Search Results (95)

Biochemical detection is fundamental to various scientific disciplines, yet conventional methods still face inherent bottlenecks in achieving rapid, ultrasensitive, and simultaneous multi-target analysis. Terahertz (THz) waves, characterized by their unique spectral fingerprinting capabilities and non-destructive properties, have emerged as a compelling platform for advanced biochemical sensing. This review outlines the evolution of THz biochemical sensing over the past two decades, tracing its progression from passive identification toward intelligent perception. We structure this technological trajectory around four core themes: sensitivity enhancement, specific recognition, multi-target visualization, and system intelligence. We first evaluate the fundamental limitations of direct detection techniques, such as THz time-domain spectroscopy (THz-TDS). Building on this, we examine how metamaterial-assisted architectures utilize high-quality-factor resonances to achieve trace-level detection, pushing the limits of detection (LOD) down to the ng/mL or even pg/mL scale, and how surface chemical functionalization provides a molecular lock mechanism for selective targeting in complex samples. Furthermore, we highlight the paradigm shift from single-point spectral measurements to spatially resolved multi-target imaging using pixelated metasurfaces. Finally, the review addresses emerging directions, including dynamically tunable intelligent metasurfaces, multimodal on-chip integration platforms, and the growing integration of artificial intelligence (AI) in inverse design and data interpretation, which achieves classification accuracies exceeding 95% even in complex matrices. By synthesizing these developments, this review provides a comprehensive perspective on the future trajectory of THz sensing technologies. Full article

The query propagation paradigm provides a unified theoretical framework for end-to-end multi-object tracking, yet it still faces challenges in complex scenarios involving multi-scale variations, dense interactions, and trajectory fragmentation, including insufficient query initialization quality, imprecise feature alignment, and difficult identity recovery. Building upon MOTRv2, this paper proposes three core improvements. First, we design a geometric prior injection strategy based on sine–cosine encoding, which explicitly encodes target location and scale information into detection queries, providing high-quality initialization for tracking queries. Second, we propose a width–height-modulated deformable attention mechanism that dynamically adjusts the sampling range of deformable convolution according to target size, enabling fine-grained feature matching for multi-scale targets. Third, we construct a motion-direction-consistency-based trajectory re-association module that leverages motion continuity to efficiently recover lost trajectories without introducing additional appearance models. Furthermore, we introduce a progressive joint training strategy that optimizes detection and tracking modules in stages, effectively mitigating gradient competition in multi-task learning. Extensive quantitative and qualitative experiments on the BEE24, UAVSwarm, and VTMOT infrared datasets validate the effectiveness of the proposed method. On the UAVSwarm dataset, our method achieves state-of-the-art performance with 52.4% HOTA, 72.1% MOTA, and only 51 identity switches. Ablation studies further reveal the synergistic enhancement mechanism among the proposed modules. Full article

Industrialization has led to the substantial release of heavy metals and organic pollutants into soil and groundwater, resulting in severe contaminated site issues that pose significant threats to ecosystems and human health. This review aims to systematically review the current development status and challenges of contaminated site remediation technologies, and explore the potential of artificial intelligence (AI) applications in site remediation, to provide a theoretical reference for advancing intelligent remediation. Conventional remediation technologies mainly include physical methods (e.g., solidification/stabilization (S/S), soil vapor extraction (SVE), thermal desorption, pump and treat (P&T), groundwater circulation wells (GCWs)), chemical methods (e.g., chemical oxidation/reduction, electrokinetic remediation (EKR), soil washing), and biological methods (phytoremediation, microbial remediation), along with combined strategies that integrate multiple approaches. Although these technologies have achieved certain successes in engineering practice, they still face common challenges such as risks of secondary pollution, long remediation periods, high costs, poor adaptability to complex hydrogeological conditions, and insufficient long-term stability, making it difficult to fully meet the remediation demands of complex contaminated sites. Subsequently, the potential of emerging technologies—including nanomaterial-based remediation, bioelectrochemical systems, and molecular biology-assisted remediation—is introduced. On this basis, the forefront applications of AI in contaminated site remediation are discussed, covering site monitoring and characterization, risk assessment, remedial strategy selection, process prediction and parameter optimization, material design, and post-remediation intelligent stewardship. Machine learning (ML), explainable AI (XAI), and hybrid modeling approaches have markedly improved remediation efficiency and decision-making. Looking forward, with advancements in XAI, mechanism-data fusion models, and environmental foundation models, AI is poised to drive a paradigm shift toward intelligent and precision remediation. However, challenges related to data quality, model interpretability, and interdisciplinary expertise remain key barriers to overcome. Full article

