Search Results (630)

Accurate tree health monitoring in orchards is essential for optimal orchard production. This study investigates the efficacy of a deep learning-based object detection single-step method for detecting tree health on multispectral UAV imagery. A modified Mask R-CNN framework is employed with four different backbones—ResNet-50, ResNet-101, ResNeXt-101, and Swin Transformer—on three image combinations: (1) RGB images, (2) 5-band multispectral images comprising RGB, Red-Edge, and Near-Infrared (NIR) bands, and (3) three principal components (3PCs) computed from the reflectance of the five spectral bands and twelve associated vegetation index images. The Mask R-CNN, having a ResNeXt-101 backbone, and applied to the 5-band multispectral images, consistently outperforms other configurations, with an F1-score of 85.68% and a mean Intersection over Union (mIoU) of 92.85%. To address the class imbalance, class weighting and focal loss were integrated into the model, yielding improvements in the detection of the minority class, i.e., the unhealthy trees. The tested method has the advantage of allowing the detection of unhealthy trees over UAV images using a single-step approach. Full article

Unimodal brain–computer interfaces (BCIs) often suffer from inherent limitations due to the characteristic of using single modalities. While hybrid BCIs combining electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) offer complementary advantages, effectively integrating their spatiotemporal features remains a challenge due to inherent signal asynchrony. This study aims to develop a novel deep fusion network to achieve synergistic integration of EEG and fNIRS signals for improved classification performance across different tasks. We propose a novel Temporal-Spatial Fusion Network (TSFNet), which consists of two key sublayers: the EEG-fNIRS-guided Fusion (EFGF) layer and the Cross-Attention-based Feature Enhancement (CAFÉ) layer. The EFGF layer extracts temporal features from EEG and spatial features from fNIRS to generate a hybrid attention map, which is utilized to achieve more effective and complementary integration of spatiotemporal information. The CAFÉ layer enables bidirectional interaction between fNIRS and fusion features via a cross-attention mechanism, which enhances the fusion features and selectively filters informative fNIRS representations. Through the two sublayers, TSFNet achieves deep fusion of multimodal features. Finally, TSFNet is evaluated on motor imagery (MI), mental arithmetic (MA), and word generation (WG) classification tasks. Experimental results demonstrate that TSFNet achieves superior classification performance, with average accuracies of 70.18% for MI, 86.26% for MA, and 81.13% for WG, outperforming existing state-of-the-art multimodal algorithms. These findings suggest that TSFNet provides an effective solution for spatiotemporal feature fusion in hybrid BCIs, with potential applications in real-world BCI systems. Full article

Understanding and interpreting human emotions through neurophysiological signals has become a central goal in affective computing. This paper presents a focused survey of recent advances in emotion recognition using tensor factorization techniques specifically applied to functional Near-Infrared Spectroscopy (fNIRS) data. We examine how tensor-based frameworks have been leveraged to capture the temporal, spatial, and spectral characteristics of fNIRS brain signals, enabling effective dimensionality reduction and latent pattern extraction. Focusing on third-order tensor constructions (trials × channels × time), we compare the use of Canonical Polyadic (CP) and Tucker decompositions in isolating components representative of emotional states. The review further evaluates the performance of extracted features when classified by conventional machine learning models such as Random Forests and Support Vector Machines. Emphasis is placed on comparative accuracy, interpretability, and the advantages of tensor methods over traditional approaches for distinguishing arousal and valence levels. We conclude by discussing the relevance of these methods for the development of real-time, explainable, emotion-aware systems in wearable neurotechnology, with a particular focus on medical applications such as mental health monitoring, early diagnosis of affective disorders, and personalized neurorehabilitation. Full article

