Todor Ganchev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Todor Ganchev has a total of 168 co-authors. Here are the top co-authors by number of shared publications:
Nikos Fakotakis
University of Patras
40 shared publicationsIosif Mporas
University of Hertfordshire,Sch. of Eng/ring and Computer Science,Hatfield,United Kingdom
28 shared publications- Valentina Markova
Department of Communication Engineering and Technologies, Technical University of Varna, 9000 Varna, Bulgaria
22 shared publications - Theodoros Kostoulas
Department of Information and Communication Systems Engineering, University of the Aegean, Greece
14 shared publications - Otilia Kocsis
Raising the Floor, 1210 Brussels, Belgium
12 shared publications - Alexandros Lazaridis
University of Patras
10 shared publications
Latest Publications
- Open Access
- 18 November 2026
- Published by MDPI AG in Preprints.org
Probabilistic Gust Exceedance Forecasting from Coastal Weather Station Observations
Coastal monitoring and marine traffic management services can benefit from short-horizon estimates of gust exceedance, but precursor detection and probability forecasting require different evaluations. In this work, we analyse one year of observations from ten meteorological stations located in the Varna Bay and the area of the Varna–Beloslav Lake system. Exploratory pressure-fall and gust-rise rules are compared against 23 network-wise events. A pressure fall of 1 hPa over three hours detects 26% of events with a 98% false-alarm ratio; a network-median gust rise of 1.5 m/s over one hour detects all 23 events with a 96% false-alarm ratio. Separately, a pooled current-gust logistic model estimates station-level exceedance of 12 m/s within two hours. The reported later-period Brier scores are 0.01134 for this model and 0.01931 for a constant training-frequency reference, giving a Brier skill score of 0.413. Adding an analogous station-level preceding-hour change predictor gives a Brier score of 0.01151 and a skill difference of −0.009, with a reported 95% block-bootstrap interval of [−0.0185, −0.0006]. Thus, adding this predictor does not improve the evaluated logistic specification. The diagnostics motivate investigation of gust trend but do not establish its incremental predictive value. Full-record feature exploration, overlapping targets and limited seasonal coverage constrain interpretation of the probability comparison. The results support further validation of local gust probabilities rather than an operational warning claim.
- 18 November 2026
- Published by MDPI AG in Preprints.org
Open AccessProbabilistic Gust Exceedance Forecasting from Coastal Weather Station Observations
Coastal monitoring and marine traffic management services can benefit from short-horizon estimates of gust exceedance, but precursor detection and probability forecasting require different evaluations. In this work, we analyse one year of observations from ten meteorological stations located in the Varna Bay and the area of the Varna–Beloslav Lake system. Exploratory pressure-fall and gust-rise rules are compared against 23 network-wise events. A pressure fall of 1 hPa over three hours detects 26% of events with a 98% false-alarm ratio; a network-median gust rise of 1.5 m/s over one hour detects all 23 events with a 96% false-alarm ratio. Separately, a pooled current-gust logistic model estimates station-level exceedance of 12 m/s within two hours. The reported later-period Brier scores are 0.01134 for this model and 0.01931 for a constant training-frequency reference, giving a Brier skill score of 0.413. Adding an analogous station-level preceding-hour change predictor gives a Brier score of 0.01151 and a skill difference of −0.009, with a reported 95% block-bootstrap interval of [−0.0185, −0.0006]. Thus, adding this predictor does not improve the evaluated logistic specification. The diagnostics motivate investigation of gust trend but do not establish its incremental predictive value. Full-record feature exploration, overlapping targets and limited seasonal coverage constrain interpretation of the probability comparison. The results support further validation of local gust probabilities rather than an operational warning claim.
- Open Access
- 27 June 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 392
Bottlenose Dolphins’ Clicks Comply with Three Laws of Efficient Communication
Bottlenose dolphins’ broadband click vocalisations are well-studied in the literature concerning their echolocation function. Their potential use for communication among conspecifics has long been speculated but has yet to be conclusively established. In this study, we first categorised dolphins’ click production based on their amplitude contour and then analysed the distribution of individual clicks and click sequences against their duration and length. The results show that the repertoire and composition of clicks and click sequences adhere to the three essential linguistic laws of efficient communication: Zipf’s rank–frequency law, the law of brevity, and the Menzerath–Altmann law. Conforming to the rank–frequency law suggests that clicks may form a linguistic code subject to selective pressures for unification, on the one hand, and diversification, on the other. Conforming to the other two laws also implies that dolphins use clicks according to the compression criterion or minimisation of code length without losing information. Such conformity of dolphin clicks might indicate that these linguistic laws are more general, which produces an exciting research perspective on animal communication.
