Alexandru-George Berciu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alexandru-George Berciu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Eva Henrietta Dulf
Department of Automation, Technical University of Cluj Napoca, Cluj-Napoca, Romania
11 shared publications - Dan Doru Micu
Technical University of Cluj-Napoca, Cluj-Napoca, Romania
7 shared publications - Teodora Mocan
Discipline of Physiology, Department of Functional Biosciences, “Iuliu Hațieganu” University of Medicine and Pharmacy, 400006 Cluj-Napoca, Romania
6 shared publications - Alex Ede Danku
Automation Department, Faculty of Automation and Computer Science, Energy Transition Research Center, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania
3 shared publications - Evelin-Henrietta Dulf
Iuliu Hatieganu University of Medicine and Pharmacy
3 shared publications - Lucia Agoston-Coldea
Department of Internal Medicine, Iuliu Haţieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania
3 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (3) , 45
Multi-Modal Data Processing in Digital Twins: Connecting Sensors and Actuators for Health Optimisation
The continuous monitoring of population health is a major focus in scientific literature, with numerous studies highlighting the critical role of sleep. However, to the best of the authors’ knowledge, the multi-modal data processing required to fully map the tripartite relationship between environmental stimuli, sleep, and health has not been achieved. This paper proposes a comprehensive data fusion strategy, integrating public databases to extract common features from historical sensor data. The present paper proposes a robust processing architecture by training four classes of algorithms (mathematical, machine learning, artificial intelligence, and ensemble models) to analyse how environmental inputs impact sleep quality and, consequently, physiological health. The resulting state-of-the-art model, a multi-modal architecture comprising 10 integrated models, was tested on a massive combined dataset of 139,950 rows and 8249 columns. The model achieved an R-squared of 0.958, demonstrating superior data processing and predictive accuracy. Alongside the integrated dataset, this research establishes the computational groundwork for human-centric Digital Twins, paving the way for closed-loop IoT environments where sensor-driven analytics inform automated actuator interventions to improve sleep and health.
- 10 June 2026
- Published by MDPI AG in Journal of Sensor and Actuator Networks
- Vol. 15 (3) , 45
Open AccessMulti-Modal Data Processing in Digital Twins: Connecting Sensors and Actuators for Health Optimisation
The continuous monitoring of population health is a major focus in scientific literature, with numerous studies highlighting the critical role of sleep. However, to the best of the authors’ knowledge, the multi-modal data processing required to fully map the tripartite relationship between environmental stimuli, sleep, and health has not been achieved. This paper proposes a comprehensive data fusion strategy, integrating public databases to extract common features from historical sensor data. The present paper proposes a robust processing architecture by training four classes of algorithms (mathematical, machine learning, artificial intelligence, and ensemble models) to analyse how environmental inputs impact sleep quality and, consequently, physiological health. The resulting state-of-the-art model, a multi-modal architecture comprising 10 integrated models, was tested on a massive combined dataset of 139,950 rows and 8249 columns. The model achieved an R-squared of 0.958, demonstrating superior data processing and predictive accuracy. Alongside the integrated dataset, this research establishes the computational groundwork for human-centric Digital Twins, paving the way for closed-loop IoT environments where sensor-driven analytics inform automated actuator interventions to improve sleep and health.
