Search Results (5,343)

Considering the nonlinear trends, multi-scale variations, and capacity regeneration phenomena exhibited by battery capacity degradation under real-world conditions, accurately predicting its trajectory remains a critical challenge for ensuring the reliability and safety of electric vehicles. To address this, this study proposes a hybrid prediction framework based on Variational Mode Decomposition and a Transformer–Long Short-Term Memory architecture. Specifically, the proposed Variational Mode Decomposition–Transformer for Time Series–Long Short-Term Memory (VMD–TTS–LSTM) framework first decomposes the capacity sequence using Variational Mode Decomposition. The resulting modal components are then aggregated into high-frequency and low-frequency parts based on their frequency centroids, followed by targeted feature analysis for each part. Subsequently, a simplified Transformer encoder (Transformer for Time Series, TTS) is employed to model high-frequency fluctuations, while a Long Short-Term Memory (LSTM) network captures the long-term degradation trends. Evaluated on charging data from 20 commercial electric vehicles under a long-horizon setting of 20 input steps predicting 100 steps ahead, the proposed method achieves a mean absolute error of 0.9247 and a root mean square error of 1.0151, demonstrating improved accuracy and robustness. The results confirm that the proposed frequency-partitioned, heterogeneous modeling strategy provides a practical and effective solution for battery health prediction and energy management in real-world electric vehicle operation. Full article

Respiratory disorders remain a major cause of morbidity and mortality in neonatal intensive care units, particularly among preterm infants. Advances in physiological monitoring, medical imaging, and electronic health records have enabled the growing application of artificial intelligence in neonatal respiratory care. This narrative review summarizes current applications and emerging directions of artificial intelligence in the diagnosis, monitoring, and management of neonatal respiratory disorders. Machine learning and deep learning approaches have demonstrated promising performance in respiratory distress syndrome, bronchopulmonary dysplasia, apnea of prematurity, ventilatory management, and severe respiratory complications. By integrating multimodal clinical, physiological, and imaging data, these methods support earlier detection of respiratory deterioration and improved clinical decision-making. However, challenges related to data quality, generalizability, interpretability, and limited prospective validation continue to constrain widespread clinical implementation, highlighting the need for careful integration into neonatal care workflows. Full article

Industrial Control Systems (ICSs) are critical infrastructure for maintaining social and economic stability, but they face increasing security threats that require robust anomaly detection mechanisms. Anomaly detection in ICS, based on sensor data, is essential for identifying abnormal behaviors caused by factors such as equipment failures, cyber-attacks, and operational mistakes. However, industrial time series data are often multimodal, noisy, and exhibit both short-term fluctuations and long-term dependencies, making them difficult to model effectively. Additionally, ICS data often contain high-frequency noise and complex periodic patterns, which traditional methods and standalone models, such as Long Short-Term Memory (LSTM), fail to capture effectively. To address these challenges, we propose a novel anomaly detection framework that leverages Gated Recurrent Units for short-term dynamics and PatchTST for long-term dependencies. The GRU module extracts dynamic short-term features, while PatchTST models long-term dependencies by segmenting the feature sequence processed by GRU into overlapping patches. Additionally, we innovatively introduce Frequency-Enhanced Channel Attention Module to capture frequency domain features, mitigating high-frequency noise and enhancing the model’s ability to detect long-term trends and periodic patterns. Experimental results on the SWaT and WADI datasets show that the proposed method achieves strong anomaly detection performance, attaining F1 scores of 0.929 and 0.865, respectively, which are superior to those of representative existing methods, demonstrating the effectiveness of the proposed design for robust anomaly detection in complex ICS environments. Full article

