Todor Ganchev

Todor Ganchev
Technical University of Varna | TUV · Faculty of Computing and Automation

Professor

About

218
Publications
48,043
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
2,140
Citations
Citations since 2017
73 Research Items
911 Citations
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
Introduction
Authored two books and co-authored over 150 scientific publications in the areas of Bioacoustics, Signal processing, Speech and Audio processing, Pattern recognition, and applications. Senior Member of the Institute of Electrical and Electronics Engineers (IEEE).
Additional affiliations
January 2014 - present
Technical University of Varna
Position
  • Professor (Associate)
October 2012 - December 2013
Technical University of Varna
Position
  • Professor (Assistant)
October 2012 - October 2015
Technical University of Varna
Position
  • Head of Department

Publications

Publications (218)
Article
We present the results from the first large-scale study on pollution in the Varna Lake sediments, which was implemented in two preselected zones with significant importance for developing economic activities and urban planning. Based on 140 probes, we developed a digital map of the pollution gradients in these zones. The sediment analysis shows tha...
Article
Full-text available
Prolonged computer-related work can be linked to musculoskeletal disorders (MSD) in the upper limbs and improper posture. In this regard, we report on developing resources supporting improper posture studies based on motion capture sensors. These resources were used to create a baseline detector for the automated detection of improper sitting postu...
Chapter
Work efficiency and quality of life largely depend on health. Daily computer use is an integral part of work, educational activities, and entertainment, and as it is already well known, it increases the risk of developing various musculoskeletal disorders (MSDs). MSDs are the main reason for chronic body pain, most often in the upper limbs, shoulde...
Chapter
Full-text available
We present a recent study on musculoskeletal disorders (MSDs) risk assessment in computer users. For this research, we developed a modification of the Nordic Musculoskeletal Questionnaire (NMQ), where respondents are asked to report only about pain and musculoskeletal discomfort, which they consider linked to the prolonged work with a computer. The...
Chapter
We present an automated annotation method, which infers emotional arousal and valence tags based on physiological signals. This is performed with the help of binary detectors trained to recognize high/low arousal or passive/negative valence. The arousal and valence detectors were created from representative datasets containing evoked emotional reac...
Article
Full-text available
We report on the development of an automated detector of acute stress based on physiological signals. Our detector discriminates between high and low levels of acute stress accumulated by students when performing cognitive tasks on a computer. The proposed detector builds on well-known physiological signal processing principles combined with the st...
Article
Full-text available
Distress management is of particular importance in all disease treatment strategies that aim to cope with medical conditions, which require prolonged therapy. Here, we present results obtained in a comparative study of various classification methods for automated distress detection. For the purposes of the present study, use was made of a common ex...
Article
Full-text available
There is a strong correlation between the like/dislike responses to audio–visual stimuli and the emotional arousal and valence reactions of a person. In the present work, our attention is focused on the automated detection of dislike responses based on EEG activity when music videos are used as audio–visual stimuli. Specifically, we investigate the...
Conference Paper
We present an adaptive feature selection method that makes use of Fisher's discriminant ratio (FDR) with flexible threshold which is adjusted in a person-specific manner. The proposed method is shown to improve the detection of high-arousal negative-valence (HANV) conditions, based on two combinations of physiological signals (ECG+GSR and PPG+GSR)....
Conference Paper
We present the overall design and the implementation of the CLAS dataset, a multimodal resource which was purposely developed in support of research and technology development (RTD) activities oriented towards the automated recognition of some specific states of mind. Although the particular focus of our research is on the states of mind associated...
Data
The CLAS dataset was created in support of RTD activates focusing on the development of functionalities related to the automated recognition of specific human emotions, detection of stress-related conditions and negative emotional states, as well as the automated assessment of the degree of attention and concentration, cognitive load and momentary...
Article
Full-text available
Automated acoustic recognition of birds is considered an important technology in support of biodiversity monitoring and biodiversity conservation activities. These activities require processing large amounts of soundscape recordings. Typically, recordings are transformed to a number of acoustic features, and a machine learning method is used to bui...