Background/Objectives: There is scarce evidence on the neural underpinnings of balance in people with chronic acquired brain injury (ABI). Thus, the objective was to measure this in adults with ABI during four balance tasks and to examine the relationship between neural activity and balance performance. Methods: Twenty-seven adults with chronic ABI (Age (M ± SD): 51.30 ± 18.67 years, 18 females) were included in this study. Functional near-infrared spectroscopy (fNIRS) was used to measure task-dependent neural activity, which was quantified using oxygenated hemoglobin (HbO) beta values. A force plate was used to measure balance performance, quantified as the amount of sway. One-sample t-tests were used to test for significant task-dependent neural activity during each balance task (HbO > 0) at each fNIRS channel. Pearson’s correlations were used to test for relationships between fNIRS channels with significant task-dependent activity and balance performance. Results: Significant task-dependent neural activity was observed in an fNIRS channel situated over the right superior parietal lobe, p = 0.039, along with 4 channels over the right inferior parietal lobe (IPL), p range = 0.013–0.043 and 3 channels over left IPL, p range = 0.019–0.030. There were moderate negative relationships between IPL activity and balance, r range = −0.441–0.419, p range = 0.031–0.046. Conclusions: We observed significant task-dependent neural activity in superior and inferior parietal lobes. Additionally, greater neural recruitment of the inferior parietal lobes was associated with less sway during balance performance, which provides evidence of the neural underpinnings of balance in ABI. Full article

Spatial representation is a core element of spatial cognition in orienteering, but the visual-spatial neural modulation mechanisms underlying spatial representations with differently oriented maps have not yet been systematically elucidated. This study recruited 67 orienteering athletes as participants and employed a single-factor (map orientation: normal vs. rotated) between-subjects experimental design. Eye-tracking and functional near-infrared spectroscopy (fNIRS) techniques were used simultaneously to collect behavioral, eye movement, and brain activity data, investigating the effects of map orientation on visual attention and brain activity characteristics during terrain symbol representation processing in orienteering athletes. The results revealed that compared to the normal orientation, the rotated orientation led to significantly decreased task accuracy, significantly prolonged reaction times, and significantly increased saccade amplitude and pupil diameter. Brain activation analysis showed that the rotated orientation elicited significantly higher activation levels in the right dorsolateral prefrontal cortex (R-DLPFC), bilateral parietal lobe cortex (L-PL, R-PL), right temporal lobe (R-TL), and visual cortex (VC) compared to the normal orientation, along with enhanced functional connectivity. Correlation analysis revealed that under normal map orientation, accuracy was positively correlated with both saccade amplitude and pupil diameter; accuracy was positively correlated with activation in the R-DLPFC; saccade amplitude was positively correlated with activation in the R-DLPFC and R-PL; and pupil diameter was positively correlated with activation in the R-DLPFC. Under rotated map orientation, accuracy was positively correlated with saccade amplitude and pupil diameter, and pupil diameter was positively correlated with activation in both the L-PL and R-PL. The results indicate that map orientation significantly influences the visual search patterns and neural activity characteristics of orienteering athletes, impacting task performance through the coupling mode of visual-neural activity. Full article

Background/Objectives: The YSK olfactory function (YOF) test is a culturally adapted psychophysical tool that assesses threshold, discrimination, and identification. This study evaluated whether functional near-infrared spectroscopy (fNIRS) synchronized with routine YOF testing, combined with machine learning, can predict YOF subdomain performance in healthy adults, providing an objective neural correlate to complement behavioral testing. Methods: In this prospective diagnostic-accuracy (feasibility/validation) study in healthy adults with algorithm development, 100 healthy adults completed the YOF test while undergoing prefrontal/orbitofrontal fNIRS during odor blocks. Feature sets from ΔHbO/ΔHbR included time-domain descriptors, complexity (Lempel–Ziv), and information-theoretic measures (mutual information); the identification task used a hybrid attention–CNN. Separate models were developed for threshold (binary classification), discrimination (binary classification), and identification (binary classification). Performance was summarized with accuracy, area under the curve (AUC), F1-score, and (where applicable) sensitivity/specificity, using participant-level cross-validation. Results: The threshold classifier achieved accuracy 0.86, AUC 0.86, and F1 0.86, indicating strong discrimination of correct vs. incorrect threshold responses. The discrimination model yielded accuracy 0.75, AUC 0.76, and F1 0.75. The identification model (attention–convolutional neural network [CNN]) achieved accuracy 0.88, sensitivity 0.86, specificity 0.91, and F1 0.88. Feature-attribution (e.g., SHapley Additive exPlanations [SHAP]) provided interpretable links between fNIRS features and task performance for threshold and discrimination. Conclusions: Olfactory-evoked fNIRS signals can accurately predict YOF subdomain performance in healthy adults, supporting the feasibility of non-invasive, portable, near–real-time olfactory monitoring. These findings are preliminary and not generalizable to clinical populations; external validation in diverse cohorts is warranted. The approach clarifies the scientific essence of the method by (i) aligning psychophysical outcomes with objective hemodynamic signatures and (ii) introducing a feature-rich modeling pipeline (ΔHbO/ΔHbR + Lempel–Ziv complexity/mutual information; attention–CNN) that advances prior work. Full article

