Spatial Domain Research Articles

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training.

The superior performance of modern computer vision backbones (e.g., vision Transformers learned on ImageNet-1K/22K) usually comes with a costly training procedure. This study contributes to this issue by generalizing the idea of curriculum learning beyond its original formulation, i.e., training models using easier-to-harder data. Specifically, we reformulate the training curriculum as a soft-selection function, which uncovers progressively more difficult patterns within each example during training, instead of performing easier-to-harder sample selection. Our work is inspired by an intriguing observation on the learning dynamics of visual backbones: during the earlier stages of training, the model predominantly learns to recognize some 'easier-to-learn' discriminative patterns in the data. These patterns, when observed through frequency and spatial domains, incorporate lower-frequency components, and the natural image contents without distortion or data augmentation. Motivated by these findings, we propose a curriculum where the model always leverages all the training data at every learning stage, yet the exposure to the 'easier-to-learn' patterns of each example is initiated first, with harder patterns gradually introduced as training progresses. To implement this idea in a computationally efficient way, we introduce a cropping operation in the Fourier spectrum of the inputs, enabling the model to learn from only the lower-frequency components. Then we show that exposing the contents of natural images can be readily achieved by modulating the intensity of data augmentation. Finally, we integrate these two aspects and design curriculum learning schedules by proposing tailored searching algorithms. Moreover, we present useful techniques for deploying our approach efficiently in challenging practical scenarios, such as large-scale parallel training, and limited input/output or data pre-processing speed. The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective. As an off-the-shelf approach, it reduces the training time of various popular models (e.g., ResNet, ConvNeXt, DeiT, PVT, Swin, CSWin, and CAFormer) by [Formula: see text] on ImageNet-1K/22K without sacrificing accuracy. It also demonstrates efficacy in self-supervised learning (e.g., MAE). Code is available at: https://github.com/LeapLabTHU/EfficientTrain.

Sweeping jet impingement heat transfer on concave surface: Influence of trapped vortex ring revealed by generalized k-ω (GEKO) model

Jet impingement-based heat transfer enhancement is widely employed due to the significant mass, momentum, and energy it accompanied. While the steady jet with high energy flux is commonly favored, it still exhibit few defects, including heat transfer deterioration away from the stagnation point and mutual flow interference in the jet arrays, which are particularly critical in demanding applications. Recently, the sweeping jet has been proposed to resolve the above challenges owing to its self-excited and self-sustaining unsteady oscillation. However, current research predominately focuses on impinging on the flat surface, neglecting impinging on the concave surface, such as internal cooling at the gas turbine blade leading-edge as well as the hot gas de-icing at the aircraft wing leading-edge. Understanding the heat transfer characteristics in these scenarios is crucial as they notably differ from those on flat surfaces. Therefore, this paper investigates the heat transfer characteristics and the related essential flow dynamics of a sweeping jet with a Reynolds number of 2577 impinging on a concave surface, and those of a steady jet under the same conditions are compared. The jet-to-wall distance and the curvature of the impingement surface are 4 and 10 times the jet's hydraulic diameter, respectively. To correctly capture the three-dimensional characteristics of the sweeping jet, this research employs the Reynolds stress model for turbulence modeling and the Generalized k-ω (GEKO) model for better calibration of the jet's spreading and dissipation rates, as well as the characteristics of trapped vortex generated due to the confined concave flow channel. The study initially focuses on the average Nusselt number on the impingement surface, revealing a 15.2% increase in heat transfer intensity of the sweeping jet compared to the steady jet, and the sweeping jet covers a larger area with enhanced uniformity. Subsequent analysis on streamlines in two perpendicular planes and Q criterion iso-surfaces in the spatial domain shows the formation of a trapped vortex ring with a constant location around the jet, restricting the effective cooling range to its inner side and thus resulting in a steep temperature rise on the two lateral sides of the vortex ring. The stability of the trapped vortex is enhanced by the curved impingement wall in the oscillation plane, which on the one hand forces the high-temperature fluid that has exchanged heat with the wall to repeatedly wash the same location, and on the other hand significantly reduces the jet oscillation angle compared to a free sweeping jet. Consequently, the heat transfer intensity of the sweeping jet is lower in the main oscillation plane than in the non-oscillation plane. Analysis of the near-wall flow parameters indicates that the sweeping jet generates higher velocity and turbulence kinetic energy in the wall jet zone far away from the stagnation point compared to the steady jet, which results in a higher local heat transfer intensity. The unsteady transverse oscillation of the sweeping jet disturbs the wall jet zone and disrupts the formation of the wall boundary layer, causing a higher velocity gradient at the wall and hence the lower thicknesses of the velocity boundary layer and the thermal boundary layer than those of the steady jet. In conclusion, this study reveals the flow and heat transfer features of the sweeping jet impingement on confined concave surface, with the influence of the trapped vortex ring mattering significantly. The findings provide a reference for designing a more effective jet arrangement. Future work will focus on investigating the effects of jet Reynolds number and impingement distance variations on the trapped vortex ring, and how to mitigate the adverse effects of the trapped vortex ring on impingement heat transfer.

