Search Results (2,991)

Background/Objectives: Multimodal depression detection research has traditionally relied on early or hybrid fusion strategies without systematically analyzing how dynamic fusion mechanisms interact with modality-specific pretraining. Although gated and attention-based architectures are increasingly adopted, their behavior is rarely examined within a structured fusion taxonomy framework. Methods: In this study, we conduct a controlled taxonomy-level evaluation of multimodal fusion strategies in a Japanese PHQ-9-annotated depression dataset. We compare four fusion paradigms (concatenation, summation, gated fusion, and cross-attention) across three integration stages, crossed with modality-specific affective pretraining configurations for visual (CMU-MOSI/MOSEI), acoustic (JTES), and textual (WRIME) encoders, yielding 512 experimental conditions. Results: The results reveal strong position-dependent effects of fusion strategy. Cross-attention fusion at the audio integration stage achieved the highest mean AUC (0.774) and PR-AUC (0.606), with statistically significant superiority over gated and concatenation-based fusion (Kruskal–Wallis $H=86.28$, $p<0.001$). In contrast, fusion effects at the text stage were non-significant in AUC but significant in PR-AUC, highlighting metric-sensitive behavior under class imbalance. Pretraining effects were modality-specific: SigLIP initialization produced significant positive transfer $(\Delta =+0.018,p<0.001)$, whereas audio pretraining on JTES resulted in negative transfer $(\Delta =-0.014,p=0.004)$, suggesting domain mismatch effects. Gate analysis further revealed condition-dependent modality dominance, including cases of semantic–geometric reversal under joint auxiliary augmentation. Conclusions: Our findings suggest that multimodal depression detection systems should not be interpreted through static fusion categories alone. Instead, modality contribution appears to be associated with structured interaction effects between fusion strategy, integration position, and affective pretraining. This work provides a controlled empirical bridge between fusion taxonomy and dynamic modality weighting in clinical multimodal modeling. Full article

The hybrid parallel operation of the grid-following (GFL) converter and the grid-forming (GFM) converter has become a typical scenario in distribution networks. The vastly different control philosophies and dynamics between the two give rise to complex small-signal stability issues, especially under weak grids. Traditional methods primarily rely on equivalent models or impedance-based approaches at fixed operating points, which struggle to reveal the system instability mechanisms when the capacity ratio between the two types of converters changes. This paper establishes a three-port dynamic average model for a grid-connected system with heterogeneous GFL-GFM converters. Using the participation factor analysis method, the system’s dominant modes are identified, and the key parameters influencing oscillations at different frequencies, as well as their formation processes, are revealed. Furthermore, a stability analysis method for variable capacity ratios is proposed. This method re-performs modal analysis based on the varying capacities of the GFM and GFL converters, revealing the dominant factors and influencing mechanisms of system instability during capacity transitions. Finally, a simulation model is built in PSCAD/EMTDC to verify the correctness of the proposed three-port model and the theoretical analysis results. Full article

Background: The pain experienced by people with fibromyalgia (FM) is thought to be the result of altered nociceptive processing, impaired descending inhibition and reduced tolerance to physical load. However, the relationship between the amount of exercise and pain reduction remains unclear. Methods: This study synthesized randomized controlled trials of exercise interventions for FM to quantify the combined analgesic effects of different types of exercise. A secondary aim was to standardize exposure using metabolic equivalent of task (MET)-based metrics and examine the association between cumulative intervention dose (MET·h) and analgesic response (Hedges’ g) across intervention arms. Following the PRISMA guidelines, a search was conducted in PubMed for randomized controlled trials published up to 31 December 2025. After screening and a full-text assessment, 15 trials were included. The protocols were converted into MET-defined intensity and weekly MET·min exposure, and the cumulative dose was calculated as the total MET·h accrued over the intervention period. Random-effects models were used to estimate the pooled effects within modality subgroups. Results: Across modalities, exercise was associated with reductions in pain, with effects typically falling within the small-to-moderate range. Larger improvements were observed in structured or supervised programs. The dose-response scatter plot showed wide variability across the dose range, with overlapping confidence intervals. An exploratory fourth-degree polynomial fit explained limited variance (R² = 0.1615) and did not indicate a monotonic dose-response pattern. This suggests that cumulative workload alone is a weak proxy for therapeutic response. Conclusions: Based on these findings, a pain-responsive algorithm combining weekly Visual Analogue Scale (VAS), ΔVAS and Talk Test thresholds was implemented as a preliminary online calculator to support the prescription of exercise tailored to symptoms. Full article