Interferometric Synthetic Aperture Radar (InSAR) is an advanced imaging geodesy technique for detecting and characterizing surface deformation with high spatial resolution and broad spatial coverage. However, as an inherently post-event observation method, InSAR suffers from limited capability for near-real-time and short-term updates of deformation time series. In this paper, we proposed a data-driven adaptive framework for deformation prediction based on a hybrid deep learning method to accurately predict the InSAR-derived deformation time series and take the Xi’erguazi−Mawo landslide complex (XMLC) as a case study. The InSAR-derived time series was initially decomposed into trend and periodic components with a two-step decomposition process, which were thereafter modeled separately to enhance the characterization of motion kinematics and prediction accuracy. After retrieving the observations from the multi-temporal InSAR method, two-step signal decomposition was then performed using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD). The decomposed trend and periodic components were further evaluated using statistical hypothesis testing to verify their significance and reliability. Compared with the single-decomposition model, the further decomposition leads to an overall improvement in prediction accuracy, i.e., the Mean Absolute Errors (MAEs) and the Root Mean Square Errors (RMSEs) are reduced by 40–49% and 36–42%, respectively. Subsequently, the Radial Basis Function (RBF) neural network and the proposed CNN-BiLSTM-SelfAttention (CBS) models were constructed to predict the trend and periodic variations, respectively. The CNN and self-attention help to extract local features in time series and strengthen the ability to capture global dependencies and key fluctuation patterns. Compared with the single network model in prediction, the MAEs and RMSEs are reduced by 22–57% and 4–33%, respectively. Finally, the two predicted components were integrated to generate the fused deformation prediction results. Ablation experiments and comparative experiments show that the proposed method has superior ability. Through rapid and accurate prediction of InSAR-derived deformation time series, this research could contribute to the early-warning systems of slope instabilities. Full article

Fibromyalgia is a chronic condition characterized by widespread pain, fatigue, and reduced quality of life. Exercise therapy, including Pilates, is commonly recommended; however, current reviews report inconsistent findings across specific modalities. This PRISMA 2020 systematic review and meta-analysis with a PROSPERO-registered protocol, designed as a focused update of post-2020 RCTs complementing prior comprehensive syntheses, evaluated Pilates-based interventions for pain and fibromyalgia impact (FIQ). HRQoL outcomes were synthesized narratively due to heterogeneity in measurement instruments, and all outcomes were extracted at the first post-intervention assessment (no pooled long-term data were available). Seven RCTs (6–12 weeks; 2–3 sessions/week) met eligibility criteria. Methodological quality was generally moderate (PEDro), and risk of bias was assessed using RoB 2. Certainty of evidence (GRADE) was rated very low for pain and low for FIQ. Among trials reporting adherence (4/7), values ranged from 68% to 92%; adverse event monitoring was inconsistent (systematically reported in 2/7), limiting tolerability conclusions. Between-group effects versus active comparators were small and non-significant for pain (pooled Hedges’ g = −0.10, 95% CI [−0.83, 0.63], p = 0.79; I² = 73%); this wide interval, spanning potential benefit to harm, precludes definitive conclusions. For FIQ, the primary (unadjusted) analysis was non-significant: pooled MD = −5.53 (95% CI [−11.96, 0.89], p = 0.09); sensitivity analysis using ANCOVA-adjusted estimates yielded MD = −6.71 (95% CI [−13.11, −0.30], p = 0.04). Both estimates remained below MCID thresholds and were sensitive to estimator choice. Absence of statistical significance does not demonstrate equivalence; non-inferiority designs with predefined margins would be required. Given very low (pain) to low (FIQ) certainty of evidence, adequately powered trials with standardized protocols and longer follow-up are needed to resolve uncertainty regarding Pilates’ comparative effectiveness within multimodal fibromyalgia management. Full article

Digital technologies that continuously quantify animal behavior, physiology, and production offer significant potential for the early identification of health and welfare disorders of dairy cows. In this study, a multimodal artificial intelligence (AI) framework is proposed for real-time health monitoring of dairy cows through the integration of physiological, behavioral, production, and thermal imaging data, targeting veterinarian-confirmed udder, leg, and hoof infections. Predictions are generated at the cow-day level by aggregating multimodal measurements collected during daily milking events. The dataset comprised 88 lactating cows, including veterinarian-confirmed udder, leg, and hoof infections grouped under a single ‘sick’ label. To prevent information leakage, model evaluation was performed using a cow-level data split, ensuring that data from the same animal did not appear in both training and testing sets. The system is designed to detect early deviations from normal health trajectories prior to the appearance of overt clinical symptoms. All measurements, with the exception of the intra-ruminal bolus sensor, were obtained non-invasively within a commercial dairy farm equipped with automated milking and monitoring infrastructure. A key novelty of this work is the simultaneous integration of data from three independent sources: an automated milking system, a thermal imaging camera, and an intra-ruminal bolus sensor. A hybrid deep learning architecture is introduced that combines the core components of established models, including U-Net, O-Net, and ResNet, to exploit their complementary strengths for the analysis of dairy cow health states. The proposed multimodal approach achieved an overall accuracy of 91.62% and an AUC of 0.94 and improved classification performance by up to 3% compared with single-modality models, demonstrating enhanced robustness and sensitivity to early-stage disease. Full article

