Search Results (130)

Alzheimer’s Disease and Dementia (ADD) progresses along a continuum of cognitive decline, typically from Subjective Cognitive Impairment (SCI) to Mild Cognitive Impairment (MCI) and eventually to dementia. While many studies have focused on classifying these clinical stages, fewer have examined whether brain connectomes encode this continuum in a low-dimensional, interpretable form. Motivated by the hypothesis that structural brain connectomes undergo complex yet compact changes across cognitive decline, we propose a Graph Neural Network (GNN)-based framework that embeds these connectomes into a two-dimensional manifold to capture the evolving patterns of structural connectivity associated with cognitive deterioration. Using attention-based graph aggregation and Principal Component Analysis (PCA), we find that MCI subjects consistently occupy an intermediate position between SCI and ADD, and that the observed transitions align with known clinical biomarkers of ADD pathology. This hypothesis-driven analysis is further supported by the model’s robust separation performance, with ROC-AUC scores of 0.93 for ADD vs. SCI and 0.81 for ADD vs. MCI. These findings offer an interpretable and neurologically grounded representation of dementia progression, emphasizing structural connectome alterations as potential markers of cognitive decline. Full article

Efficient prediction of shallow-water acoustic transmission loss (TL) is crucial for underwater detection, recognition, and communication systems. Traditional physical modeling methods require repeated calculations for each new scenario in practical waveguide environments, leading to low computational efficiency. Deep learning approaches, based on data-driven principles, enable accurate input–output approximation and batch processing of large-scale datasets, significantly reducing computation time and cost. To establish a rapid prediction model mapping sound speed profiles (SSPs) to acoustic TL through controllable generation, this study proposes a hybrid framework that integrates a variational autoencoder (VAE) and a normalizing flow (Flow) through a two-stage training strategy. The VAE network is employed to learn latent representations of TL data on a low-dimensional manifold, while the Flow network is additionally used to establish a bijective mapping between the latent variables and underwater physical parameters, thereby enhancing the controllability of the generation process. Combining the trained normalizing flow with the VAE decoder could establish an end-to-end mapping from SSPs to TL. The results demonstrated that the VAE–Flow network achieved higher computational efficiency, with a computation time of 4 s for generating 1000 acoustic TL samples, versus the over 500 s required by the KRAKEN model, while preserving accuracy, with median structural similarity index measure (SSIM) values over 0.90. Full article

The Flamelet Generated Manifold (FGM) method is widely employed in turbulent combustion simulations due to its high accuracy and computational efficiency. However, the model’s ability to capture turbulent combustion interactions is limited by the shape of the presumed probability density function (PDF) of the mixture fraction and progress variable. To construct a conditional $\beta$ PDF with better performance, a systematic PDF modeling and analysis framework coupled with machine learning methods based on the sparse experimental data was proposed. A comparative analysis was conducted for five machine learning methods across two experimental datasets using this framework. The results demonstrate that the random forest algorithm represents the optimal choice when both training complexity and predictive performance are comprehensively considered. To expand the model’s applicable range, a data fusion strategy was applied in different machine learning methods. The effectiveness of data fusion is demonstrated by comparative analysis between single-dataset and fused-dataset models. The analysis of convex hull in low-dimensional space reveals the fundamental mechanism of data fusion in the FGM-PDF method, which is significantly important to construct a data-driven PDF model in sparse-data scenarios with much better performance. Full article

Hybrid electric vertical take-off and landing (HEVTOL) flying vehicles serve as effective platforms for efficient transportation, forming a cornerstone of the emerging low-altitude economy. However, the current lack of co-optimization methods for powertrain component sizing and energy controller design often leads to suboptimal HEVTOL performance. To address this, this paper proposes a hierarchical manifold-enhanced Bayesian evolutionary optimization (HM-BEO) approach for HEVTOL systems. This framework employs lightweight manifold dimensionality reduction to compress the decision space, enabling Bayesian optimization (BO) on low-dimensional manifolds for a global coarse search. Subsequently, the approximate Pareto solutions generated by BO are utilized as initial populations for a non-dominated sorting genetic algorithm III (NSGA-III), which performs fine-grained refinement in the original high-dimensional design space. The co-optimization aims to minimize fuel consumption, battery state-of-health (SOH) degradation, and manufacturing costs while satisfying dynamic and energy management constraints. Evaluated using representative HEVTOL duty cycles, the HM-BEO demonstrates significant improvements in optimization efficiency and solution quality compared to conventional methods. Specifically, it achieves a 5.3% improvement in fuel economy, a 7.4% mitigation in battery SOH degradation, and a 1.7% reduction in system manufacturing cost compared to standard NSGA-III-based optimization. Full article

