Search Results (87)

Motor imagery (MI) electroencephalograms (EEGs) are pivotal cortical potentials reflecting cortical activity during imagined motor actions, widely leveraged for brain-computer interface (BCI) system development. However, effectively decoding these MI EEG signals is often overshadowed by flawed methods in signal processing, deep learning methods that are clinically unexplained, and highly inconsistent performance across different datasets. We propose BCINetV1, a new framework for MI EEG decoding to address the aforementioned challenges. The BCINetV1 utilizes three innovative components: a temporal convolution-based attention block (T-CAB) and a spectral convolution-based attention block (S-CAB), both driven by a new convolutional self-attention (ConvSAT) mechanism to identify key non-stationary temporal and spectral patterns in the EEG signals. Lastly, a squeeze-and-excitation block (SEB) intelligently combines those identified tempo-spectral features for accurate, stable, and contextually aware MI EEG classification. Evaluated upon four diverse datasets containing 69 participants, BCINetV1 consistently achieved the highest average accuracies of 98.6% (Dataset 1), 96.6% (Dataset 2), 96.9% (Dataset 3), and 98.4% (Dataset 4). This research demonstrates that BCINetV1 is computationally efficient, extracts clinically vital markers, effectively handles the non-stationarity of EEG data, and shows a clear advantage over existing methods, marking a significant step forward for practical BCI applications. Full article

This study revealed variations in the composition and in vitro antioxidant activity of proanthocyanidins, hydroxycinnamic acid derivatives, flavonols, anthocyanins, and triterpene compounds in small cranberry fruit samples collected from a bog-type natural habitat in Lithuania during intensive ripening of the fruit. The highest total amounts of identified flavonols were determined at the beginning of fruit ripening on September 10 (1232.84 ± 31.73 µg/g). The highest total amounts of proanthocyanidins (1.85 ± 0.02 mg EE/g, p < 0.05), anthocyanins (4096.79 ± 5.93 µg/g, p < 0.05), and triterpene compounds (8248.46 ± 125.60 µg/g, p < 0.05) were detected in small cranberry fruit samples collected in the middle of the ripening period (September 16–18). The most potent in vitro antiradical and reducing activity was found in extracts of small cranberry fruit collected on September 10 (95.25 ± 1.15 µmol TE/g and 159.26 ± 0.77 µmol/g, respectively). The strongest correlation was found between the total content of hydroxycinnamic acid derivatives in the small cranberry fruit samples and the in vitro reducing activity of their extracts (0.858, p < 0.01). Among the individual compounds, the strongest correlation was observed between the amounts of isoquercitrin and guaijaverin in V. oxycoccos fruit samples and the in vitro reducing activity as assessed by the CUPRAC method (0.844, p < 0.01 and 0.769, p < 0.05, respectively). Full article

This study investigates the effects of transcutaneous electroacupuncture stimulation (TEAS) on eyeblink rate, EEG, and heart rate variability (HRV), emphasising whether eyeblink data—often dismissed as artefacts—can serve as useful physiological markers. Sixty-six participants underwent four TEAS sessions with different stimulation frequencies (2.5, 10, 80, and 160 pps, with 160 pps as a low-amplitude sham). EEG, ECG, PPG, and respiration data were recorded before, during, and after stimulation. Using non-parametric statistical analyses, including Friedman’s test, Wilcoxon, Conover–Iman, and bootstrapping, the study found significant changes across eyeblink, EEG, and HRV measures. Eyeblink laterality, particularly at 2.5 and 10 pps, showed strong frequency-specific effects. EEG power asymmetry and spectral centroids were associated with HRV indices, and 2.5 pps stimulation produced the strongest parasympathetic HRV response. Blink rate correlated with increased sympathetic and decreased parasympathetic activity. Baseline HRV measures, such as lower heart rate, predicted participant dropout. Eyeblinks were analysed using BLINKER software (v. 1.1.0), and additional complexity and entropy (‘CEPS-BLINKER’) metrics were derived. These measures were more predictive of adverse reactions than EEG-derived indices. Overall, TEAS modulates multiple physiological markers in a frequency-specific manner. Eyeblink characteristics, especially laterality, may offer valuable insights into autonomic function and TEAS efficacy in neuromodulation research. Full article

