Stefan Todorov Hadjitodorov

Stefan Todorov Hadjitodorov
Bulgarian Academy of Sciences | BAS · Department of Bioinformatics and Mathematical Modelling

Professor

About

62
Publications
5,932
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,205
Citations

Publications

Publications (62)
Chapter
The research and results in the field of acoustic analysis of voices for different purposes—laryngeal pathology detection, speaker recognition and evaluation of the emotional state at the Center on Biomedical Engineering, Bulgarian Academy of Sciences (now Institute of Biophysics and Biomedical Engineering) has been described. A lot of novelties ha...
Conference Paper
Full-text available
This paper presents a method for quantifying resilience which is exemplified by a case study on critical infrastructure resilience in the Republic of Bulgaria. The research links quantitative research methods for measuring critical infrastructure resilience with qualitative legal, strategic and sector research. The main research results are policy...
Article
Full-text available
The paper presents a case study on the potential application of serious gaming in the area of European Defence. In the last years game technology has been successfully applied to enhance capabilities in many areas, including in the training of peacekeeping personnel. The role of serious game technology for EU Defence has not been sufficiently explo...
Article
Full-text available
In order to effectively counter hybrid warfare, it is necessary to understand it. However, certain aspects of hybrid warfare are often confused with traditional soft power. This article aims to highlight the differences between the two by analyzing the relationship between Bulgaria and Russia. The latter enjoys considerable opportunities to exercis...
Chapter
Multiple sclerosis (MS) is a chronic disease of the central nervous system, which affects most often the young age. The disease has a social importance, as it leads to disability in active age. The course of the disease is individual and requires an adequate approach in selecting the appropriate treatment strategy. This requires periodic monitoring...
Article
Full-text available
Due to explosion in the number of autonomous data sources, there is an emergent need for effective approaches to distributed clustering. Intuitionistic Fuzzy Set is a suitable tool to cope with imperfectly defined facts and data, as well as with imprecise knowledge. One of the authors introduced a novel intuitionistic fuzzy based distributed cluste...
Article
Full-text available
In the present work an attempt is made to evaluate objectively the ventilated patients' condition from the monitored parameters (standard physiological parameters, parameters of the ventilation and respiratory mechanics, parameters of the gas exchange and energy expenditure) in order to determine their readiness for weaning from mechanical ventilat...
Conference Paper
Full-text available
The purpose of the paper is to present an algorithm for concurrent processing on multi-layer neural networks and its advantages in the context of development of parallel computing systems and clouds.
Article
Determining the readiness of the patient for weaning from long-term mechanical ventilation with high degree of accuracy is a prerequisite for successful weaning attempt. A computer system for the determination of the moment for beginning the weaning process is proposed and realized as a program package WeaningMV. It is designed on the basis of four...
Article
Full-text available
An idea presented in (6,7) has been developed further, and the patients readiness for weaning form long-term mechanical ventilation has been determined in the sense of intuitionistic fuzzy logic (1). In the present paper it is solved as pattern recognition problem. As a final estimate of the classification an estimate aggregated from four estimates...
Conference Paper
Full-text available
The main goal of this paper is to formulate fundamental principles in shaping an efficient security and defence R&T policy of the Republic of Bulgaria. Presently, due to a variety of reasons, there is no comprehensive, well-focused and sustainable security and defence R&T policy of the country that is clearly linked to its security and defence obje...
Conference Paper
Full-text available
Cluster ensembles are deemed to be better than single clustering algorithms for discovering complex or noisy structures in data. Various heuristics for constructing such ensembles have been examined in the literature, e.g., random feature selection, weak clusterers, random projections, etc. Typically, one heuristic is picked at a time to construct...
Article
Full-text available
Determining the readiness of the patient for weaning from long-term mechanical ventilation is one of the main tasks that need to be overcome by clinician in the intensive care units. In the present paper it is defined as a pattern recognition problem and four classification methods are applied in order to solve it: Stepwise discriminant analysis (S...
Article
Full-text available
The Ceneralized Nets (GN) that are an extension of Petri Nets have been used for modeling of di®erent processes, including intellectual ones. In this paper a CN model is developed for the description of the functioning of an biometrics based access-control system. The model gives the possibility for the investigation and practical realization of sp...
Article