Background: Hemiplegic cerebral palsy (HCP) is a motor dysfunction disorder resulting from perinatal developmental brain injury, predominantly impairing upper limb function in children. Nonetheless, there has been insufficient research on the brain activation patterns and inter-brain coordination mechanisms of HCP children when performing motor control tasks, especially in contrast to children with typical development(CD). Objective: This cross-sectional study employed functional near-infrared spectroscopy (fNIRS) to systematically compare the cerebral blood flow dynamics and brain network characteristics of HCP children and CD children while performing upper-limb mirror training tasks. Methods: The study ultimately included 14 HCP children and 28 CD children. fNIRS technology was utilized to record changes in oxygenated hemoglobin (HbO) signals in the bilateral prefrontal cortex (LPFC/RPFC) and motor cortex (LMC/RMC) of the subjects while they performed mirror training tasks. Generalized linear model (GLM) analysis was used to compare differences in activation intensity between HCP children and CD children in the prefrontal cortex and motor cortex. Finally, conditional Granger causality (GC) analysis was applied to construct a directed brain network model, enabling directional analysis of causal interactions between different brain regions. Results: Brain activation: HCP children showed weaker LPFC activation than CD children in the NMR task (t = −2.032, p = 0.049); enhanced LMC activation in the NML task (t = 2.202, p = 0.033); and reduced RMC activation in the MR task (t = −2.234, p = 0.031). Intragroup comparisons revealed significant differences in LMC activation between the NMR and NML tasks (M = −1.128 ± 2.764, t = −1.527, p = 0.025) and increased separation in RMC activation between the MR and ML tasks (M = −1.674 ± 2.584, t = −2.425, p = 0.031). Cortical effective connectivity: HCP group RPFC → RMC connectivity was weaker than that in CD children in the NMR/NML tasks (NMR: t = −2.491, p = 0.018; NML: t = −2.386, p = 0.023); RMC → LMC connectivity was weakened in the NMR task (t = −2.395, p = 0.022). Conclusions: This study reveals that children with HCP exhibit distinct abnormal characteristics in both cortical activation patterns and effective brain network connectivity during upper limb mirror training tasks, compared to children with CD. These characteristic alterations may reflect the neural mechanisms underlying motor control deficits in HCP children, involving deficits in prefrontal regulatory function and compensatory reorganization of the motor cortex. The identified fNIRS indicators provide new insights into understanding brain dysfunction in HCP and may offer objective evidence for research into personalized, precision-based neurorehabilitation intervention strategies. Full article

The present study aimed to investigate sex differences in the hemodynamic response of the cerebral cortex during interactive and passive tasks using functional near-infrared spectroscopy fNIRS. Ninety-seven healthy adults (63 women, 34 men) participated in the study. Participants performed two tasks: an interactive motor game and a passive hand movement, and activation was measured in five cortical regions. Statistically significant differences in the amplitude of the hemodynamic response of oxygenated haemoglobin ΔHbO levels were observed, particularly in the parietal cortex, where men showed higher activation levels. The differences remained significant in the parietal, prefrontal, left hemisphere, and visual cortex. The differences were more pronounced in the passive task, which may indicate different processing strategies in women and men. Although no significant group differences were found in the latency time of maximum reaction t_max, men tended to have longer times in the visual cortex. Additionally, a moderate positive correlation between ΔHbO and t_max was observed among men, particularly in the prefrontal cortex. These results highlight the importance of considering biological sex in neuroimaging studies and suggest directions for further analysis. Full article

