Search Results (693)

Background: Colorectal liver metastasis (CRLM) represents a major clinical challenge in oncology, affecting 25–50% of colorectal cancer patients and significantly impacting survival. While multimodal therapies—including surgical resection, systemic chemotherapy, and local ablative techniques—have improved outcomes, prognosis remains heterogeneous due to variations in tumor biology, patient factors, and institutional practices. Methods: This review synthesizes current evidence on prognostic factors influencing CRLM management, encompassing clinical (e.g., tumor burden, anatomic distribution, timing of metastases), biological (e.g., CEA levels, inflammatory markers), and molecular (e.g., RAS/BRAF mutations, MSI status, HER2 alterations) determinants. Results: Key findings highlight the critical role of molecular profiling in guiding therapeutic decisions, with RAS/BRAF mutations predicting resistance to anti-EGFR therapies and MSI-H status indicating potential responsiveness to immunotherapy. Emerging tools like circulating tumor DNA (ctDNA) and radiomics offer promise for dynamic risk stratification and early recurrence detection, while the gut microbiome is increasingly recognized as a modulator of treatment response. Conclusions: Despite advancements, challenges persist in standardizing resectability criteria and integrating multidisciplinary approaches. Current guidelines (NCCN, ESMO, ASCO) emphasize personalized strategies but lack granularity in terms of incorporating novel biomarkers. This exhaustive review underscores the imperative for the development of a unified, biomarker-integrated framework to refine CRLM management and improve long-term outcomes. Full article

This study demonstrates the successful fabrication of high-performance reaction-bonded silicon carbide (RBSC) ceramics through an optimized liquid silicon infiltration (LSI) process employing multi-modal SiC particle gradation and nano-carbon black (0.6 µm) additives. By engineering porous preforms with hierarchical SiC distributions and tailored carbon sources, the resulting ceramics achieved a compressive strength of 2393 MPa and a flexural strength of 380 MPa, surpassing conventional RBSC systems. Microstructural analyses revealed homogeneous β-SiC formation and crack deflection mechanisms as key contributors to mechanical enhancement. Ultrafine SiC particles (0.5–2 µm) refined pore architectures and mediated capillary dynamics during infiltration, enabling nanoscale dispersion of residual silicon phases and minimizing interfacial defects. Compared to coarse-grained counterparts, the ultrafine SiC system exhibited a 23% increase in compressive strength, attributed to reduced sintering defects and enhanced load transfer efficiency. This work establishes a scalable strategy for designing RBSC ceramics for extreme mechanical environments, bridging material innovation with applications in high-stress structural components. Full article

Marine–continental transitional shale is a promising unconventional gas reservoir, playing an increasingly important role in China’s energy portfolio. However, compared to marine shale, research on marine–continental transitional shale’s fractal characteristics of pore structure and complete pore size distribution remains limited. In this work, high-pressure mercury intrusion, N₂ adsorption, and CO₂ adsorption techniques, combined with fractal geometry modeling, were employed to characterize the pore structure of the Shanxi Formation marine–continental transitional shale. The shale exhibits generally high TOC content and abundant clay minerals, indicating strong hydrocarbon-generation potential. The pore size distribution is multi-modal: micropores and mesopores dominate, contributing the majority of the specific surface area and pore volume, whereas macropores display a single-peak distribution. Fractal analysis reveals that micropores have high fractal dimensions and structural regularity, mesopores exhibit dual-fractal characteristics, and macropores show large variations in fractal dimension. Characteristics of pore structure is primarily controlled by TOC content and mineral composition. These findings provide a quantitative basis for evaluating shale reservoir quality, understanding gas storage mechanisms, and optimizing strategies for sustainable of oil and gas development in marine–continental transitional shales. Full article

