Dragos Vicoveanu

This paper proposes a real-time physiological monitoring and biofeedback model based on the console of an indoor cycling bike, applied within high-school physical education. The system uses heart rate (HR) as a control signal for exercise intensity within a closed-loop human–machine system, complemented by the Borg Scale of Perceived Exertion (RPE 6–20) as a subjective validation of the objective feedback loop. The 12-week intervention, conducted with 48 adolescents aged 15–17 years, was evaluated using a battery of six standardized psychomotor tests from EUROFIT and cardiovascular indicators, including 1-min heart rate recovery (HRR). The results show significant improvements in balance, coordination, agility, and autonomic recovery in the experimental group, confirming the effectiveness of the integrated biofeedback system as an accessible biomedical monitoring platform in the school setting. These findings suggest that heart-rate-based biofeedback, delivered through the bicycle console, may represent an accessible and effective strategy for regulating exercise intensity and supporting psychomotor and cardiovascular adaptation in the school environment.

This present paper proposes the development and validation of a low-cost, portable system for the acquisition, processing, and classification of four-channel surface electromyography (i.e., sEMG) signals recorded from the forearm. The hardware platform integrates an STM32F4 family microcontroller and BioAmp EXG Pill module. The software component was developed in Python to implement an adaptive filtering method. To evaluate gesture classification performance, three machine learning classifiers (SVM, Random Forest, kNN) were compared against a classical adaptive threshold-based detection method (75th percentile of the RMS distribution). To reveal the inter-subject variability across 10 subjects, a data augmentation procedure using a Deep Convolutional Conditional Generative Adversarial Network (i.e., DCGAN) was used. The results demonstrate the superiority of machine learning (i.e., ML) classifiers (SVM: 99.86% accuracy, 5-fold CV) over the threshold-based method (33.00%) in classifying seven gestures, confirming the necessity of pattern recognition approaches for gesture discrimination in neuromotor rehabilitation applications.

Background/Objectives: Maternal nutrition and physical activity are modifiable behaviours relevant to pregnancy outcomes, but higher activity may coexist with both favourable and unfavourable dietary patterns. This study examined associations between pregnancy physical activity, individualised fruit–vegetable adequacy, energy-dense, nutrient-poor (EDNP) food and beverage intake, and preterm birth. Methods: This cross-sectional study included 1048 postpartum women with singleton live births recruited consecutively at a tertiary maternity hospital in Romania. Physical activity during the last three months of pregnancy was assessed using the Pregnancy Physical Activity Questionnaire and categorised into quartiles of total MET-hours/week. Dietary intake was assessed using an adapted food frequency questionnaire. Fruit–vegetable adequacy was evaluated against individualised recommendations, and EDNP intake was summarised using a composite score derived from fast food, sweets, chocolate, and sugar-sweetened beverages. Preterm birth was defined as delivery before 37 completed weeks of gestation. Results: Preterm birth occurred in 118 cases (11.3%). Higher physical activity categories showed greater fruit–vegetable intake and adequacy, but also higher EDNP intake. After adjustment for maternal age, pregestational BMI, parity, education, and income, physical activity category remained associated with all modelled dietary outcomes. Category 4 had higher odds of fruit–vegetable adequacy than category 1 (OR 2.24, 95% CI 1.55–3.24). In diet-informed models, category 3 had the lowest odds of preterm birth (OR 0.38, 95% CI 0.21–0.68). Conclusions: Total physical activity during pregnancy was associated with a complex dietary profile rather than a uniformly favourable lifestyle pattern. The lowest odds of preterm birth were observed in the third activity category, suggesting a non-linear association.

