Wyszukiwarka
dr inż. Tomasz Maria Boiński
Zatrudnienie
- Adiunkt w Katedra Architektury Systemów Komputerowych
- Dyrektor Centrum Usług Informatycznych w Centrum Usług Informatycznych
Publikacje
Filtry
wszystkich: 47
Katalog Publikacji
Rok 2024
-
Data on LEGO sets release dates and worldwide retail prices combined with aftermarket transaction prices in Poland between June 2018 and June 2023
PublikacjaThe dataset contains LEGO bricks sets item count and pricing history for AI-based set pricing prediction. The data spans the timeframe from June 2018 to June 2023. The data was obtained from three sources: Brickset.com (LEGO sets retail prices, release dates, and IDs), Lego.com official web page (ID number of each set that was released by Lego, its retail prices, the current status of the set) and promoklocki.pl web page (the retail...
Rok 2023
-
Optimization of Bread Production Using Neuro-Fuzzy Modelling
PublikacjaAutomation of food production is an actively researched domain. One of the areas, where automation is still not progressing significantly is bread making. The process still relies on expert knowledge regarding how to react to procedure changes depending on environmental conditions, quality of the ingredients, etc. In this paper, we propose an ANFIS-based model for changing the mixer speed during the kneading process. Although the...
-
Photos and rendered images of LEGO bricks
PublikacjaThe paper describes a collection of datasets containing both LEGO brick renders and real photos. The datasets contain around 155,000 photos and nearly 1,500,000 renders. The renders aim to simulate real-life photos of LEGO bricks allowing faster creation of extensive datasets. The datasets are publicly available via the Gdansk University of Technology “Most Wiedzy” institutional repository. The source files of all tools used during...
Rok 2022
-
Active Learning Based on Crowdsourced Data
PublikacjaThe paper proposes a crowdsourcing-based approach for annotated data acquisition and means to support Active Learning training approach. In the proposed solution, aimed at data engineers, the knowledge of the crowd serves as an oracle that is able to judge whether the given sample is informative or not. The proposed solution reduces the amount of work needed to annotate large sets of data. Furthermore, it allows a perpetual increase...
-
How to Sort Them? A Network for LEGO Bricks Classification
PublikacjaLEGO bricks are highly popular due to the ability to build almost any type of creation. This is possible thanks to availability of multiple shapes and colors of the bricks. For the smooth build process the bricks need to properly sorted and arranged. In our work we aim at creating an automated LEGO bricks sorter. With over 3700 different LEGO parts bricks classification has to be done with deep neural networks. The question arises...
-
Segmentacja obrazów medycznych przy ograniczonej liczbie adnotacji
PublikacjaW dziedzinie badań klinicznych i opieki zdrowotnej tradycyjne podejście w uczeniu głębokim polegające na wykorzystaniu dużych zbiorów danych jest trudne w realizacji. Przyczyną takiego stanu rzeczy są koszty znakowania obrazów medycznych, zwłaszcza w przypadku segmentacji obrazów medycznych. Jest to żmudna operacja, która zazwyczaj wymaga intensywnego znakowania pikseli wykonanego przez ekspertów – lekarzy. W tym rozdziale zaprezentowano...
-
Video of LEGO Bricks on Conveyor Belt Dataset Series
PublikacjaThe dataset series titled Video of LEGO bricks on conveyor belt is composed of 14 datasets containing video recordings of a moving white conveyor belt. The recordings were created using a smartphone camera in Full HD resolution. The dataset allows for the preparation of data for neural network training, and building of a LEGO sorting machine that can help builders to organise their collections.
Rok 2021
-
ANFIS-Based NPC Population Control in Video Games
PublikacjaModern computer games aim at providing rich, vivid worlds. The aim is to encourage the player to explore and interact with the in-game world. To describe the complex relations between in-game NPCs and their surrounding fuzzy logic is used. The paper presents ANFIS based population control in the video game. We present an approach allowing stabilizing the number of NPCs in-game by providing a certain amount of food to the environment....
-
Hierarchical 2-step neural-based LEGO bricks detection and labeling
PublikacjaLEGO bricks are extremely popular and allow the creation of almost any type of construction due to multiple shapes available. LEGO building requires however proper brick arrangement, usually done by shape. With over 3700 different LEGO parts this can be troublesome. In this paper, we propose a solution for object detection and annotation on images. The solution is designed as a part of an automated LEGO bricks arrangement. The...