A model of a biometric access-control system is suggested based on the theory of the Generalized Nets. The major stages of processing, feature extraction and classification are described. The model could be used for implementation of different strategies of decision-making depending on the particular problem.
Article
Adjusted Rand index is used to measure diversity in cluster ensembles and a diversity measure is subsequently proposed. Although the measure was found to be related to the quality of the ensemble, this relationship appeared to be non-monotonic. In some cases, ensembles which exhibited a moderate level of diversity gave a more accurate clustering. B...
Article
Full-text available
Cluster ensembles are deemed to be a robust and accurate alternative to single clustering runs. 24 methods for designing cluster ensembles are compared here using 24 data sets, both artificial and real. Adjusted Rand index and classification accuracy are used as accuracy criteria with respect to a known partition assumed to be the "true" one. The d...
Article
Full-text available
The article presents the major findings of a comprehensive study (White Paper on Civil Protection) accomplished by the Center for National Security and Defense Research (CNSDR) in the Bulgarian Academy of Sciences (BAS). The re- search is presently further developed within the framework of a NATO Science for Peace Project SFP-981149 for building ne...
Conference Paper
The article focuses on a type of client/server multiagent system. Such system consists of several server environments, each populated by a single server agent and multiple client agents. We propose that a server agent should monitor clients activity in order to perform better. We employ the term agent tracking, introduced by Tambe and Rosenbloom. W...
Conference Paper
Full-text available
The pairwise approach to cluster ensembles uses multiple partitions, each of which constructs a coincidence matrix between all pairs of objects. The matrices for the partitions are then combined and a final clustering is derived thereof. Here we study the diversity within such cluster ensembles. Based on this, we propose a variant of the generic en...
Article
The present paper is aimed at the development of new methods of fundamental frequency determination of voiced signal, uttered by patients with severe laryngeal disorders due to various diseases. The necessity to seek new methods is set by the increasing use of acoustic voice analysis as non-invasive technique for supporting diagnosis in laryngeal p...
Article
A Generalized Net (GN – an extension of the Petri net) model of the process of speaker classification – identification and verification is described. The model is the latest from a series of investigations on the application of the GNs to the pattern and speak recognition problems.
Article
A system for acoustic analysis of pathological voices is proposed. The vocalized part of the voice signal is separated and all glottal cycles are traced by means of a cross-correlation detector. Based on the so determined beginning and duration of all glottal cycles, shimmer, jitter, several harmonics-to-noise ratios and other widely used acoustic...
Article
Full-text available
An intuitionistic fuzzy version of one of the statistical nonparametrical methods, the nearest prototype (NT) method, is proposed. The degrees of membership, nonmember-ship and indeterminacy (uncertainty) of a pattern with unknown classification to a given class have been evaluated taking into account the distance to the prototype (mean) vector of...
Article
Full-text available
In this article a new acoustic parameter is introduced and it is shown that it may serve as an indicator of laryngeal function. It is termed the turbulent noise index (TNI) and is defined as 100(1 - Rmax), where Rmax is the mean value of the maximum correlation coefficient between each pair of consecutive glottal cycles in the voiced signal. A meth...
Article
Full-text available
Most of the existing systems and methods for laryngeal pathology detection are characterized by a classification error. One of the basic problems is the approximation and estimation of the probability density functions of the given classes. In order to increase the accuracy of laryngeal pathology detection and to eliminate the most dangerous error-...
Article
The Self-Organizing Map (SOM) has the special property to create effectively a spatially organized internal representations of various features of input vectors. SOM is widely used for clustering and classification. In its classical training procedure if there exists more than one closest neuron the algorithm chooses the first one and ignores the o...
Article
Full-text available
The aim of the current study was to compare the predictive performance of a mechanistically based model and an empirical artificial neural network (ANN) model to describe the relationship between the tissue-to-unbound plasma concentration ratios (Kpu's) of 14 rat tissues and the lipophilicity (LogP) of a series of nine 5-n-alkyl-5-ethyl barbituric...
Article
Full-text available
A software system for pathological voice analysis using only the resources of a personal computer with a sound card is proposed. The system is written on the basis of specific methods and algorithms for pathological voice analysis and allows evaluation of: 1) Pitch period (To); 2) Degree of unvoiceness; 3) Pitch perturbation and amplitude perturbat...
Article
A PC-based system for robust speaker recognition is proposed. It includes three one level recognition methods and a two level classifier. New procedures for voice analysis are proposed: a) Robust periodicity/aperiodicity separation by neural networks; b) Robust pitch period detection; c) Analysis of the temporal, spectral and cepstral speech charac...
