Search Results (163)

The graph Hilbert transform (GHT) is a key tool in constructing analytic signals and extracting envelope and phase information in graph signal processing. However, its utility is limited by confinement to the graph Fourier domain, a fixed phase shift, information loss for real-valued spectral components, and the absence of tunable parameters. The graph fractional Fourier transform introduces domain flexibility through a fractional order parameter $\alpha$ but does not resolve the issues of phase rigidity and information loss. Inspired by the dual-parameter fractional Hilbert transform (FRHT) in classical signal processing, we propose the graph FRHT (GFRHT). The GFRHT incorporates a dual-parameter framework: the fractional order $\alpha$ enables analysis across arbitrary fractional domains, interpolating between vertex and spectral spaces, while the angle parameter $\beta$ provides adjustable phase shifts and a non-zero real-valued response ($cos\beta$) for real eigenvalues, thereby eliminating information loss. We formally define the GFRHT, establish its core properties, and design a method for graph analytic signal construction, enabling precise envelope extraction and demodulation. Experiments on anomaly identification, speech classification and edge detection demonstrate that GFRHT outperforms GHT, offering greater flexibility and superior performance in graph signal processing. Full article

In order to screen high-quality processed tomato germplasm resources, the present research measured the content of quality indicators—lycopene, soluble solids, total acidity, total sugar, and vitamin C—in mature fruits of 113 processed tomato high-generation inbred lines. Comprehensive evaluations of germplasm quality were conducted through genetic diversity analysis, correlation analysis, principal component analysis, and cluster analysis. The results indicated that the variability of the five quality traits in the materials under test was relatively high, with a range of variation from 12.21% to 39.04%. Total sugar exhibited the greatest variation, while soluble solids content showed the least variation. The genetic diversity index ranged from 1.899 to 2.064, with total sugar, vitamin C, and lycopene showing high genetic variation. Soluble solids content was significantly positively correlated with lycopene, total sugar, and total acidity, while lycopene content was significantly positively correlated with total sugar. Vitamin C showed weaker correlations with other traits, but exhibited a significant negative correlation with total sugar. Total acidity had relatively simple correlations with other traits, being significantly correlated only with soluble solids. The three principal components extracted from the principal component analysis all had eigenvalues above 0.8%, contributing to a cumulative contribution rate of 77.435%. Through cluster analysis, the tested materials were divided into six major groups at an Euclidean distance of 15. Group I serves as candidate materials for breeding varieties with good basic quality and high vitamin C content. Group II stood out in terms of high sugar and lycopene content, suitable for developing tomato sauce or juice products with high vibrancy and sweetness. Group III had a high nutritional value and vibrant color, serving as core germplasm resources for breeding high-end processing-specific varieties. Group IV had high soluble solids content, making it a parent source for improving the viscosity and flavor of sauce tomatoes. Group V was suitable for specific formulations requiring high acidity or as breeding materials for high-acidity characteristics. Group VI had limited processing potential and should be used cautiously in breeding. The comprehensive evaluation results showed that the top five germplasm resources in terms of score were W119, 61, 82, 83, and W144. This study enriched the high-quality processed tomato germplasm resources and provided parental resources for quality breeding of processed tomatoes. Full article

Direction of arrival (DOA) estimation is a fundamental problem in array signal processing, with extensive applications in radar, communications, sonar, and other fields. Traditional DOA estimation methods, such as MUSIC and ESPRIT, rely on eigenvalue decomposition or spectral peak search, which suffer from high computational complexity and performance degradation under conditions of low signal-to-noise ratio (SNR), coherent signals, and array imperfections. Cylindrical arrays offer unique advantages for omnidirectional sensing due to their circular structure and three-dimensional coverage capability; however, their nonlinear array manifold increases the difficulty of estimation. This paper proposes a circular-attention residual network (CA-ResNet) for DOA estimation using uniform cylindrical arrays. The proposed approach achieves high accuracy and robust angle estimation through phase difference feature extraction, a multi-scale residual network, an attention mechanism, and a joint output module. Simulation results demonstrate that the proposed CA-ResNet method delivers superior performance under challenging scenarios, including low SNR (−10 dB), a small number of snapshots (L = 5), and multiple sources (1 to 4 signal sources). The corresponding root mean square errors (RMSE) are 0.21°, 0.45°, and below 1.5°, respectively, significantly outperforming traditional methods like MUSIC and ESPRIT, as well as existing deep learning models (e.g., ResNet, CNN, MLP). Furthermore, the algorithm exhibits low computational complexity and a small parameter size, highlighting its strong potential for practical engineering applications and robustness. Full article