Background: Auricular keloids and ear helix deformities are undesirable and aesthetically unpleasing deformities that can cause significant patient psychologic and self-esteem problems. Pressure therapy for keloids is well documented to be an effective non-invasive treatment modality. However, current devices lack comfort and aesthetic appeal to deliver the pressure forces required effectively and uniformly. This work aims to highlight some different pressure therapy approaches for the management of keloids and irregularities in the ear helix morphology. Methods: A case series of four patients presenting with auricle keloids of various sizes and at different locations secondary to ear piercing and one case of congenital helix deformity were treated successfully with pressure therapy devices. The device designs varied based on the keloids’ characteristics and patients’ preferences and involved wire-based spring-activated appliances resembling ear rings for moderate keloid lesions, modified double-spring systems for large or elongated lesions, and magnet-based devices. A pair of inert magnetic discs of different diameters was positioned on the anterior and posterior aspects of the keloid lesion. The magnets were then encapsulated in acrylic resin to improve retention and adaptation, and the external surface was masked with gold glitter to enhance aesthetics and patient acceptance. The helix-deformity case was treated following a complete digital workflow integration where the sound contralateral ear was digitally scanned, mirror-imaged and then 3D-printed in resin to produce an ear model based on which an anatomically symmetrical pressure device was constructed. Results: All devices were successfully fitted and well tolerated, with no reported discomfort or adverse reactions. The wire spring devices were effective in reducing a large keloids volume; however, frequent reactivation every two weeks was required to ensure continuous pressure application. Incorporating magnets in the customised design allowed controlled and uniform pressure application to small keloid-lesion morphology, with enhanced aesthetics and improved patient acceptance and compliance. The digitally assisted case achieved near-perfect anatomical symmetry with the contralateral ear, reducing operator dependency and fabrication guesswork. Conclusions: Customised pressure therapy devices, of magnetic and spring-based systems, alongside utilising digital technologies, offer effective, non-invasive management for auricular keloids and irregular ear helices as long as the patient is committed to wearing the device. Full article

Background and Objectives: This meta-analysis aimed to compare the clinical efficacy and safety of the Thulium fiber laser (TFL) and Holmium:Yttrium-Aluminum-Garnet (Ho:YAG) laser for ureteroscopic lithotripsy, considering the distinct technical characteristics of these two systems. Materials and Methods: Following the PRISMA guidelines and PROSPERO registration (CRD42023461573), a systematic search of PubMed, EMBASE, Cochrane Library, and Web of Science was conducted through August 2025. We included randomized controlled trials and non-randomized comparative studies comparing TFL and Ho:YAG laser in patients undergoing ureteroscopic management for urolithiasis. The primary outcomes were the stone-free rate (SFR) and complication rates (intraoperative and postoperative). Results: Thirteen studies involving 2217 patients were included. Overall, the TFL group demonstrated a significantly higher SFR compared to the Ho:YAG group (OR = 1.57, 95% CI 1.20–2.06, p = 0.001). In subgroup analysis, TFL showed superior SFR compared to Ho:YAG without pulse modulation (OR = 1.69, p = 0.01) and comparable efficacy to Ho:YAG with pulse modulation (OR = 1.52, p = 0.24). Regarding safety, no significant difference was observed in the intraoperative complication rate (OR = 0.77, 95% CI 0.35–1.70, p = 0.52) or the postoperative complication rate (OR = 1.02, 95% CI 0.65–1.60, p = 0.93) between the two groups. Conclusions: TFL provides a superior SFR compared to the Ho:YAG laser overall, a benefit primarily driven by its significant outperformance of standard Ho:YAG systems without pulse modulation. Importantly, TFL demonstrates comparable efficacy to modern Ho:YAG systems equipped with pulse modulation. The safety profile of TFL, including intraoperative and postoperative complications, is comparable to that of the Ho:YAG laser. Our findings suggest that TFL is a highly effective and safe modality for ureteroscopic lithotripsy, offering distinct advantages over standard Ho:YAG lasers while performing comparably to the latest pulse-modulated systems. Full article