From the perspective of biogas plant (BGP) operators, it is highly challenging to make a profitable decision on optimal biomethane production and allocation across interconnected markets. The aim of this study is to analyze the dynamics of biomethane markets, develop the gas allocation portfolio (GAP) for BGPs, investigate the impact of GHG quota price on the market dynamics and substrate mix consumption, and evaluate the profitability of the biomethane market system under various demand-based scenarios. A two-step optimization approach based on linear programming is adopted. Firstly, the optimized substrate mix and corresponding GAP are determined for all BGPs. Secondly, by leveraging the options flexibility created by the interconnected nature of biomethane markets, the BGPs’ GAP is further developed. Through an in-depth sensitivity analysis, the effects of GHG quota price variations on the market dynamics are assessed. The results indicate that integrated production, obtained by implementing the improved GAP across all BGPs, maximizes the profitability of the system. At higher quota prices, the consumption of manure, residuals, and grass is encouraged, while the use of energy crops declines. Furthermore, higher quota prices lead to a substantial increase in biomethane price in the EEG market, highlighting the need for further governmental support for biomethane CHP units. The anticipated competition between hydrogen and biomethane to achieve a greater share in the heating sector could pose risks to long-term investments in biomethane. The system achieves its highest profitability, a total contribution margin of EUR 2254.8 million, under the Transport Biofuels Expansion scenario. Generally, policies and regulations that raise the quota price (e.g., the 36. BImSchV) or promote biomethane demand in the heating sector (e.g., the GEG) can provide both economic and ecological benefits to the system. Full article

Recent advancements in lightweight electroencephalogram(EEG) signal classification have enabled real-time human–robot interaction, yet challenges persist in balancing computational efficiency and safety in dynamic path planning. This study proposes an EEG-based inverse reinforcement learning (EIRL) framework to simulate human navigation strategies by decoding neural decision preferences. The method integrates a pruned WNFG-SSCCNet-ADMM classifier for EEG signal mapping, apprenticeship learning for reward function extraction, and Q-learning for policy optimization. Experimental validation in an 8 × 8 FrozenLake-v1 environment demonstrates that EIRL reduces average path risk values by 50% compared with traditional reinforcement learning, achieving expert-level safety ($\Delta$ = 4) while maintaining optimal path lengths. The framework enhances adaptability in unknown environments by embedding human-like risk aversion into robotic planning, offering a robust solution for applications requiring minimal prior environmental knowledge. Results highlight the synergy between neural feedback and computational models, advancing inclusive human–robot collaboration in safety-critical scenarios. Full article

Silver nanoparticles belong to a highly versatile group of nanomaterials with an appealing range of potential applications. In the realm of antimicrobial and antioxidant application, silver nanoparticles (AgNPs) exhibit auspicious capabilities. This research, for the very first time, endeavors to carry out biosynthesis of AgNPs coupled with fermentation using Medusomyces gisevii and Origanum vulgare L. (O. vulgare) plant species. Fermentation (F) via Medusomyces gisevii is responsible for chemical, physical, biological, and electrochemical processes. During in vitro study of antioxidant activity, fermented O. vulgare herb extract showed strong reductive activity as evaluated by the cupric reducing antioxidant capacity (CUPRAC), ferric reducing antioxidant power (FRAP), and 2,2′-azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) (ABTS•+) assay, with a value of 1.45 ± 0.048 mmol TE/g, 0.95 ± 0.04 mmol TE/g, and 0.59 ± 0.023 mmol TE/g, respectively. The highest antimicrobial activity was shown by Staphylococcus aureus in the inhibition zone, with values of 1.40 ± 0.12 mm of OrV and of 10.30 ± 0.04 mm and 11.54 ± 0.10 mm for OrV-AgNPs and OrV-F-AgNPs, respectively. Analysis of phenolic compounds revealed that the highest total amount of the apigenin, 87.78 µg/g, was detected in OrV-F-AgNPs and the lowest amount, 16.56 µg/g, in OrV-AgNPs. Moreover, in OrV-F-AgNPs, the collective amount of proanthocyanidins, hydroxycinnamic, and flavonoids was prominently high in all cases, i.e., 145.00 ± 0.02 mg EE/g DW, 2.86 ± 0.01 mg CAE/g DW, and 0.55 ± 0.01 mg RE/g DW, respectively, as compared to the original extract (102.1 ± 0.03 mg EE/g DW, 2.78 ± 0.02 mg CAE/g DW, and 0.47 ± 0.01 mg RE/g DW, respectively). During the characterization of biosynthesized nanoparticles by scanning electron microscopy (SEM), AgNPs demonstrated a uniform spherical shape with even distribution. The sample’s elemental composition was confirmed with a signal of 3.2 keV using energy-dispersive X-ray spectroscopy (EDS) analysis. Transmission electron microscopy (TEM) analysis showed silver nanoparticles that were round and spherical in shape in both stacked and congested form, with a size range of less than 30 nm. Thus, this green and sustainable synthesis of AgNPs, a blend of Medusomyces gisevii and O. vulgare herbal extract, has adequate potential for increased antimicrobial and antioxidant activity. Full article