Male turkeys are raised mainly for meat production due to their high carcass yields and good capacity to convert food into meat. However, their carcass characteristics remain poorly understood. The objective of the study was to describe the carcass traits of 45 male native Mexican turkeys raised in the municipality of Champoton, Mexico, using principal component analysis (PCA). Fourteen carcass traits, namely, slaughter weight (SW), hot carcass weight (HCW), cold carcass weight (CCW), dressing percentage (DP), neck weight (NEW), foot weight (FEW), breast weight (BRW), thigh weight (THW), drumstick weight (DRW), wing weight (WIW), back weight (BAW), gizzard weight (GIW), heart weight (HEW), and liver weight (LIW), were collected. Pearson’s correlation analysis revealed strong positive relationships among carcass variables, with the highest correlations observed between CCW and HCW (r = 0.99; p < 0.001), SW and HCW (r = 0.98; p < 0.001), and SW and CCW (r = 0.98; p < 0.001). Hierarchical clustering identified four main groups of variables with similar correlation patterns. Three principal components (PCs) with eigenvalues greater than 1.0 were extracted, explaining 85.48% of the total variance in carcass traits. The first principal component (PC1) contributed 72.81% of the total variation (eigenvalue = 10.19), with high loadings (>0.70) for CCW (0.98), HCW (0.98), SW (0.98), DRW (0.95), BRW (0.91), WIW (0.90), THW (0.89), HEW (0.87), BAW (0.81), and FEW (0.82), representing a general size factor. PC2 explained 6.86% of the variance (eigenvalue = 0.96), characterized by a negative loading for DP (−0.64) and positive loadings for GIW (0.35) and LIW (0.34). PC3 accounted for 5.81% of the variance (eigenvalue = 0.81), with a negative loading for LIW (−0.63) and positive loadings for NEW (0.51) and FEW (0.46). Communality values exceeded 0.85 for all variables, indicating adequate representation in the reduced dimensional space. It was concluded that PCA effectively reduced dimensionality while retaining 85.48% of original information and can be used for the improvement of the carcass traits of male native Mexican turkey breeding programs. Full article

We construct a family of self-adjoint operators on the prime numbers whose entries depend on pairwise arithmetic divergences, replacing geometric distance with number-theoretic dissimilarity. The resulting spectra encode how coherence propagates through the prime sequence and define an emergent arithmetic geometry. From these spectra we extract observables such as the heat trace, entropy, and eigenvalue growth, which reveal persistent spectral compression): eigenvalues grow sublinearly, entropy scales slowly, and the inferred dimension remains strictly below one. This rigidity appears across logarithmic, entropic, and fractal-type kernels, reflecting intrinsic arithmetic constraints. Analytically, we show that for the unnormalized Laplacian, the continuum limit of its squared Hamiltonian corresponds to the one-dimensional bi-Laplacian, whose heat trace follows a short-time scaling proportional to $t^{-1/4}$. Under the spectral dimension convention $d_s=-2d\log \Theta /d\log t$, this result produces $d_s=1/2$ directly from first principles, without fitting or external hypotheses. This value signifies maximal spectral compression and the absence of classical diffusion, indicating that arithmetic sparsity enforces a coherence-limited, non-Euclidean geometry linking spectral and number-theoretic structure. Full article

To rationally utilize Morchella germplasm resources, this study investigated 13 phenotypic traits in 231 Chinese Morchella germplasm accessions. Accessions were stratified by cap color and subjected to comparative analyses using four sampling methods, five sampling intensities, two genetic distance metrics, and four hierarchical clustering algorithms to determine the optimal strategy for core collection construction. The optimal sampling strategy for core collection construction was identified using six evaluation. Phenotypic traits of the core collection were evaluated using genetic diversity eigenvalues, t-tests, F-tests, and systematic clustering, with confirmation via principal component analysis. The results indicate that the logarithmic ratio method yielded the smallest differences in group proportions, making it the optimal sampling method. A 15% sample intensity proved optimal, with Euclidean distance outperforming Mahalanobis distance. The longest-distance method was determined to be the optimal clustering approach. Within the optimal sampling strategy combination, the CR value reached its maximum (97.77%). Ultimately, 34 Morchella germplasm resources were extracted, accounting for 14.72% of the total germplasm (original germplasm). The mean values, standard deviations, and genetic diversity of phenotypic traits were similar between the original germplasm and the core collection. However, the coefficient of variation for quantitative traits showed significant differences. In the t-test, only the maturity period showed a significant difference. In the F-test, only the cap length/width and maturity period showed significant differences. Cluster analysis grouped the germplasm resources of the core collection and the original germplasm into relatively consistent clusters. In principal component analysis, the eigenvalues and cumulative contribution rates of the first four principal components were higher for the core collection than for the original germplasm. This indicates that the core collection eliminated most genetic redundancy while preserving the genetic diversity of the original germplasm. The core collection selection is representative and can be effectively utilized as breeding material. This study provides a reference for the effective utilization and germplasm innovation of Morchella germplasm resources. Full article