Early detection of battery degradation is essential for ensuring the safety and reliability of electric vehicle (EV) systems under real-world operating variability. This paper proposes a physics-guided multi-sensor learning framework, termed SensorFusion-Former (SFF), for early warning of short-term EV battery performance degradation. The proposed approach integrates a physics-based baseline model for operational normalization, a multi-sensor fusion attention mechanism to model cross-modality interactions, and a lightweight transformer architecture for efficient temporal representation learning. Weak supervision is derived from physics-consistent residual analysis with temporal smoothing, enabling scalable training without dense manual annotations. To support reliable deployment, evidential uncertainty modeling and conformal calibration are incorporated to obtain statistically controlled decision thresholds. Experiments conducted on a real driving cycle dataset from IEEE DataPort demonstrate that SFF consistently outperforms classical machine learning methods, deep neural networks, and standard transformer models in terms of early-warning lead time, false alarm rate, and inference efficiency while maintaining competitive discriminative performance. Cross-scenario evaluations under diverse thermal conditions further confirm the robustness and generalization capability of the proposed framework. Full article

Access control systems rely increasingly on multimodal biometric and behavioral signals to enhance security and robustness against sophisticated attacks. However, when heterogeneous modalities provide conflicting evidence, such as valid biometric credentials accompanied by abnormal behavioral or acoustic patterns, traditional fusion strategies based on static thresholds or majority voting often fail, leading to false alarms or insecure authorization decisions. This paper addresses this critical limitation by proposing a contextual decision-making fusion framework designed to resolve conflicting multimodal evidence at the decision-making level. The proposed approach models access control as a decision-making problem in a context of uncertainty, where independent agents generate modality-specific evidence from authentication channels based on face, voice, and fingerprints. A centralized fusion mechanism integrates heterogeneous results using adaptive reliability weighting and contextual reasoning to resolve conflicts before operational decisions are made. Rather than treating each modality independently, the framework explicitly considers inconsistencies, uncertainties, and situational context when aggregating evidence. The framework is evaluated using public benchmarks, including VGGFace2, VoxCeleb2, and FVC2004, combined with controlled multimodal scenarios that induce conflicting evidence. Experimental results obtained under controlled contradiction scenarios show that the proposed fusion strategy reduces false alarms and improves decision consistency by approximately 18%. These results are interpreted within the scope of controlled multimodal simulations. Full article

Background: Intrahepatic cholangiocarcinoma (ICC) is an uncommon but increasingly recognized primary liver malignancy with a poor prognosis. Although surgical resection offers the only realistic opportunity for cure, recurrence is common and the optimal integration of surgery with systemic and liver-directed therapies continues to evolve. Summary: This review summarizes contemporary evidence on the diagnosis and multidisciplinary management of ICC with particular emphasis on surgical, systemic, locoregional, and transplant-based strategies. Cross-sectional imaging plays a central role in staging and assessing resectability including evaluation of vascular invasion and the future liver remnant. Upfront resection is appropriate for selected patients with resectable disease and preserved liver function, with margin-negative resection and lymphadenectomy remaining key oncologic goals. Systemic therapy continues to evolve with cytotoxic chemotherapy forming the backbone of treatment for advanced disease and immunotherapy and targeted agents demonstrating promise in biomarker-defined subgroups. Locoregional modalities such as hepatic arterial infusion therapy and radioembolization may provide disease control in liver-dominant ICC and are increasingly used within a multidisciplinary framework. Liver transplantation remains investigational but may offer favorable outcomes in highly selected early-stage disease. Full article

Background: Middle-aged women with obesity frequently exhibit postural misalignment and impaired balance control, which may increase the risk of functional limitations and falls. This study aimed to compare the effects of Pilates circuit training and weight circuit training on body composition, pelvic alignment indices, and balance performance in obese middle-aged women. Methods: Eighteen women (body fat ≥ 30%) were randomized to either a Pilates circuit training group (PCG, n = 9) or a weight circuit training group (WCG, n = 9) in an exploratory comparative study. Both groups performed supervised exercise three times per week for eight weeks. Outcome measures included body composition, pelvic alignment indices, dynamic balance (Y-Balance Test), and static balance (BESS). Data were analyzed using a two-way mixed ANOVA to examine time, group, and interaction effects. Results: Both groups showed significant reductions in body weight (PCG: −3.09 kg; WCG: −2.00 kg), percentage body fat (PCG: −1.85%; WCG: −1.53%), and waist-to-hip ratio (PCG: −0.05; WCG: −0.04) (p < 0.01). Significant improvements in pelvic alignment indices were observed primarily in the PCG, whereas the WCG showed smaller changes. Dynamic and static balance improved in both groups, with greater improvements observed in the PCG. Conclusions: Both training modalities improved body composition and balance outcomes in obese middle-aged women. Pilates circuit training may be associated with greater improvements in pelvic alignment and balance; however, these findings should be interpreted cautiously due to the exploratory design and small sample size. Further adequately powered randomized controlled trials are required to confirm these findings. Full article