- 27 June 2025
- Published by MDPI AG in Algorithms
- Vol. 18 (7) , 392
Open AccessBottlenose Dolphins’ Clicks Comply with Three Laws of Efficient Communication
Bottlenose dolphins’ broadband click vocalisations are well-studied in the literature concerning their echolocation function. Their potential use for communication among conspecifics has long been speculated but has yet to be conclusively established. In this study, we first categorised dolphins’ click production based on their amplitude contour and then analysed the distribution of individual clicks and click sequences against their duration and length. The results show that the repertoire and composition of clicks and click sequences adhere to the three essential linguistic laws of efficient communication: Zipf’s rank–frequency law, the law of brevity, and the Menzerath–Altmann law. Conforming to the rank–frequency law suggests that clicks may form a linguistic code subject to selective pressures for unification, on the one hand, and diversification, on the other. Conforming to the other two laws also implies that dolphins use clicks according to the compression criterion or minimisation of code length without losing information. Such conformity of dolphin clicks might indicate that these linguistic laws are more general, which produces an exciting research perspective on animal communication.
- Open Access
- 30 September 2024
- Published by Pensoft Publishers in Arpha Proceedings
- Vol. 1, 61-65
The Iliad digital twins of the ocean: opportunities for citizen science
In recent years, there has been growing interest in digital twins (or virtual representations) of the environment. Programs in the European Union and the UN are investing in digital twins, particularly those of the ocean (DTOs). While citizen science has been mentioned as a potential data source for digital twins, the full potential of citizen science in this context has yet to be fully realised. The Iliad project (https://ocean-twin.eu), funded by the European Commission, is developing a comprehensive set of digital twins of the oceans which are interoperable, data-intensive, and cost-effective. The project (2022–2025) brings together over 50 partners to demonstrate the technologies and methodologies required to develop DTOs. Citizen science and engagement play a pivotal role in the project, with the following goals: (a) exploring the potential for citizen science to contribute to digital twins of the oceans; (b) demonstrating how citizen scientists (and society more broadly) can benefit from digital twins. The Iliad team is currently working on over 20 separate digital twins of the oceans that fall into two primary categories: (i) environmental and ecological digital twins; (ii) engineering and industrial digital twins. Using the Iliad DTOs as case studies, lessons learned for citizen science are presented from the development of each digital twin.
- 30 September 2024
- Published by Pensoft Publishers in Arpha Proceedings
- Vol. 1, 61-65
Open AccessThe Iliad digital twins of the ocean: opportunities for citizen science
In recent years, there has been growing interest in digital twins (or virtual representations) of the environment. Programs in the European Union and the UN are investing in digital twins, particularly those of the ocean (DTOs). While citizen science has been mentioned as a potential data source for digital twins, the full potential of citizen science in this context has yet to be fully realised. The Iliad project (https://ocean-twin.eu), funded by the European Commission, is developing a comprehensive set of digital twins of the oceans which are interoperable, data-intensive, and cost-effective. The project (2022–2025) brings together over 50 partners to demonstrate the technologies and methodologies required to develop DTOs. Citizen science and engagement play a pivotal role in the project, with the following goals: (a) exploring the potential for citizen science to contribute to digital twins of the oceans; (b) demonstrating how citizen scientists (and society more broadly) can benefit from digital twins. The Iliad team is currently working on over 20 separate digital twins of the oceans that fall into two primary categories: (i) environmental and ecological digital twins; (ii) engineering and industrial digital twins. Using the Iliad DTOs as case studies, lessons learned for citizen science are presented from the development of each digital twin.
- Open Access
- 9 September 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (17) , 2796
A Method for Transforming Non-Convex Optimization Problem to Distributed Form
We propose a novel distributed method for non-convex optimization problems with coupling equality and inequality constraints. This method transforms the optimization problem into a specific form to allow distributed implementation of modified gradient descent and Newton’s methods so that they operate as if they were distributed. We demonstrate that for the proposed distributed method: (i) communications are significantly less time-consuming than oracle calls, (ii) its convergence rate is equivalent to the convergence of Newton’s method concerning oracle calls, and (iii) for the cases when oracle calls are more expensive than communication between agents, the transition from a centralized to a distributed paradigm does not significantly affect computational time. The proposed method is applicable when the objective function is twice differentiable and constraints are differentiable, which holds for a wide range of machine learning methods and optimization setups.