- 1 May 2026
- Published by Springer Nature
- p. 266-273
Multi-Modal Video Analysis System for Early Autism Detection Using Computer Vision
- 1 May 2026
- Published by Springer Nature
- p. 266-273
Multi-Modal Video Analysis System for Early Autism Detection Using Computer Vision
- Open Access
- 1 April 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (4) , 131
Meta-optimised environmental control for sleep and health enhancement
Unsuitable physical environments are increasingly recognised not just as a nuisance, but also as a significant determinant in the pathophysiology of sleep disorders and chronic illness. According to the literature, even little environmental changes can have a significant impact on sleep homeostasis: persistent exposure to background noise above 30 decibels causes autonomic arousal associated to cardiovascular disease, but even low-level artificial light (5–10 lux) suppresses melatonin and disrupts metabolic homeostasis. When paired with thermal stress outside the ideal 18–21 $$^\circ $$ C, window or ventilation deficiencies enabling carbon dioxide to increase over 1,000 ppm, these environmental stressors affect sleep architecture and impede long-term cognitive recovery. This paper introduces an innovative approach to automatically regulating environmental conditions to ensure proper sleep. This approach leverages an integrated framework of model predictive control, fuzzy logic, and reinforcement learning. To validate this deterministic approach, the study utilises a high-fidelity digital twin of student accommodations at the Mărăşti Student Campus of the Technical University of Cluj-Napoca. Experimental results demonstrate that the proposed Meta-Controller significantly enhances physiological outcomes, yielding a notable 10.06% improvement in objective sleep quality metrics and a 5.41% reduction in health risk indicators associated with sleep deprivation. By achieving an optimised sleep score in 99.24% of cases, the study underscores the efficacy of merging heuristic logic with predictive and adaptive control paradigms. This work provides a pioneering contribution to the field of cyber-physical systems, laying a robust foundation for future advancements in environmental modelling and the development of intelligent, health-centric living spaces through advanced system dynamics.- 1 April 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (4) , 131
Open AccessMeta-optimised environmental control for sleep and health enhancement
Unsuitable physical environments are increasingly recognised not just as a nuisance, but also as a significant determinant in the pathophysiology of sleep disorders and chronic illness. According to the literature, even little environmental changes can have a significant impact on sleep homeostasis: persistent exposure to background noise above 30 decibels causes autonomic arousal associated to cardiovascular disease, but even low-level artificial light (5–10 lux) suppresses melatonin and disrupts metabolic homeostasis. When paired with thermal stress outside the ideal 18–21 $$^\circ $$ C, window or ventilation deficiencies enabling carbon dioxide to increase over 1,000 ppm, these environmental stressors affect sleep architecture and impede long-term cognitive recovery. This paper introduces an innovative approach to automatically regulating environmental conditions to ensure proper sleep. This approach leverages an integrated framework of model predictive control, fuzzy logic, and reinforcement learning. To validate this deterministic approach, the study utilises a high-fidelity digital twin of student accommodations at the Mărăşti Student Campus of the Technical University of Cluj-Napoca. Experimental results demonstrate that the proposed Meta-Controller significantly enhances physiological outcomes, yielding a notable 10.06% improvement in objective sleep quality metrics and a 5.41% reduction in health risk indicators associated with sleep deprivation. By achieving an optimised sleep score in 99.24% of cases, the study underscores the efficacy of merging heuristic logic with predictive and adaptive control paradigms. This work provides a pioneering contribution to the field of cyber-physical systems, laying a robust foundation for future advancements in environmental modelling and the development of intelligent, health-centric living spaces through advanced system dynamics. - Open Access
- 31 March 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (4) , 152
Semi-Automated Computational Identification of Fibrosis for Enhanced Histopathological Decision Support
Myocardial fibrosis is a critical prognostic marker involving a progressive cascade of pathological conditions. Accurate assessment of fibrosis in myocardial samples is a routine but difficult procedure for pathologists. This article presents a semi-automated system designed to ease this task while providing pixel-level accuracy that exceeds manual estimation capabilities. The proposed innovative approach combines Gabor filters with CIELAB color space analysis to ensure the efficiency and interpretability of calculations. Testing on histopathological samples, differentiating between fibrous, healthy, and variant tissues, yielded a promising accuracy of 87.5% for images with fibrosis and 80% for all 45 images tested. This system successfully establishes a solid foundation for automated diagnosis, providing pathologists with a reliable and highly accurate tool for quantitative analysis of cardiac tissue.
- 31 March 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (4) , 152
Open AccessSemi-Automated Computational Identification of Fibrosis for Enhanced Histopathological Decision Support
Myocardial fibrosis is a critical prognostic marker involving a progressive cascade of pathological conditions. Accurate assessment of fibrosis in myocardial samples is a routine but difficult procedure for pathologists. This article presents a semi-automated system designed to ease this task while providing pixel-level accuracy that exceeds manual estimation capabilities. The proposed innovative approach combines Gabor filters with CIELAB color space analysis to ensure the efficiency and interpretability of calculations. Testing on histopathological samples, differentiating between fibrous, healthy, and variant tissues, yielded a promising accuracy of 87.5% for images with fibrosis and 80% for all 45 images tested. This system successfully establishes a solid foundation for automated diagnosis, providing pathologists with a reliable and highly accurate tool for quantitative analysis of cardiac tissue.
