Gennady Agre | Bulgarian Academy of Sciences (original) (raw)

Papers by Gennady Agre

Abstract. The paper presents the main results of the IST FP6 INFRAWEBS project. The project has d... more Abstract. The paper presents the main results of the IST FP6 INFRAWEBS project. The project has developed an easy and effective way of constructing and using semantic descriptions for existing and new Web services. INFRAWEBS has adopted the WSMO (Web Service Modeling Ontology) and WSML (Web Service Modeling Language) specifications and has imposed no additional requirements to them. Therefore, the advanced software components developed during the project are of interest to the whole WSMO community. INFRAWEBS offers a SOA framework – INFRAWEBS Integrated Framework (IIF), based on the ESB integration paradigm, which can be easily used by different groups of users (application providers, designers of SWS, etc.). The IIF enables integration of components of different technologies. Furthermore, it can be considered as one of the first frameworks for semantic service engineering that covers the whole SWS life-cycle and allows for creation of complex, semantically-enabled applications.

Book of Abstracts, 2022

Targeting sonic hedgehog pathway in combination with proton radiation or gamma irradiation decrea... more Targeting sonic hedgehog pathway in combination with proton radiation or gamma irradiation decreases viability of glioma cell lines .

IFAC Proceedings Volumes, Aug 1, 1987

A robotized manipulating s ystem, which performs the task of quality recognition, separation and ... more A robotized manipulating s ystem, which performs the task of quality recognition, separation and palletization of packs of wall tiles in an existing ceramic factory is described in this paper. The ~acks, previously marked according to their quality, arrive at the end of a production line, where the robot picks them up , arranges them in pallets and takes them out of the palletization area, following a program , specially developed for the purpose. The main components and assemblies of the system are described and some details are given for the most characteristic equipment. The essence of the pa ll e ti zation process , the possib l e types of arrangement and the associated software in th e contro l unit of a VERSATRAN type robot are discussed.

Book of Abstracts, 2023

Jasna Paradiž, Determining the genetic vulnerability of plants due to ionizing radiation: a compr... more Jasna Paradiž, Determining the genetic vulnerability of plants due to ionizing radiation: a comprehensive analysis of the cytogenetic balance and responses of the Allium root meristem to various radiation doses .

Springer eBooks, Aug 3, 2012

arXiv (Cornell University), Apr 2, 2009

The current INFRAWEBS European research project aims at developing ICT framework enabling softwar... more The current INFRAWEBS European research project aims at developing ICT framework enabling software and service providers to generate and establish open and extensible development platforms for Web Service applications. One of the concrete project objectives is developing a full-life-cycle software toolset for creating and maintaining Semantic Web Services (SWSs) supporting specific applications based on Web Service Modelling Ontology (WSMO) framework. According to WSMO, functional and behavioural descriptions of a SWS may be represented by means of complex logical expressions (axioms). The paper describes a specialized user-friendly tool for constructing and editing such axioms - INFRAWEBS Axiom Editor. After discussing the main design principles of the Editor, its functional architecture is briefly presented. The tool is implemented in Eclipse Graphical Environment Framework and Eclipse Rich Client Platform.

Book of Abstracts

activesolutions.bg The intention of this article is to describe the use of fuzzy logic techniques... more activesolutions.bg The intention of this article is to describe the use of fuzzy logic techniques applied to an Organizational Memory (OM) – a module of the INFRAWEBS framework [1] dedicated to the collection, organization, refinement, and distribution of entity specific knowledge. The module is based on the new streams and ap-proaches in the area of Fuzzy Concept Set (FCS) Modeling, especially Fuzzy Concept Matching (FCM) [2]. The paper gives an over-view about the INFRAWBS conceptual model as well as presents the automatic object feature vector generation, objects classification and clustering mechanisms, as well as techniques for retrieving similar objects and ontology based semantic objects descriptions.