- 9 September 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (17) , 2796
Open AccessA Method for Transforming Non-Convex Optimization Problem to Distributed Form
We propose a novel distributed method for non-convex optimization problems with coupling equality and inequality constraints. This method transforms the optimization problem into a specific form to allow distributed implementation of modified gradient descent and Newton’s methods so that they operate as if they were distributed. We demonstrate that for the proposed distributed method: (i) communications are significantly less time-consuming than oracle calls, (ii) its convergence rate is equivalent to the convergence of Newton’s method concerning oracle calls, and (iii) for the cases when oracle calls are more expensive than communication between agents, the transition from a centralized to a distributed paradigm does not significantly affect computational time. The proposed method is applicable when the objective function is twice differentiable and constraints are differentiable, which holds for a wide range of machine learning methods and optimization setups.
- Open Access
- 29 April 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (5) , 187
MMD-MSD: A Multimodal Multisensory Dataset in Support of Research and Technology Development for Musculoskeletal Disorders
Improper sitting positions are known as the primary reason for back pain and the emergence of musculoskeletal disorders (MSDs) among individuals who spend prolonged time working with computer screens, keyboards, and mice. At the same time, it is well understood that automated technological tools can play an important role in the process of unhealthy habit alteration, so plenty of research efforts are focused on research and technology development (RTD) activities that aim to provide support for the prevention of back pain or the development of MSDs. Here, we report on creating a new resource in support of RTD activities aiming at the automated detection of improper sitting positions. It consists of multimodal multisensory recordings of 100 persons, made with a video recorder, camera, and wrist-attached sensors that capture physiological signals (PPG, EDA, skin temperature), as well as motion sensors (three-axis accelerometer). Our multimodal multisensory dataset (MMD-MSD) opens new opportunities for modeling the body stance (sitting posture and movements), physiological state (stress level, attention, emotional arousal and valence), and performance (success rate on the Stroop test) of people working with a computer. Finally, we demonstrate two use cases: improper neck posture detection from pictures, and task-specific cognitive load detection from physiological signals.
- 29 April 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (5) , 187
Open AccessMMD-MSD: A Multimodal Multisensory Dataset in Support of Research and Technology Development for Musculoskeletal Disorders
Improper sitting positions are known as the primary reason for back pain and the emergence of musculoskeletal disorders (MSDs) among individuals who spend prolonged time working with computer screens, keyboards, and mice. At the same time, it is well understood that automated technological tools can play an important role in the process of unhealthy habit alteration, so plenty of research efforts are focused on research and technology development (RTD) activities that aim to provide support for the prevention of back pain or the development of MSDs. Here, we report on creating a new resource in support of RTD activities aiming at the automated detection of improper sitting positions. It consists of multimodal multisensory recordings of 100 persons, made with a video recorder, camera, and wrist-attached sensors that capture physiological signals (PPG, EDA, skin temperature), as well as motion sensors (three-axis accelerometer). Our multimodal multisensory dataset (MMD-MSD) opens new opportunities for modeling the body stance (sitting posture and movements), physiological state (stress level, attention, emotional arousal and valence), and performance (success rate on the Stroop test) of people working with a computer. Finally, we demonstrate two use cases: improper neck posture detection from pictures, and task-specific cognitive load detection from physiological signals.
- Open Access
- 8 April 2024
- Published by MDPI AG in Preprints.org
MMD-MSD: A Multimodal Multisensory Dataset in Support of Musculoskeletal Disorders Research and Technology Development
Improper sitting positions are known as the primary reason for back pain and the emergence of musculoskeletal disorders (MSD) among individuals who spend prolonged time working with computer screens, keyboards, and mice. At the same time, it is well understood that automated technological tools can play an important role in the process of unhealthy habit alteration, so plenty of research efforts are focused on research and technology development (RTD) activities that aim to provide support to the prevention of back pain or the development of MSD. Here, we report on creating a new resource in support of RTD activities aiming at the automated detection of improper sitting positions. It consists of multimodal multisensory recordings of 100 persons made with a video recorder, camera, and wrist-attached sensors that capture physiological signals (PPG, EDA, Skin temperature), as well as motion sensors (three-axis accelerometer). Our multimodal multisensory dataset (MMD-MSD) opens new opportunities for modeling the body stance (sitting posture and movements), physiological state (stress level, attention, emotional arousal, valence), and performance (success rate on the Stroop test) of people working with a computer. Finally, we demonstrate two use cases: improper neck posture detection from pictures and cognitive load detection from physiological signals.
