Search Results (85)

Background and Objectives: Mild cognitive impairment (MCI) and dementia are prevalent public health challenges with limited pharmacological options for cognitive enhancement. Digital cognitive rehabilitative interventions (DCIs) have emerged as a promising non-pharmacological approach, offering accessibility and personalized strategies. However, their efficacy across diverse populations and contexts remains unclear. This study evaluated the effectiveness of DCIs in improving global cognitive function in individuals with MCI and dementia by comparing them to active controls and usual care. Materials and Methods: Ten databases, including Ovid-Medline, Ovid–Embase, Cochrane Library, CINAHL, Web of Science, PsycINFO, KoreaMed, KMbase, RISS, and KISS, were searched for studies published up to May 2025. Global cognitive and executive functions, along with quality of life, were assessed. Meta-analyses using Review Manager version 5.4 were conducted to evaluate global cognitive function improvements, first stratified by comparator group (active control vs. usual care) and further stratified by patient (MCI vs. dementia) and intervention (computer-based vs. virtual reality cognitive training) types. Results: This systematic review and meta-analysis analyzed 37 studies. Overall, DCIs improved global cognitive function compared to the control group (SMD = 0.44, 95% CI: 0.18, 0.69). However, subgroup analysis showed no significant effect when DCIs were compared with active controls (SMD = 0.24, 95% CI: −0.35, 0.82). Subgroup analysis showed benefits for individuals with MCI (SMD = 0.43, 95% CI: 0.16, 0.70) but yielded inconclusive results for those with dementia (SMD = 0.95, 95% CI: −0.69, 2.59). Computer-based DCIs were effective (SMD = 0.57, 95% CI: 0.20, 0.93), whereas VR-based interventions had inconsistent outcomes (SMD = 0.32, 95% CI: −0.34, 0.98). Conclusions: DCIs may improve cognitive function compared with usual care, particularly in patients with MCI. However, their added benefits overactive cognitive interventions remain uncertain. Further well-designed studies are needed to clarify the relative advantages of DCIs across patient populations and intervention formats. Full article

Introduction: Schizophrenia is characterised by distributed abnormalities in electrophysiological dynamics and large-scale brain networks, yet unimodal EEG or MRI alone cannot fully explain how fast neural computations relate to spatially organised circuit dysfunction. Multimodal EEG–MRI approaches offer a bridge across temporal and anatomical scales by explicitly modelling cross-modal coupling. Methods: Following PRISMA 2020 guidance, we conducted a systematic, mechanistic review of human studies (adults ≥ 18 years) comparing schizophrenia-spectrum groups with healthy controls using EEG combined with at least one MRI modality (fMRI, structural MRI, and/or diffusion MRI) and explicit EEG–MRI integration (e.g., EEG-informed fMRI, joint ICA, mCCA/MCCA, coupled matrix–tensor factorisation, DCM-based fusion). Searches were performed in PubMed/MEDLINE, Embase, Web of Science, Scopus, PsycINFO, IEEE Xplore, ResearchGate, and Google Scholar for January 2000–December 2025, supplemented by citation tracking. Risk of bias was assessed with ROBINS-I, and due to heterogeneity, results were synthesised narratively by integration of families. Results: From 148 records, 23 studies met the inclusion criteria. Studies used mainly simultaneous EEG–fMRI at 3T and spanned resting-state designs and task paradigms dominated by auditory processing (oddball, MMN/N100–P200, ASSR/aeGBR), with additional work in affective context, working memory, semantic processing (N400), sensory gating, and pharmacologic challenge. Across tasks, the most reproducible multimodal signature was disrupted coupling between electrophysiological markers and the recruitment of large-scale networks, rather than isolated changes in EEG or fMRI metrics. Target detection/oddball paradigms converged on reduced late ERP responses (especially P300, sometimes N2) alongside reduced expression or loss of coupling to salience/ventral attention and control circuitry (including ACC/anterior insula/TPJ). Resting-state studies most consistently indicated altered “coupling rules” (frequency specificity, timing/lag structure, and directionality), including abnormalities detectable even when unimodal summaries were weak. Extended multimodal studies (adding sMRI/DTI and/or classification) suggested that combining modalities can improve discrimination, though performance was sensitive to sample size, demographic imbalance, and feature-selection/validation choices. Conclusions: Multimodal EEG–MRI studies support schizophrenia as a disorder involving persistent structural and circuit-level abnormalities whose functional expression varies dynamically across cognitive states and task demands. Future progress will depend on harmonised acquisition/artefact-control practices for simultaneous EEG–fMRI, larger and more diverse samples (including early/CHR and longitudinal designs), and cross-site replication of mechanistically interpretable coupling biomarkers. Full article