This study examines the influence of dynamic and verbal elements in logo design on consumer behaviour in the luxury retail sector using advanced neuroscience technology (Predict v.1.0) and traditional cognitive survey methods. AI-powered eye tracking (n = 255,000), EEG technology (n = 45,000), implicit testing (n = 9000), and memory testing (n = 7000) were used to predict human behaviour. Qualitative cognitive surveys (n = 297), saliency map analysis, and emotional response evaluation were employed to analyse three distinct logo designs. The results indicate that logos with prominent dynamic elements, particularly visually distinct icons, demonstrate superior performance in capturing and maintaining viewer attention compared with static designs. A strong correlation was found between cognitive demand and engagement, suggesting that dynamic elements enhance emotional connections and brand recall. However, the effectiveness of dynamic features varied, with more pronounced elements yielding better results for industry associations and premium market alignment. This study, combining advanced neuroscience technology with traditional cognitive survey methods, makes significant contributions to the field and opens up new avenues for research and application. The findings provide valuable insights for luxury brand managers in optimising logo designs to enhance emotional connection and brand perception and improve academia by providing powerful tools for understanding and predicting human responses to visual stimuli. Full article

Objective: Clinically, patients in a coma after cardiac arrest are given the prognosis of “neurological recovery” to minimize discrepancies in opinions and reduce judgment errors. This study aimed to analyze the background patterns of electroencephalogram (EEG) signals from such patients to identify the key indicators for assessing the prognosis after coma. Approach: Standard machine learning models were applied sequentially as feature selectors and filters. CatBoost demonstrated superior performance as a classification method compared to other approaches. In addition, Shapley additive explanation (SHAP) values were utilized to rank and analyze the importance of the features. Results: Our results indicated that the three different EEG features helped achieve a fivefold cross-validation receiver-operating characteristic (ROC) of 0.87. Our evaluation revealed that functional connectivity features contribute the most to classification at 70%. Among these, low-frequency long-distance functional connectivity (45%) was associated with a poor prognosis, whereas high-frequency short-distance functional connectivity (25%) was linked with a good prognosis. Burst suppression ratio is 20%, concentrated in the left frontal–temporal and right occipital–temporal regions at high thresholds (10/15 mV), demonstrating its strong discriminative power. Significance: Our research identifies key electroencephalographic (EEG) biomarkers, including low-frequency connectivity and burst suppression thresholds, to improve early and objective prognosis assessments. By integrating machine learning (ML) algorithms, such as Gradient Boosting Models and Support Vector Machines, with SHAP-based feature visualization, robust screening methods were applied to ensure the reliability of predictions. These findings provide a clinically actionable framework for advancing neurological prognosis and optimizing patient care. Full article