Article
Full-text available
Acoustic monitoring provides the opportunity to study ecological pro-cesses that are difficult to assess with traditional surveys. Elachistocleis matogrosso is an anuran species, described in 2010, for which limited biological information is available. This study investigated the calling activity of the species in the north-eastern portion of the Pan...
Article
Full-text available
The processing of inputs in the first two layers of the probabilistic neural network (PNN) is highly parallel which makes it quite appropriate for hardware implementations with FPGA. One of the main inconveniences however remains the implementation of the nonlinear activation function of the pattern layer neurons. In the present study, we investiga...
Conference Paper
In this paper an architecture for the classification of Schizophrenia using EEG-based brain connectivity is proposed. Functional and effective networks were constructed from the EEG using a variety of connectivity measures and with graph theory metrics complex network features were extracted. Several classification algorithms were used for the eval...
Conference Paper
Full-text available
We present a constrained attribute selection method that makes use of feature assessment based on the Fisher's separation criterion followed by variety reduction post-processing. The post-processing incorporates task-specific constrain into the feature selection process, as this is expected to facilitate the subsequent data modeling and classificat...
Conference Paper
Full-text available
We present the overall design of a data acquisition system developed for the needs of the SLADE (Stress Level and Emotional State Assessment Database) database. The database consists of synchronized EEG, ECG, skin temperature (ST), and galvanic skin response (GSR) recordings, used in stress level assessment and recognition of emotional states. SLAD...
Conference Paper
The study of physiological signals and the evaluation of their features are of great importance for the automated emotion detection, as these are directly connected with the successful modelling and classification of the states of interest. In the presented work, we present an evaluation of the appropriateness of LFCC and the logarithmic energy of...
Conference Paper
The Locally Recurrent Probabilistic Neural Network (LRPNN) consists of an input layer, three hidden layers and an output layer. The first two hidden layers are derived from the original PNN, while the third layer referred as recurrent layer is capable to model correlations within temporal sequences of observations. In the present study, we investig...
Article
Full-text available
This study evaluates the relationship between shape and size of tegmen, harp, mirror, and spectral range of calling song frequency of a Neotropical cricket subpopulation (Lerneca inalata beripocone. In addition, we compare intraspecific morphological divergence and calling song properties between individuals from different sites of the Pantanal of...
Conference Paper
Full-text available
We present the design of a mobile system for real-time stress-level assessment. The system combines wearable sensors, wireless data acquisition, and Cloud computing in order to collect and analyze physiological signals, such as, Galvanic Skin Response (GSR) and skin temperature. We report on the implementation of a specific use case, which incorpor...
Chapter
Stress is widely associated with increased health risks (heart and brain diseases, diabetes, cancer, behavioural disorders, etc.). Moreover, a prolonged exposure to stress is known to negatively affect work performance, attitude, decision-making, etc. Furthermore, monitoring of stress levels and proper stress management are of crucial importance fo...
Book
This book offers an overview of some recent advances in the Computational Bioacoustics methods and technology. In the focus of discussion is the pursuit of scalability, which would facilitate real-world applications of different scope and purpose, such as wildlife monitoring, biodiversity assessment, pest population control, and monitoring the spre...
Article
Full-text available
Computer-assisted species recognition facilitates the analysis of relevant biological information in continuous audio recordings. In the present study, we assess the suitability of this approach for determining distinct life-cycle phases of the Southern Lapwing Vanellus chilensis lampronotus based on adult vocal activity. For this purpose we use pa...