When Structured Light Encounters Liquid Crystals

AbstractStructured light refers to the light field tailored by various degrees of freedom including intensity, phase, and polarization states in both spatial and temporal domains, which may greatly vitalize the technologies in both optics, such as the next‐generation optical communication as well as subwavelength imaging and the materials science in both fabrication and characterization. The structured characteristics of the structure light need materials also with structured optical properties that can generate or manipulate structured light in a straightforward way, which can be well satisfied by liquid crystals, a soft mater that can self‐assemble into tunable ordered structures through external stimuli. This review summarizes the research progress of the liquid crystal‐based devices used in structured light generations and modulations, including the well‐established techniques in the market, like the spatial light modulator, q‐plate and the liquid crystal integrated optical metasurfaces. Especially, light‐matter interactions are discussed from the topological view of both the structured light and the liquid crystal structures. Such a perfect matching in topology makes the liquid crystal a promising star together with structured light in future optic and photonic technologies.

Automated Vibroacoustic Monitoring of Trees for Borer Infestation

In previous research, we presented an apparatus designed for comprehensive and systematic surveillance of trees against borers. This apparatus entailed the insertion of an uncoated waveguide into the tree trunk, enabling the transmission of micro-vibrations generated by moving or digging larvae to a piezoelectric probe. Subsequent recordings were then transmitted at predetermined intervals to a server, where analysis was conducted manually to assess the infestation status of the tree. However, this method is hampered by significant limitations when scaling to monitor thousands of trees across extensive spatial domains. In this study, we address this challenge by integrating signal processing techniques capable of distinguishing vibrations attributable to borers from those originating externally to the tree. Our primary innovation involves quantifying the impulses resulting from the fracturing of wood fibers due to borer activity. The device employs criteria such as impulse duration and a strategy of waiting for periods of relative quietness before commencing the counting of impulses. Additionally, we provide an annotated large-scale database comprising laboratory and field vibrational recordings, which will facilitate further advancements in this research domain.

Evolutionary equations are G-compact

We prove a compactness result related to G-convergence for autonomous evolutionary equations in the sense of Picard. Compared to previous work related to applications, we do not require any boundedness or regularity of the underlying spatial domain; nor do we assume any periodicity or ergodicity assumption on the potentially oscillatory part. In terms of abstract evolutionary equations, we remove any compactness assumptions of the resolvent modulo kernel of the spatial operator. To achieve the results, we introduced a slightly more general class of material laws. As a by-product, we also provide a criterion for G-convergence for time-dependent equations solely in terms of static equations.