With the accelerated digital transformation of the power industry, critical infrastructures such as power grids are increasingly migrating to cloud-native architectures, leading to unprecedented growth in service scale and complexity. Traditional operation and maintenance (O&M) methods struggle to meet the demands for real-time monitoring, accuracy, and scalability in such environments. This paper proposes a novel service performance anomaly detection system based on large language models (LLMs) and multi-agent systems (MAS). By integrating the semantic understanding capabilities of LLMs with the distributed collaboration advantages of MAS, we construct a high-precision and robust anomaly detection framework. The system adopts a hierarchical architecture, where lower-layer agents are responsible for tasks such as log parsing and metric monitoring, while an upper-layer coordinating agent performs multimodal feature fusion and global anomaly decision-making. Additionally, the LLM enhances the semantic analysis and causal reasoning capabilities for logs. Experiments conducted on real-world data from the State Grid Corporation of China, covering 1289 service combinations, demonstrate that our proposed system significantly outperforms traditional methods in terms of the F1-score across four platforms, including customer services and grid resources (achieving up to a 10.3% improvement). Notably, the system excels in composite anomaly detection and root cause analysis. This study provides an industrial-grade, scalable, and interpretable solution for intelligent power grid O&M, offering a valuable reference for the practical implementation of AIOps in critical infrastructures. Evaluated on real-world data from the State Grid Corporation of China (SGCC), our system achieves a maximum F1-score of 88.78%, with a precision of 92.16% and recall of 85.63%, outperforming five baseline methods. Full article

The design and optimization of drive distribution strategies are critical for enhancing the performance of Formula Student electric racing cars, which face demanding operational conditions such as rapid acceleration, tight cornering, and variable track surfaces. Given the increasing complexity of racing environments and the need for adaptive control solutions, a multi-mode adaptive drive distribution strategy for four-wheel-drive Formula Student electric racing cars is proposed in this study to meet specialized operational demands. Based on the dynamic characteristics of standardized test scenarios (e.g., straight-line acceleration and figure-eight loop), two control modes are designed: slip-ratio-based anti-slip control for longitudinal dynamics and direct yaw moment control for lateral stability. A CarSim–Simulink co-simulation platform is established, with test scenarios conforming to competition standards, including variable road adhesion coefficients (μ is 0.3–0.9) and composite curves. Simulation results indicate that, compared to conventional PID control, the proposed strategy reduces the peak slip ratio to the optimal range of 18% during acceleration and enhances lateral stability in the figure-eight loop, maintaining the sideslip angle around −0.3°. These findings demonstrate the potential for significant improvements in both performance and safety, offering a scalable framework for future developments in racing vehicle control systems. Full article

In the field of high-altitude operations, the frequent occurrence of fall accidents is usually closely related to safety measures such as the incorrect use of safety locks and the wrong installation of safety belts. At present, the manual inspection method cannot achieve real-time monitoring of the safety status of the operators and is prone to serious consequences due to human negligence. This paper designs a new type of high-altitude operation safety device based on the STM32F103 microcontroller. This device integrates ultra-wideband (UWB) ranging technology, thin-film piezoresistive stress sensors, Beidou positioning, intelligent voice alarm, and intelligent safety lock. By fusing five modes, it realizes the functions of safety status detection and precise positioning. It can provide precise geographical coordinate positioning and vertical ground distance for the workers, ensuring the safety and standardization of the operation process. This safety device adopts multi-modal fusion high-altitude operation safety monitoring technology. The UWB module adopts a bidirectional ranging algorithm to achieve centimeter-level ranging accuracy. It can accurately determine dangerous heights of 2 m or more even in non-line-of-sight environments. The vertical ranging upper limit can reach 50 m, which can meet the maintenance height requirements of most transmission and distribution line towers. It uses a silicon carbide MEMS piezoresistive sensor innovatively, which is sensitive to stress detection and resistant to high temperatures and radiation. It builds a Beidou and Bluetooth cooperative positioning system, which can achieve centimeter-level positioning accuracy and an identification accuracy rate of over 99%. It can maintain meter-level positioning accuracy of geographical coordinates in complex environments. The development of this safety device can build a comprehensive and intelligent safety protection barrier for workers engaged in high-altitude operations. Full article

Aiming at the goal of preparing high-quality coatings, this paper reviews the progress on circular arc source structure and magnetic field arc controlling technology in arc ion plating (AIP), with a focus on design characteristics of the different structures and configuration optimization of the corresponding magnetic fields. The circular arc source, due to its simple structure, convenient installation, flexible target combination, high cooling efficiency, and high ionization rate and deposition rate, has shown significant application potential in AIP technology. In terms of magnetic field arc controlling technology, this paper delves into the design progress of various magnetic field configurations, including fixed magnetic fields generated by permanent magnets, dynamic rotating magnetic fields, axially symmetric magnetic fields, rotating transverse magnetic fields, and multi-mode alternating electromagnetic coupling fields. By designing the magnetic field distribution reasonably, the trajectory and velocity of the arc spot can be controlled precisely, thus reducing the generation of macroparticles, improving target utilization, and enhancing coating uniformity. In particular, the introduction of multi-mode magnetic field coupling technology has broken through the limitations of traditional single magnetic field structures, achieving comprehensive optimization of arc spot motion and plasma transport. Hopefully, these research advances provide an important theoretical basis and technical support for the application of AIP technology in the preparation for high-quality decorative and functional coatings. Full article