Medical image segmentation still faces three critical challenges: insufficient joint modeling of local details and long-range dependencies, the high computational burden of transformer-based architectures for high-resolution inputs, and performance degradation caused by domain shift across imaging centers and acquisition devices. To address these issues, this paper proposes CMFA-Net, a CNN–Mamba collaborative feature alignment network for robust medical image segmentation. The proposed framework adopts Vision Mamba (VSSM) as the encoder backbone to capture long-range contextual dependencies with linear computational complexity. A CNN–Mamba fusion attention (CMFA) module is designed to integrate the local representation capability of convolution with the long-range modeling capability of Mamba, improving the segmentation of complex boundaries and multi-scale targets. In addition, an enhanced multi-scale context aggregation decoder (EMCAD) is introduced to reduce the semantic gap between encoder and decoder features and strengthen hierarchical feature fusion. To enhance cross-dataset robustness, a contrastive domain alignment learning (cDAL) strategy is applied in the intermediate feature space to learn domain-invariant discriminative representations via an InfoNCE-based objective. Experiments on the CirrMRI600+ pathological liver MRI dataset and several public polyp segmentation benchmarks show that the proposed method achieves competitive segmentation performance. Ablation studies provide empirical evidence for the contributions of the CMFA module, EMCAD decoder, and cDAL mechanism under the same experimental protocol. These results suggest that CMFA-Net is a promising framework for medical image segmentation across heterogeneous datasets. Full article

Late deliveries represent one of the most persistent operational disruptions in global supply chains, eroding service reliability, triggering contractual penalties, and undermining the resilience of logistics networks. As supply chains become increasingly digitalized, the integration of advanced predictive analytics into operational decision-making offers a pathway toward proactive rather than reactive disruption management. This study develops and evaluates a digital analytics framework in which eXtreme Gradient Boosting (XGB), a high-performance ensemble learning algorithm, is optimized by three recent population-based metaheuristic algorithms: the weighted mean of vectors algorithm (INFO), Harris Hawks Optimization (HHO), and the Red-Billed Blue Magpie Optimizer (RBMO). Four critical XGB hyperparameters, number of estimators, maximum tree depth, learning rate, and complexity penalty, are tuned on a supply chain dataset. A population-size sensitivity analysis at two swarm configurations reveals that all three optimizers converge to functionally equivalent solutions at sufficient population diversity, providing practical guidance for computational resource allocation. The best-performing configuration, HHO-XGB, achieves a test accuracy of 97.47% and a Matthews correlation coefficient of 0.949, substantially outperforming the baseline XGB and other benchmark classifiers. To ensure transparency and support data-driven decision-making, SHapley Additive exPlanations (SHAP) analysis is applied to the optimized model, revealing that shipping mode, scheduled shipment days, shipping date, order day, order status, and order month are the dominant predictive features, confirming that late-delivery risk is primarily driven by shipment configuration and temporal patterns. The proposed framework demonstrates that integrating metaheuristic intelligence with machine learning delivers better predictive performance. Interpretability is essential to trustworthy, resilient supply chain decision-support systems. Full article