With the rapid development of wearable technology, multifunctional sensors have demonstrated immense application potential. However, the limitations of traditional rigid materials restrict the flexibility and widespread adoption of such sensors. Hydrogels, as flexible materials, provide an effective solution to this challenge due to their excellent stretchability, biocompatibility, and adaptability. This study developed a multifunctional flexible sensor based on a composite hydrogel of polyvinyl alcohol (PVA) and sodium alginate (SA), using poly(3,4-ethylenedioxythiophene)/polystyrene sulfonate (PEDOT:PSS) as the conductive material to achieve multifunctional detection of strain, temperature, and physiological signals. The sensor features a simple fabrication process, low cost, and low impedance. Experimental results show that the prepared hydrogel exhibits outstanding mechanical properties and conductivity, with a strength of 118.8 kPa, an elongation of 334%, and a conductivity of 256 mS/m. In strain sensing, the sensor demonstrates a rapid response to minor strains (4%), high sensitivity (gauge factors of 0.39 for 0–120% and 0.73 for 120–200% strain ranges), short response time (2.2 s), low hysteresis, and excellent cyclic stability (over 500 cycles). For temperature sensing, the sensor achieves high sensitivities of −27.43 Ω/K (resistance mode) and 0.729 mV/K (voltage mode), along with stable performance across varying temperature ranges. Furthermore, the sensor has been successfully applied to monitor human motion (e.g., finger bending, wrist movement) and physiological signals such as electrocardiogram (ECG), electromyogram (EMG), and electroencephalogram (EEG), highlighting its significant potential in wearable health monitoring. By employing a simple and efficient fabrication method, this study presents a high-performance multifunctional flexible sensor, offering novel insights and technical support for the advancement of wearable devices. Full article

Background/Objectives: Neonatal hypoxic-ischemic encephalopathy (HIE) due to perinatal complications remains an important pathology with a significant burden for neonates, families, and the healthcare system. Resuscitation and simulation team training are key elements in increasing patient safety. In this retrospective cohort study, we evaluated whether regular constant training of all personnel working in delivery rooms in South Tyrol improved the outcome of neonates with HIE. Methods: We retrospectively analyzed three groups of neonates with moderate to severe HIE who required therapeutic hypothermia. The first group included infants born before the systematic introduction of training and was compared to the second group, which included infants born after three years of regular training. A third group, which included infants born after the SARS-CoV-2 pandemic, was compared with the previous two to evaluate retention of skills and the long-term effect of our training program. Results: Over the three study periods, mortality decreased from 41.2% to 0% and 14.3%, respectively. There was also a significant reduction of patients with subclincal seizures detected only through EEG, from 47.1% in the first period to 43.7% and 14.3% in the second and third study periods, respectively. Clinical manifestations of seizures decreased significantly from 47.1% to 37.5% and 10.7%, respectively, as well as severe brain lesions in ultrasound (US) and MRI. Conclusions: In this study, constant and regular simulation training for all birth attendants significantly decreases mortality and improves the outcome in neonates with moderate to severe HIE. This positive effect seems to last even after a one-year period during which training sessions could not be performed due to the COVID-19 pandemic. Full article

Background: Emotions significantly influence decision-making, social interactions, and medical outcomes. Leveraging emotion recognition through Electroencephalography (EEG) signals offers potential advancements in personalized medicine, adaptive technologies, and mental health diagnostics. This study aimed to evaluate the performance of three neural network architectures—ShallowFBCSPNet, Deep4Net, and EEGNetv4—for emotion classification using the SEED-V dataset. Methods: The SEED-V dataset comprises EEG recordings from 16 individuals exposed to 15 emotion-eliciting video clips per session, targeting happiness, sadness, disgust, neutrality, and fear. EEG data were preprocessed with a bandpass filter, segmented by emotional episodes, and split into training (80%) and testing (20%) sets. Three neural networks were trained and evaluated to classify emotions from the EEG signals. Results: ShallowFBCSPNet achieved the highest accuracy at 39.13%, followed by Deep4Net (38.26%) and EEGNetv4 (25.22%). However, significant misclassification issues were observed, such as EEGNetv4 predicting all instances as “Disgust” or “Neutral” depending on the configuration. Compared to state-of-the-art methods, such as ResNet18 combined with differential entropy, which achieved 95.61% accuracy on the same dataset, the tested models demonstrated substantial limitations. Conclusions: Our results highlight the challenges of generalizing across emotional states using raw EEG signals, emphasizing the need for advanced preprocessing and feature-extraction techniques. Despite these limitations, this study provides valuable insights into the potential and constraints of neural networks for EEG-based emotion recognition, paving the way for future advancements in the field. Full article