Hot rolled steel surface defect detection and classification using an automatic ensemble approach

Abstract This study introduces an ensemble-based Deep Neural Network (DNN) model for detecting defects on steel surfaces. The method suggested in this study classifies steel surface conditions into six possible fault categories, namely, crazing, inclusion, rolled in, pitted surface, scratches, and patches. The images undergo preprocessing and extraction of features in spatial and frequency domains using image segmentation techniques such as grey level difference method (GLDM), fast Fourier Transform (FFT), grey level co-occurrence matrix (GLCM), texture analysis and discrete wavelet transform (DWT). The ensembling of image features into a fused feature pool is carried out after the preprocessing of input images that are provided as input to a light-weight neural network model for training and testing. The performance of the model is comprehensively evaluated via an ablation study both before and after ensembling. In addition, the model capability is effectively analyzed using receiver operating characteristics (ROC) curve, confusion matrix from which classification accuracy of the model could be obtained and other parameters including precision and f1-score. It was observed that the proposed deep learning network presents phenomenally high accuracy of 99.72% for detection and classification of steel surface faults. This result was found to be superior when compared with the performance of the same neural network over each feature type individually. This study also compares the classification results of the model built based on the ensembled feature set with the results of various other classification approaches available in literature. The ensemble-based model could potentially be integrated into existing inspection systems for real-time, efficient and robust condition monitoring of steel surfaces.

Cascaded framework for earthquake building damage detection combining spatial and frequency domain feature integration

Abstract. Building collapse is a major cause of casualties after an earthquake, so accurately extracting building damage information is critical for post-earthquake assessment and rescue. Currently, most deep learning methods focus on the end-to-end detection of building collapse. However, in real-world earthquake scenarios, the end-to-end computational process often lacks flexibility and struggles to meet the requirements of rapid emergency response. To address this issue, this paper proposes a cascaded framework that combines pre-earthquake building extraction and post-earthquake building damage classification. The proposed framework includes two sections: (1) Progressive building semantic segmentation model in the joint frequency domain. This model is designed to accurately extract buildings prior to an earthquake, with the goal of minimizing error propagation throughout the cascading process. The model addresses the spatial similarity of buildings under complicated backgrounds, as well as the high internal heterogeneity of buildings, by utilizing frequency domain techniques. It compensates for the shortcomings of traditional models in terms of incomplete information extraction through the effective integration of global and local information. Finally, the model employs edge priors for edge regularization. (2) Rapid building damage classification process. Based on the accurate building extraction results, a fast and efficient classification process is developed. This process uses a simple and lightweight classification network to effectively extract building damage information caused by the earthquake. The superiority of the proposed framework is validated through comparison with traditional cascading architectures and end-to-end models. The results show that the cascading framework not only provides accurate pre-earthquake building extraction, but also enables efficient and accurate post-earthquake damage classification, which meets the requirements of rapid post-earthquake emergency response. This balance of accuracy and speed is essential for effective disaster management and recovery.

High-Speed Spatial–Temporal Saliency Model: A Novel Detection Method for Infrared Small Moving Targets Based on a Vectorized Guided Filter

Infrared (IR) imaging-based detection systems are of vital significance in the domains of early warning and security, necessitating a high level of precision and efficiency in infrared small moving target detection. IR targets often appear dim and small relative to the background and are easily buried by noise and difficult to detect. A novel high-speed spatial–temporal saliency model (HS-STSM) based on a guided filter (GF) is proposed, which innovatively introduces GF into IR target detection to extract the local anisotropy saliency in the spatial domain, and substantially suppresses the background region as well as the bright clutter false alarms present in the background. Moreover, the proposed model extracts the motion saliency of the target in the temporal domain through vectorization of IR image sequences. Additionally, the proposed model significantly improves the detection efficiency through a vectorized filtering process and effectively suppresses edge components in the background by integrating a prior weight. Experiments conducted on five real infrared image sequences demonstrate the superior performance of the model compared to existing algorithms in terms of the detection rate, noise suppression, real-time processing, and robustness to the background.