Cognition and intelligence are central concepts in cognitive science, biology, philosophy of mind, and artificial intelligence, yet these disciplines offer conflicting accounts of what each of them means and how the two notions are related. In many accounts the two notions are used interchangeably, while in others intelligence is defined independently of cognitive processes. Dominant human-centered traditions identify cognition with mental processes associated with brains, whereas life-centered perspectives attribute cognitive capacities to all living systems. This article proposes a relational, life-centered, info-computational framework in which cognition is the ongoing autopoietic and sense-making organization of living systems, while intelligence is the degree of competence with which such organization achieves goal-directed problem solving under novelty, perturbation, and uncertainty. Cognition exists in degrees across living systems, from basal cellular sensing and regulation to increasingly complex cognitive organizations, while intelligence correspondingly appears in degrees in the ability to solve cognitive problems. Current artificial systems can exhibit engineered or derivative intelligence and may implement cognition-like functions, but they are not cognitive in the biological sense. The resulting framework clarifies how human-centered, life-centered, computational, and artificial intelligence can be related. Full article

As one of the world’s leading cotton-producing countries, China frequently experiences severe yield reductions due to crop diseases and pest infestations, with losses often exceeding 20%. Although computer vision models can identify diseased plants, they currently fail to connect visual symptoms to the diagnostic reasoning process used by agronomists. This leads to text descriptions that ignore the biological causes of the damage. To fix this, we built Multimodal Knowledge Graph-Enhanced Cross Vision Transformer-18-Dagger-408 and Text-to-Text Transfer Transformer for Cotton Disease and Pest Image Captioning (MKG-CottonCapT6), a model that uses a local knowledge database to generate professional diagnostic reports from field images. The technical core consists of a Multimodal Knowledge Graph (MMKG) containing 14 types of entities (such as Pathogens and Control Agents) and 12 types of relations. We use a Cross Vision-Transformer-18-Dagger-408 (CrossViT) encoder to capture both the overall leaf shape and microscopic details of pests. Through a Visual Entity Grounding (VEG) module, the model maps visual features directly to specific triplets in the graph. These triplets are then turned into text sequences and fused with image data in a Text-to-Text-Transfer-Transformer (T5) decoder. To train the model, we collected a dataset of cotton images paired with expert descriptions of lesions, colors, and affected plant parts. Tests show that MKG-CottonCapT6 performs better than standard models, reaching an Information-based Metric for Image Captioning (InfoMetIC) score of 72.6%. Results prove that by using a specific alignment loss (${\mathcal{L}}_{align}$), the model generates reports that correctly name the disease stage and recommend specific chemicals, such as Carbendazim or Triadimefon. This framework provides a practical tool for farmers to record and treat cotton diseases with high precision. Full article

Modeling the temporal dynamics of student learning is a central goal in educational data mining. Deep Knowledge Tracing (DKT) has emerged as a key approach, yet existing models are highly sensitive to out-of-distribution (OOD) inputs, such as those arising from curriculum changes, new assessment formats, or behavioral noise, which severely degrade predictive reliability. To address this challenge, we propose Energy-Based Out-of-Distribution Deep Knowledge Tracing (EB-OOD DKT), a unified framework that integrates energy-based uncertainty estimation and contrastive representation learning within a transformer-based DKT architecture. The model computes energy scores via the negative log-sum-exponential of prediction logits, serving as confidence indicators for detecting OOD inputs during inference. Additionally, an InfoNCE-based contrastive loss enhances representation robustness by aligning in-distribution samples and separating OOD cases in latent space. Temporal and behavioral context features, such as normalized response intervals and cumulative attempt counts, are incorporated to enrich cognitive-behavioral modeling. Experiments on four public educational datasets demonstrate consistent improvements in prediction accuracy and OOD detection. EB-OOD DKT provides a promising approach for more reliable student modeling across educational platforms with different content distributions. Full article