Brain–Computer Interfaces (BCIs) offer a non-invasive pathway for restoring motor function, particularly for individuals with limb loss. This review explored the effectiveness of Electroencephalography (EEG) and function Near-Infrared Spectroscopy (fNIRS) in decoding Motor Imagery (MI) movements for both offline and online BCI systems. EEG has been the dominant non-invasive neuroimaging modality due to its high temporal resolution and accessibility; however, it is limited by high susceptibility to electrical noise and motion artifacts, particularly in real-world settings. fNIRS offers improved robustness to electrical and motion noise, making it increasingly viable in prosthetic control tasks; however, it has an inherent physiological delay. The review categorizes experimental approaches based on modality, paradigm, and study type, highlighting the methods used for signal acquisition, feature extraction, and classification. Results show that while offline studies achieve higher classification accuracy due to fewer time constraints and richer data processing, recent advancements in machine learning—particularly deep learning—have improved the feasibility of online MI decoding. Hybrid EEG–fNIRS systems further enhance performance by combining the temporal precision of EEG with the spatial specificity of fNIRS. Overall, the review finds that predicting online imagined movement is feasible, though still less reliable than motor execution, and continued improvements in neuroimaging integration and classification methods are essential for real-world BCI applications. Broader dissemination of recent advancements in MI-based BCI research is expected to stimulate further interdisciplinary collaboration among roboticists, neuroscientists, and clinicians, accelerating progress toward practical and transformative neuroprosthetic technologies. Full article

Dendrobium officinale is a valuable Chinese medicinal herb, but distinguishing it from other Dendrobium species after processing is challenging, leading to low classification accuracy and time-consuming analysis. This study proposes a rapid classification model based on near-infrared hyperspectral imaging (NIR-HSI), incorporating data preprocessing and feature wavelength selection. Five Dendrobium species—D. officinale, D. aphyllum, D. chrysanthum, D. fimbriatum, and D. thyrsiflorum—were used. Spectral preprocessing techniques like normalization and smoothing were applied, and Support Vector Machine (SVM) models were constructed. Normalization improved both accuracy and stability, with the full-spectrum Normalize-SVM model achieving 97% accuracy for calibration and 88% for prediction. D. chrysotoxum performed best, with all metrics reaching 100%, while D. aphyllum had poor classification (40% recall and 51.74% F1 score). To improve efficiency and performance, feature wavelength selection was performed using Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA). The CARS-Normalize-SVM model yielded the best results: 98% accuracy for calibration and 96% for prediction, improving by 1% and 8%, respectively. D. aphyllum’s classification also improved significantly, with a 100% recall rate and 95.24% F1 score. These findings highlight hyperspectral imaging’s potential for rapid Dendrobium species identification, supporting future quality control and market supervision. Full article

At present, it is a real challenge to measure brain signals outside of the lab with portable systems that are robust, comfortable and easy to use. We propose in this article a bimodal electroencephalography–functional near-infrared spectroscopy (EEG-fNIRS) sensor whose spatial geometry allows the robust estimation of colocated electrical and hemodynamic brain activity. The geometry allows for the correction of extra-cerebral activity (short-channel distance) as well as the computation of the spatial gradient of absorbance required in the spatially resolved spectroscopy (SRS) method. The complete system is described, detailing the technical solutions implemented to provide signals at 250 Hz for both synchronized modalities and without crosstalk. The system performances are validated during an N-Back mental workload protocol. Full article

It was demonstrated that various defects can be induced in halide crystals by irradiation with swift heavy ions. Here, we irradiated barium fluoride (BaF₂) single crystals with 220 MeV xenon ions at room temperature and performed stepwise thermal annealing up to the temperature of 825 K to study the kinetics of ion-induced defects at different temperatures. Optical spectroscopy was utilized for the measurement of the wide range of absorption spectra from NIR to VUV. A sharp decrease in the F₂ absorption peak was observed for the samples annealed in the temperature range of 400–450 K. This result can be explained by their recombination with anion interstitials during thermal decay of the complex hole centers. The mobile interstitials, those did not recombine with the F₂ centers, increase the absorption peaks in the 9–10 eV region, which can be associated with interstitial aggregates. Full article