-
Licencjonowanie oprogramowania
PublikacjaWolne i otwarte oprogramowanie przeżywa ostatnimi laty rozkwit. Co raz więcej przedsiębiorstw komercyjnych opiera rozwój swoich firm na otwartym oprogramowaniu. Zarówno mali, jak i duzi gracze mają świadomość komplikacji współczesnych systemów i niemożności samodzielnego ich rozwoju. Z pomocą przychodzi otwarte podejście do wytwarzania oprogramowania. Wymaga to jednak pewnego zrozumienia uwarunkowań prawnych, a w szczególności...
-
Optimization of Data Assignment for Parallel Processing in a Hybrid Heterogeneous Environment Using Integer Linear Programming
PublikacjaIn the paper we investigate a practical approach to application of integer linear programming for optimization of data assignment to compute units in a multi-level heterogeneous environment with various compute devices, including CPUs, GPUs and Intel Xeon Phis. The model considers an application that processes a large number of data chunks in parallel on various compute units and takes into account computations, communication including...
Rok 2020
-
Bidirectional Fragment to Fragment Links in Wikipedia
PublikacjaThe paper presents a WikiLinks system that extends the Wikipedia linkage model with bidirectional links between fragments of the articles and overlapping links’ anchors. The proposed model adopts some ideas from the research conducted in a field of nonlinear, computer-aided writing, often called a hypertext. WikiLinks may be considered as a web augmentation tool but it presents a new approach to the problem that addresses the specific...
-
Collaborative Data Acquisition and Learning Support
PublikacjaWith the constant development of neural networks, traditional algorithms relying on data structures lose their significance as more and more solutions are using AI rather than traditional algorithms. This in turn requires a lot of correctly annotated and informative data samples. In this paper, we propose a crowdsourcing based approach for data acquisition and tagging with support for Active Learning where the system acts as an...
-
NLP Questions Answering Using DBpedia and YAGO
PublikacjaIn this paper, we present results of employing DBpedia and YAGO as lexical databases for answering questions formulated in the natural language. The proposed solution has been evaluated for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference). Our method uses dependency trees generated from the user query. The trees are browsed for paths leading from the root of the tree to the question...
-
Towards Extending Wikipedia with Bidirectional Links
PublikacjaIn this paper, we present the results of our WikiLinks project which aims at extending current Wikipedia linkage mechanisms. Wikipedia has become recently one of the most important information sources on the Internet, which still is based on relatively simple linkage facilities. A WikiLinks system extends the Wikipedia with bidirectional links between fragments of articles. However, there were several attempts to introduce bidirectional...
Rok 2019
-
Crowdsourcing-Based Evaluation of Automatic References Between WordNet and Wikipedia
PublikacjaThe paper presents an approach to build references (also called mappings) between WordNet and Wikipedia. We propose four algorithms used for automatic construction of the references. Then, based on an aggregation algorithm, we produce an initial set of mappings that has been evaluated in a cooperative way. For that purpose, we implement a system for the distribution of evaluation tasks, that have been solved by the user community....
-
Exact-match Based Wikipedia-WordNet Integration
PublikacjaAbility to link between WordNet synsets and Wikipedia articles allows usage of those resources by computers during natural language processing. A lot of work was done in this field, however most of the approaches focus on similarity between Wikipedia articles and WordNet synsets rather than creation of perfect matches. In this paper we proposed a set of methods for automatic perfect matching generation. The proposed methods were...
Rok 2018
-
Assessing Word Difficulty for Quiz-Like Game
PublikacjaMappings verification is a laborious task. Our research aims at providing a framework for manual verification of mappings using crowdsourcing approach. For this purpose we plan on implementing a quiz like game. For this purpose the mappings have to be evaluated in terms of difficulty to better present texts in respect of game levels. In this paper we present an algorithm for assessing word difficulty. Three approaches...
-
DBpedia and YAGO as Knowledge Base for Natural Language Based Question Answering—The Evaluation
PublikacjaThe idea of automatic question answering system has a very long history. Despite constant improvement of the systems asking questions in the natural language requires very complex solutions. In this paper the DBpedia and YAGO are evaluated as a knowledge bases for simple class 1 and 2 question answering system. For this purpose a question answering system was designed and implemented. The proposed solution and the knowledge bases...
