Search Results (537)

In distance learning environments, learner engagement directly impacts attention, motivation, and academic performance. Signs of fatigue, negative affect, or critical remarks can warn of growing disengagement and potential dropout. However, most existing approaches rely on a single modality, visual or text-based, without providing a general view of learners’ cognitive and affective states. We propose a multimodal system that integrates three complementary analyzes: (1) a CNN-LSTM model augmented with warning signs such as PERCLOS and yawning frequency for fatigue detection, (2) facial emotion recognition by EmoNet and an LSTM to handle temporal dynamics, and (3) sentiment analysis of feedback by a fine-tuned BERT model. It was evaluated on three public benchmarks: DAiSEE for fatigue, AffectNet for emotion, and MOOC Review (Coursera) for sentiment analysis. The results show a precision of 88.5% for fatigue detection, 70% for emotion detection, and 91.5% for sentiment analysis. Aggregating these cues enables an accurate identification of disengagement periods and triggers individualized pedagogical interventions. These results, although based on independently sourced datasets, demonstrate the feasibility of an integrated approach to detecting disengagement and open the door to emotionally intelligent learning systems with potential for future work in real-time content personalization and adaptive learning assistance. Full article

Background: Depression that is resistant to two or more adequate treatment trials—treatment-resistant depression (TRD)—is a prevalent clinical challenge. Although psychotherapies have been recommended by clinical guidelines as an alternative or adjunctive treatment strategy, the effectiveness of psychotherapy in individuals with TRD has not yet been evaluated through meta-analytic methods, primarily due to a limited number of trials. This highlights the necessity of personalized research targeting this specific population. This systematic review and meta-analysis aimed to summarize the evidence on psychotherapy in treating TRD. Methods: A systematic search was conducted following the Guidelines from Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Articles were included if they quantitatively examined the efficacy of psychotherapy on depression symptoms in individuals diagnosed with depression who had not responded to at least two prior treatments (i.e., pharmacotherapy and/or psychotherapy). Results: A total of 12 studies were included. The quality of evidence was evaluated as being globally moderate. When pooling all psychotherapies, a small-to-moderate, but significant, effect on depressive symptoms was observed compared to the control group (SMD = −0.49, CI = −0.63; −0.34). The observed effect remained unchanged after removing the outlier (SMD = −0.47, CI = −0.62; −0.32). When examining depressive symptoms by type of psychotherapy, Mindfulness-Based Cognitive Therapy (SMD = −0.51, CI = −0.76; −0.25), Cognitive Behavioral Therapy (SMD = −0.53, CI = −0.92; −0.14), and Cognitive Therapy (SMD = −0.51, CI = −1.01; −0.01) showed a moderately significant effect on depressive symptoms compared to the control group. Conclusions: Although this potentially represents the first meta-analysis in this area, the number of studies specifically addressing this complex population remains limited, and the existing literature is still in its early stages. Research focusing on TRD is notably sparse compared to the broader body of work on depression without treatment resistance. Consequently, it was not possible to conduct meta-analyses by type of psychotherapy across all treatment modalities and by type of control group. Due to several study limitations, there is currently limited evidence available about the effectiveness of psychotherapy for TRD, and further trials are needed. Beyond the treatments usually offered for depression, it is possible that TRD requires a personalized medicine approach. Full article

Background and objectives: Trismus is a frequent and debilitating complication in people with head and neck cancer (HNC) which leads to significant functional limitations and reduced quality of life. Rehabilitation interventions are commonly recommended to manage or prevent trismus. However, in many randomized controlled trials (RCTs), the theoretical justification for these interventions is poorly articulated, and the underlying biological or physiological mechanisms are not described in detail, limiting our understanding of why certain treatments may (or may not) work. This review aimed to identify and analyze how RCTs report the rationale for rehabilitation interventions and the explanations used to manage this population. Materials and Methods: A scoping review was conducted in accordance with the PRISMA-ScR guidelines. Five databases (PubMed, PEDro, Web of Science, Scopus, and EMBASE) were searched up to May 2025 for RCTs evaluating rehabilitation interventions for the management or prevention of treatment-induced trismus in patients with HNC. Data were extracted and synthesized narratively, focusing on the type of intervention, the rationale for its use, and the proposed mechanisms of action. Results: Of 2215 records identified, 24 RCTs met the inclusion criteria. Thirteen studies focused on preventive interventions—primarily exercise therapy—while the remainder addressed established trismus using exercise, manual therapy, electrotherapy, or combined treatment modalities. The rationales provided for intervention selection were heterogeneous and often lacked depth, with most studies justifying interventions based on their potential to improve mouth opening or reduce fibrosis but rarely grounding these claims in detailed pathophysiological models. Only half of the studies provided any mechanistic explanation for the intervention’s effects, and these were typically generic or speculative. Conclusions: RCTs investigating rehabilitation interventions for treatment-induced trismus in patients with HNC frequently lack comprehensive rationales and mechanistic explanations for their interventions. This gap limits the ability to refine and optimize treatment approaches, as the underlying processes driving clinical improvements remain poorly understood. Future research should be guided by theoretical models and include objective outcomes to better elucidate the mechanisms of action of interventions to inform clinical practice. Full article