Multi-Object Tracking (MOT) is a fundamental research topic in the field of computer vision, with broad application potential in unmanned aerial vehicle (UAV) videos. However, existing methods still face significant challenges in detection discriminability and identity association stability due to the small scale and weak appearance of objects under aerial viewpoints, as well as complex background interference. To address these issues, we propose an Edge-Graph Enhanced Network (EGEN) for UAV aerial MOT, aiming to improve the performance of small object detection (SOD) and tracking in complex scenes. The framework follows a one-step tracking paradigm and consists of three main components: object detection, embedding feature extraction, and data association. In the detection stage, we design an Edge-Guided Gaussian Enhancement Module (EGGEM), which models edge relationships between objects and backgrounds from a global perspective and selectively enhances Gaussian features guided by edge information, thereby strengthening key structural features of small objects while suppressing background interference. In the embedding feature extraction stage, we develop a Graph-Guided Embedding Enhancement Module (GGEEM), which explicitly represents re-identification (ReID) embeddings as a graph structure and jointly models nodes and their neighborhood relationships to fully capture inter-object associations and enhance embedding discriminability. In the data association stage, we introduce a hierarchical two-stage association strategy to match objects with different confidence levels separately, improving tracking stability and robustness. Extensive experiments on the VisDrone, UAVDT, and self-constructed WildDrone datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both SOD and MOT, demonstrating strong generalization and practical applicability. Full article

Accurate state of health (SOH) assessment is the cornerstone for ensuring the safety, reliability, and lifecycle value prediction of electric vehicles. While extensive research has demonstrated the significant advantages of data-driven approaches in SOH evaluation, the vast majority of work still relies on standardized test data obtained under laboratory conditions. These ideal conditions, including complete charge–discharge cycles and constant temperatures, are often unattainable in real-world operation where EV batteries face highly irregular driving patterns, fragmented charging segments, and unpredictable environmental disturbances. This paper provides a comprehensive and systematic overview of data-driven SOH assessment based on real-vehicle data, aiming to address the current research gap in unified laboratory-to-vehicle transfer frameworks. This paper first reviews existing SOH evaluation methodologies and highlights the challenges encountered when transitioning to real-world vehicle data. It delves into core technical challenges and solutions across the entire real-world SOH assessment chain, closely examining the complex characteristics of real-world data. The paper thoroughly evaluates the role of cutting-edge paradigms including weakly supervised, self-supervised, and transfer learning in mitigating label scarcity. We summarize a unified evaluation framework tailored for real-world scenarios: Vehicles-Out, Time-Rolling, Domain-Stratified (VTDS). This framework aims to systematically assess models’ generalization limits and engineering deployability across vehicles, time, and operating conditions. This work provides systematic guidance for researchers and practitioners, advancing data-driven SOH evaluation methods from theoretical research to engineering applications. Full article