Unfolding the ventral nerve center of chaetognaths

BackgroundChaetognaths are a clade of marine worm-like invertebrates with a heavily debated phylogenetic position. Their nervous system superficially resembles the protostome type, however, knowledge regarding the molecular processes involved in neurogenesis is lacking. To better understand these processes, we examined the expression profiles of marker genes involved in bilaterian neurogenesis during post-embryonic stages of Spadella cephaloptera. We also investigated whether the transcription factor encoding genes involved in neural patterning are regionally expressed in a staggered fashion along the mediolateral axis of the nerve cord as it has been previously demonstrated in selected vertebrate, insect, and annelid models.MethodsThe expression patterns of genes involved in neural differentiation (elav), neural patterning (foxA, nkx2.2, pax6, pax3/7, and msx), and neuronal function (ChAT and VAChT) were examined in S. cephaloptera hatchlings and early juveniles using whole-mount fluorescent in situ hybridization and confocal microscopy.ResultsThe Sce-elav+ profile of S. cephaloptera hatchlings reveals that, within 24 h of post-embryonic development, the developing neural territories are not limited to the regions previously ascribed to the cerebral ganglion, the ventral nerve center (VNC), and the sensory organs, but also extend to previously unreported CNS domains that likely contribute to the ventral cephalic ganglia. In general, the neural patterning genes are expressed in distinct neural subpopulations of the cerebral ganglion and the VNC in hatchlings, eventually becoming broadly expressed with reduced intensity throughout the CNS in early juveniles. Neural patterning gene expression domains are also present outside the CNS, including the digestive tract and sensory organs. ChAT and VAChT domains within the CNS are predominantly observed in specific subpopulations of the VNC territory adjacent to the ventral longitudinal muscles in hatchlings.ConclusionsThe observed spatial expression domains of bilaterian neural marker gene homologs in S. cephaloptera suggest evolutionarily conserved roles in neurogenesis for these genes among bilaterians. Patterning genes expressed in distinct regions of the VNC do not show a staggered medial-to-lateral expression profile directly superimposable to other bilaterian models. Only when the VNC is conceptually laterally unfolded from the longitudinal muscle into a flat structure, an expression pattern bearing resemblance to the proposed conserved bilaterian mediolateral regionalization becomes noticeable. This finding supports the idea of an ancestral mediolateral patterning of the trunk nervous system in bilaterians.

Iris Recognition based on Statistically Bound Spatial Domain Zero Crossing and Neural Networks

Purpose The iris pattern is an important biological feature of the human body. The recognition of an individual based on an iris pattern is gaining more popularity due to the uniqueness of the pattern among the people. Iris recognition systems have received attention very much due to their rich iris texture which gives robust standards for identifying individuals. Notwithstanding this, there are several challenges in unrestricted recognition environments. Methods This article discusses a highly error-resistant technique to implement a biometric recognition system based on the iris portion of the human eye. All iris recognition algorithms of the current day face a major problem of localization errors and the enormous time involved in this localization process. Spatial domain zero crossing may be the simplest and least complex method for localization. Yet, it has not been used due to its high sensitivity to erroneous edges, as a consequence of which more complex and time-consuming algorithms have taken its place. Appropriate statistical bounds imposed on this process help this method to be the least erroneous and time-consuming. Errors were reduced to 0.022% using this approach on the CASIA v1 & v2 datasets. Time consumption in this stage was the least compared to other algorithms. At the comparison stage, most algorithms use multiple comparisons to account for translation and rotation errors. This is time-consuming and very resource-hungry. Results The current approach discusses a robust method based on a single comparison, which works with a correct recognition of over 99.78% which is clearly demonstrated by tests. Conclusions The technique is to use a neural network trained to recognize special statistical and regional parameters unique to every person’s iris. The algorithm also gives sufficient attention to consider illumination errors, elliptical pupils, excess eyelash errors and bad contrast.