Interpreting diagnostic imaging and identifying clinically relevant features remain challenging tasks, particularly for novice radiologists who often lack structured guidance and expert feedback. To bridge this gap, we propose an Eye-Gaze Guided Multimodal Fusion framework that leverages expert eye-tracking data to enhance learning and decision-making in medical image interpretation. By integrating chest X-ray (CXR) images with expert fixation maps, our approach captures radiologists’ visual attention patterns and highlights regions of interest (ROIs) critical for accurate diagnosis. The fusion model utilizes a shared backbone architecture to jointly process image and gaze modalities, thereby minimizing the impact of noise in fixation data. We validate the system’s interpretability using Gradient-weighted Class Activation Mapping (Grad-CAM) and assess both classification performance and explanation alignment with expert annotations. Comprehensive evaluations, including robustness under gaze noise and expert clinical review, demonstrate the framework’s effectiveness in improving model reliability and interpretability. This work offers a promising pathway toward intelligent, human-centered AI systems that support both diagnostic accuracy and medical training. Full article

Background: Cyclic vomiting syndrome (CVS) is a functional gastrointestinal disorder characterized by recurrent episodes of intense nausea and vomiting. Despite increasing awareness, a standardized treatment approach remains lacking in pediatric populations. Lifestyle factors and anxiety are common triggers, yet their systematic management has not been fully incorporated into therapeutic strategies. Objective: To evaluate the effectiveness of lifestyle modifications and selective serotonin reuptake inhibitors (SSRIs) in the management of pediatric CVS and to compare their outcomes with standard cyproheptadine prophylaxis. Methods: This retrospective study included 119 patients aged 1.2–17.5 years who were diagnosed with CVS according to Rome IV criteria between September 2021 and January 2025. Clinical, psychiatric, and lifestyle data were retrieved from the university’s digital medical records. Patients were grouped according to treatment modality: cyproheptadine, SSRI, or acute attack management alone. Treatment success at 12 weeks was defined as complete cessation of vomiting episodes or absence of hospitalization, prolonged attacks, and school/work absenteeism. Results: Anxiety symptoms were present in 78.2% of patients. SSRIs were prescribed to 34 patients with moderate to severe anxiety, all of whom achieved treatment success. Lifestyle adherence was observed in 73.9% and was found to be a predictor of treatment success. Cyproheptadine was administered to 66 patients but did not provide additional benefit over effective lifestyle modification. Six patients discontinued cyproheptadine due to drowsiness or weight gain. Conclusions: Lifestyle interventions significantly improve outcomes in pediatric CVS. SSRIs represent a safe and effective prophylactic option for patients with comorbid anxiety or poor adherence to behavioral recommendations. These findings support the integration of psychosocial and lifestyle-based strategies into standard CVS treatment protocols. Full article

Fish is important for human health due to its high nutritional value. However, it is prone to spoilage due to its structural characteristics. Traditional freshness assessment methods, such as visual inspection, are subjective and prone to inconsistency. This study proposes a novel, cost-effective hybrid methodology for automated three-level fish freshness classification (Day 1, Day 2, Day 3) by integrating single-wavelength laser reflectance data with deep learning-based image features. A comprehensive dataset was created by collecting visual and laser data from 130 mackerel specimens over three consecutive days under controlled conditions. Image features were extracted using four pre-trained CNN architectures and fused with laser features to form a unified representation. The combined features were classified using SVM, MLP, and RF algorithms. The experimental results demonstrated that the proposed multimodal approach significantly outperformed single-modality methods, achieving average classification accuracy of 88.44%. This work presents an original contribution by demonstrating, for the first time, the effectiveness of combining low-cost laser sensing and deep visual features for freshness prediction, with potential for real-time mobile deployment. Full article