Background/Objectives: Accurate target delineation is critical in radiotherapy for head and neck non-melanoma skin cancer (NMSC), where tumor depth and subclinical extension are often underestimated by clinical and dermoscopic assessment alone. While high frequency ultrasound has shown value in surface-based radiotherapy techniques, the role of ultra-high frequency ultrasound (UHFUS) within external beam radiotherapy (EBRT) workflows remains poorly defined. Methods: We conducted a single-institution observational feasibility study including all consecutive patients with head and neck NMSC treated with definitive or adjuvant radiotherapy between July 2022 and July 2023 using a structured multidisciplinary workflow integrating pre-treatment UHFUS. UHFUS was systematically performed prior to CT simulation and incorporated into radiotherapy planning. The primary endpoint was the impact of UHFUS on radiotherapy decision-making, predefined as modification of target delineation, treatment intent, or beam modality selection. Secondary endpoints included feasibility, early local control, and late toxicity (descriptive). Results: Thirty patients were included (median age 85 years; range 66–99). UHFUS influenced at least one decision endpoint in 13 patients (43.3%). In the definitive radiotherapy cohort (n = 18), UHFUS modified gross tumor volume delineation in eight patients (44.4%), with an increase in median GTV from 17.5 cm³ to 24.3 cm³. Among patients initially referred for adjuvant radiotherapy (n = 12), UHFUS identified macroscopic residual disease in two cases, leading to a change in treatment intent from adjuvant to definitive radiotherapy. UHFUS supported beam modality selection in three patients by enabling safe use of electron therapy for superficial lesions. After a median follow-up of 24 months (range 12–24), no local recurrences were observed. Late toxicity was limited to grade 1 cutaneous events. Conclusions: Integration of UHFUS into EBRT planning for head and neck NMSC is feasible and clinically informative. UHFUS acts as a decision-shaping tool, influencing target delineation, treatment intent, and modality selection within a multidisciplinary workflow. These findings support further prospective evaluation of UHFUS-guided radiotherapy planning to standardize decision algorithms and assess long-term clinical impact. Full article

Reducing measurement uncertainty is crucial to enable the adoption of rapid point-of-use techniques for clinical and industrial applications. Diagnosis of neonatal respiratory distress syndrome and liposome formulation quality control are two applications for which measuring the ratio of the lecithin to sphingomyelin composition of liposomes is important, for which no rapid measurement currently exists. Raman and infrared spectroscopies are two complementary approaches to examine characteristic molecular vibrations that can spectroscopically measure liposomes and, when combined with machine learning, predict their composition. We show that employing a data-fusion approach the uncertainty in the predicted compositions compared to the individual modalities (IR R²: 0.902 and Raman R²: 0.951) can be reduced to obtain more accurate and precise measurements (low-level fused model R²: 0.973, mean squared error: 0.024, prediction interval width: 0.303, high-level weighted fusion model R²: 0.970, mean squared error: 0.027, prediction interval width: 0.268). Full article

This study investigated the effects of mental fatigue induced by social media (SM) use and the Stroop task on decision-making, visual search strategies, and reaction time in elite collegiate handball players (n = 16). Using a randomized, counterbalanced cross-over design, both interventions successfully induced subjective mental fatigue, as confirmed by visual analog scale (VAS) ratings. Decision-making accuracy and reaction time improved following the Stroop task, likely due to compensatory mechanisms described in the regulatory-control model. In the SM condition, no significant impairments were observed in decision-making performance; however, visual reaction time was specifically delayed, while auditory reaction time remained unaffected, suggesting modality-specific effects of SM-induced fatigue. Visual search behaviors remained largely stable, with only marginal alterations observed in non-task-relevant areas following the Stroop task. These findings highlight the cognitive resilience and adaptive control mechanisms of elite athletes in maintaining and, in some cases, enhancing performance under mental fatigue. Future studies should integrate neurophysiological indices and manipulate motivational factors to further clarify these mechanisms across diverse athletic populations. Full article