Deep learning approaches based on autoencoders have been widely used for structural monitoring. Traditional approaches of autoencoders based on reconstruction errors involve limitations, since they do not exploit their hierarchical nature, and only healthy data are used for training. In this work, some health indicators, based on manifold invariance through the encoding procedure, were built for the monitoring of concrete structures strengthened with carbon fiber-reinforced polymers by directly exploring the latent space representation of the input data to a deep autoencoder. Latent representations of experimental observations of different classes were used for the learning of the network, delimiting areas in a low-dimensional space. New synthetic data with their variations, generated with a variational autoencoder, were encompassed to the trained autoencoder. The proposed method was verified on raw electromechanical impedance spectra obtained from lead zirconate titanate sensors bonded on a specimen subjected to different loading stages. The results of this research demonstrate the efficiency of the proposed approach. Full article

Full-body movement involving multi-segmental coordination has been essential to our evolution as a species, but its study has been focused mostly on the analysis of one-dimensional data. The field is poised for a change by the availability of high-density recording and data sharing. New ideas are needed to revive classical theoretical questions such as the organization of the highly redundant biomechanical degrees of freedom and the optimal distribution of variability for efficiency and adaptiveness. In movement science, there are popular methods that up-dimensionalize: they start with one or a few recorded dimensions and make inferences about the properties of a higher-dimensional system. The opposite problem, dimensionality reduction, arises when making inferences about the properties of a low-dimensional manifold embedded inside a large number of kinematic degrees of freedom. We present an approach to quantify the smoothness and degree to which the kinematic manifold of full-body movement is distributed among embedding dimensions. The principal components of embedding dimensions are rank-ordered by variance. The power law scaling exponent of this variance spectrum is a function of the smoothness and dimensionality of the embedded manifold. It defines a threshold value below which the manifold becomes non-differentiable. We verified this approach by showing that the Kuramoto model obeys the threshold when approaching global synchronization. Next, we tested whether the scaling exponent was sensitive to participants’ gait impairment in a full-body motion capture dataset containing short gait trials. Variance scaling was highest in healthy individuals, followed by osteoarthritis patients after hip replacement, and lastly, the same patients before surgery. Interestingly, in the same order of groups, the intrinsic dimensionality increased but the fractal dimension decreased, suggesting a more compact but complex manifold in the healthy group. Thinking about manifold dimensionality and smoothness could inform classic problems in movement science and the exploration of the biomechanics of full-body action. Full article

Wind energy has emerged as a cornerstone in global efforts to transition to renewable energy, driven by its low environmental impact and significant generation potential. However, the inherent intermittency of wind, influenced by complex and dynamic atmospheric patterns, poses significant challenges for accurate wind speed prediction. Existing approaches, including statistical methods, machine learning, and deep learning, often struggle with limitations such as non-linearity, non-stationarity, computational demands, and the requirement for extensive, high-quality datasets. In response to these challenges, we propose a novel neighborhood preserving cross-dataset data augmentation framework for high-horizon wind speed prediction. The proposed method addresses data variability and dynamic behaviors through three key components: (i) the uniform manifold approximation and projection (UMAP) is employed as a non-linear dimensionality reduction technique to encode local relationships in wind speed time-series data while preserving neighborhood structures, (ii) a localized cross-dataset data augmentation (DA) approach is introduced using UMAP-reduced spaces to enhance data diversity and mitigate variability across datasets, and (iii) recurrent neural networks (RNNs) are trained on the augmented datasets to model temporal dependencies and non-linear patterns effectively. Our framework was evaluated using datasets from diverse geographical locations, including the Argonne Weather Observatory (USA), Chengdu Airport (China), and Beijing Capital International Airport (China). Comparative tests using regression-based measures on RNN, GRU, and LSTM architectures showed that the proposed method was better at improving the accuracy and generalizability of predictions, leading to an average reduction in prediction error. Consequently, our study highlights the potential of integrating advanced dimensionality reduction, data augmentation, and deep learning techniques to address critical challenges in renewable energy forecasting. Full article