Domain Transformation of Distortion Costs for Efficient JPEG Steganography with Symmetric Embedding

Nowadays, most image steganographic schemes embed secret messages by minimizing a well-designed distortion cost function for the corresponding domain, i.e., the spatial domain for spatial image steganography or the JPEG (Joint Photographic Experts Group) domain for JPEG image steganography. In this paper, we break the boundary between these two types of schemes by establishing a theoretical link between the distortion costs in the spatial domain and those in the JPEG domain and thus propose a scheme for domain transformations of distortion costs for efficient JPEG steganography with symmetric embedding, which can directly convert the spatial distortion cost into its JPEG counterpart. Specifically, by formulating the distortion cost function for JPEG images in the decompressed spatial domain, a closed-form expression for a distortion cost cross-domain transformation is derived theoretically, which precisely characterizes the conversion from the distortion costs obtained by existing spatial steganographic schemes to those applied in JPEG steganography. Experimental results demonstrate that the proposed method outperforms other advanced JPEG steganographic schemes, e.g., JUNIWARD (JPEG steganography with Universal Wavelet Relative Distortion), JMiPOD (JPEG steganography by Minimizing the Power of the Optimal Detector), and DCDT (Distortion Cost Domain Transformation), in resisting the detection of various advanced steganalyzers.

Computationally-efficient linear scheme for overlap time-gating spatial frequency domain diffuse optical tomography using an analytical diffusion model

Time-domain (TD) spatial frequency domain (SFD) diffuse optical tomography (DOT) potentially enables laminar tomography of both the absorption and scattering coefficients. Its full time-resolved-data scheme is expected to enhance performances of the image reconstruction but poses heavy computational costs and also susceptible signal-to-noise ratio (SNR) limits, as compared to the featured-data one. We herein propose a computationally-efficient linear scheme of TD-SFD-DOT, where an analytical solution to the TD phasor diffusion equation for semi-infinite geometry is derived and used to formulate the Jacobian matrices with regard to overlap time-gating data of the time-resolved measurement for improved SNR and reduced redundancy. For better contrasting the absorption and scattering and widely adapted to practically-available resources, we develop an algebraic-reconstruction-technique-based two-step linear inversion procedure with support of a balanced memory-speed strategy and multi-core parallel computation. Both simulations and phantom experiments are performed to validate the effectiveness of the proposed TD-SFD-DOT method and show an achieved tomographic reconstruction at a relative depth resolution of ∼4 mm.

Unveiling the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset.

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear. We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits. While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R2 (0.12-0.49, 0.15-0.42, and 0.25-0.56) and increased NRMSE (3.58-18.24%, 6.27-11.55%, and 7.0-33.12%) compared with nonspatial random cross-validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability. These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

Strategic planning for spatial governance: a case study of the Central District in Arak County, Iran

ABSTRACT Spatial governance involves studying the relationship between trade, and politics, resolving tensions, and harmonizing various social forces within a spatial domain within the framework of democratic governance models. The importance of this approach in space management stems from the increasing delegation of government responsibilities and powers to the non-governmental sector. Political space managers need to use strategic plans to achieve sustainable development and spatial justice. The general objectives of this research are an understanding of strategic planning and to apply it in one of the aspects of regional development, to explain the steps and process of strategic planning, and also how to determine and prioritize strategies. This research is descriptive in nature and applied-developmental in terms of purpose. The method of collecting information is a library, face-to-face interviews with experts, personal observation, and questionnaire completion. SWOT analysis method has been used to determine the importance and weighting of internal and external factors and to formulate strategies. A quantitative strategic planning matrix (QSPM) has been used to measure the attractiveness of each of the desired strategies. The results of the study indicate that conservative strategies are proposed as executive strategies in the Central District of Arak County, Iran.