Industrial Quality Inspection (IQI) is a pivotal part of intelligent manufacturing, critical to ensuring product quality. Deep learning-based methods have attracted growing attention for their excellent feature extraction ability, outperforming traditional detection approaches. However, existing methods still face issues of insufficient efficiency and poor transferability, and this paper proposes a Fine-tuned Lightweight Faster RCNN (FLF-RCNN) framework designed to address key challenges in IQI, including the trade-off between accuracy and computational efficiency, and the insufficient adaptability of preset anchor box ratios. FLF-RCNN introduces a lightweight backbone network, LSNet, which enhances the receptive field through architectural optimization. Specifically, it uses a collaborative mechanism that combines large kernel convolutions for extracting contextual information and small kernel convolutions for capturing fine-grained details. This mechanism enables the model to efficiently and precisely represent defects. To enhance generalization in data-scarce industrial scenarios, the framework leverages transfer learning with pretrained weights. Furthermore, an Adaptive Anchor Box-Adjustment Module (AAB-AM) based on K-means clustering is introduced to improve detection across varied defect scales. Extensive experiments conducted on the Tianchi dataset show that FLF-RCNN achieves a mAP50 of 43.6%, outperforming detectors using MobileNet and EfficientNet backbones and surpassing the baseline Faster R-CNN by 7.9% in mAP50. Meanwhile, the proposed method reduces computational complexity by approximately 40%, reaching 98.65 GFLOPs, and decreases parameter count by around 30% to 28.2M. These results demonstrate that FLF-RCNN offers a feasibility and practical solution for IQI, achieving a superior accuracy-efficiency balance within the two-stage detection paradigm. Full article

As a mesh-free solving paradigm, Physics-Informed Neural Networks (PINNs) demonstrate potential in both forward and inverse problems by embedding physical equations into the loss function. However, they still face challenges in capturing the spatiotemporal evolution of complex physical processes. When applied to time-dependent complex flows, such as high-Reynolds-number cylinder flow, they often rely on supervised data, which is frequently difficult to obtain accurately in practice. To address these issues, this paper proposes a novel unsupervised solving framework—the Adaptive Hard-Constraint Physics-Informed Neural Network (AHC-PINN). This method integrates an adaptive sampling mechanism based on partial differential equation residuals with a hard-constraint strategy. By dynamically evaluating the contribution of collocation points to the loss and incorporating analytically embedded boundary constraints, it directs the network training entirely toward solving the governing equations. Using two-dimensional unsteady cylinder flow as a validation case, experimental results show that AHC-PINN significantly improves the prediction accuracy of wake evolution under unsupervised conditions. Its performance surpasses that of traditional soft-constraint PINNs by an order of magnitude and is even superior to methods using sparse supervised data. Furthermore, through analysis of the PDE loss and gradient distribution, the study explicitly identifies the impact of large-gradient regions on PINN training stability and prediction accuracy, providing a basis for subsequent optimization. Full article

The dominance of centralized artificial intelligence architectures raises significant concerns regarding privacy, data ownership, and control. These limitations have motivated the development of decentralized learning paradigms that aim to remove reliance on a central authority during model training. While federated learning represents an intermediate step by allowing distributed training without raw data exchange, it still depends on a centralized server which could lead to single-point vulnerabilities. Beyond this, a fully decentralized learning in general faces challenges in security vulnerabilities, absence of governance, and lack of incentive alignment. Recent advances in blockchain technology offer a promising foundation for addressing these issues. This paper provides a systematic analysis of blockchain’s mechanism-level roles in security, consensus, smart contract, and incentives to support decentralized learning. By reviewing state-of-the-art approaches, this paper suggests that appropriately designed blockchain architectures have the potential to enable practical, secure, and incentive-compatible decentralized learning as technological capabilities continue to evolve. Full article