Annals of Anatomy - Anatomischer Anzeiger, 2022

BACKGROUND Metopic suture lies between the halves of the growing frontal bone and usually closes ... more BACKGROUND Metopic suture lies between the halves of the growing frontal bone and usually closes in early infancy. If the metopic suture fails to close it persists in adulthood and could be considered an anterior continuation of the sagittal suture (SS). This study aimed to investigate if the metopic suture persistence is related to any significant deviations from the normal SS maturation. We also aimed to elaborate linear regression models for age-at-death prediction of the metopic crania and to compare their accuracy with the models developed on the control ones. METHODS The SS was investigated in a total of 122 dry adult contemporary male crania of known age-at-death divided in a metopic series (n = 34) and a control one (n = 88). The crania were scanned and high-resolution volumetric images were generated using an industrial µCT system. The SS closure degree was assessed on cross-sectional tomograms using a scale of grades. Both series were compared and linear regression models for age-at-death prediction were elaborated. RESULTS The comparison between both series showed that the degree of SS closure differs significantly in all SS sections and bone layers and it is considerably lower in the metopic series. The elaborated linear regression models showed that the error in the age-at-death prediction of the metopic crania is almost two times bigger than that in the control. CONCLUSIONS The SS closure in metopic crania is significantly delayed compared to the control, which means that it is entirely unreliable and misleading as an indicator for age-at-death prediction.

Forensic Science International, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Anthropologischer Anzeiger, Jul 27, 2023

Springer eBooks, Jul 26, 2014

Artificial Intelligence: Methodology, Systems, and Applications, 2018

The paper presents a new supervised approach for solving the all-words sense disambiguation (WSD)... more The paper presents a new supervised approach for solving the all-words sense disambiguation (WSD) task, which allows avoiding the necessity to construct different specialized classifiers for disambiguating different target words. In the core of the approach lies a new interpretation of the notion ‘class’, which relates each possible meaning of a word to a frequency with which it occurs in some corpora. In such a way all possible senses of different words can be classified in a unified way into a restricted set of classes starting from the most frequent, and ending with the least frequent class. For representing target and context words the approach uses word embeddings and information about their part-of-speech (POS) categories. The experiments have shown that classifiers trained on examples created by means of the approach outperform the standard baselines for measuring the behavior of all-words WSD classifiers.

Proceedings of the 17th International Conference on Computer Systems and Technologies 2016, 2016

In this paper we present an expert system for healthful and dietary nutrition. It was built as pa... more In this paper we present an expert system for healthful and dietary nutrition. It was built as part of the research project financed by Bulgarian SME fund [1]. The main purpose of the system is to facilitate the classification of the unknown food products to the set of predefined classes related to different client groups. In our case these classes are food products appropriate/not appropriate for children, adults below 60 years with high physical activity, low physical activity, adults above 60, etc but the system is not limited to these classes and can be used with any other classification hierarchy. The base metric that the system uses to compare food products was thoroughly presented in our previous publication [5]. In this paper we introduce the remaining part of the system including overall architecture, classification process, believability propagation, different user roles, implementation, and general considerations.

Proceedings of the 16th International Conference on Computer Systems and Technologies - CompSysTech '15, 2015

The paper presents practical approaches and techniques to speeding up implementations of nearest ... more The paper presents practical approaches and techniques to speeding up implementations of nearest neighbour search/classification algorithm for high dimensional data and/or many training examples. Such settings often appear in the fields of big data and data mining. We apply a fast iterative form of polar decomposition and use the computed matrix to pre-select smaller number of candidate classes for the query element. We show that additional speed up can be achieved when the training classes consists of many instances by subdividing them in subclasses by fast approximation of some clustering algorithm and the resulting classification is used for building the decomposition matrix. Our pre-processing (depends linearly or near linearly on the number of examples and dimensions) and pre-selection steps (depends on number of classes) can be used with any well-known indexing method as annulus method, kd-trees, metric trees, r-trees, cover trees, etc to limit the training instances used in the search/classification process. Finally we introduce what we name cluster index and show that in practice it extends the applicability of the indexing structures with higher order complexity to bigger datasets.