Latent Representation Learning for Geospatial Entities

Representation learning has been instrumental in the success of machine learning, offering compact and performant data representations for diverse downstream tasks. In the spatial domain, it has been pivotal in extracting latent patterns from various data types, including points, polylines, polygons, and networked structures. However, existing approaches often fall short of explicitly capturing both semantic and spatial information, relying on proxies and synthetic features. This paper presents GeoNN, a novel graph neural network-based model designed to learn spatially-aware embeddings for geospatial entities. GeoNN leverages edge features generated from geodesic functions, dynamically selecting relevant features based on relative locations. It introduces both transductive (GeoNN-T) and inductive (GeoNN-I) models, ensuring effective encoding of geospatial features and scalability with entity changes. Extensive experiments demonstrate GeoNN’s effectiveness in location-sensitive superpixel-based graphs and real-world points of interest, outperforming baselines across various evaluation measures.

Multiplexed Imaging Mass Cytometry Analysis Characterizes the Vascular Niche in Pancreatic Cancer.

Oncogenesis and progression of pancreatic ductal adenocarcinoma (PDAC) is driven by complex interactions between the neoplastic component and the tumor microenvironment (TME), which includes immune, stromal, and parenchymal cells. In particular, most PDACs are characterized by a hypovascular and hypoxic environment that alters tumor cell behavior and limits the efficacy of chemotherapy and immunotherapy. Characterization of the spatial features of the vascular niche could advance our understanding of inter- and intra-tumoral heterogeneity in PDAC. Here, we investigated the vascular microenvironment of PDAC by applying imaging mass cytometry using a 26-antibody panel on 35 regions of interest (ROIs) across 9 patients, capturing over 140,000 single cells. The approach distinguished major cell types, including multiple populations of lymphoid and myeloid cells, endocrine cells, ductal cells, stromal cells, and endothelial cells. Evaluation of cellular neighborhoods identified 10 distinct spatial domains, including multiple immune and tumor-enriched environments as well as the vascular niche. Focused analysis revealed differential interactions between immune populations and the vasculature and identified distinct spatial domains wherein tumor cell proliferation occurs. Importantly, the vascular niche was closely associated with a population of CD44-expressing macrophages enriched for a pro-angiogenic gene signature. Together, this study provides insights into the spatial heterogeneity of PDAC and suggests a role for CD44-expressing macrophages in shaping the vascular niche.

Predator-prey interactions across hunting mode, spatial domain size, and habitat complexities.

Predator-prey interactions are a fundamental part of community ecology, yet the relative importance of consumptive and nonconsumptive effects (NCEs) (defined as a risk-induced response that alters prey fitness) has not been resolved. Theory suggests that the emergence and subsequent predominance of consumptive or NCEs depend on the given habitat's complexity as well as predator hunting mode and spatial domain sizes of both predator and prey, but their relative influence on the outcome of predator-prey interactions is unknown. We built agent-based models in NetLogo to simulate predator-prey interactions for three hunting modes-sit-and-wait, sit-and-pursue, and active-while concurrently simulating large versus small spatial domain sizes for both predators and prey. We studied (1) how hunting mode and spatial domain size interact to influence the emergence of consumptive or NCEs and (2) how, when NCEs do dominate, hunting mode and spatial domain separately or additively determine prey shifts in time, space, and habitat use. Our results indicate consumptive effects only dominate for active predators when prey habitat domains overlap completely with the predator's spatial domain and when sit-and-wait and sit-and-pursue predators and their prey both have large spatial domains. Prey are most likely to survive when they shift their time but most frequently shift their habitat. Our paper helps to better understand the underlying mechanisms that drive consumptive or NCEs to be most dominant.

