Cătălin Petrescu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cătălin Petrescu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Alin Moldoveanu
National University of Science and Technology Politehnica Bucharest
4 shared publications - Florica Moldoveanu
National University of Science and Technology Politehnica Bucharest
4 shared publications - Livia Petrescu
University of Bucharest
4 shared publications - Oana Mitruț
Faculty of Automatic Control and Computers, University Politehnica of Bucharest, 060042 Bucharest, Romania
4 shared publications - Ana Magdalena Anghel
Automatic Control and Applied Informatics Department, Faculty of Automatic Control and Computers, National University of Science and Technology Politehnica Bucharest, 060042 Bucharest, Romania
2 shared publications - Gabriela Moise
Faculty of Letters and Sciences, Petroleum-Gas University of Ploiesti, 100680 Ploiesti, Romania
2 shared publications
Latest Publications
- 16 June 2026
- Published by Taylor & Francis in Interactive Learning Environments
- p. 1-26
Actionable quantification of fear of public speaking for VR-based treatment and training
- 16 June 2026
- Published by Taylor & Francis in Interactive Learning Environments
- p. 1-26
Actionable quantification of fear of public speaking for VR-based treatment and training
- Open Access
- 16 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10365
Immersive Phobia Therapy through Adaptive Virtual Reality and Biofeedback
Phobias are a type of anxiety disorder characterized by severe fear of objects and situations. In recent years, virtual reality exposure therapy has emerged as a safer and more convenient method of treating phobias, with the same rate of success as classical therapy, the in vivo exposure to stimuli. Following extensive research concerning the available technologies and after studying the state of the art in the field, we developed the PhoVR (Phobia therapy through Virtual Reality) system during a 2-year long project that involved the participation of a technical university, a biology faculty, and an industry partner specialized in designing 3D applications. Our final prototype incorporates scenarios for acrophobia, claustrophobia, and fear of public speaking therapy, in which the user is required to perform gamified tasks and navigate virtual reality environments with biophysical data acquisition (electrodermal activity and heart rate), automatic anxiety level classification, biofeedback integrated into the scenes’ elements, the dynamic adaptation of the virtual environments, and relaxation techniques made available at any moment. The control panel is an application dedicated to psychotherapists for managing patients’ profiles and therapy sessions. The feedback obtained in a qualitative survey with subjects and psychotherapists who evaluated the prototype validated the system and provided suggestions for refinement.
- 16 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10365
Open AccessImmersive Phobia Therapy through Adaptive Virtual Reality and Biofeedback
Phobias are a type of anxiety disorder characterized by severe fear of objects and situations. In recent years, virtual reality exposure therapy has emerged as a safer and more convenient method of treating phobias, with the same rate of success as classical therapy, the in vivo exposure to stimuli. Following extensive research concerning the available technologies and after studying the state of the art in the field, we developed the PhoVR (Phobia therapy through Virtual Reality) system during a 2-year long project that involved the participation of a technical university, a biology faculty, and an industry partner specialized in designing 3D applications. Our final prototype incorporates scenarios for acrophobia, claustrophobia, and fear of public speaking therapy, in which the user is required to perform gamified tasks and navigate virtual reality environments with biophysical data acquisition (electrodermal activity and heart rate), automatic anxiety level classification, biofeedback integrated into the scenes’ elements, the dynamic adaptation of the virtual environments, and relaxation techniques made available at any moment. The control panel is an application dedicated to psychotherapists for managing patients’ profiles and therapy sessions. The feedback obtained in a qualitative survey with subjects and psychotherapists who evaluated the prototype validated the system and provided suggestions for refinement.
- Open Access
Machine Learning Methods for Fear Classification Based on Physiological Features
This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.
Open AccessMachine Learning Methods for Fear Classification Based on Physiological Features
This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.
- Open Access
Integrating Biosignals Measurement in Virtual Reality Environments for Anxiety Detection
This paper proposes a protocol for the acquisition and processing of biophysical signals in virtual reality applications, particularly in phobia therapy experiments. This protocol aims to ensure that the measurement and processing phases are performed effectively, to obtain clean data that can be used to estimate the users’ anxiety levels. The protocol has been designed after analyzing the experimental data of seven subjects who have been exposed to heights in a virtual reality environment. The subjects’ level of anxiety has been estimated based on the real-time evaluation of a nonlinear function that has as parameters various features extracted from the biophysical signals. The highest classification accuracy was obtained using a combination of seven heart rate and electrodermal activity features in the time domain and frequency domain.