Phage display has advanced the discovery of peptides that selectively bind to a wide variety of cell surface molecules, offering new modalities to modulate disease-related protein–protein interactions (PPIs). These cell-binding peptides occupy a unique pharmaceutical space between small molecules and large biologics, and their growing popularity has opened up new avenues for targeting cell surface proteins that were previously considered undruggable. This work provides an overview of methods for identifying cell-selective peptides using phage display combinatorial libraries, covering in vitro, ex vivo, and in vivo biopanning approaches. It addresses key considerations in library design, including the peptide conformation (linear vs. cyclic) and length, and highlights examples of clinically approved peptides developed through phage display. It also discusses the on-phage chemical cyclization of peptides to overcome the limitations of genetically encoded disulfide bridges and emphasizes advances in combining next-generation sequencing (NGS) with phage display to improve peptide selection and analysis workflows. Furthermore, due to the often suboptimal binding affinity of peptides identified in phage display selections, this article discusses affinity maturation techniques, including random mutagenesis and rational design through structure–activity relationship (SAR) studies to optimize initial peptide candidates. By integrating these developments, this review outlines practical strategies and future directions for harnessing phage display in targeting challenging cell surface proteins. Full article

Glaucoma is a leading cause of irreversible blindness worldwide, yet early detection can prevent vision loss. This paper proposes a novel deep learning approach that combines two ophthalmic imaging modalities, fundus photographs and optical coherence tomography scans, as paired images from the same eye of each patient for automated glaucoma detection. We develop separate convolutional neural network models for fundus and optical coherence tomography images and a fusion model that integrates features from both modalities for each eye. The models are trained and evaluated on a private clinical dataset (Bangladesh Eye Hospital and Institute Ltd.) consisting of 216 healthy eye images (108 fundus, 108 optical coherence tomography) from 108 patients and 200 glaucomatous eye images (100 fundus, 100 optical coherence tomography) from 100 patients. Our methodology includes image preprocessing pipelines for each modality, custom convolutional neural network/ResNet-based architectures for single-modality analysis, and a two-branch fusion network combining fundus and optical coherence tomography feature representations. We report the performance (accuracy, sensitivity, specificity, and area under curve) of the fundus-only, optical coherence tomography-only, and fusion models. In addition to a fixed test set evaluation, we perform five-fold cross-validation, confirming the robustness and consistency of the fusion model across multiple data partitions. On our fixed test set, the fundus-only model achieves 86% accuracy (AUC 0.89) and the optical coherence tomography-only model, 84% accuracy (AUC 0.87). Our fused model reaches 92% accuracy (AUC 0.95), an absolute improvement of 6 percentage points and 8 percentage points over the fundus and OCT baselines, respectively. McNemar’s test on pooled five-fold validation predictions (b = 3, c = 18) yields ${\chi }^2=10.7$ (p = 0.001), and on optical coherence tomography-only vs. fused (b_o = 5, c_o = 20) ${\chi }_o^2=9.0$ (p = 0.003), confirming that the fusion gains are significant. Five-fold cross-validation further confirms these improvements (mean AUC $0.952\pm 0.011$. We also compare our results with the existing literature and discuss the clinical significance, limitations, and future work. To the best of our knowledge, this is the first time a novel deep learning model has been used on a fusion of paired fundus and optical coherence tomography images of the same patient for the detection of glaucoma. Full article