The ability to autonomously navigate and explore complex 3D environments in a purposeful manner, while integrating visual perception with natural language interaction in a human-like way, represents a longstanding research objective in Artificial Intelligence (AI) and embodied cognition. Vision-Language Navigation (VLN) has evolved from geometry-driven to semantics-driven and, more recently, knowledge-driven approaches. With the introduction of Large Language Models (LLMs) and Vision-Language Models (VLMs), recent methods have achieved substantial improvements in instruction interpretation, cross-modal alignment, and reasoning-based planning. However, existing surveys primarily focus on traditional VLN settings and offer limited coverage of LLM-based VLN, particularly in relation to Sim2Real transfer and edge-oriented deployment. This paper presents a structured review of LLM-enabled VLN, covering four core components: instruction understanding, environment perception, high-level planning, and low-level control. Edge deployment and implementation requirements, datasets, and evaluation protocols are summarized, along with an analysis of task evolution from path-following to goal-oriented and demand-driven navigation. Key challenges, including reasoning complexity, spatial cognition, real-time efficiency, robustness, and Sim2Real adaptation, are examined. Future research directions, such as knowledge-enhanced navigation, multimodal integration, and world-model-based frameworks, are discussed. Overall, LLM-driven VLN is progressing toward deeper cognitive integration, supporting the development of more explainable, generalizable, and deployable embodied navigation systems. Full article

This paper focuses on the modeling and design of an adaptive vortex generator (AVG). The device is actuated through shape memory alloy (SMA) elements. The interest of the research community in these devices is due to their ability to improve the performance of the aircraft, directly altering and controlling the boundary layer. Their action consists of energizing the flow, thereby hindering separation. The peculiarity of the presented AVG architecture lies in its compactness and adaptability, which allows for its activation just for some specific phases that are not adequately covered by the conventional. This system can enable load alleviation in the cruise phase when a gust occurs (spoiler modality) and stall prevention in high-lift conditions (vane modality). These two working capabilities can be obtained by mounting the AVGs at different angles of incidence, with respect to the direction of the flow. The present paper is structured as follows. First, the project of RADAR, hosting the activities, is presented with specific focus on the main objectives and on the strategy of maturation of the technologies. Then, attention is paid to the simulations of the aerodynamic field produced by the AVG. These outcomes have driven the next part of the work, focusing on the identification of the architecture of the AVG. A dedicated finite element modeling approach was implemented to address the design task, even in the presence of SMA non-linear elements. Three main operational phases were simulated: (1) the stretching of the springs up to their connection to the architecture (pre-load phase); (2) the elastic recovery of the springs and the achievement of equilibrium with the hosting structure; and (3) the activation of the springs through heating to deflect the AVG. The simulations proved the capability of the system to produce the required deflection/deployment, even under the most severe load conditions. In particular, the simulations highlighted the capability of the system to produce a deflection of the vortex generator of 83.5 deg under the most severe load conditions, against the required value of 80 deg. This result was obtained by also keeping the structural safety factor at a value of four, in line with the wind tunnel facility requirement. Another key outcome of the dynamic analysis was the absence of coupling with vortex shedding, since the system resonance frequencies (135 and 415 Hz) are well outside the vortex-shedding frequency range (500–1400 Hz). Full article

Emergent tracheal intubation in critically ill patients is a common, yet high-risk, intervention. It is frequently complicated by peri-intubation hypoxemia, hemodynamic instability, and metabolic derangements that increase the risk of arrhythmias, hypotension, cardiac arrest, and death. Because the highest-risk interval often occurs in the minutes surrounding induction, when apnea, derecruitment, and abrupt cardiopulmonary shifts converge, oxygenation failure frequently reflects a mismatch between preoxygenation strategy and the underlying physiology rather than inadequate oxygen delivery alone. This review proposes a phenotype-based approach to peri-intubation oxygenation and focuses on four high-risk phenotypes in whom standard preoxygenation strategies commonly fail: obesity, neuromuscular disease, right ventricular dysfunction or pulmonary hypertension, and post-operative respiratory failure with altered respiratory mechanics or airway anatomy. We summarize the key mechanisms that shorten safe apnea time, including reduced functional residual capacity, intrapulmonary shunt, elevated oxygen consumption, rapid derecruitment after induction, and impaired oxygenation–hemodynamics coupling. We then compare preoxygenation modalities as physiologic tools, including facemask oxygen, high-flow nasal cannula (HFNC), noninvasive ventilation (NIV), and controlled bag-mask ventilation (BMV), and integrate contemporary randomized trial evidence that informs bedside selection and combination of these approaches. Finally, we synthesize these concepts into a practical, physiology-informed framework to guide clinicians in choosing and troubleshooting preoxygenation strategies in high-risk patients undergoing emergent intubation. Full article