Personal health records (PHRs) are digital repositories that allow individuals to access, manage, and share their health information. By enabling patients to track their health over time and communicate effectively with healthcare providers, personal health records support more personalized care and improve the quality of healthcare. Their integration with emerging technologies, such as the Internet of Things (IoT), artificial intelligence (AI), and blockchain, enhances the utility and security of health data management, facilitating continuous health monitoring, automated decision support, and secure, decentralized data exchange. Despite their potential, PHR systems face significant challenges, including privacy concerns, security issues, and digital accessibility problems. This paper discusses the fundamental concepts, requirements, system architectures, and data sources that underpin modern PHR implementations, highlighting how they enable continuous health monitoring through the integration of wearable sensors; mobile health applications; and IoT-enabled medical devices that collect, process, and transmit data to support proactive care and personalized treatments. The benefits and limitations of PHR systems are also discussed in detail, with a focus on interoperability, adoption drivers, and the role of advanced technologies in supporting the development of secure and scalable health information systems for a smarter world.

Background and Objectives: College life is a time when students take more responsibility for health-related behaviors. Aim: To determine the oral health behaviors of dental students, to motivate their transformation into cyanogenic behaviors by applying the planned behavior model, and to determine the degree to which students can modify behavior for oral health. Material and Methods: The results of the initial and final assessment (4 months apart) of the bacterial plaque present by means of the Quigley Hein and API indexes were collected from the student files. The Health-Promoting Lifestyle Profile II -HPLP II and Generalized Self-Efficacy Scale (GSE) questionnaires were used to determine the variables with predictor values that influence the cognitive-perceptual factors. Results: For the “health responsibility” domain, the average total value was 2.53 ± 0.9 (SD). For the “interpersonal relationships” domain, the average value was 2.82 ± 0.79. In the case of the “nutrition” domain, the desire to change the behavior of the participants was moderate (2.53 ± 1.19). “Physical activity” represents an important field in the everyday life of young adults. The results of the study indicated a moderate desire for change (2.52 ± 0.97). In the case of “spiritual growth”, in which self-esteem, the way the individual perceives the environment and the adaptation to it were evaluated, a great desire for change was observed (2.74 ± 0.82). Scale GSE questionnaire showed an α coefficient of 28.52 ± 0.82, a value that indicated a moderate to a high level of efficacy and self-confidence. Conclusions: The results of the study showed that students have a moderate tendency to change in all areas, except for interpersonal relationships, where the desire to change something is increased. The participants have a moderate to a high level of self-efficacy and self-confidence.

Background and Objectives: The interaction between dental alloys and saliva affects both its own properties and those of metallic materials. Materials and Methods: Samples made of Cr-Co and Ni-Cr were studied. It was opted for corrosion under tension, scanning electron microscopy was used to characterize the surface morphology, and the chemical composition of the surface was assessed with the help of an Energy Dispersive Spectrometer. In vitro testing of the cytotoxic impact of the study eluates was carried out by flow cytometric analysis. Results: Pitting areas appear in the mass of the Ni-Cr alloy. Nickel, Manganese, and Cobalt dissolve and go into the solution. Corrosion is superficial in the case of the Cr-Co alloy, the corrosion points are shallow, and the amount of dissolved metal is relatively small. Mostly Nickel passes into the solution, unlike Chromium and Cobalt, which remain at this level. We noticed an increase in the viability of cell cultures in the case of Cr-Co alloy and a decrease in the number of living cells (87%) for Ni-Cr alloy. Conclusions: Common alloys (Ni-Cr and Cr-Co) are prone to corrosion, because they lack structural features that would shield the alloy from corrosion agents.