Data
Display, including agitated cackling, of a V. chilensis pair flying over their inundated territory. Recording station PPA001, 29 Apr. 2013, 16:35 h; gradually filtered in the range 0–0.5 kHz to remove wind noise (Fig 1B). (MP3)
Data
Example 1 for short series of cackling alarm calls of perched V. chilensis close to its nest. Background (faint): a second Southern Lapwing, E. thula, Yellow-chevroned Parakeet Brotogeris chiriri, and insects. Recording station PPA001, 31 May 2013, 14:31 h; unfiltered (Fig 1C). (MP3)
Data
Example 2 for long alarm call series of a V. chilensis pair or flock mobbing a potential predator or food competitor (e.g. Limpkin Aramus guarauna) to defend their chicks. Background (partially faint): A. guarauna (faint cackling), E. thula, Yellowish Pipit Anthus lutescens, other birds, and wind. Recording station PPA001, 21 Jun. 2013, 12:28 h; fi...
Data
Midnight soundscape at the end of the rainy season when V. chilensis reestablished its territories in the Fazenda Pouso Alegre area. Sound-producing insects and anurans, at least 2–3 species each, are still dominant in the frequency range 0–10.5 kHz. Other species (mostly faint): D. viduata, D. autumnalis, Cocoi Heron Ardea cocoi, Black-crowned Nig...
Data
Validation Library: monthly number of confirmed and unconfirmed sound events according to the loudest call amplitude in Vanellus chilensis vocalizations. Table 2 presents the cumulated numbers (Apr. to Sep. 2013). (PDF)
Data
Monthly and cumulated recognizer performance according to the loudest call amplitude in Vanellus chilensis vocalizations. (PDF)
Data
Fazenda Pouso Alegre area in the northern Pantanal, municipality of Poconé, Mato Grosso, Brazil, during the Vanellus chilensis breeding season in 2013. Landsat images by courtesy of the U.S. Geological Survey (http://landsatlook.usgs.gov): A = 4 May, B = 5 Jun., C = 7 Jul., D = 8 Aug., E = 24 Aug., and F = 25 Sep.; in 2013 no cloud-free images were...
Data
Vanellus chilensis habitat near recording station PPA001 in the Fazenda Pouso Alegre area. A: flooded cattle pasture with macrophytes at the height of the flood season. The water level at PPA001 was about 65 cm on that date (24 Feb. 2013). B: dry savannah-like cattle pasture at PPA001 at the end of the V. chilensis breeding season (2 Aug. 2013). (P...
Data
Uncorrected Vanellus chilensis cumulative daily acoustic activity for the period April to September 2013. Cf. Fig 3, Table 3, and S2 Table. (PDF)
Data
Example 2 for short series of cackling alarm calls of perched V. chilensis close to its nest. Background (faint): Southern Lapwing and other bird species. Recording station PPA001, 11 Jun. 2013, 14:21 h; unfiltered. (MP3)
Data
Example 2 for short series of agitated alarm calls of V. chilensis flushed from its nest or close to it. Background (faint): other Southern Lapwings, D. autumnalis, and others. Recording station PPA001, 06 Jun. 2013, 14:15 h; unfiltered. (MP3)
Data
Example 1 for long alarm call series of a V. chilensis flock mobbing a predator (e.g. Southern Crested Caracara Caracara plancus) to defend their chicks. Background (faint): E. thula, C. plancus (faint cackling), other birds, and insects. Recording station PPA001, 16 Jun. 2013, 15:35 h; filtered in range 0–100 Hz to remove wind noise (Fig 1E). (MP3...
Data
Midnight soundscape at the height of the rainy season in the Fazenda Pouso Alegre area. Sound-producing insects and anurans, at least 6 species each, fill the entire frequency range 0–22 kHz with audio signals. Other species (mostly faint): White-faced Whistling Duck Dendrocygna viduata, D. autumnalis, Wattled Jacana Jacana jacana, Rufescent Tiger-...
Data
Flight calls of Vanellus chilensis patrolling its inundated territory in the Fazenda Pouso Alegre area. Background (faint): a second Southern Lapwing, frogs, and insects. Recording station PPA001, 28 Apr. 2013, 17:38 h; unfiltered (Fig 1A). (MP3)
Data
Single-note alarm calls and agitated cackling of a V. chilensis pair, presumably close to their nest. Background (partially faint): another Southern Lapwing, Snowy Egret Egretta thula (three loud calls), Bare-faced Ibis Phimosus infuscatus, Black-bellied Whistling Duck Dendrocygna autumnalis, and insects. Recording station PPA001, 26 May 2013, 08:0...