RGB-infrared (RGB-IR) object detection leverages complementary information from these two modalities to substantially enhance perception in complex environments, which is particularly beneficial for reliable detection under adverse imaging conditions such as low illumination and severe haze. However, RGB-IR object detection still faces several challenges due to pronounced intra-modality and cross-modality discrepancies. On the one hand, many existing approaches rely on complex architectures to strengthen cross-modal interactions, which increases computational cost. On the other hand, symmetric dual-branch backbones with a static fusion paradigm often struggle to explicitly characterize discrepancies between the RGB and IR modalities. This limitation prevents effective mining of complementary information and reduces the discriminability of fused representations. To address these issues, this paper presents a lightweight RGB-IR multimodal detection network (LMDENet), which consists of three key components: (1) an illumination-guided label selection (IGLS) that integrates RGB and IR labels based on cross-modal matching and illumination-aware rules to construct consistent and reliable supervision; (2) a heterogeneous backbone network (HBN) with differentiated branches that separately model RGB appearance details and IR structural information, improving modality-specific representation learning; and (3) a difference-complement enhancement module (DCEM) that explicitly decomposes cross-modal features into common and difference components and performs selective enhancement to amplify complementary information while suppressing redundant noise. We systematically evaluate the detection performance of the proposed model on the multimodal remote sensing dataset DroneVehicle, and further conduct supplementary experiments on the LLVIP dataset to verify its generalization ability across different scenarios. Experimental results on the DroneVehicle and LLVIP datasets demonstrate that LMDENet achieves $78.9\%$ and $93.6\%$ mAP@0.5, respectively. Meanwhile, the model contains only 3.3 M parameters and 8.7 G FLOPs, reflecting a favorable accuracy–efficiency balance. Full article

Industrial heritage—particularly large modern cement plants—serves as a crucial witness to the architectural and technological evolution of modern urbanization. In Europe, North America, and East Asia, many decommissioned cement factories have been transformed into cultural venues, creative districts, or urban landmarks, while a greater number of sites still face the risks of functional decline and spatial disappearance. In China, early large-scale cement plants have received limited attention in international industrial heritage research, and their conservation and adaptive reuse practices remain underdeveloped. This study takes the Huaxin Cement Plant, founded in 1907, as the research object. As the birthplace of China’s modern cement industry, it preserves the world’s only complete wet-process rotary kiln production line, representing exceptional rarity and typological significance. Combining social media perception analysis with the Hidalgo-Giralt four-quadrant model, the study aims to clarify the plant’s value positioning and propose a design-oriented pathway for spatial activation. Based on 378 short videos and 75,001 words of textual data collected from five major platforms, the study conducts a value-tag analysis of public perceptions across five dimensions—historical, technological, social, aesthetic, and economic. Two composite indicators, Cultural Representativeness (CR) and Utilization Intensity (UI), are further established to evaluate the relationship between heritage value and spatial performance. The findings indicate that (1) historical and aesthetic values dominate public perception, whereas social and economic values are significantly underrepresented; (2) the Huaxin Cement Plant falls within the “high cultural representativeness/low utilization intensity” quadrant, revealing concentrated heritage value but insufficient spatial activation; (3) the gap between value cognition and spatial transformation primarily arises from limited public accessibility, weak interpretive narratives, and a lack of immersive experience. In response, the study proposes five optimization strategies: expanding public access, building a multi-layered interpretive system, introducing immersive and interactive design, integrating into the Yangtze River Industrial Heritage Corridor, and encouraging community co-participation. As a representative case of modern Chinese industrial heritage distinguished by its integrity and scarcity, the Huaxin Cement Plant not only enriches the understanding of industrial heritage typology in China but also provides a methodological paradigm for the “value positioning–spatial utilization–heritage activation” framework, bearing both international comparability and disciplinary methodological significance. Full article

Seed phenomics is a critical research field for understanding seed germination mechanisms. Metasurfaces, composed of subwavelength nanostructures, offer a promising pathway to achieve both dispersion control and imaging functionalities within an ultra-compact form factor. Recent advances in micro–nano-optics and computational imaging have opened new avenues for high-dimensional, multimodal imaging. However, conventional hyperspectral and light-field systems still face limitations in compactness, depth resolution, and spectral–spatial integration. This review summarizes recent progress in metalens and metasurface lens array-based light-field systems for hyperspectral imaging and 3D reconstruction, with a focus on the underlying principles, design strategies, and reconstruction algorithms that enable single-shot 3D hyperspectral acquisition. We further present a forward-looking roadmap toward the realization of a revolutionized imaging paradigm: a metasurface-based light-field platform that fully integrates 3D and hyperspectral imaging capabilities. In particular, we examine how dispersive metasurfaces serve as core optical elements for precise dispersion control in hyperspectral imaging systems, while metalens arrays enable accurate modulation of spatial–angular distributions in light-field configurations. We systematically review both 3D and spectral reconstruction algorithms, highlighting their roles in decoding complex optical encodings. The application of these integrated systems in seed phenotyping is emphasized, demonstrating their capability to capture 3D spatial–spectral distributions in a single exposure. This approach facilitates high-throughput analysis of morphological traits, germination potential, and internal biochemical composition, offering a comprehensive solution for advanced seed characterization. Finally, we outline a practical roadmap for implementing a metasurface-based light-field platform that integrates hyperspectral imaging and computational 3D reconstruction. This review offers a comprehensive overview of the state of the art in compact 3D light-field systems and multimodal hyperspectral imaging platforms, while providing forward-looking insights aimed at advancing smart seed phenotyping, precision agriculture, and next-generation optical imaging technologies. Full article