Open AccessIntegrating Biosignals Measurement in Virtual Reality Environments for Anxiety Detection
This paper proposes a protocol for the acquisition and processing of biophysical signals in virtual reality applications, particularly in phobia therapy experiments. This protocol aims to ensure that the measurement and processing phases are performed effectively, to obtain clean data that can be used to estimate the users’ anxiety levels. The protocol has been designed after analyzing the experimental data of seven subjects who have been exposed to heights in a virtual reality environment. The subjects’ level of anxiety has been estimated based on the real-time evaluation of a nonlinear function that has as parameters various features extracted from the biophysical signals. The highest classification accuracy was obtained using a combination of seven heart rate and electrodermal activity features in the time domain and frequency domain.
- Open Access
- 25 March 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2236
Voting-Based Document Image Skew Detection
Optical Character Recognition (OCR) is an indispensable tool for technology users nowadays, as our natural language is presented through text. We live under the need of having information at hand in every circumstance and, at the same time, having machines understand visual content and thus enable the user to be able to search through large quantities of text. To detect textual information and page layout in an image page, the latter must be properly oriented. This is the problem of the so-called document deskew, i.e., finding the skew angle and rotating by its opposite. This paper presents an original approach which combines various algorithms that solve the skew detection problem, with the purpose of always having at least one to compensate for the others’ shortcomings, so that any type of input document can be processed with good precision and solid confidence in the output result. The tests performed proved that the proposed solution is very robust and accurate, thus being suitable for large scale digitization projects.
- 25 March 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2236
Open AccessVoting-Based Document Image Skew Detection
Optical Character Recognition (OCR) is an indispensable tool for technology users nowadays, as our natural language is presented through text. We live under the need of having information at hand in every circumstance and, at the same time, having machines understand visual content and thus enable the user to be able to search through large quantities of text. To detect textual information and page layout in an image page, the latter must be properly oriented. This is the problem of the so-called document deskew, i.e., finding the skew angle and rotating by its opposite. This paper presents an original approach which combines various algorithms that solve the skew detection problem, with the purpose of always having at least one to compensate for the others’ shortcomings, so that any type of input document can be processed with good precision and solid confidence in the output result. The tests performed proved that the proposed solution is very robust and accurate, thus being suitable for large scale digitization projects.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 833-838
Optimal and Safety Hardware and Software Control Structure for Dual Axes Solar Tracker
The main idea of this approach is to analyze and implement in real time a structure (hardware and software) that ensures the optimal orientation (on two axes) of a group of photovoltaic panels. The safety of exploiting the whole system is a particularly important practical aspect, which is ensured by the hardware and software elements included in the approach. The solution proposed is implemented and tested on a real architecture, analyzing at the end the results obtained.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 833-838
Optimal and Safety Hardware and Software Control Structure for Dual Axes Solar Tracker
The main idea of this approach is to analyze and implement in real time a structure (hardware and software) that ensures the optimal orientation (on two axes) of a group of photovoltaic panels. The safety of exploiting the whole system is a particularly important practical aspect, which is ensured by the hardware and software elements included in the approach. The solution proposed is implemented and tested on a real architecture, analyzing at the end the results obtained.
- Open Access
- 30 June 2017
- Published by Arab Academy for Science, Technology, and Maritime Transport (AASTMT) in Renewable Energy and Sustainable Development
- Vol. 3 (2) , 218-223
Artificial Neural Network Based Model of Photovoltaic Cell
Artificial Neural Network Based Model of Photovoltaic Cell
- 30 June 2017
- Published by Arab Academy for Science, Technology, and Maritime Transport (AASTMT) in Renewable Energy and Sustainable Development
- Vol. 3 (2) , 218-223
Open AccessArtificial Neural Network Based Model of Photovoltaic Cell
Artificial Neural Network Based Model of Photovoltaic Cell
- 1 August 2001
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 34 (13) , 675-680
Design, Refinement and Accuracy of PID Controllers
- 1 August 2001
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 34 (13) , 675-680
Design, Refinement and Accuracy of PID Controllers