Data
Example 1 for short series of agitated alarm calls of V. chilensis flushed from its nest or close to it. Background (faint): D. autumnalis, Greater Rhea Rhea americana (low frequency boom), and others. Recording station PPA001, 30 May 2013, 06:13 h; unfiltered (Fig 1D). (MP3)
Data
Midnight soundscape at the height of the dry season. Sound-producing insects and anurans are virtually absent. Background species (faint): R. americana, N. nycticorax, B. indicus, Feral Horse Equus ferus caballus, and others. Recording station PPA001, 25 Jul. 2013, 23:51 h; unfiltered, loudest signal equalized to –9 dB (Fig 6C). (MP3)
Data
Identified sound sources in a random sample of 1250 detections, drawn from 48 879 Vanellus chilensis recognizer detections in soundscapes recorded at monitoring station PPA001, Pantanal region, Brazil, between April and September 2013. The false positive rates (= 100 –Precision [%]) were used to correct the number of diurnal and nocturnal detection...
Data
Vanellus chilensis lampronotus searching for food at a muddy lake margin in the Fazenda Pouso Alegre area (18 Jul. 2012). (PDF)
Data
Cumulated monthly daytime and nighttime detections of Vanellus chilensis call events and calculation of precision for the period April to September 2013. See Table 3 for acoustic activity periods. (PDF)
Data
Validation library: soundscapes annotated for the performance assessment of the Vanellus chilensis recognizer. See S1 Appendix for performance assessment results. Double hits refer to repeated detections of the same lapwing call series and were omitted in subsequent analyses. The weakest event in dB refers to the loudest note of the weakest V. chil...
Article
Full-text available
See the Data Sets: http://cobra.ic.ufmt.br/web/guest/publications-data_sets The first record of the Orthoptera species Lerneca inalata for Brazil is presented here. The taxon is represented by a new subspecies Lerneca inalata beripocone subsp. nov. (Phalangopsidae, Luzarinae), collected in the Pantanal of Poconé, Mato Grosso, Brazil. This work inc...
Poster
Full-text available
The increasing loss of biodiversity urges scientists to develop new techniques for species inventorying. One approach is monitoring of vocalizing species via acoustic sound detectors. Automated sound classifiers (ASCs) can screen digital audio recordings for species-specific calls. In order to build ASCs, audio libraries of the target species and e...
Poster
Full-text available
The increasing loss of biodiversity urges scientists to develop new techniques for species inventorying. One approach is monitoring of vocalizing species via acoustic sound detectors. Automated sound classifiers (ASCs) can screen digital audio recordings for species-specific calls. In order to build ASCs, audio libraries of the target species and e...
Conference Paper
In the following paper we present a study on novel signal descriptors for the purposes of automated recognition of negative emotional states from EEG signals - namely, the decorrelated values of the energy of the spatio-temporal distribution of EEG activity. Using the extracted features person-specific SVM models are created. The experimental setup...
Article
Full-text available
Hidden Markov Model (HMM) Mel Frequency Cepstral Coefficients (MFCCs) Robust frame selection a b s t r a c t A major challenge in the automated acoustic recognition of bird species is the audio segmentation, which aims to select portions of audio that contain meaningful sound events and eliminates segments that contain predominantly background nois...
Article
Full-text available
The 50 days free access to the article is available through the link: http://authors.elsevier.com/a/1Qzvs3PiGSx4Z0 until June 24, 2015. Traditional human-observer-based biological surveys are expensive. Therefore, most biodiversity studies are implemented only periodically, for short periods, and predominantly during daytime and under favorable w...
Article
Full-text available
A major challenge in the automated acoustic recognition of bird species is the audio segmentation, which aims to select portions of audio that contain meaningful sound events and eliminates segments that contain predominantly background noise or sound events of other origin. Here we report on the development of an audio parameterization method with...