity results are also presented.
-
Strategien der NSZZ Solidarność. Ein kurzer Abriss über bewährte Verfahrensweisen
PublicationDuring the recent years, the difficulties faced by trade unions to maintain their representation base and capacity to regulate employment relations have provoked numerous discussions. The issue of declining trade union membership, as well as density, has been repeatedly addressed by major trade unions including NSZZ “S”.
-
Composition of data visualizations by sub-bottom profiler and multibeam echosounder in Matlab
PublicationThis paper contains description of procedure, which was elaborated in a numerical computing environment Matlab. The result of these procedures is a graphical composition of images obtained from two different hydroacoustic devices. It enables to compare different types of visualizations for the same geographical position and simultaneous work with graphical representation of all data types.
-
The Hopf type theorem for equivariant gradient local maps
PublicationWe construct a degree-type otopy invariant for equivariant gradient local maps in the case of a real finite-dimensional orthogonal representation of a compact Lie group. We prove that the invariant establishes a bijection between the set of equivariant gradient otopy classes and the direct sum of countably many copies of Z.
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationThe study addresses the issues related to the appropriateness of a two-dimensional representation of speech signal for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and time-frequency signal representation converted to the investigated feature spaces. In particular, waveforms and fractal dimension features of the signal were chosen for the time domain, and...
-
LEVEL OF DETAIL CATEGORIZATION FOR THE APPLICATION IN URBAN DESIGN
PublicationUrban planning and urban design involve complex processes that require detailed information about the visual information of a place at various scales. Different graphic tools, such as game engines, are evolving to use urban representation fields. The concept of "level of detail" (LOD) has been used to categorize the level of detail in AEC applications such as BIM and GML for urban representation models. However, there is a need...
-
Block-based Representation of Application Execution on Modern Parallel Systems
PublicationThe chapter presents how to model execution of a parallel computational application that is to be executed in a large-scale parallel or distributed environment with potentially thousands to millions of execution units. The representation uses pre- viously attributes and factors representative of modern high performance systems including multicore CPUs, GPUs, dedicated accelerators such as Intel Phi.
-
Application of Intelligent Conversational Agents in E-learing Environments
PublicationThe paper concerns intelligent tutoring systems and concentrates on apliaction of virtual mentors in distance learning environments. Different educational agent types are described. The prototype of an agent developed at Gdansk University of Technology is also presented, as well as its internal representation and construction. Benefits of virtual mentors applied in distance learning are also pointed out.
-
Multi-objective optimization of microwave couplers using corrected domain patching
PublicationPractical design of microwave components and circuits is a compromise between various, often conflicting objectives. In case of compact structures, the trade-offs are typically concerned with the circuit size and its electrical performance. Comprehensive information about the best possible trade-offs can be obtained by means of multi-objective optimization. In this paper, we propose a computationally efficient technique for identifying...
-
Spectral Clustering Wikipedia Keyword-Based search Results
PublicationThe paper summarizes our research in the area of unsupervised categorization of Wikipedia articles. As a practical result of our research, we present an application of spectral clustering algorithm used for grouping Wikipedia search results. The main contribution of the paper is a representation method for Wikipedia articles that has been based on combination of words and links and used for categoriation of search results in this...
-
Modelling of Geared Multi-Rotor System
PublicationIn the paper the method of modelling a speed-varying geared rotor system is presented. The proposed approach enables us to obtain an accurate low-order lumped parameter representation of the investigated system. The final model consists of reduced modal models of an undamped beam/torsional shaft system as well as a spatially lumped model of other linear and nonlinear phenomena including gear mesh interaction.
-
Distributed Representations Based on Geometric Algebra: the Continuous Model
PublicationAuthors revise the concept of a distributed representation of data as well as two previously developed models: Holographic Reduced Representation (HRR) and Binary Spatter Codes (BSC). A Geometric Analogue (GAc - ''c'' stands for continuous as opposed to its discrete version) of HRR is introduced - it employs role-filler binding based on geometric products. Atomic objects are real-valued vectors in n-dimensional Euclidean space...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
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...