To address the high false alarm rate of intrusion detection systems based on distributed acoustic sensing (DAS) for power cables in complex underground environments, an innovative GRT-Transformer multimodal deep learning model is proposed. The core of this model lies in its distinctive three-branch parallel collaborative architecture: two branches employ Gramian Angular Summation Field (GASF) and Recursive Pattern (RP) algorithms to convert one-dimensional intrusion waveforms into two-dimensional images, thereby capturing rich spatial patterns and dynamic characteristics and the third branch utilizes a Gated Recurrent Unit (GRU) algorithm to directly focus on the temporal evolution features of the waveform; additionally, a Transformer component is integrated to capture the overall trend and global dependencies of the signals. Ultimately, the terminal employs a Bidirectional Long Short-Term Memory (BiLSTM) network to perform a deep fusion of the multidimensional features extracted from the three branches, enabling a comprehensive understanding of the bidirectional temporal dependencies within the data. Experimental validation demonstrates that the GRT-Transformer achieves an average recognition accuracy of 97.3% across three typical intrusion events—illegal tapping, mechanical operations, and vehicle passage—significantly reducing false alarms, surpassing traditional methods, and exhibiting strong practical potential in complex real-world scenarios. Full article

The exponential growth of video data across domains such as surveillance, transportation, and healthcare has raised critical challenges in scalability, real-time processing, and privacy preservation. While existing studies have addressed individual aspects of Video Big Data Analytics (VBDA), an integrated, up-to-date perspective remains limited. This paper presents a comprehensive survey of system architectures and enabling technologies in VBDA. It categorizes system architectures into four primary types as follows: centralized, cloud-based infrastructures, edge computing, and hybrid cloud–edge. It also analyzes key enabling technologies, including real-time streaming, scalable distributed processing, intelligent AI models, and advanced storage for managing large-scale multimodal video data. In addition, the study provides a functional taxonomy of core video processing tasks, including object detection, anomaly recognition, and semantic retrieval, and maps these tasks to real-world applications. Based on the survey findings, the paper proposes ViMindXAI, a hybrid AI-driven platform that combines edge and cloud orchestration, adaptive storage, and privacy-aware learning to support scalable and trustworthy video analytics. Our analysis in this survey highlights emerging trends such as the shift toward hybrid cloud–edge architectures, the growing importance of explainable AI and federated learning, and the urgent need for secure and efficient video data management. These findings highlight key directions for designing next-generation VBDA platforms that enhance real-time, data-driven decision-making in domains such as public safety, transportation, and healthcare. These platforms facilitate timely insights, rapid response, and regulatory alignment through scalable and explainable analytics. This work provides a robust conceptual foundation for future research on adaptive and efficient decision-support systems in video-intensive environments. Full article

The rapid spread of COVID-19 increased the need for speedy diagnostic tools, which led scientists to conduct extensive research on deep learning (DL) applications that use chest imaging, such as chest X-ray (CXR) and computed tomography (CT). This review examines the development and performance of DL architectures, notably convolutional neural networks (CNNs) and emerging vision transformers (ViTs), in identifying COVID-19-related lung abnormalities. Individual ResNet architectures, along with CNN models, demonstrate strong diagnostic performance through the transfer protocol; however, ViTs provide better performance, with improved readability and reduced data requirements. Multimodal diagnostic systems now incorporate alternative methods, in addition to imaging, which use lung ultrasounds, clinical data, and cough sound evaluation. Information fusion techniques, which operate at the data, feature, and decision levels, enhance diagnostic performance. However, progress in COVID-19 detection is hindered by ongoing issues stemming from restricted and non-uniform datasets, as well as domain differences in image standards and complications with both diagnostic overfitting and poor generalization capabilities. Recent developments in COVID-19 diagnosis involve constructing expansive multi-noise information sets while creating clinical process-oriented AI algorithms and implementing distributed learning protocols for securing information security and system stability. While deep learning-based COVID-19 detection systems show strong potential for clinical application, broader validation, regulatory approvals, and continuous adaptation remain essential for their successful deployment and for preparing future pandemic response strategies. Full article