Digital Mental Health Interventions (DMHIs) offer a scalable solution to the global mental health crisis, yet their real-world impact is often hampered by low user engagement. Gamification has been widely adopted as a strategy to enhance adherence, but its implementation creates a complex and often unacknowledged “Engagement–Efficacy–Ethics Trilemma”. This systematic review synthesises the current literature to deconstruct this trilemma, arguing that an uncritical focus on maximising engagement can fail to improve—or may even undermine—clinical efficacy, while simultaneously introducing significant ethical risks. Our analysis reveals a persistent “Engagement–Efficacy Gap”, where increased usage of mobile health applications (mHealth apps) does not consistently translate to better therapeutic outcomes. Furthermore, we map the ethical landscape, identifying potential harms such as manipulation, psychological distress, and privacy violations that arise from persuasive design. The roles of Artificial Intelligence (AI) in personalising these experiences and Human–Computer Interaction (HCI) in mediating user responses are critically examined as key factors that both amplify and potentially mitigate the tensions of the trilemma. The findings indicate a pressing need for a paradigm shift toward an integrated approach that concurrently evaluates engagement, efficacy, and ethical integrity. We conclude by proposing a framework for responsible innovation, emphasising theory-driven design, co-design with users, and prioritising intrinsic motivation to harness the potential of gamified DMHIs safely and effectively. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic search was conducted across Scopus, Web of Science, MEDLINE, and PsycINFO for studies published between 2015 and 2025. Full article

This study evaluated the applicability of the dual drainage model, Hyper Connected–Solution for Urban Flood (HC-SURF), for real-time urban flood forecasting. The model was applied to the extreme rainfall event of August 2022 in the Sillim and Daerim drainage basins in Seoul. Its accuracy and computational efficiency were quantitatively compared with those of two widely used commercial models, the Personal Computer Storm Water Management Model (PC-SWMM) and InfoWorks Integrated Catchment Modelling (ICM). Accuracy was assessed by measuring spatial agreement with observed inundation trace maps using binary indicators, including the Critical Success Index (CSI), Probability of Detection (POD), and False Alarm Ratio (FAR). Computational efficiency was evaluated by comparing simulation times under identical conditions. In terms of accuracy against observations, HC-SURF achieved CSI values ranging from 0.26 to 0.45, with POD values from 0.37 to 0.81 and FAR values from 0.49 to 0.53 across the two basins. In inter-model comparisons, the model showed high hydraulic consistency, demonstrating CSI values between 0.72 and 0.88, POD between 0.82 and 0.99, and FAR between 0.08 and 0.15. In terms of computational efficiency, HC-SURF reduced calculation times by approximately 9% and 44% compared with InfoWorks ICM and PC-SWMM, respectively, for a 48 h simulation. The model also completed a 6 h rainfall simulation in approximately 8 min, meeting the lead time requirements for rapid urban flood forecasting. Overall, these findings show that HC-SURF effectively balances simulation accuracy with computational efficiency, demonstrating its suitability for real-time urban flood forecasting. Full article

Next Point-of-Interest (POI) recommendation is a crucial task in personalized location-based services, aiming to predict the next POI that a user might visit based on their historical trajectories. Although sequence models and Graph Neural Networks (GNNs) have achieved significant success, they often overlook the diversity and dynamics of user preferences. To address these issues, researchers have begun to employ Hypergraph Convolutional Networks (HGCNs) for disentangled representation learning. However, two critical problems have received less attention: (1) the limited expressive capacity of conventional hypergraph convolution layers, which restricts the modeling of complex nonlinear user–POI preference interactions and consequently weakens generalization performance, and (2) the inadequate utilization of contrastive learning mechanisms, which prevents fully capturing cross-view collaborative signals and limits the exploitation of complementary multi-view information. To tackle these challenges, we propose a Nonlinear Enhanced Disentangled Contrastive Hypergraph Learning (NE-DCHL) for next POI recommendation. The proposed model enhances nonlinear modeling capability and generalization by integrating ReLU activation, residual connections, and dropout regularization within the hypergraph convolution layer. A K-Nearest Neighbor (KNN)-based weighted adjacency matrix is employed to construct the geographical-view hypergraph, reducing computational complexity while maintaining essential spatial correlations. Moreover, a mini-batch InfoNCE loss and the GRACE (deep GRAph Contrastive rEpresentation learning) framework are utilized to improve efficiency and cross-view collaboration. Extensive experiments on two real-world datasets demonstrate that NE-DCHL consistently outperforms the original DCHL and other state-of-the-art approaches. Full article