The complex environment of electrical work sites presents hazards that are diverse in form, easily concealed, and difficult to distinguish from their surroundings. Due to poor model generalization, most traditional visual recognition methods are prone to errors and cannot meet the current safety management needs in electrical work. This paper presents a novel framework for hazard identification that integrates chain-of-thought reasoning and self-verification mechanisms within a visual-language large model (VLLM) to enhance accuracy. First, typical hazard scenario data for crane operation and escalator work areas were collected. The Janus-Pro VLLM model was selected as the base model for hazard identification. Then, designing a chain-of-thought enhanced the model’s capacity to identify critical information, including the status of crane stabilizers and the zones where personnel are located. Simultaneously, a self-verification module was designed. It leveraged the multimodal comprehension capabilities of the VLLM to self-check the identification results, outputting confidence scores and justifications to mitigate model hallucination. The experimental results show that integrating the self-verification method significantly improves hazard identification accuracy, with average increases of 2.55% in crane operations and 4.35% in escalator scenarios. Compared with YOLOv8s and D-FINE, the proposed framework achieves higher accuracy, reaching up to 96.3% in crane personnel intrusion detection, and a recall of 95.6%. It outperforms small models by 8.1–13.8% in key metrics without relying on massive labeled data, providing crucial technical support for power operation hazard identification. Full article

Non-invasive electrocardiogram (ECG) and respiratory signals are easy to acquire via low-cost sensors, making them promising alternatives for sleep staging. However, existing methods using these signals often yield insufficient accuracy. To address this challenge, we incrementally optimized the sleep staging model by designing a structured experimental workflow: we first preprocessed respiratory and ECG signals, then extracted fused features using an enhanced feature selection technique, which not only reduces redundant features, but also significantly improves the class discriminability of features. The resulting fused features serve as a reliable feature subset for the classifier. In the meantime, we proposed a hybrid optimization algorithm that integrates the snake optimization algorithm (SO) and ant colony optimization algorithm (ACO) for automated hyperparameter optimization of support vector machines (SVMs). Experiments were conducted using two PSG-derived public datasets, the Sleep Heart Health Study (SHHS) and MIT-BIH Polysomnography Database (MIT-BPD), to evaluate the classification performance of multimodal features compared with single-modal features. Results demonstrate that the bimodal staging using SHHS multimodal signals significantly outperformed single-modal ECG-based methods, and the overall accuracy of the SHHS dataset was improved by 12%. The SVM model optimized using the hybrid Snake–ACO algorithm achieved an average accuracy of 89.6% for wake versus sleep classification on the SHHS dataset, representing a 5.1% improvement over traditional grid search methods. Under the subject-independent partitioning experiment, the wake versus sleep classification task maintained good stability with only a 1.8% reduction in accuracy. This study provides novel insights for non-invasive sleep monitoring and clinical decision support. Full article

Rapid urbanization and spatial constraints in high-density residential areas pose significant challenges to public health and well-being. This study investigates the mechanisms by which the visual environment of urban micro public spaces shapes residents’ psychophysiological responses to encourage spontaneous physical activity and advance active health. Using machine learning and 11-based semantic segmentation, 9 core visual elements across 20 micro public space scenes in high-density urban neighborhoods were quantified. An immersive virtual reality (VR) experiment was conducted, collecting synchronized multimodal psychophysiological data from 60 participants, which yielded 600 valid observations. Through an analytical framework combining Self-Organizing Map (SOM) clustering and Random Forest (RF) modeling, three distinct functional archetypes were identified: Restoration-Supporting, Activity-Promoting, and Stress-Inducing. The Activity-Promoting archetype was most effective in fostering spontaneous activity intention, characterized by a high proportion of activity areas, a moderate sky view factor, and minimal physical barriers. RF modeling further pinpointed pedestrian density, activity area ratio, and green space ratio as key visual drivers of health-promoting outcomes. Based on these findings, a “Visual Activation for Active Health” framework is proposed. It posits that moderate visual-environmental stimulation is the core mechanism for transforming passive spaces into health-promotive settings, thereby establishing a theoretical foundation for the evidence-based design of healthy and sustainable urban environments. Full article