Non-negative Matrix Factorization (NMF) has gained popularity due to its effectiveness in clustering and feature selection tasks. It is particularly valuable for managing high-dimensional data by reducing dimensionality and providing meaningful semantic representations. However, traditional NMF methods may encounter challenges when dealing with noisy data, outliers, or when the underlying manifold structure of the data is overlooked. This paper introduces an innovative approach called SGRiT, which employs Stiefel manifold optimization to enhance the extraction of latent features. These learned features have been shown to be highly informative for clustering tasks. The method leverages a spectral decomposition criterion to obtain a low-dimensional embedding that captures the intrinsic geometric structure of the data. Additionally, this paper presents a solution for addressing the Stiefel manifold problem and utilizes a Riemannian-based trust region algorithm to optimize the loss function. The outcome of this optimization process is a new representation of the data in a transformed space, which can subsequently serve as input for the NMF algorithm. Furthermore, this paper incorporates a novel subspace graph regularization term that considers high-order geometric information and introduces a sparsity term for the factor matrices. These enhancements significantly improve the discrimination capabilities of the learning process. This paper conducts an impartial analysis of several essential NMF algorithms. To demonstrate that the proposed approach consistently outperforms other benchmark algorithms, four clustering evaluation indices are employed. Full article

The working environment at coal mining faces is harsh, leading to high failure rates and significant maintenance issues with roadheaders. This study explores multi-layer dimensionality reduction of vibration signal features in complex environments to enhance the differentiation of different operational states of a roadheader, thereby achieving fault recognition of key components. Concurrently, reducing dimensionality in manifold spaces positively influences operational state differentiation. Therefore, this paper integrates manifold learning to conduct multi-sensor and multi-layer data mining to enhance the differential phenotypes between faults of key components of the roadheader. Initially, we constructed multiple status-reference sample sets for each sensor individually, forming multiple manifolds at different spatial points, and utilizing locality-preserving projections (LPP) to extract low-dimensional manifold features. Further fusion of low-dimensional features from multiple sensors was used to elevate samples, constructing an enhanced spatial pseudo-manifold. Finally, we used LPP to re-reduce the enhanced sensitive feature set from multiple vibration sensors, establishing a dual-layer sensitive feature enhancement learning model. Conducting fault recognition analysis on experimental vibration signals, using k-nearest neighbors (KNN) to classify the enhanced feature set, we achieved a recognition success rate of 98.75% for samples, proving the method’s feasibility in fault recognition under complex loads. Full article

Systems may depend on parameters that can be controlled, serve to optimise the system, are imposed externally, or are uncertain. This last case is taken as the “Leitmotiv” for the following discussion.A reduced-order model is produced from the full-order model through some kind of projection onto a relatively low-dimensional manifold or subspace. The parameter-dependent reduction process produces a function mapping the parameters to the manifold.One now wants to examine the relation between the full and the reduced state for all possible parameter values of interest. Similarly, in the field of machine learning, a function mapping the parameter set to the image space of the machine learning model is learned from a training set of samples, typically minimising the mean square error. This set may be seen as a sample from some probability distribution, and thus the training is an approximate computation of the expectation, giving an approximation of the conditional expectation—a special case of Bayesian updating, where the Bayesian loss function is the mean square error. This offers the possibility of having a combined view of these methods and also of introducing more general loss functions. Full article

This study proposes a novel self-supervised data-preprocessing framework for time-series forecasting in complex ship systems. The framework integrates an improved Learnable Wavelet Packet Transform (L-WPT) for adaptive denoising and a correlation-based Uniform Manifold Approximation and Projection (UMAP) approach for dimensionality reduction. The enhanced L-WPT incorporates Reversible Instance Normalization to improve training efficiency while preserving denoising performance, especially for low-frequency sporadic noise. The UMAP dimensionality reduction, combined with a modified K-means clustering using correlation coefficients, enhances the computational efficiency and interpretability of the reduced data. Experimental results validate that state-of-the-art time-series models can effectively forecast the data processed by this framework, achieving promising MSE and MAE metrics. Full article