Global food security is increasingly challenged by climate change and the availability of arable land. This situation calls for improved crop monitoring and management strategies. Rice is a staple food for nearly half of the world’s population and a significant source of calories. Accurately identifying rice varieties is crucial for maintaining varietal purity, planning agricultural activities, and enhancing genetic improvement strategies. This study evaluates the effectiveness of machine learning algorithms to identify the most effective approach to predicting rice varieties, using multitemporal Sentinel-2 images in the Marismas del Guadalquivir of Sevilla, Spain. Spectral reflectance data were collected from ten Sentinel-2 bands, which include visible, red-edge, near-infrared, and shortwave infrared regions, at two key phenological stages: tillering and reproduction. The models were trained on pixel-level data from the growing seasons of 2021 and 2024, and they were evaluated using a test set from 2022. Four classifiers were compared: random forest, XGBoost, K-nearest neighbors, and logistic regression. Performance was assessed based on accuracy, precision, recall, specificity and F1 score. Non-linear models outperformed linear ones. The highest performance was achieved with the Random Forest classifier during the reproduction phase, reaching an exceptional accuracy of 0.94 using all bands or only the most informative subset (red edge, NIR, and SWIR). This classifier also maintained excellent accuracy (0.93 and 0.92) during the initial tillering phase. This fact demonstrates that it is possible to perform reliable varietal mapping in the early stages of the growing season. Full article

Functional near-infrared spectroscopy (fNIRS) offers a safe and portable signal source for brain–computer interface (BCI) applications, particularly in motor imagery (MI) decoding. However, its low sampling rate and hemodynamic delay pose challenges for temporal modeling and dynamic brain network analysis. To address these limitations in temporal dynamics, static graph modeling, and feature fusion interpretability, we propose TopoTempNet, an innovative topology-enhanced temporal network for biomedical signal decoding. TopoTempNet integrates multi-level graph features with temporal modeling through three key innovations: (1) multi-level topological feature construction using local and global functional connectivity metrics (e.g., connection strength, density, global efficiency); (2) a graph-modulated attention mechanism combining Transformer and Bi-LSTM to dynamically model key connections; and (3) a multimodal fusion strategy uniting raw signals, graph structures, and temporal representations into a high-dimensional discriminative space. Evaluated on three public fNIRS datasets (MA, WG, UFFT), TopoTempNet achieves superior accuracy (up to 90.04% ± 3.53%) and Kappa scores compared to state-of-the-art models. The ROC curves and t-SNE visualizations confirm its excellent feature discrimination and structural clarity. Furthermore, the statistical analysis of graph features reveals the model’s ability to capture task-specific functional connectivity patterns, enhancing the interpretability of decoding outcomes. TopoTempNet provides a novel pathway for building interpretable and high-performance BCI systems based on fNIRS. Full article

(1) Background: Virtual Reality (VR) films challenge traditional visual cognition by offering novel perceptual experiences. This study investigates the applicability of Gestalt grouping principles in dynamic VR scenes, the influence of VR environments on grouping efficiency, and the relationship between viewer experience and grouping effects. (2) Methods: Eye-tracking experiments were conducted with 42 participants using the HTC Vive Pro Eye and Tobii Pro Lab. Participants watched a non-narrative VR film with fixed camera positions to eliminate narrative and auditory confounds. Eye-tracking metrics were analyzed using SPSS version 29.0.1, and data were visualized through heat maps and gaze trajectory plots. (3) Results: Viewers tended to focus on spatial nodes and continuous structures. Initial fixations were anchored near the body but shifted rapidly thereafter. Heat maps revealed a consistent concentration of fixations on the dock area. (4) Conclusions: VR reshapes visual organization, where proximity, continuity, and closure outweigh traditional saliency. Dynamic elements draw attention only when linked to user goals. Designers should prioritize spatial logic, using functional nodes as cognitive anchors and continuous paths as embodied guides. Future work should test these mechanisms in narrative VR and explore neural correlates via fNIRS or EEG. Full article