Infertility affects 10–30% of couples globally, with significant psychological and social impacts in sub-Saharan Africa, where fertility is closely tied to identity and social status. To explore how couples’ understanding of infertility causes influences their treatment-seeking behaviours and healthcare decision-making processes in Ghana, this cross-sectional qualitative study used in-depth interviews with 24 married participants (nine dyads and six individuals) experiencing current or past infertility in Greater Accra, Ghana, from August to October 2023. Data were analysed using thematic analysis with NVivo version 15. Couples demonstrated comprehensive knowledge of infertility causes spanning medical, spiritual, cultural, and lifestyle factors, although they lacked knowledge of clinical diagnostic criteria. Three main treatment pathways emerged: medical/orthodox, herbal, and spiritual interventions, pursued either sequentially or concurrently. Decision-making was influenced by internal factors (treatment effectiveness, financial constraints, and safety concerns) and external factors (family influence and peer testimonials). Four distinct navigation strategies were identified: informed notification, trial periods and evaluation, parallel relationship management, and strategic sequencing. Couples experiencing infertility are sophisticated healthcare consumers who skilfully navigate pluralistic healthcare systems through strategic decision-making. Rather than representing non-compliance, their multimodal approaches reflect rational responses to structural constraints and cultural values. Healthcare systems should recognise and accommodate these navigation strategies to improve therapeutic relationships and outcomes. Full article

Background and Objective: Postoperative hospital length of stay (LOS) reflects surgical recovery and resource demand but remains difficult to predict due to heterogeneous perioperative trajectories. We aimed to develop and validate an interpretable machine learning framework that integrates multimodal perioperative data to accurately predict LOS and uncover clinically meaningful drivers of prolonged hospitalization. Methods: We studied 97,937 adult surgical cases from a large perioperative registry. Routinely collected perioperative data included patient demographics, comorbid conditions, preoperative laboratory values, intraoperative physiologic summaries, and procedural characteristics. Length of stay was modeled using a supervised regression approach with internal cross-validation and independent holdout evaluation. Model performance was assessed at both the cohort and individual levels, and explanatory analyses were performed to quantify the contribution of clinically defined perioperative domains. Results: The model achieved R² = 0.61 and MAE ≈ 1.34 days on the holdout set, with nearly identical cross-validation performance (R² = 0.60, MAE ≈ 1.34 days). Operative duration, diagnostic complexity, intraoperative hemodynamic variability, and preoperative laboratory indices—particularly albumin and hematocrit—emerged as the strongest determinants of postoperative stay. Patients with shorter recoveries typically had brief operations, stable physiology, and normal laboratory profiles, whereas prolonged hospitalization was linked to complex procedures, malignant or respiratory diagnoses, and lower albumin levels. Conclusions: Interpretable machine learning enables accurate and generalizable estimation of postoperative LOS while revealing clinically actionable perioperative domains. Such frameworks may facilitate more efficient perioperative planning, improved allocation of hospital resources, and personalized recovery strategies. Full article

The cutterhead torque of a full-face tunnel boring machine (TBM) is a pivotal parameter that characterises the rock-machine interaction. Its dynamic prediction is of considerable significance to achieve intelligent regulation of the boring parameters and enhance the construction efficiency and safety. In order to achieve high-precision time series prediction of cutterhead torque under complex geological conditions, this study proposes an intelligent prediction method (VBGAP) that integrates signal decomposition mechanism and physical constraints. At the data preprocessing level, a multi-step data cleaning process is designed. This process comprises the following steps: the processing of invalid values, the detection of outliers, and normalisation. The non-smooth torque time-series signal is decomposed by variational mode decomposition (VMD) into narrow-band sub-signals that serve as a data-driven, frequency-specific input for subsequent modelling, and a hybrid deep learning model based on Bi-GRU and self-attention mechanism is built for each sub-signal. Finally, the prediction results of each component are linearly superimposed to achieve signal reconstruction. Concurrently, a novel modal energy conservation loss function is proposed, with the objective of effectively constraining the information entropy decay in the decomposition-reconstruction process. The validity of the proposed method is supported by empirical evidence from a real tunnel project dataset in Northeast China, which demonstrates an average accuracy of over 90% in a multi-step prediction task with a time step of 30 s. This suggests that the proposed method exhibits superior adaptability and prediction accuracy in comparison to existing mainstream deep learning models. The findings of the research provide novel concepts and methodologies for the intelligent regulation of TBM boring parameters. Full article