Self-paced exercise protocols have gained attention for their potential to optimize performance and manage fatigue by allowing individuals to regulate their efforts based on perceived exertion. This pilot study aimed to investigate the neural and physiological responses during a self-paced $\dot{\mathrm{V}}$O₂max (SPV) and incremental exercise tests (IET). Six trained male cyclists (mean age 39.2 ± 13.3 years; $\dot{\mathrm{V}}$O₂max 54.3 ± 8.2 mL·kg⁻¹·min⁻¹) performed both tests while recording their brain activity using electroencephalography (EEG). The IET protocol involved increasing the power every 3 min relative to body weight, while the SPV allowed participants to self-regulate the intensity using ratings of perceived exertion (RPE). Gas exchange, EEG, heart rate (HR), stroke volume (SV), and power output were continuously monitored. Statistical analyses included a two-way repeated measures ANOVA and Wilcoxon signed-rank tests to assess differences in alpha and beta power spectral densities (PSDs) and the EEG/$\dot{\mathrm{V}}$O₂ ratio. Our results showed that during the SPV test, the beta PSD initially increased but stabilized at around 80% of the test duration, suggesting effective management of effort without further neural strain. In contrast, the IET showed a continuous increase in beta activity, indicating greater neural demand and potentially leading to an earlier onset of fatigue. Additionally, participants maintained similar cardiorespiratory parameters ($\dot{\mathrm{V}}$O₂, HR, SV, respiratory frequency, etc.) across both protocols, reinforcing the reliability of the RPE scale in guiding exercise intensity. These findings suggest that SPV better optimizes neural efficiency and delays fatigue compared to fixed protocols and that individuals can accurately control exercise intensity based on perceived exertion. Despite the small sample size, the results provide valuable insights into the potential benefits of self-paced exercise for improving adherence to exercise programs and optimizing performance across different populations. Full article

Brain–computer interface (BCI) offers a novel means of communication and control for individuals with disabilities and can also enhance the interactions between humans and machines for the broader population. This paper explores the brain neural signatures of unmanned aerial vehicle (UAV) operators in emergencies and develops an operator’s electroencephalography (EEG) signals-based detection method for UAV emergencies. We found regularity characteristics similar to classic event-related potential (ERP) components like visual mismatch negativity (vMMN) and contingent negative variation (CNV). Source analysis revealed a sequential activation of the occipital, temporal, and frontal lobes following the onset of emergencies, corresponding to the processing of attention, emotion, and motor intention triggered by visual stimuli. Furthermore, an online detection system was implemented and tested. Experimental results showed that the system achieved an average accuracy of over 88% in detecting emergencies with a detection latency of 431.95 ms from the emergency onset. This work lays a foundation for understanding the brain activities of operators in emergencies and developing an EEG-based detection method for emergencies to assist UAV operations. Full article

Transformer models have revolutionized fields like Natural Language Processing (NLP) by enabling machines to accurately understand and generate human language. However, these models’ inherent complexity and limited interpretability pose barriers to their broader adoption. To address these challenges, we propose a simplified query-only attention mechanism specifically for encoder-based transformer models to reduce complexity and improve interpretability. Unlike conventional attention mechanisms, which rely on query (Q), key (K), and value (V) vectors, our method uses only the Q vector for attention calculation. This approach reduces computational complexity while maintaining the model’s ability to capture essential relationships, enhancing interpretability. We evaluated the proposed query-only attention on an EEG conformer model, a state-of-the-art architecture for EEG signal classification. We demonstrated that it performs comparably to the original QKV attention mechanism, while simplifying the model’s architecture. Our findings suggest that query-only attention offers a promising direction for the development of more efficient and interpretable transformer-based models, with potential applications across various domains beyond NLP. Full article

The precision of electroencephalograms (EEGs) significantly impacts the performance of brain–computer interfaces (BCI). Currently, the majority of research into BCI technology gives priority to lightweight design and a reduced electrode count to make it more suitable for application in wearable environments. This paper introduces a deep learning-based time series bidirectional (BiLSTM) network that is designed to capture the inherent characteristics of EEG channels obtained from neighboring electrodes. It aims to predict the EEG data time series and facilitate the conversion process from low-density EEG signals to high-density EEG signals. BiLSTM pays more attention to the dependencies in time series data rather than mathematical maps, and the root mean square error can be effectively restricted to below 0.4μV, which is less than half the error in traditional methods. After expanding the BCI Competition III 3a dataset from 18 channels to 60 channels, we conducted classification experiments on four types of motor imagery tasks. Compared to the original low-density EEG signals (18 channels), the classification accuracy was around 82%, an increase of about 20%. When juxtaposed with real high-density signals, the increment in the error rate remained below 5%. The expansion of the EEG channels showed a substantial and notable improvement compared with the original low-density signals. Full article