The failure to accurately identify abnormal vibrations in protected metro areas is a serious threat to the operational safety of metro tunnels and trains, and there is currently no suitable method for effectively improving the accuracy of abnormal vibration identification. To address this issue, an accurate method for identifying abnormal vibrations in a metro reserve based on spatially correlated dense measurement points is proposed. First, by arranging distributed optical fibers along the longitudinal length of a tunnel, dynamic strain vibration signals are extracted via phase-sensitive optical time-domain reflectometry analysis, and analysis of variance (ANOVA) and Pearson correlation analysis are used to jointly downscale the dynamic strain features. On this basis, a spatial correlation between the calculated values of the features of the target measurement points to be updated and its adjacent measurement points is constructed, and the spatial correlation credibility of the dynamic strain features between the dense measurement points and the target measurement points to be updated is calculated via quadratic function weighting and kernel density estimation methods. The weights are calculated, and the eigenvalues of the target measurement points are updated on the basis of the correlation credibility weights between the adjacent measurement points. Finally, a support vector machine (SVM) and back propagation (BP) identification model for the eigenvalues of the target measurement points are constructed to identify the dynamic strain eigenvalues of the abnormal vibrations in the underground tunnel. Numerical simulations and an experiment in an actual tunnel verify the effectiveness of the proposed method. Full article

This research aims to actively suppress vibrations at the end-effector of a flexible manipulator. When configured in a locked state, the system behaves as a two-link manipulator subjected to disturbances on the first link. To analyze its behavior, Finite Element Analysis (FEA) is employed to extract the natural frequencies (eigenvalues) and corresponding mode shapes (eigenvectors) of a two-link, two-joint flexible manipulator (2L2JM). The obtained eigenvectors are transformed into uncoupled state-space equations using balanced realization and the Match-DC-Gain model reduction algorithm. An H-infinity controller is then designed and applied to both the full-order and reduced-order models of the manipulator. The objective of this study is to validate an analytical framework through FEA, demonstrating its applicability to complex manipulators with multiple joints and flexible links. Given that the full state-space representation typically results in high-dimensional matrices, model reduction enables effective vibration control with a minimal number of states. The derivation of the 2L2JM state space, its model reduction, and a subsequent control strategy have not been previously addressed in this manner. Simulation results showcasing vibration suppression of a cantilever beam are presented and benchmarked against two alternative modeling approaches. Full article

Unsupervised representation learning has emerged as a promising paradigm in machine learning, owing to its capacity to extract semantically meaningful features from unlabeled data. Despite recent progress, however, such methods remain vulnerable to collapse phenomena, wherein the expressiveness and diversity of learned representations are severely degraded. This phenomenon poses significant challenges to both model performance and generalizability. This paper presents a systematic investigation into two distinct forms of collapse: complete collapse and dimensional collapse. Complete collapse typically arises in non-contrastive frameworks, where all learned representations converge to trivial constants, thereby rendering the learned feature space non-informative. While contrastive learning has been introduced as a principled remedy, recent empirical findings indicate that it falls to prevent collapse entirely. In particular, contrastive methods are still susceptible to dimensional collapse, where representations are confined to a narrow subspace, thus restricting both the information content and effective dimensionality. To address these concerns, we conduct a comprehensive literature analysis encompassing theoretical definitions, underlying causes, and mitigation strategies for each collapse type. We further categorize recent approaches to collapse prevention, including feature decorrelation techniques, eigenvalue distribution regularization, and batch-level statistical constraints, and assess their effectiveness through a comparative framework. This work aims to establish a unified conceptual foundation for understanding collapse in unsupervised learning and to guide the design of more robust representation learning algorithms. Full article