In computer vision, the performance of detectors trained under optimal lighting conditions is significantly impaired when applied to infrared domains due to the scarcity of labeled infrared target domain data and the inherent degradation in infrared image quality. Progress in cross-domain pedestrian re-identification is hindered by the lack of labeled infrared image data. To address the degradation of pedestrian recognition in infrared environments, we propose a framework for zero-shot infrared domain adaptation. This integrated approach is designed to mitigate the challenges of pedestrian recognition in infrared domains while enabling zero-shot domain adaptation. Specifically, an advanced reflectance representation learning module and an exchange–re-decomposition–coherence process are employed to learn illumination invariance and to enhance the model’s effectiveness, respectively. Additionally, the CLIP (Contrastive Language–Image Pretraining) image encoder and DINO (Distillation with No Labels) are fused for feature extraction, improving model performance under infrared conditions and enhancing its generalization capability. To further improve model performance, we introduce the Non-Local Attention (NLA) module, the Instance-based Weighted Part Attention (IWPA) module, and the Multi-head Self-Attention module. The NLA module captures global feature dependencies, particularly long-range feature relationships, effectively mitigating issues such as blurred or missing image information in feature degradation scenarios. The IWPA module focuses on localized regions to enhance model accuracy in complex backgrounds and unevenly lit scenes. Meanwhile, the Multi-head Self-Attention module captures long-range dependencies between cross-modal features, further strengthening environmental understanding and scene modeling. The key innovation of this work lies in the skillful combination and application of existing technologies to new domains, overcoming the challenges posed by vision in infrared environments. Experimental results on the SYSU-MM01 dataset show that, under the single-shot setting, Rank-1 Accuracy (Rank-1) andmean Average Precision (mAP) values of 37.97% and 37.25%, respectively, were achieved, while in the multi-shot setting, values of 34.96% and 34.14% were attained. Full article

The integration of artificial intelligence into healthcare has advanced rapidly in recent years, with multimodal approaches emerging as promising tools for improving diagnostic accuracy and clinical decision making. These approaches combine heterogeneous data sources such as medical images, electronic health records, physiological signals, and clinical notes to better capture the complexity of disease processes. Despite this progress, only a limited number of studies offer a unified view of multimodal AI applications in medicine. In this review, we provide a comprehensive and up-to-date analysis of machine learning and deep learning-based multimodal architectures, fusion strategies, and their performance across a range of diagnostic tasks. We begin by summarizing publicly available datasets and examining the preprocessing pipelines required for harmonizing heterogeneous medical data. We then categorize key fusion strategies used to integrate information from multiple modalities and overview representative model architectures, from hybrid designs and transformer-based vision-language models to optimization-driven and EHR-centric frameworks. Finally, we highlight the challenges present in existing works. Our analysis shows that multimodal approaches tend to outperform unimodal systems in diagnostic performance, robustness, and generalization. This review provides a unified view of the field and opens up future research directions aimed at building clinically usable, interpretable, and scalable multimodal diagnostic systems. Full article

The determination of precise and reliable interior (IO) and relative (RO) orientation parameters for thermal infrared (TIR) cameras is critical for their subsequent use in photogrammetric processes. Although 2D calibration boards have become the predominant approach for TIR geometric calibration, these targets are susceptible to projective coupling and often introduce error through manual construction methods, necessitating the development of 3D targets tailored to TIR geometric calibration. Therefore, this paper evaluates TIR geometric calibration results obtained from 2D board and 3D field calibration approaches, documenting the construction, observation, and calculation of IO and RO parameters. This includes a comparative analysis of values derived from three popular commercial software packages commonly used for geometric calibration: MathWorks’ MATLAB, Agisoft Metashape, and Photometrix’s Australis. Furthermore, to assess the validity of derived parameters, two InfraRed Thermography 3D-Data Fusion (IRT-3DDF) methods are developed to model historic building façades and medieval frescoes. The results demonstrate the success of the proposed 3D field calibration targets for the calculation of both IO and RO parameters tailored to photogrammetric data fusion. Additionally, a novel combined TIR-RGB bundle block adjustment approach demonstrates the success of applying ‘out-of-the-box’ deep-learning neural networks for multi-modal image matching and thermal modelling. Considerations for the development of TIR geometric calibration approaches and the evolution of proposed IRT-3DDF methods are provided for future work. Full article