The underwater electric field signal can be excited by underwater vehicles, such as the shaft-rate electric field and the corrosion electric field. The electric field signature of each vehicle exhibits significant differences in time and frequency domain, which can be exploited to determine target positions. In this paper, a novel passive localization method for underwater targets is presented, leveraging a uniform linear electrode array (ULEA). The ULEA manifold along the axial direction is derived from the electric field propagation in an infinite lossy medium, which provides the nonlinear mapping relationship between the target position and the voltage data acquired by the ULEA. In order to locate the targets, the multiple signal classification (MUSIC) algorithm is applied. Then, capitalizing on the rotational invariance of matrix operations and exploiting the symmetry inherent in the ULEA, we streamline the six-dimensional spatial spectral scanning onto a two-dimensional plane, providing azimuth and distance information for the targets. This method significantly reduces computational overhead. To validate the efficacy of our proposed method, we devise a localization system and conduct a simulation environment to estimate targets. Results show that our method achieves satisfactory direction and reliable distance estimations, even in scenarios with low signal-to-noise ratios. Full article

Hierarchical clustering analysis (HCA) is a widely used unsupervised learning method. Limitations of HCA, however, include imposing an artificial hierarchy onto non-hierarchical data and fixed two-way mergers at every level. To address this, the current work describes a novel rootlets hierarchical principal component analysis (hPCA). This method extends typical hPCA using multivariate statistics to construct adaptive multiway mergers and Riemannian geometry to visualize nested dependencies. The rootlets hPCA algorithm and its projection onto the Poincaré disk are presented as examples of this extended framework. The algorithm constructs high-dimensional mergers using a single parameter, interpreted as a p-value. It decomposes a similarity matrix from GL(m, ℝ) using a sequence of rotations from SO(k), k << m. Analysis shows that the rootlets algorithm limits the number of distinct eigenvalues for any merger. Nested clusters of arbitrary size but equal correlations are constructed and merged using their leading principal components. The visualization method then maps elements of SO(k) onto a low-dimensional hyperbolic manifold, the Poincaré disk. Rootlets hPCA was validated using simulated datasets with known hierarchical structure, and a neuroimaging dataset with an unknown hierarchy. Experiments demonstrate that rootlets hPCA accurately reconstructs known hierarchies and, unlike HCA, does not impose a hierarchy on data. Full article

Building on a previously developed partially synthetic data generation algorithm utilizing data visualization techniques, this study extends the novel algorithm to generate fully synthetic tabular healthcare data. In this enhanced form, the algorithm serves as an alternative to conventional methods based on Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). By iteratively applying the original methodology, the adapted algorithm employs UMAP (Uniform Manifold Approximation and Projection), a dimensionality reduction technique, to validate generated samples through low-dimensional clustering. This approach has been successfully applied to three healthcare domains: prostate cancer, breast cancer, and cardiovascular disease. The generated synthetic data have been rigorously evaluated for fidelity and utility. Results show that the UMAP-based algorithm outperforms GAN- and VAE-based generation methods across different scenarios. In fidelity assessments, it achieved smaller maximum distances between the cumulative distribution functions of real and synthetic data for different attributes. In utility evaluations, the UMAP-based synthetic datasets enhanced machine learning model performance, particularly in classification tasks. In conclusion, this method represents a robust solution for generating secure, high-quality synthetic healthcare data, effectively addressing data scarcity challenges. Full article

The stability of a nonlinear aero-thermo-elastic panel in supersonic flow is analyzed numerically. In light of Hamilton’s principle, the governing equation of motion for a two-dimensional aero-thermo-elastic panel is established taking geometric nonlinearity and curvature effect into account. Coupling with the panel vibration, aerodynamic pressure is evaluated by first order supersonic piston theory and aerothermal load is approximated by the quasi-steady theory of thermal stress. A Galerkin method based on approximate inertial manifolds is deduced for low-dimensional dynamic modeling. The efficiency of the method is discussed. Finally, the complex stability regions of the system are presented within the parametric space. The Hopf bifurcation is found during the onset of flutter as the dynamic pressure increases. The temperature rise imposes a significant effect on the stability region of the panel. Since the material parameters of the panel (elastic modulus and thermal expansion coefficient in this case) are the function of temperature, the panel tends to lose its stability as the temperature gets higher. Full article