Article
The authors propose a software system for pathological voice analysis and screening of laryngeal diseases that has the following properties: a) The analysis is totally noninvasive-the microphone is about 30 cm from the patient's mouth, and contact microphones or laryngophones are not used. b) The system is built around a low-cost personal computer...
Article
Full-text available
A hybrid speech period (To) detector characterizided by parallel analyses of three speech signals in temporal spectral and cepstral domains and preprocessing for periodic/aperiodic (unvoiced) separation (PAS) is proposed. The preprocessing is realized by analysis in these three domains and PAS by multi layer Perceptron neural network.Two phonations...
Article
Full-text available
A two-level scheme for speaker identification is proposed. The first classifier level is based on the self-organizing map (SOM) of Kohonen. LPCC coefficients are used as input vectors for this classifier. LPCC coefficients are passed again through the already trained SOMs and as result the prototype distribution maps (PDMs) are obtained. The PDMs a...
Conference Paper
In this paper we consider a radial basis function (RBF) network with tunable shape and spreadout parameters of the activation function. We argue that fewer hidden nodes with different RBF shapes can better match the classification regions still preserving the context of the probabilistic semiparametric approximation of the conditional probability d...
Article
A method for speaker identification based on the analysis of four sets of speech parameters is proposed. The recognition is carried out by means of two classifiers: the first is based on self-organising Kohonen maps a new prototype distribution map and a new similarity measure, and the second on AR-vector models. The final decision is realised by a...
Article
A hybrid pitch detector characterised by parallel analysis of the speech signal in temporal, spectral and cepstral domains is proposed. The voiced/unvoiced decision and pitch period evaluation is realised by a logical analysis of the results from three domains. The experimental analysis shows the robustness of the detector for noisy and telephone s...
Article
A version for increasing of the classification accuracy of one of the basic statistical nonparametrical methods, the K-NN method, is proposed. Here the idea of including fuzzy information in the K-NN method is applied in a new way. The distances are modified by means of the pattern degrees of membership to the classes to which the pattern belongs....
Article
A method for bispectral analysis of the voiced speech for recognition purposes is proposed. The phase relations between the harmonic components are evaluated using the bispectrum. The experiments show that this approach may be used for laryngeal pathology detection and speaker recognition.
Article
A low cost microcomputer system for analysis of the voice of patients with laryngeal diseases is proposed. The system realizes an evaluation of the following speech parameters affected by laryngeal disease: voice degree of hoarseness; pitch period (T0); pitch period perturbations; degree of subharmonic components; and number of the stops in T0 gene...
Article
The term ‘key features’ is introduced to denote features with rare occurrence and great diagnostic power, which are implemented in a two-level classification scheme. Experiments with medical data illustrate the idea, confirming the expected improvement of the classification accuracy.
Conference Paper
The problem of the recognition of Bulgarian words by means of HMM (hidden Markov models) is discussed. The speech signal was low-pass filtered up to 4 kHz, sampled at 10 kHz, and pushed directly into the computer's memory (IBM PC/XT). Unvoiced segments were separated, and the pitch period was evaluated. For every voiced and unvoiced segment 12 LPC...
Article
Full-text available
A Generalized Net (GN — an extension of the Petri net) model of the proc-ess of laryngeal pathology detection is described. The model is the second one from a series of investigations on the application of the GNs to the speech analysis prob-lems.
Article
Full-text available
A generalized Net model describing the process of computer scene analysis is developed. It takes into account both the objects in the scene background. The flexibility of the model allows its implementation in different specific applications.
Article
A model of the automatic document processing in terms of generalized nets is described. The basic steps of that process including pre-processing, document segmentation, feature extraction and classification are presented through a reduced net without priorities of the transitions, places, tokens and capacities.
Article
Full-text available
Generalized Nets (GNs) are extensions of Petri nets and their other extensions and modi¯-cations. A lot of research was carried out in the last 15 years to show the possibilities for the representdtion by GNs of di®erent objects from the area of Arti¯cial Intelligence. In a series of papers they were used for modelling in image processing. The poss...
Article
An intuitionistic fuzzy version of one of the statistical nonparametrical methods, the Nearest Prototype (NP) method, has been proposed. The degrees of membership, nonmembership and indeterminacy (uncertainty) of a pattern with unknown classification to a given class have been evaluated taking into account the distance to the prototype (mean) vecto...

Network

Cited By