Filters
total: 125
filtered: 113
-
Catalog
Chosen catalog filters
Search results for: SEMANTIC KNOWLEDGE
-
Problemy wnioskowania z ontologii Semantic Web
PublicationIdea Semantic Web (Semantycznego Internetu) opiera się m.in. na ogłaszaniu w Internecie ontologii stanowiących opis pewnego fragmentu rzeczywistości. Aby miało to sens, ontologie te muszą być sformułowane w jednym, powszechnie akceptowanym języku. Takim językiem jest OWL-DL, promowany i standaryzowany przez konsorcjum W3C. Jest to język opary na formalizmie logicznym zwanym logiką opisową. W tym artykule, po krótkim i nieformalnym...
-
Wnioskowanie z danych zapisanych w zewnętrznych źródłach w systemie zarządzania wiedzą
PublicationRozdział prezentuje proces wnioskowania z danych przechowywanych w zewnętrznych źródłach. W procesie tym wykorzystywane są dwie nowe metody: metoda semantycznego wzbogacania źródeł - SED (Semantic Enrichment of Data) oraz wykorzystująca ją metoda wnioskowania z danych zewnętrznych - RED (Reasoning over External Data). Obie te metody zostały w niniejszym rozdziale przedstawione. Metoda SED służy do opisania zewnętrznych źródeł danych...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Semantic segmentation training using imperfect annotations and loss masking
PublicationOne of the most significant factors affecting supervised neural network training is the precision of the annotations. Also, in a case of expert group, the problem of inconsistent data annotations is an integral part of real-world supervised learning processes, well-known to researchers. One practical example is a weak ground truth delineation for medical image segmentation. In this paper, we have developed a new method of accurate...
-
Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift
PublicationWhile recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task...
-
Urban scene semantic segmentation using the U-Net model
PublicationVision-based semantic segmentation of complex urban street scenes is a very important function during autonomous driving (AD), which will become an important technology in industrialized countries in the near future. Today, advanced driver assistance systems (ADAS) improve traffic safety thanks to the application of solutions that enable detecting objects, recognising road signs, segmenting the road, etc. The basis for these functionalities...
-
Asking Data in a Controlled Way with Ask Data Anything NQL
PublicationWhile to collect data, it is necessary to store it, to understand its structure it is necessary to do data-mining. Business Intelligence (BI) enables us to make intelligent, data-driven decisions by the mean of a set of tools that allows the creation of a potentially unlimited number of machine-generated, data-driven reports, which are calculated by a machine as a response to queries specified by humans. Natural Query Languages...
-
Techniki modularyzacji ontologii
PublicationW ciągu ostatnich kilku lat tematem wielu prac naukowych stała się modularyzacja ontologii. Istnieje kilka przyczyn dużego zainteresowania tym kierunkiem prac. Z jednej strony ontologie wykazały swoją przydatność w różnego rodzaju przedsięwzięciach związanych z inicjatywą Semantic Web. Z drugiej strony okazało się, że po przekroczeniu pewnej granicy wielkości ontologii inżynierowie wiedzy natykają się na problemy, z którymi inżynieria...
-
Distributed Architectures for Intensive Urban Computing: A Case Study on Smart Lighting for Sustainable Cities
PublicationNew information and communication technologies have contributed to the development of the smart city concept. On a physical level, this paradigm is characterised by deploying a substantial number of different devices that can sense their surroundings and generate a large amount of data. The most typical case is image and video acquisition sensors. Recently, these types of sensors are found in abundance in urban spaces and are responsible...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublicationTo effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches...
-
Ontological Modeling for Contextual Data Describing Signals Obtained from Electrodermal Activity for Emotion Recognition and Analysis
PublicationMost of the research in the field of emotion recognition is based on datasets that contain data obtained during affective computing experiments. However, each dataset is described by different metadata, stored in various structures and formats. This research can be counted among those whose aim is to provide a structural and semantic pattern for affective computing datasets, which is an important step to solve the problem of data...
-
Identification of category associations using a multilabel classifier
PublicationDescription of the data using categories allows one to describe it on a higher abstraction level. In this way, we can operate on aggregated groups of the information, allowing one to see relationships that do not appear explicit when we analyze the individual objects separately. In this paper we present automatic identification of the associations between categories used for organization of the textual data. As experimental data...