Accurate sleep staging and sleep-disordered breathing (SDB) severity prediction are critical for the early diagnosis and management of sleep disorders. However, real-world polysomnography (PSG) data often suffer from modality heterogeneity, label scarcity, and non-independent and identically distributed (non-IID) characteristics across institutions, posing significant challenges for model generalization and clinical deployment. To address these issues, we propose a federated multi-task learning (FMTL) framework that simultaneously performs sleep staging and SDB severity classification from seven multimodal physiological signals, including EEG, ECG, respiration, etc. The proposed framework is built upon a hybrid deep neural architecture that integrates convolutional layers (CNN) for spatial representation, bidirectional GRUs for temporal modeling, and multi-head self-attention for long-range dependency learning. A shared feature extractor is combined with task-specific heads to enable joint diagnosis, while the FedAvg algorithm is employed to facilitate decentralized training across multiple institutions without sharing raw data, thereby preserving privacy and addressing non-IID challenges. We evaluate the proposed method across three public datasets (APPLES, SHHS, and HMC) treated as independent clients. For sleep staging, the model achieves accuracies of 85.3% (APPLES), 87.1% (SHHS_rest), and 79.3% (HMC), with Cohen’s Kappa scores exceeding 0.71. For SDB severity classification, it obtains macro-F1 scores of 77.6%, 76.4%, and 79.1% on APPLES, SHHS_rest, and HMC, respectively. These results demonstrate that our unified FMTL framework effectively leverages multimodal PSG signals and federated training to deliver accurate and scalable sleep disorder assessment, paving the way for the development of a privacy-preserving, generalizable, and clinically applicable digital sleep monitoring system. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

We present a formal framework for modeling neural network dynamics using Category Theory, specifically through Markov categories. In this setting, neural states are represented as objects and state transitions as Markov kernels, i.e., morphisms in the category. This categorical perspective offers an algebraic alternative to traditional approaches based on stochastic differential equations, enabling a rigorous and structured approach to studying neural dynamics as a stochastic process with topological insights. By abstracting neural states as submeasurable spaces and transitions as kernels, our framework bridges biological complexity with formal mathematical structure, providing a foundation for analyzing emergent behavior. As part of this approach, we incorporate concepts from Interacting Particle Systems and employ mean-field approximations to construct Markov kernels, which are then used to simulate neural dynamics via the Ising model. Our simulations reveal a shift from unimodal to multimodal transition distributions near critical temperatures, reinforcing the connection between emergent behavior and abrupt changes in system dynamics. Full article

Multi-modal remote sensing image (MRSI) matching suffers from severe nonlinear radiometric distortions and geometric deformations, and conventional feature-based techniques are generally ineffective. This study proposes a novel and robust MRSI matching method using the side window filter (MSWF). First, a novel side window scale space is constructed based on the side window filter (SWF), which can preserve shared image contours and facilitate the extraction of feature points within this newly defined scale space. Second, noise thresholds in phase congruency (PC) computation are adaptively refined with the Weibull distribution; weighted phase features are then exploited to determine the principal orientation of each point, from which a maximum index map (MIM) descriptor is constructed. Third, coarse position, orientation, and scale information obtained through global matching are employed to estimate image-pair geometry, after which descriptors are recalculated for precise correspondence search. MSWF is benchmarked against eight state-of-the-art multi-modal methods—six hand-crafted (PSO-SIFT, LGHD, RIFT, RIFT2, HAPCG, COFSM) and two learning-based (CMM-Net, RedFeat) methods—on three public datasets. Experiments demonstrate that MSWF consistently achieves the highest number of correct matches (NCM) and the highest rate of correct matches (RCM) while delivering the lowest root mean square error (RMSE), confirming its superiority for challenging MRSI registration tasks. Full article

Many radar applications rely primarily on visual classification for their evaluations. However, new research is integrating textual descriptions alongside visual input and showing that such multimodal fusion improves contextual understanding. A critical issue in this area is the effective alignment of coded text with corresponding images. To this end, our paper presents an adversarial training framework that generates descriptive text from the latent space of a visual radar classifier. Our quantitative evaluations show that this dual-task approach maintains a robust classification accuracy of 98.3% despite the inclusion of Gaussian-distributed latent spaces. Beyond these numerical validations, we conduct a qualitative study of the text output in relation to the classifier’s predictions. This analysis highlights the correlation between the generated descriptions and the assigned categories and provides insight into the classifier’s visual interpretation processes, particularly in the context of normally uninterpretable radar data. Full article