- 8 April 2024
- Published by MDPI AG in Preprints.org
Open AccessMMD-MSD: A Multimodal Multisensory Dataset in Support of Musculoskeletal Disorders Research and Technology Development
Improper sitting positions are known as the primary reason for back pain and the emergence of musculoskeletal disorders (MSD) among individuals who spend prolonged time working with computer screens, keyboards, and mice. At the same time, it is well understood that automated technological tools can play an important role in the process of unhealthy habit alteration, so plenty of research efforts are focused on research and technology development (RTD) activities that aim to provide support to the prevention of back pain or the development of MSD. Here, we report on creating a new resource in support of RTD activities aiming at the automated detection of improper sitting positions. It consists of multimodal multisensory recordings of 100 persons made with a video recorder, camera, and wrist-attached sensors that capture physiological signals (PPG, EDA, Skin temperature), as well as motion sensors (three-axis accelerometer). Our multimodal multisensory dataset (MMD-MSD) opens new opportunities for modeling the body stance (sitting posture and movements), physiological state (stress level, attention, emotional arousal, valence), and performance (success rate on the Stroop test) of people working with a computer. Finally, we demonstrate two use cases: improper neck posture detection from pictures and cognitive load detection from physiological signals.
- 13 February 2024
- Published by Taylor & Francis in Bioacoustics
- Vol. 33 (2) , 103-121
The importance of acoustic background modelling in CNN-based detection of the neotropical White-lored Spinetail (Aves, Passeriformes, Furnaridae)
- 13 February 2024
- Published by Taylor & Francis in Bioacoustics
- Vol. 33 (2) , 103-121
The importance of acoustic background modelling in CNN-based detection of the neotropical White-lored Spinetail (Aves, Passeriformes, Furnaridae)
- Open Access
- 12 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3852
Towards Implementation of Emotional Intelligence in Human–Machine Collaborative Systems
Social awareness and relationship management components can be seen as a form of emotional intelligence. In the present work, we propose task-related adaptation on the machine side that accounts for a person’s momentous cognitive and emotional state. We validate the practical significance of the proposed approach in person-specific and person-independent setups. The analysis of results in the person-specific setup shows that the individual optimal performance curves for that person, according to the Yerkes–Dodson law, are displaced. Awareness of these curves allows for automated recognition of specific user profiles, real-time monitoring of the momentous condition, and activating a particular relationship management strategy. This is especially important when a deviation is detected caused by a change in the person’s state of mind under the influence of known or unknown factors.
- 12 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3852
Open AccessTowards Implementation of Emotional Intelligence in Human–Machine Collaborative Systems
Social awareness and relationship management components can be seen as a form of emotional intelligence. In the present work, we propose task-related adaptation on the machine side that accounts for a person’s momentous cognitive and emotional state. We validate the practical significance of the proposed approach in person-specific and person-independent setups. The analysis of results in the person-specific setup shows that the individual optimal performance curves for that person, according to the Yerkes–Dodson law, are displaced. Awareness of these curves allows for automated recognition of specific user profiles, real-time monitoring of the momentous condition, and activating a particular relationship management strategy. This is especially important when a deviation is detected caused by a change in the person’s state of mind under the influence of known or unknown factors.
- 1 November 2022
- Published by Bulgarian Geological Society in Review of the Bulgarian Geological Society
- Vol. 83 (2) , 3-9
Assessment of pollution with heavy metals and petroleum products in the sediments of Varna Lake
- 1 November 2022
- Published by Bulgarian Geological Society in Review of the Bulgarian Geological Society
- Vol. 83 (2) , 3-9
Assessment of pollution with heavy metals and petroleum products in the sediments of Varna Lake
- Open Access
Automated Detection of Improper Sitting Postures in Computer Users Based on Motion Capture Sensors
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 postures, which was next used to evaluate the applicability of Hjorth’s parameters—Activity, Mobility and Complexity—on the specific classification task. Specifically, based on accelerometer data, we computed Hjorth’s time-domain parameters, which we stacked as feature vectors and fed to a binary classifier (kNN, decision tree, linear SVM and Gaussian SVM). The experimental evaluation in a setup involving two different keyboard types (standard and ergonomic) validated the practical worth of the proposed sitting posture detection method, and we reported an average classification accuracy of up to 98.4%. We deem that this research contributes toward creating an automated system for improper posture monitoring for people working on a computer for prolonged periods.
Open AccessAutomated Detection of Improper Sitting Postures in Computer Users Based on Motion Capture Sensors
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 postures, which was next used to evaluate the applicability of Hjorth’s parameters—Activity, Mobility and Complexity—on the specific classification task. Specifically, based on accelerometer data, we computed Hjorth’s time-domain parameters, which we stacked as feature vectors and fed to a binary classifier (kNN, decision tree, linear SVM and Gaussian SVM). The experimental evaluation in a setup involving two different keyboard types (standard and ergonomic) validated the practical worth of the proposed sitting posture detection method, and we reported an average classification accuracy of up to 98.4%. We deem that this research contributes toward creating an automated system for improper posture monitoring for people working on a computer for prolonged periods.