This paper presents a modeling framework for hysteretically nonlinear piezoelectric composite beams using functional differential equations (FDEs). While linear piezoelectric models are well established, they fail to capture the complex nonlinear behaviors that emerge at higher electric field strengths, particularly history-dependent hysteresis effects. This paper develops a cascade model that integrates a high-dimensional linear piezoelectric composite beam representation with a nonlinear Krasnosel’skii–Pokrovskii (KP) hysteresis operator. The resulting system is formulated using a state-space model where the input voltage undergoes a history-dependent transformation. Through modal expansion and discretization of the Preisach plane, we derive a tractable numerical implementation that preserves essential nonlinear phenomena. Numerical investigations demonstrate how system parameters, including the input voltage amplitude, and hysteresis parameters significantly influence the dynamic response, particularly the shape and amplitude of limit cycles. The results reveal that while the model accurately captures memory-dependent nonlinearities, it depends on numerous real and distributed parameters, highlighting the need for efficient reduced-order modeling approaches. This work provides a foundation for understanding and predicting the complex behavior of piezoelectric systems with hysteresis, with potential applications in vibration control, energy harvesting, and precision actuation. Full article

Modern oncology increasingly relies on personalized strategies that aim to customize medical interventions, using both tumor biology and clinical features to enhance efficacy and minimize adverse effects. In recent years, precision medicine has been implemented as part of systemic therapies; however, its integration into radiation therapy (RT) is still a work in progress. Conventional RT treatment plans are based on the Linear Quadratic (LQ) model and utilize standardized alpha and beta ratios (α/β), which ignore the high variability in terms of treatment response between and within patients. Recent advances in radiobiology, as well as general medical technologies, have also driven a shift toward more tailored approaches, including in RT. This review provides an overview of current knowledge and future perspectives for the personalization of RT, highlighting the role of tumor and patient-specific biomarkers, advanced imaging techniques, and novel therapeutic approaches. As an alternative to conventional RT modalities, hadron therapy and Flash RT are discussed as innovative approaches with the potential to improve tumor targeting while sparing normal tissues. Furthermore, the synergistic combination of RT with immunotherapy is discussed as a potential strategy to support antitumor immune responses and overcome resistance. By integrating biological insights, technological innovation, and clinical expertise, personalized radiation therapy may significantly advance the precision oncology paradigm. Full article

Graphene interfaces in layered dielectrics can support unique electromagnetic modes, but analyzing these modes requires robust computational techniques. This work presents a numerical method for computing TE-polarized eigenmodes in a planar stratified dielectric slab with an infinitesimally thin graphene sheet at its interface. The governing boundary-value problem is reformulated as coupled initial-value problems and solved via a customized shooting method, enabling accurate calculation of complex propagation constants and field profiles despite the discontinuity at the graphene layer. We demonstrate that the graphene significantly alters the modal spectrum, introducing complex leaky and surface waves with attenuation due to graphene’s conductivity. Numerical results illustrate how the layers’ inhomogeneity and the graphene’s surface conductivity influence mode confinement and loss. These findings confirm the robustness of the proposed computational approach and provide insights relevant to the design and analysis of graphene-based waveguiding devices. Full article

The vibration noise of plate structures in engineering is strongly related to the modal resonance, and modal design is the key to improve the dynamic characteristics of plate structures and avoid structural resonance. This paper investigates the dynamic and mode characteristics for an edge periodic acoustic black hole plate structure to provide a new approach to vibration and sound attenuation in plate structures. Firstly, based on the principles of symmetry and periodicity, this work presents the geometrical modeling and mathematical description of a rectangular plate with symmetrical periodic acoustic black holes at its edge. Then, it presents the dynamic modeling of a rectangular plate with periodic acoustic black holes at its edge via the “remove-and-fill” substitution method, which reveals the effects of the structural parameters and period distribution, etc., on the modal characteristics of vibration. The study indicates that the power law index, radius, number and configuration (e.g., semicircular, rectangular block shape) of the edge periodic acoustic black holes significantly affect the modal frequency of the rectangular plate, and increasing the radius of the acoustic black holes or the number of the black holes results in a decrease in the modal frequency of the rectangular plate. Moreover, the four-side symmetric layout achieves broader modal frequency modulation, while semicircular acoustic black holes can achieve a lower modal frequency compared with the rectangular wedge-shaped acoustic black hole. The theoretical model is verified by finite element simulation (FEM) and experiments, in which the errors of the first six modal frequencies are within 2%. The research in this paper provides a theoretical basis for the realization of modal frequency control in plate structures and the suppression of structural resonance through the design of edge periodic acoustic black hole structures. Full article