Large Language Model (LLM) agents depend heavily on multiple external tools such as APIs, databases and computational services to perform complex tasks. However, these tool executions create latency and introduce costs, particularly when agents handle similar queries or workflows. Most current caching methods focus on LLM prompt–response pairs or execution plans and overlook redundancies at the tool level. To address this, we designed a multi-level caching architecture that captures redundancy at both the workflow and tool level. The proposed system integrates four key components: (1) hierarchical caching that operates at both the workflow and tool level to capture coarse and fine-grained redundancies; (2) dependency-aware invalidation using graph-based techniques to maintain consistency when write operations affect cached reads across execution contexts; (3) category-specific time-to-live (TTL) policies tailored to different data types, e.g., weather APIs, user location, database queries and filesystem and computational tasks; and (4) session isolation to ensure multi-tenant cache safety through automatic session scoping. We evaluated the system using synthetic data with 2.25 million queries across ten configurations in fifteen runs. In addition, we conducted four targeted evaluations—write intensity robustness from 4 to 30% writes, personalized memory effects under isolated vs. shared cache modes, workflow-level caching comparison and workload sensitivity across five access distributions—on an additional 2.565 million queries, bringing the total experimental scope to 4.815 million executed queries. The architecture achieved 76.5% caching efficiency, reducing query processing time by 13.3× and lowering estimated costs by 73.3% compared to a no-cache baseline. Multi-tenant testing with fifteen concurrent tenants confirmed robust session isolation and 74.1% efficiency under concurrent workloads. Our evaluation used controlled synthetic workloads following Zipfian distributions, which are commonly used in caching research. While absolute hit rates vary by deployment domain, the architectural principles of hierarchical caching, dependency tracking and session isolation remain broadly applicable. Full article

Urban intersections are critical nodes for roadway safety, congestion management, and autonomous vehicle coordination. Traditional traffic control systems based on fixed-time signals and static sensors lack adaptability to real-time risks such as red-light violations, near-miss incidents, and multimodal conflicts. This study presents a grid-enabled framework integrating computer vision and machine learning to enhance real-time intersection intelligence and road safety. The system overlays a computational grid on the roadway, processes live video feeds, and extracts dynamic parameters including vehicle trajectories, deceleration patterns, and queue evolution. A novel active learning module improves detection accuracy under low visibility and occlusion, reducing false alarms in collision and violation detection. Designed for edge-computing environments, the framework interfaces with signal controllers to enable adaptive signal timing, proactive collision avoidance, and emergency vehicle prioritization. Case studies from multiple intersections typical of US cities show improved phase utilization, reduced intersection conflicts, and enhanced throughput. A grid-based heatmap visualization highlights spatial risk zones, supporting data-driven decision-making. The proposed framework bridges static infrastructure and intelligent mobility systems, advancing safer, smarter, and more connected roadway operations. Full article

Over the past decades, remarkable progress in multimodal therapy has significantly improved survival outcomes for children with cancer. Yet, considerable variability in treatment response and toxicity persists, often driven by underlying genetic differences that affect the pharmacokinetics and pharmacodynamics of anticancer drugs. Pharmacogenomics, the study of genetic determinants of drug response, offers a powerful approach to personalize pediatric cancer therapy by optimizing efficacy while minimizing adverse effects. This review synthesizes current evidence on key pharmacogenetic variants influencing the response to major classes of antineoplastic agents used in children, including thiopurines, methotrexate, anthracyclines, alkylating agents, vinca alkaloids, and platinum compounds. Established gene–drug associations such as TPMT, NUDT15, DPYD, SLC28A3, and RARG are discussed alongside emerging biomarkers identified through genome-wide and multi-omics studies. The review also examines the major challenges that impede clinical implementation, including infrastructural limitations, cost constraints, population-specific variability, and ethical considerations. Furthermore, it highlights how integrative multi-omics, systems pharmacology, and artificial intelligence may accelerate the translation of pharmacogenomic data into clinical decision-making. The integration of pharmacogenomic testing into pediatric oncology protocols has the potential to transform cancer care by improving drug safety, enhancing treatment precision, and paving the way toward ethically grounded, personalized therapy for children. Full article