In dealing with emergency events, it is very important when making scientific and correct decisions. As an important premise, the creation of information needs is quite essential. Taking earthquakes as a type of unexpected event, this paper constructs a large and model-driven system for automating the generating process of information requirements for earthquake response. This research explores how the different departments interact during an earthquake emergency response, how the information interacts with each other, and how the information requirement process operates. The system is designed from three points of view, building a knowledge base, designing and developing prompts, and designing the system structure. It talks about how computers automatically make info needs for sudden emergencies. During the experimental process, the backbone architectures used were four Large Language Models (LLMs): chatGLM (GLM-4.6), Spark (SparkX1.5), ERNIE Bot (4.5 Turbo), and DeepSeek (V3.2). According to the desired system process, information needs is generated by real-word cases and then they are compared to the gathered information needs by experts. In the comparison process, the “keyword weighted matching + text structure feature fusion” method was used to calculate the semantic similarity. Like true positives, false positives, and false negatives can be used to find differences and calculate metrics like precision and recal. And the F1-score is also computed. The experimental results show that all four LLMs achieved a precision and recall of over 90% in earthquake information extraction, with their F1-scores all exceeding 85%. This verifies the feasibility of the analytical method a chatGLM dopted in this research. Through comparative analysis, it was found that chatGLM exhibited the best performance, with an F1-score of 93.2%. Eventually, Python is used to script these aforementioned processes, which then create complete comparison charts for visual and test result checking. In the course of researching we also use Protege to create the knowledge requirements ontology, so it is easy for us to show and look at it. This research is particularly useful for emergency management departments, earthquake emergency response teams, and those working on intelligent emergency information systems or those focusing on the automated information requirement generation using technologies such as LLMs. It provides practical support for optimizing rapid decision-making in earthquake emergency response. Full article

The rising urbanization and climate change have increased pluvial flood risks, especially in highly urbanized areas. This study focuses on the Lake Ganzirri area in Messina, Italy, where street-level floods have raised concerns for infrastructure resilience and public safety. This study aims to explore how to effectively represent key urban features, emphasizing buildings and low-impact development/sustainable urban drainage systems (LID/SUDS). For the buildings, a combination of referred approaches to represent buildings is compared against the widely used method to represent buildings as voids in a 2D mesh, ignoring them in the water balance calculations. For the LID/SUDS control elements, a 2D representation is presented and compared against the widely used 1D approach to model such elements. The study uses three well-known software packages—EPA-SWMM 5.2, HEC-RAS 6.2, and InfoWorks ICM 2021.9—applied to the Lake Ganzirri area, to explore the representation of buildings using the building void method (available in InfoWorks ICM 2021.9) against the proposed method (in HEC-RAS 6.2) to replicate runoff flow over a 2D model of a highly urbanized area. From scenario S0, three more scenarios were derived: S1 (S0 with pluvial drainage network), S2 (S1 with LID/SUDS control elements), and S3 (S0 with 2D representation of LID/SUDS), which were then compared against using four comparison schemes. Results show that the proposed method for representing buildings computed the propagation of the runoff comparable to when the building void method is used, with some shortcomings regarding mesh adjustments and computational times. Regarding the 2D representation of LID/SUDS, the effects were unperceivable on water depth maps (reduction in water depths of 1.5 mm on average for all the rainfall events). Still, they were reflected in the increase of 62% of the infiltration volume on average of all the rainfall scenarios and a decrease of 9.1% of water flowing outside the 2D area, therefore replicating the effect of capturing water. Full article