-
DBpedia and YAGO Based System for Answering Questions in Natural Language
PublikacjaIn this paper we propose a method for answering class 1 and class 2 questions (out of 5 classes defined by Moldovan for TREC conference) based on DBpedia and YAGO. Our method is based on generating dependency trees for the query. In the dependency tree we look for paths leading from the root to the named entity of interest. These paths (referenced further as fibers) are candidates for representation of actual user intention. The...
-
Evaluating Asymmetric N-Grams as Spell-Checking Mechanism
PublikacjaTypical approaches to string comparing marks two strings as either different or equal without taking into account any similarity measures. Being able to judge similarity is however required for spelling error corrections, as we want to find the best match for a given word. In this paper we present a bi2quadro-grams method for spelling errors correction. The method proposed uses different n-grams dimension for the source (checked)...
Rok 2017
-
Towards facts extraction from text in Polish language
PublikacjaNatural Language Processing (NLP) finds many usages in different fields of endeavor. Many tools exists allowing analysis of English language. For Polish language the situation is different as the language itself is more complicated. In this paper we show differences between NLP of Polish and English language. Existing solutions are presented and TEAMS software for facts extraction is described. The paper shows also evaluation of...
Rok 2016
-
Adaption of Open Science Paradigm at Gdańsk University of Technology
PublikacjaThe paper describes the basic principles standing behind Open Access and will try to dispel the doubts behind them. Further the solution adapted by the Gdańsk University of Technology is presented. Later on the systems that the University uses and means of their integration into a complex Open Science platform are described. Finally the procedures needed to publish a document in the repository alongside the University's policy...
-
Game with a Purpose for Mappings Verification
PublikacjaMappings verification is a laborious task. The paper presents a Game with a Purpose based system for verification of automatically generated mappings. General description of idea standing behind the games with the purpose is given. Description of TGame system, a 2D platform mobile game with verification process included in the gameplay, is provided. Additional mechanisms for anti-cheating, increasing player’s motivation and gathering...
Rok 2015
-
Adaption of Open Science Paradigm at Gdańsk University of Technology
PublikacjaOpen Access plays growing role in sharing results of today's research. The movement is very strong and many Universities, including Gdańsk University of Technology, are adapting this approach. This paper presents general information about Open Access movement and the approach adapted by the Gdańsk University of Technology. The components of Open Science platform as well as the procedures are described.
-
DBpedia As a Formal Knowledge Base – An Evaluation
PublikacjaDBpedia is widely used by researchers as a mean of accessing Wikipedia in a standardized way. In this paper it is characterized from the point of view of questions answering system. Simple implementation of such system is also presented. The paper also characterizes alternatives to DBpedia in form of OpenCyc and YAGO knowledge bases. A comparison between DBpedia and those knowledge bases is presented.
Rok 2014
-
Knowledge Base Suitable for Answering Questions in Natural Language
PublikacjaThis paper presents three knowledge bases widely used by researchers coping with natural language processing: OpenCyc, DBpedia and YAGO. They are characterized from the point of view of questions answering system. In this paper a short description of the aforementioned system implementation is also presented.
-
Relation-based Wikipedia Search System for Factoid Questions Answering
PublikacjaIn this paper we propose an alternative keyword search mechanism for Wikipedia, designed as a prototype solution towards factoid questions answering. The method considers relations between articles for finding the best matching article. Unlike the standard Wikipedia search engine and also Google engine, which search the articles content independently, requiring the entire query to be satisfied by a single article, the proposed...
-
Towards Facts Extraction From Texts in Polish Language
PublikacjaThe Polish language differs from English in many ways. It has more complicated conjugation and declination. Because of that automatic facts extraction from texts is difficult. In this paper we present basic differences between those languages. The paper presents an algorithm for extraction of facts from articles from Polish Wikipedia. The algorithm is based on 7 proposed facts schemes that are searched for in the analyzed text....
Rok 2013
-
Improvement of Imperfect String Matching Based on Asymetric n-Grams
PublikacjaTypical approaches to string comparing treats them as either different or identical without taking into account the possibility of misspelling of the word. In this article we present an approach we used for improvement of imperfect string matching that allows one to reconstruct potential string distortions. The proposed method increases the quality of imperfect string matching, allowing the lookup of misspelled words without significant...