Convolution-transformer blend pyramid network for underwater image enhancement

Underwater images suffer from different types of degradation, where color degradation occurs in the spatial domain and edge degradation in the frequency domain. The high-quality underwater image enhancement represents a crucial milestone in advancing computer vision systems tailored for marine environments. This foundational endeavor encompasses a wide array of applications in computer vision tasks, including underwater inspection, underwater archaeology, and environmental monitoring. However, current convolutional neural network (CNN)-based pyramid frameworks primarily focus on capturing local features, often overlooking the significance of global semantic features that play a crucial role in understanding underwater scenes. Moreover, these frameworks handle spatial and frequency features independently, failing to enhance images by exploring correlation among domain-specific attributes for enabling information consistency. Besides, optimizing the model using a loss function with the same domain attributes from the ground truth may not lead to a better generalization ability. To solve these problems, we propose a new Convolution-Transformer Blend Pyramid Network (CTPN), which consists of a spatial branch and several frequency branches. The CTPN has four key components: a Swin transformer encoder, a CNN-Transformer aggregated encoder–decoder (CTED) and a blend pyramid framework. The Swin transformer encoder is employed to capture global semantic features, benefiting from its ability to extract long-range and global dependencies among features. The CTED fuses local features captured by CNN layers and global semantic features captured by the Swin transformer encoder in the spatial branch, with the help of the Cross-Model Fusion Module (CFM) and Skip-Aggregation Module (SAM). Subsequently, a blend pyramid framework is designed which not only progressively expands the transformed information of the previous domain branch to the current domain branch via the CTED-based refining operation, but also utilizes the proposed Domain Affinity Block (DAB) to explore the connection between domain attributes, ensuring information consistency. The experimental results demonstrate that the proposed method outperforms existing underwater image enhancement methods quantitatively and qualitatively.

Quantitative Assessment via Multi-Domain Fusion of Muscle Synergy Associated With Upper-Limb Motor Function for Stroke Rehabilitation.

Quantitative assessment of upper limb motor function aids therapists in providing appropriate rehabilitation strategies, which plays an essential role in post-stroke rehabilitation. Traditional assessments, relying on clinical scales or kinematic metrics, often involve subjective scores or are influenced by compensatory strategies. Recently, the use of muscle synergies, representing simplified neuromuscular control, has emerged as a promising approach for post-stroke assessment. In general, muscle synergies are decomposed into two components: synergy vectors and synergy activation. Synergy vectors represent the relative weighting of each muscle within each synergy, that is muscle coordination; synergy activation represents the recruitment of the muscle synergy over time, that is muscle activation strength. Both components are vital for adequately assessing patients' motor function. Therefore, we integrate the spatial domain and temporal domain features extracted from synergy vectors and synergy activation, constructing a multi-domain assessment system using a Random Forest classifier, which may provide great qualitative classification accuracy. Furthermore, a novel functional score is generated from the probabilities belonging to the pathological group. Finally, A study involving ten healthy subjects and ten post-stroke patients validates the proposed method. The experimental results show that the classification accuracy was enhanced to 98.56% by fusing the characteristics derived from different domains, which was higher than that based on spatial domain (94.90%) and temporal domain (91.08%), respectively. Furthermore, the assessment score generated by multi-domain fusion framework exhibited a significant correlation with the clinical score. These promising results show the potential of applying the proposed method to clinical assessments for post-stroke patients.

Global pixel-value-ordering framework with dynamic sequence partition for reversible data hiding

Recently, pixel-value-ordering (PVO) based reversible data hiding (RDH) methods have become hotspots in spatial domain RDH research. In PVO-based methods, the pixel value correlation within a local region is exploited for data embedding. To embed secret data, the cover images are partitioned into non-overlapped rectangle blocks to be sorted locally, and a lower embedding distortion is thus obtained. However, their embedding capacities are often limited by the fixed local blocks from which pixels are sorted. To maintain the advantages and overcome disadvantages of the PVO-based methods, a new global pixel-value-ordering (GPVO) framework is proposed in this paper. By applying our GPVO framework, a PVO-based method can utilize pixels from any position in the cover image rather than from local pixel blocks. Then, through the dynamic sequence partition realized by the GPVO framework for the first time, the embedding capacity of PVO-based methods can be greatly improved while reducing embedding distortion further reduced. Finally, we propose a two-stage pairwise embedding scheme to be applied to the sequences, aiming to achieve an advanced embedding performance. Experimental results illustrate that the proposed GPVO works better than other related state-of-the-art RDH methods.