-
Distributed representation of information on cyclic events
PublicationA representation of information on cyclic events has been proposed which is advantageous for computing environments where a distributed set of Receivers reacts to cyclic events generated by distributed sources. In such scenario no immanent central information repository exist on event timing or volume. Receivers are able to learn the event cycles without communicating with each other, merely on the basis of the fact that an event...
-
Dangerous sound event recognition using Support Vector Machine classifiers
PublicationA method of recognizing events connected to danger based on their acoustic representation through Support Vector Machine classification is presented. The method proposed is particularly useful in an automatic surveillance system. The set of 28 parameters used in the classifier consists of dedicated parameters and MPEG-7 features. Methods for parameter calculation are presented, as well as a design of SVM model used for classification....
-
Port-based approach to distributed transfer function method
PublicationIn the paper there is presented an uniform, port-based approach to modeling of both lumped and distributed parameter systems. Port-based model of distributed system has been defined by application of distributed transfer function method (DTFM). The approach proposed combines versatility of port - based modeling and accuracy of distributed transfer function method. It enables to formulate appropriate input data for computer analysis...
-
KOLMOGOROV EQUATION SOLUTION: MULTIPLE SCATTERING EXPANSION AND PHOTON STATISTICS EVOLUTION MODELING
PublicationWe consider a formulation of the Cauchy problem for the Kolmogorov equation which corresponds to a localized source of particles to be scattered by a medium with a given scattering amplitude density. The multiple scattering amplitudes are introduced and the corresponding series solution of the equation is constructed. We investigate the integral representation for the first series terms, its estimations and values of the photon...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
Towards New Mappings between Emotion Representation Models
PublicationThere are several models for representing emotions in affect-aware applications, and available emotion recognition solutions provide results using diverse emotion models. As multimodal fusion is beneficial in terms of both accuracy and reliability of emotion recognition, one of the challenges is mapping between the models of affect representation. This paper addresses this issue by: proposing a procedure to elaborate new mappings,...
-
Analysis-by-synthesis paradigm evolved into a new concept
PublicationThis work aims at showing how the well-known analysis-by-synthesis paradigm has recently been evolved into a new concept. However, in contrast to the original idea stating that the created sound should not fail to pass the foolproof synthesis test, the recent development is a consequence of the need to create new data. Deep learning models are greedy algorithms requiring a vast amount of data that, in addition, should be correctly...
-
Properties and interpretation of Instantaneous Complex Frequency
PublicationThe concept of Instantaneous Complex Frequency (ICF) was first defined by Lindon and developed mainly in works of two authors S. Hahn and M. Rojewski. Although it is not widely used in signal analysis, ICF was already used as a complex signal representation in the verification of handwritten signatures, pitch estimation, symbol timing recovery in PSK receiver and in detection of anomalies in data transmission. It should be noted,...
-
Management of Textual Data at Conceptual Level
PublicationThe article presents the approach to the management of a large repository of documents at conceptual level. We describe our approach to representing Wikipedia articles using their categories. The representation has been used to construct groups of similar articles. Proposed approach has been implemented in prototype system that allows to organize articles that are search results for a given query. Constructed clusters allow to...
-
Integrable zero-range potentials in a plane
PublicationWe examine general statements in the Wronskian representation of Darboux transformations for plane zero-range potentials. Such expressions naturally contain scattering problem solution. We also apply Abel theorem to Wronskians for differential equations and link it to chain equations for Darboux transforms to fix conditions for further development of the underlying distribution concept. Moutard transformations give a convenient...
-
The equivariant spectral flow and bifurcation of periodic solutions of Hamiltonian systems
PublicationWe define a spectral flow for paths of selfadjoint Fredholm operators that are equivariant under the orthogonal action of a compact Lie group as an element of the representation ring of the latter. This G-equivariant spectral flow shares all common properties of the integer valued classical spectral flow, and it can be non-trivial even if the classical spectral flow vanishes. Our main theorem uses the G-equivariant spectral flow...
-
Resource constrained neural network training
PublicationModern applications of neural-network-based AI solutions tend to move from datacenter backends to low-power edge devices. Environmental, computational, and power constraints are inevitable consequences of such a shift. Limiting the bit count of neural network parameters proved to be a valid technique for speeding up and increasing efficiency of the inference process. Hence, it is understandable that a similar approach is gaining...