Rok 2012
-
Dynamic OWL Ontology matching Using Lexical Wordnet-based Measures
PublikacjaOntologies are often used as a means of describing knowledge and the domain of operation of modern applications. S need arises for the ability to quickly match those ontologies to enable interoperability of such systems. This paper presents an extension to Noy and McGuiness ontology construction methodology which should improve ontology interoperability and a lexicon-based algorithm for merging and aligning of such ontologies stored...
-
Extendable Safety and Security Ontology
PublikacjaSecurity plays an increasingly important role in our everyday life, and research and users of computer systems point out that the need arises for a common, formalised model capable of integrating different solutions. In this paper we show that an ontology can be designed and created in a way that will make it suitable for interoperability and integration. A security and safety ontology and the methodology for creating a common...
-
Inżynieria ontologii dla potrzeb integracji systemów
PublikacjaInżynieria ontologii to gałąź inżynierii wiedzy, która zajmuje się metodami i metodologiami budowy ontologii. Zajmuje się m. in. procesem wytwarzania, cyklem życia oraz narzędziami wspomagającymi wytwarzanie ontologii. W publikacji przedstawiono różne metodologie wytwarzania ontologii oraz wspierające te metodologie narzędzia. Omówiono edytor ontologii OCS, opracowany przez Katedrę ASK Wydziału ETI PG, oraz wykorzystaną w nim,...
-
Lexicon Based Algorithm for Domain Ontology Merging and Alignment
PublikacjaMore and more systems contain some kind of knowledge describing their field of operation. Such knowledge in many cases is stored as an ontology. A need arises for ability to quickly match those ontologies to enable interoperability of such systems. The paper presents a lexicon based algorithm for merging and aligning of OWL ontologies. The proposed similarity levels are being presented and the proposed algorithm is being described....
-
Optymalizacja równoważenia obciążeń w systemach klasy grid
PublikacjaZaprezentowano techniki równoważenia obciążeń testowane w systemie rozproszonym Comcute o architekturze typu grid. Omówiono niezbędne uwarunkowania środowiska prowadzenia obliczeń w zestawie laboratoryjnym Politechniki Gdańskiej, a także odniesiono się do kryteriów kierunkujących równoważenie obciążeń. Przedstawiono wielopoziomową metodę równoważenia obciążeń.
-
Procedury odwzorowania i łączenia ontologii dziedzinowych
PublikacjaW trakcie prac nad rozprawą opracowano oryginalną metodę integracji ontologii na podstawie analizy leksykalnej jej elementów. Zaproponowany algorytm został zaimplementowany w postaci biblioteki w języku Java oraz włączony do systemu OCS. Opracowano również procedury i narzędzia pomocnicze wspierające proces integracji wiedzy, w tym autorską bibliotekę wizualizacji ontologii SOVA.Zaprojektowano i zaimplementowano ontologię bezpieczeństwa...
Rok 2011
-
Security ontology construction and integration
PublikacjaThere are many different levels on which we can examine security. Each one is different from others, all of them are dependent on the context. Hence the need to bear additional knowledge enabling efficient utilization of the knowledge by the computers. Such information can be provided by ontologies. The paper presentsgathered requirements needed to be taken into account when creating an ontology. The method of ontology creation...
Rok 2010
-
Budowa ontologii usług dla potrzeb wyszukiwania
PublikacjaOntologie, dzięki zapewnieniu formalnego opisu przy zachowaniu czytelności dla człowieka, są coraz powszechniej stosowaną metodą opisu usług sieciowych. Zaprezentowano słownik WordNet i jego zastosowanie jako meta ontologia do opisów usług podobnych różnych dostawców. Zaproponowano algorytm oparty o ten słownik umożliwiający integrację ontologii usług w celu zapewnienia interoperacyjności rozwiązań dostępnych w sieci Internet.
-
Influence and selection of basic concepts on ontology design
PublikacjaOntologies as entities representing individual point of view on surrounding world introduce heterogeneity to knowledge representation. Common set of core concepts can introduce similarity big enough for further interoperability between ontologies. In this paper an experiment is presented proving that despite differences in detail ontologies stay similar in regard of core concepts. During the experiments NOIA methodology enhanced...