Oriented object detection in remote sensing images remains a challenging task due to arbitrary target rotations, extreme scale variations, and complex backgrounds. However, current rotated detectors still face several limitations: insufficient orientation-sensitive feature representation, feature misalignment for rotated proposals, and unstable optimization of rotation parameters. To address these issues, this paper proposes an enhanced Rotation-Sensitive Feature Pyramid Network (RSFPN) framework. Building upon the effective Oriented R-CNN paradigm, we introduce three novel core components: (1) a Dynamic Adaptive Feature Pyramid Network (DAFPN) that enables bidirectional multi-scale feature fusion through semantic-guided upsampling and structure-enhanced downsampling paths; (2) an Angle-Aware Collaborative Attention (AACA) module that incorporates orientation priors to guide feature refinement; (3) a Geometrically Consistent Multi-Task Loss (GC-MTL) that unifies the regression of rotation parameters with periodic smoothing and adaptive weight mechanisms. Comprehensive experiments on the DOTA-v1.0 and HRSC2016 benchmarks show that our RSFPN achieves superior performance. It attains a state-of-the-art mAP of 77.42% on DOTA-v1.0 and 91.85% on HRSC2016, while maintaining efficient inference at 14.5 FPS, demonstrating a favorable accuracy-efficiency trade-off. Visual analysis confirms that our method produces concentrated, rotation-aware feature responses and effectively suppresses background interference. The proposed approach provides a robust solution for detecting multi-oriented objects in high-resolution remote sensing imagery, with significant practical value for urban planning, environmental monitoring, and security applications. Full article

The Qinba Mountains in China span six provinces, characterized by a large population, rugged terrain, steep peaks, deep valleys, and scarce flat land, making large-scale agricultural development challenging. Terraced fields serve as the core cropland type in this region, playing a vital role in preventing soil erosion on sloping farmland and expanding agricultural production space. They also function as a crucial medium for sustaining the ecosystem services of mountainous areas. As a transitional zone between China’s northern and southern climates and a vital ecological barrier, the Qinba Mountains’ terraced ecosystems have undergone significant spatial changes over the past two decades due to compound factors including the Grain-for-Green Program, urban expansion, and population outflow. However, current large-scale, long-term, high-resolution monitoring studies of terraced fields in this region still face technical bottlenecks. On one hand, traditional remote sensing interpretation methods rely on manually designed features, making them ill-suited for the complex scenarios of fragmented, multi-scale distribution, and terrain shadow interference in Qinba terraced fields. On the other hand, the lack of high-resolution historical imagery means that low-resolution data suffers from insufficient accuracy and spatial detail for capturing dynamic changes in terraced fields. This study aims to fill the technical gap in detailed dynamic monitoring of terraced fields in the Qinba Mountains. By creating image tiles from Landsat-8 satellite imagery collected between 2017 and 2020, it employs three deep learning semantic segmentation models—DeepLabV3 based on ResNet-34, U-Net, and PSPNet deep learning semantic segmentation models. Through optimization strategies such as data augmentation and transfer learning, the study achieves 15-m-resolution remote sensing interpretation of terraced field information in the Qinba Mountains from 2000 to 2020. Comparative results revealed DeepLabV3 demonstrated significant advantages in identifying terraced field types: Mean Pixel Accuracy (MPA) reached 79.42%, Intersection over Union (IoU) was 77.26%, F1 score attained 80.98, and Kappa coefficient reached 0.7148—all outperforming U-Net and PSPNet models. The model’s accuracy is not uniform but is instead highly contingent on the topographic context. The model excels in environments that are archetypal for mid-altitudes with moderately steep slopes. Based on it we create a set of tiles integrating multi-source data from RBG and DEM. The fusion model, which incorporates DEM-derived topographic data, demonstrates improvement across these aspects. Dynamic monitoring based on the optimal model indicates that terraced fields in the Qinba Mountains expanded between 2000 and 2020: the total area was 57.834 km² in 2000, and by 2020, this had increased to 63,742 km², representing an approximate growth rate of 8.36%. Sichuan, Gansu, and Shaanxi provinces contributed the majority of this expansion, accounting for 71% of the newly added terraced fields. Over the 20-year period, the center of gravity of terraced fields shifted upward. The area of terraced fields above 500 m in elevation increased, while that below 500 m decreased. Terraced fields surrounding urban areas declined, and mountainous slopes at higher elevations became the primary source of newly constructed terraces. This study not only establishes a technical paradigm for the refined monitoring of terraced field resources in mountainous regions but also provides critical data support and theoretical foundations for implementing sustainable land development in the Qinba Mountains. It holds significant practical value for advancing regional sustainable development. Full article