Cognition is often modeled in terms of abstract reasoning and neural computation, yet a growing body of theoretical and experimental work suggests that the roots of cognition lie in fundamental embodied regulatory processes. This article presents a theory of cognition grounded in sensing, feeling, and affect—capacities that precede neural systems and are observable in even the simplest living organisms. Based on the info-computational framework, this entry outlines how cognition and proto-subjectivity co-emerge in biological systems. Embodied appraisal—the system’s ability to evaluate internal and external conditions in terms of valence (positive/negative; good/bad)—and the capacity to regulate accordingly are described as mutually constitutive processes observable at the cellular level. This concept reframes cognition not as abstract symbolic reasoning but as value-sensitive, embodied information dynamics resulting from self-regulating engagement with the environment that spans scales from unicellular organisms to complex animals. In this context, information is physically instantiated, and computation is the dynamic, self-modifying process by which organisms regulate and organize themselves. Cognition thus emerges from the dynamic coupling of sensing, internal evaluation, and adaptive morphological (material shape-based) activity. Grounded in findings from developmental biology, bioelectric signaling, morphological computation, and basal cognition, this account situates intelligence as an affect-driven regulatory capacity intrinsic to biological life. While focused on biological systems, this framework also offers conceptual insights for developing more adaptive and embodied forms of artificial intelligence. Future experiments with minimal living systems or synthetic agents may help operationalize and test the proposed mechanisms of proto-subjectivity and affect regulation. Full article

Objective: To review and synthesize the current literature of clinical trials that investigated the efficacy and safety of glucagon-like peptide-1 receptor agonists (GLP-1RAs) in people with obstructive sleep apnea (OSA). Method: MEDLINE, EMBASE, Cochrane Library, and PsycINFO were searched for randomized controlled trials (RCTs) in which GLP-1RAs were used to treat people diagnosed with OSA. This systematic review and meta-analysis complied with PRISMA 2020 guidelines and was registered on PROSPERO (CRD42024537280). A random effects model was used for meta-analysis to assess changes in OSA as measured by the apnea–hypopnea index (AHI) compared to continuous positive airway pressure (CPAP) or placebo controls. The standardized mean difference (SMD) and risk ratio (RR) were computed for continuous and binary outcomes. Variability between studies, risk of bias, subgroup analysis, and leave-one-out analysis were completed. Results: Five studies were included (N = 1023; 511 GLP-1RA and 512 control). Two trials used tirzepatide and four studies used liraglutide as the GLP-1RA. Six studies showed a decrease in AHI with an SMD of −14.5 events per hour (95%CI = −24.73 to −4.21; I² = 96.3%). When compared to placebo, GLP-1RA treatment had a significant reduction in AHI (SMD = −0.69; 95%CI = −1.10 to −0.26; p = 0.001; I² = 88.0%). When compared to CPAP, no significant difference in the reduction of AHI was found. No evidence of publication bias was found. Compared to control, there was no significant difference in serious adverse events (RR = 0.89; 95%CI = 0.50 to 1.57; p = 0.68; I² = 20.93%). Conclusions: People with psychiatric disorders may also experience comorbid OSA that can impact their quality of life, which may perpetuate psychiatric symptoms of depression. GLP-1RAs may provide therapeutic potential in the treatment of OSA in addition to their cardioprotective effects. Current studies are limited by small sample sizes, lack of blinding, and short duration. Future studies will require further investigation in long-term efficacy and safety. Full article

Image dehazing is critical for visual enhancement and a wide range of computer vision applications. Despite significant advancements, challenges remain in preserving fine details and adapting to diverse, non-uniformly degraded scenes. To address these issues, we propose a novel image dehazing method that introduces a contrastive learning framework, enhanced by the InfoNCE loss, to improve model robustness. In this framework, hazy images are treated as negative samples and their clear counterparts as positive samples. By optimizing the InfoNCE loss, the model is trained to maximize the similarity between positive pairs and minimize that between negative pairs, thereby improving its ability to distinguish haze artifacts from intrinsic scene features and better preserving the structural integrity of images. In addition to contrastive learning, our method integrates a multi-scale dynamic feature fusion with a hybrid attention mechanism. Specifically, we introduce dynamically adjustable frequency band filters and refine the hybrid attention module to more effectively capture fine-grained, cross-scale image details. Extensive experiments on the RESIDE-6K and RS-Haze datasets demonstrate that our approach outperforms most existing methods, offering a promising solution for practical image dehazing applications. Full article