-
Ontology Visualization
PublikacjaOntologie bardzo często są reprezentowane w postaci grafu, którego wierzchołkami są obiekty występujące w prezentowanej ontologii a krawędziami relacje i powiązania pomiędzy tymi obiektami. Grafy reprezentujące ontologie mogą być złożone już dla średniego rozmiaru ontologii. Stąd niezbędna jest pełna i czytelna reprezentacja elementów takiego grafu. Dostępne rozwiązania zazwyczaj nie oferują reprezentacji pełnego zbioru elementów...
-
Zespołowa budowa ontologii z wykorzystaniem systemu OCS oraz edytora Protégé
PublikacjaKonstruowanie ontologii wymaga współpracy wielu osób. W idealnej sytuacji nad pojedynczą ontologią pracować będzie duża, rozproszona społeczność tworząca tym samym wspólną reprezentację wiedzy z danej dziedziny. W publikacji zaprezentowano propozycję modelu pracy grupowej nad ontologią. Zdefiniowano model zarządzania wersjami ontologii. Przedstawiono system Ontology Creation System (OCS) oraz architekturę i implementację rozszerzenia...
Rok 2009
-
Dynamiczne zarządzanie tożsamością użytkowników w przestrzeniach inteligentnych
PublikacjaOmówiono zagadnienie uwierzytelniania oraz przedstawionoróżnice pomiędzy rozwiązaniami dostarczanymi przez systemy Linux oraz Windows. Zaprezentowano dwie metody zapewnienia centralizowanego systemu uwierzytelniającego. Obie metody były przetestowane w praktyce w sieci laboratorium komputerowego katedry KASK. Na tej podstawie wskazano metodę zdolną do zapewnienia bezpieczeństwa przestrzeni inteligentnej, w której to użytkownicy...
-
OSC - domain oriented ontology creation system
PublikacjaOntologies are, as part of semantic web, a basic component to enrich content available in the Internet with a meaning understandable for computers. In this publication an architecture and functionality of a domain oriented web portal for collaborative creation and storage of ontologies is presented. The system is being created by Gdańsk University of Technology Electronics, Telecommunications and Informatics faculty's Department...
Rok 2008
-
Portal ontologii: Architektura portalu dziedzinowego
Publikacjazaprezentowano koncepcję architektury i funkcjonalności dziedzinowego portalu tworzenia ontologii realizowanego przez Katedrę KASK. Portal podzielony został na niezależne komponenty, które z powodzeniem mozna realizować odrębnie a następnie połączyć za pomocą ich interfejsów. W dalszej części pracy omówione zostaną poszczególne elemnty systemu i ich zadania. następnie przedstawiona będzie sugerowana metodologia wytwarzania systemu....
Rok 2007
-
Object serialization and remote exception pattern for distributed C++/MPI application
PublikacjaMPI is commonly used standard in development of scientific applications. It focuses on interlanguage operability and is not very well object oriented. The paper proposes a general pattern enabling design of distributed and object oriented applications. It also presents its sample implementations and performance tests.
Rok 2006
-
Parallelisation of genetic algorithms for solving university timetabling problems
PublikacjaAlgorytmy genetyczne stanowią ważną metodę rozwiązywania problemów optymalizacyjnych. W artykule skupiono się na projekcie równoległego algorytmu genetycznego pozwalającego uzyskiwać uniwersyteckie rozkłady zajęć, spełniające zarówno twarde jak i miękkie ograniczenia. Czytelnika wprowadzono w niektóre znane sposoby zrównoleglenia, przedstawiono również podejście autorów, ykorzystujące MPI. Przyjęto strukturę zarządzania opartą...
-
Podstawowe mechanizmy systemu Linux w przetwarzaniu rozproszonym
PublikacjaLinux to otwarty, ciągle rozwijany system operacyjny. Dostępność kodu źródłowego oraz pełnej dokumentacji zaowocowała rozwojem wielumechanizmów wspierających przetwarzanie rozproszone. W systemie Linuxzaimplementowane zostały proste mechanizmy typu gniazda czy potoki jak i bardziej zaawansowane typu współdzielenie systemu plików czy możliwość tworzenia klastrów opartych o migracji procesów czy przekazywanie komunikatów. Narzędzia...
wyświetlono 6211 razy