Demyelinating diseases comprise a group of chronic and debilitating neurological disorders, with the destruction of the myelin sheath serving as the core pathological hallmark. The central pathogenesis involves immune-mediated damage to oligodendrocytes (Ols) and myelin breakdown, accompanied by a vicious cycle of neuroinflammation and impaired epigenetic repair. Current therapeutic strategies, including conventional immunomodulatory agents to targeted monoclonal antibodies, effectively control disease relapses but exhibit limited efficacy in promoting neural repair. Consequently, research focus is increasingly shifting towards neuroprotective and remyelination strategies. In this context, Emerging therapeutic promise stems primarily from two fronts: the advent of novel pharmaceuticals, such as remyelination-promoting drugs targeting oligodendrocyte maturation, interventions inhibiting epigenetic silencing, signal pathway inhibitors, and natural products derived from traditional Chinese medicine; the development of innovative technologies, including cell therapies, gene therapy, exosome and nanoparticle-based drug delivery systems, as well as extracellular protein degradation platforms. Nevertheless, drug development still faces challenges such as disease heterogeneity, limited blood–brain barrier penetration, long-term safety, and difficulties in translating findings from preclinical models. Future efforts should emphasize precision medicine, multi-target synergistic therapies, and the development of intelligent delivery systems, with the ultimate goal of achieving a paradigm shift from delaying disability progression to functional neural reconstruction. Full article

Infrared–visible (IR–VIS) image fusion is becoming central to unmanned aerial vehicle (UAV) perception, enabling robust operation across day–night cycles, backlighting, haze or smoke, and large viewpoint or scale changes. However, for practical applications some challenges still remain: visible images are illumination-sensitive; infrared imagery suffers thermal crossover and weak texture; motion and parallax cause cross-modal misalignment; UAV scenes contain many small or fast targets; and onboard platforms face strict latency, power, and bandwidth budgets. Given these UAV-specific challenges and constraints, we provide a UAV-centric synthesis of IR–VIS fusion. We: (i) propose a taxonomy linking data compatibility, fusion mechanisms, and task adaptivity; (ii) critically review learning-based methods—including autoencoders, CNNs, GANs, Transformers, and emerging paradigms; (iii) compare explicit/implicit registration strategies and general-purpose fusion frameworks; and (iv) consolidate datasets and evaluation metrics to reveal UAV-specific gaps. We further identify open challenges in benchmarking, metrics, lightweight design, and integration with downstream detection, segmentation, and tracking, offering guidance for real-world deployment. A continuously updated bibliography and resources are provided and discussed in the main text. Full article