- Open Access
- 19 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1287
A Real Time Multi Modal Computer Vision Framework for Automated Autism Spectrum Disorder Screening
Background: The early detection of autism spectrum disorder (ASD) is imperative for enhancing long-term developmental outcomes. Nevertheless, conventional screening methods depend on time-consuming, expert-driven behavioral assessments and are characterized by limited scalability. Automated video-based analysis provides a noninvasive and objective approach for the extraction of behavioral biomarkers from naturalistic recordings. Methods: A modular multimodal framework was developed that integrates motion-based video analysis and facial feature extraction for the purpose of ASD versus typically developing (TD) classification. The system is capable of processing RGB videos, skeleton/stickman representations, and motion trajectory streams. A comprehensive set of kinematic features was extracted, encompassing joint trajectories, velocity and acceleration profiles, posture variability, movement smoothness, and bilateral asymmetry. The repetitive stereotypical behaviors exhibited by the subjects were characterized using frequency-domain analysis via FFT within the 0.3–7.0 Hz band. Facial expression features derived from normalized face crops and landmark-based morphological descriptors were integrated as complementary modalities. The feature-level fusion process was executed subsequent to z-score normalization, and the classification procedure was conducted using a Random Forest model with stratified 5-fold cross validation. The implementation of GPU acceleration was instrumental in facilitating near real-time inference. Results: The motion-based ComplexVideos pipeline demonstrated a cross-validated accuracy of 94.2 ± 2.1% with an area under the ROC curve (AUC) of 0.93. Skeleton-based KinectStickman inputs demonstrated moderate performance, with an accuracy range of 60–80%. In contrast, facial-only models exhibited an accuracy of approximately 60%. The integration of multiple modalities through feature fusion has been demonstrated to enhance the robustness of classification algorithms and mitigate the occurrence of false negative outcomes, thereby surpassing the performance of single-modality models. The mean inference time remained below one second per video frame under standard operating conditions. Conclusions: The experimental results demonstrate that the integration of multimodal cues, including motion and facial features, facilitates the development of effective and efficient video-based screening methods for autism spectrum disorder (ASD). The proposed framework is designed to offer a scalable, extensible, and computationally efficient solution that can support early screening in clinical and remote assessment settings.
- 19 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1287
Open AccessA Real Time Multi Modal Computer Vision Framework for Automated Autism Spectrum Disorder Screening
Background: The early detection of autism spectrum disorder (ASD) is imperative for enhancing long-term developmental outcomes. Nevertheless, conventional screening methods depend on time-consuming, expert-driven behavioral assessments and are characterized by limited scalability. Automated video-based analysis provides a noninvasive and objective approach for the extraction of behavioral biomarkers from naturalistic recordings. Methods: A modular multimodal framework was developed that integrates motion-based video analysis and facial feature extraction for the purpose of ASD versus typically developing (TD) classification. The system is capable of processing RGB videos, skeleton/stickman representations, and motion trajectory streams. A comprehensive set of kinematic features was extracted, encompassing joint trajectories, velocity and acceleration profiles, posture variability, movement smoothness, and bilateral asymmetry. The repetitive stereotypical behaviors exhibited by the subjects were characterized using frequency-domain analysis via FFT within the 0.3–7.0 Hz band. Facial expression features derived from normalized face crops and landmark-based morphological descriptors were integrated as complementary modalities. The feature-level fusion process was executed subsequent to z-score normalization, and the classification procedure was conducted using a Random Forest model with stratified 5-fold cross validation. The implementation of GPU acceleration was instrumental in facilitating near real-time inference. Results: The motion-based ComplexVideos pipeline demonstrated a cross-validated accuracy of 94.2 ± 2.1% with an area under the ROC curve (AUC) of 0.93. Skeleton-based KinectStickman inputs demonstrated moderate performance, with an accuracy range of 60–80%. In contrast, facial-only models exhibited an accuracy of approximately 60%. The integration of multiple modalities through feature fusion has been demonstrated to enhance the robustness of classification algorithms and mitigate the occurrence of false negative outcomes, thereby surpassing the performance of single-modality models. The mean inference time remained below one second per video frame under standard operating conditions. Conclusions: The experimental results demonstrate that the integration of multimodal cues, including motion and facial features, facilitates the development of effective and efficient video-based screening methods for autism spectrum disorder (ASD). The proposed framework is designed to offer a scalable, extensible, and computationally efficient solution that can support early screening in clinical and remote assessment settings.
- Open Access
- 21 October 2025
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 654
Fog-based AI image analysis for load disaggregation using Random Forest and XGBoost
The use of artificial intelligence to energy systems is growing, and image-based analysis is showing promise as a tool to improve optimization and monitoring. This paper presents a new load disaggregation architecture that improves responsiveness and efficiency by combining fog computing with artificial intelligence-driven image recognition approaches. To categorize consumption profiles the system examines visual depictions of energy data. Two different kinds of consumption profiles were identified and differentiated using Random Forest and XGBoost classifiers, allowing precise energy usage disaggregation in complex contexts.