Increasing importance in the field of artificial intelligence has led to huge progress in remote sensing. Deep learning approaches have made tremendous progress in hyperspectral image (HSI) classification. However, the complexity in classifying the HSI data using a common convolutional neural network is still a challenge. Further, the network architecture becomes more complex when different spatial–spectral feature information is extracted. Usually, CNN has a large number of trainable parameters, which increases the computational complexity of HSI data. In this paper, an optimized squeeze–excitation AdaBound dense network (SE-AB-DenseNet) is designed to emphasize the significant spatial–spectral features of HSI data. The dense network is combined with the AdaBound and squeeze–excitation modules to give lower computation costs and better classification performance. The AdaBound optimizer gives the proposed model the ability to improve its stability and enhance its classification accuracy by approximately 2%. Additionally, the cutout regularization technique is used for HSI spatial–spectral classification to overcome the problem of overfitting. The experiments were carried out on two commonly used hyperspectral datasets (Indian Pines and Salinas). The experiment results on the datasets show a competitive classification accuracy when compared with state-of-the-art methods with limited training samples. From the SE-AB-DenseNet with the cutout model, the overall accuracies for the Indian Pines and Salinas datasets were observed to be 99.37 and 99.78, respectively.

(1) Background: Fetal growth restriction is a relatively common disorder in pregnant patients with thrombophilia. New artificial intelligence algorithms are a promising option for the prediction of adverse obstetrical outcomes. The aim of this study was to evaluate the predictive performance of a Feed-Forward Back Propagation Network (FFBPN) for the prediction of small for gestational age (SGA) newborns in a cohort of pregnant patients with thrombophilia. (2) Methods: This observational retrospective study included all pregnancies in women with thrombophilia who attended two tertiary maternity hospitals in Romania between January 2013 and December 2020. Bivariate associations of SGA and each predictor variable were evaluated. Clinical and paraclinical predictors were further included in a FFBPN, and its predictive performance was assessed. (3) Results: The model had an area under the curve (AUC) of 0.95, with a true positive rate of 86.7%, and a false discovery rate of 10.5%. The overall accuracy of our model was 90%. (4) Conclusion: This is the first study in the literature that evaluated the performance of a FFBPN for the prediction of pregnant patients with thrombophilia at a high risk of giving birth to SGA newborns, and its promising results could lead to a tailored prenatal management.

Subjects with neurological problems and neurological disorders can be recovered in the dedicated recovery centers and at home. The paper presents a smart writing system that uses dedicated movements to recover specific problems of the hands. The system is based on a smart pen equipped with vibration, acceleration, and gyroscope sensors that give remote data to a computer via an ESP Arduino board via Bluetooth. The purpose of the system design is to serve in applications such as recognizing the writing, drawings, or emotional and physiological states of the writer. The data is preprocessed by extracting the characteristics. They will be used in a prediction and classification system using machine learning (ML) algorithms. The paper proposes a new method of using the dynamic processing of certain geometric shapes that are recognized and analyzed to diagnose the mobility of the subjects hands. Using methods of clustering data as K-means and classification as support vector machine (SVM), the results obtained from the data analysis using the TensorFlow platform have an accuracy of over 70. Due to the adaptation algorithms used, the system can be customized, learning the hand movement of the subject.

COVID‐19 is a fatal disease caused by the SARS‐CoV‐2 virus that has caused around 5.3 Million deaths globally as of December 2021. The detection of this disease is a time taking process that have worsen the situation around the globe, and the disease has been identified as a world pandemic by the WHO. Deep learning‐based approaches are being widely used to diagnose the COVID‐19 cases, but the limitation of immensity in the publicly available dataset causes the problem of model over‐fitting. Modern artificial intelligence‐based techniques can be used to increase the dataset to avoid from the over‐fitting problem. This research work presents the use of various deep learning models along with the state‐of‐the‐art augmentation methods, namely, classical and generative adversarial network‐ (GAN‐) based data augmentation. Furthermore, four existing deep convolutional networks, namely, DenseNet‐121, InceptionV3, Xception, and ResNet101 have been used for the detection of the virus in X‐ray images after training on augmented dataset. Additionally, we have also proposed a novel convolutional neural network (QuNet) to improve the COVID‐19 detection. The comparative analysis of achieved results reflects that both QuNet and Xception achieved high accuracy with classical augmented dataset, whereas QuNet has also outperformed and delivered 90% detection accuracy with GAN‐based augmented dataset.