- 21 October 2025
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 654
Open AccessFog-based AI image analysis for load disaggregation using Random Forest and XGBoost
The use of artificial intelligence to energy systems is growing, and image-based analysis is showing promise as a tool to improve optimization and monitoring. This paper presents a new load disaggregation architecture that improves responsiveness and efficiency by combining fog computing with artificial intelligence-driven image recognition approaches. To categorize consumption profiles the system examines visual depictions of energy data. Two different kinds of consumption profiles were identified and differentiated using Random Forest and XGBoost classifiers, allowing precise energy usage disaggregation in complex contexts.
- 2 August 2025
- Published by Springer Nature
- p. 129-139
Artificial Intelligence in Pediatric Pneumonia Diagnosis
- 2 August 2025
- Published by Springer Nature
- p. 129-139
Artificial Intelligence in Pediatric Pneumonia Diagnosis
- 26 July 2025
- Published by Springer Nature
- p. 737-744
Artificial Intelligence in Human-Centric Sleep Monitoring
- 26 July 2025
- Published by Springer Nature
- p. 737-744
Artificial Intelligence in Human-Centric Sleep Monitoring
- Open Access
- 22 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8144
Colorectal Cancer Detection Tool Developed with Neural Networks
In the last two decades, there has been a considerable surge in the development of artificial intelligence. Imaging is most frequently employed for the diagnostic evaluation of patients, as it is regarded as one of the most precise methods for identifying the presence of a disease. However, a study indicates that approximately 800,000 individuals in the USA die or incur permanent disability because of misdiagnosis. The present study is based on the use of computer-aided diagnosis of colorectal cancer. The objective of this study is to develop a practical, low-cost, AI-based decision-support tool that integrates clinical test data (blood/stool) and, if needed, colonoscopy images to help reduce misdiagnosis and improve early detection of colorectal cancer for clinicians. Convolutional neural networks (CNNs) and artificial neural networks (ANNs) are utilized in conjunction with a graphical user interface (GUI), which caters to individuals lacking programming expertise. The performance of the artificial neural network (ANN) is measured using the mean squared error (MSE) metric, and the obtained performance is 7.38. For CNN, two distinct cases are under consideration: one with two outputs and one with three outputs. The precision of the models is 97.2% for RGB and 96.7% for grayscale, respectively, in the first instance, and 83% for RGB and 82% for grayscale in the second instance. However, using a pretrained network yielded superior performance with 99.5% for 2-output models and 93% for 3-output models. The GUI is composed of two panels, with the best ANN model and the best CNN model being utilized in each. The primary function of the tool is to assist medical personnel in reducing the time required to make decisions and the probability of misdiagnosis.
- 22 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (15) , 8144
Open AccessColorectal Cancer Detection Tool Developed with Neural Networks
In the last two decades, there has been a considerable surge in the development of artificial intelligence. Imaging is most frequently employed for the diagnostic evaluation of patients, as it is regarded as one of the most precise methods for identifying the presence of a disease. However, a study indicates that approximately 800,000 individuals in the USA die or incur permanent disability because of misdiagnosis. The present study is based on the use of computer-aided diagnosis of colorectal cancer. The objective of this study is to develop a practical, low-cost, AI-based decision-support tool that integrates clinical test data (blood/stool) and, if needed, colonoscopy images to help reduce misdiagnosis and improve early detection of colorectal cancer for clinicians. Convolutional neural networks (CNNs) and artificial neural networks (ANNs) are utilized in conjunction with a graphical user interface (GUI), which caters to individuals lacking programming expertise. The performance of the artificial neural network (ANN) is measured using the mean squared error (MSE) metric, and the obtained performance is 7.38. For CNN, two distinct cases are under consideration: one with two outputs and one with three outputs. The precision of the models is 97.2% for RGB and 96.7% for grayscale, respectively, in the first instance, and 83% for RGB and 82% for grayscale in the second instance. However, using a pretrained network yielded superior performance with 99.5% for 2-output models and 93% for 3-output models. The GUI is composed of two panels, with the best ANN model and the best CNN model being utilized in each. The primary function of the tool is to assist medical personnel in reducing the time required to make decisions and the probability of misdiagnosis.
- 11 June 2025
- Published by Springer Nature
- p. 524-536
Real Help? Smoking, Alcohol, and Their Effects on Sleep Quality in Military Environments
- 11 June 2025
- Published by Springer Nature
- p. 524-536
Real Help? Smoking, Alcohol, and Their Effects on Sleep Quality in Military Environments