The manual lifting of heavy loads by personnel is susceptible to the development of muscle fatigue, which, in severe cases, can result in the irreversible impairment of muscle function. This study proposes a novel method of signal fusion to analyse muscle fatigue during manual lifting. Furthermore, this study represents the inaugural application of the back-propagation neural network and bidirectional encoder representation from the transformer (BP + BERT) algorithm to the fusion of two sensor inputs for the analysis of muscle fatigue. Lifting action fatigue tests were carried out on 16 testers in this study, with both surface electromyography (sEMG) and mechanomyography (MMG) signals collected as part of the process. The mean power frequency (MPF) eigenvalues were extracted separately for the two signals, and the results of muscle fatigue labelling according to the trend of the MPF eigenpeak were merged to produce three datasets. Subsequently, the three datasets were employed to categorise muscle fatigue classes using the support vector machine and radial basis function (SVM + RBF), support vector machine and bidirectional encoder representation from transformer (SVM + BERT), back-propagation neural network (BP), and back-propagation neural network and bidirectional encoder representation from transformer (BP + BERT) algorithms, respectively. The results of the muscle fatigue classification model demonstrated that the sEMG and MMG fused dataset, imported into the BP + BERT algorithm, exhibited the highest average accuracy of 98.10% for the muscle fatigue classification model. This study indicates that the fusion of sEMG and MMG signals is an effective approach, and the performance of the BP + BERT muscle fatigue classification model is also enhanced. Full article

Food image recognition is a key research area in food computing, with applications in dietary assessment, menu analysis, and nutrition monitoring. However, imaging devices and environmental factors introduce noise, limiting classification performance. To address this, we propose a food image recognition method based on anti-noise learning and covariance feature enhancement. Specifically, we design a Noise Adaptive Recognition Module (NARM), which incorporates noisy images during training and treats denoising as an auxiliary task to enhance noise invariance and recognition accuracy. To mitigate the adverse effects of noise and strengthen the representation of small eigenvalues, we introduce Eigenvalue-Enhanced Global Covariance Pooling (EGCP) into NARM. Furthermore, we develop a Weighted Multi-Granularity Fusion (WMF) method to improve feature extraction. Combined with the Progressive Temperature-Aware Feature Distillation (PTAFD) strategy, our approach optimizes model efficiency without adding overhead to the backbone. Experimental results demonstrate that our model achieves state-of-the-art performance on the ETH Food-101 and Vireo Food-172 datasets. Specifically, it reaches a Top-1 accuracy of 92.57% on ETH Food-101, outperforming existing methods, and it also delivers strong results in Top-5 on ETH Food-101 and both Top-1 and Top-5 on Vireo Food-172. These findings confirmed the effectiveness and robustness of the proposed approach in real-world food image recognition. Full article

We propose an efficient Nyström-based unitary subspace method for low-complexity two-dimensional (2D) direction-of-arrival (DOA) estimation in uniform rectangular array (URA) signal processing systems. The conventional high-resolution DOA estimation methods often suffer from excessive computational complexity, particularly when dealing with large-scale antenna arrays. The proposed method addresses this challenge by combining the Nyström approximation with a unitary transformation to reduce the computational burden while maintaining estimation accuracy. The signal subspace is approximated using a partitioned covariance matrix, and a real-valued transformation is applied to further simplify the eigenvalue decomposition (EVD) process. Furthermore, the linear prediction coefficients are estimated via a weighted least squares (WLS) approach, enabling robust extraction of the angular parameters. The 2D DOA estimates are then derived from these coefficients through a closed-form solution, eliminating the need for exhaustive spectral searches. Numerical simulations demonstrate that the proposed method achieves comparable estimation performance to state-of-the-art techniques while significantly reducing computational complexity. For a fixed array size of $M=N=20$, the proposed method demonstrates significant computational efficiency, requiring less than $50\%$ of the running time compared to conventional ESPRIT, and only $6\%$ of the time required by ML methods, while maintaining similar performance. This makes it particularly suitable for real-time applications where computational efficiency is critical. The novelty lies in the integration of Nyström approximation and unitary subspace techniques, which jointly enable efficient and accurate 2D DOA estimation without sacrificing robustness against noise. The method is applicable to a wide range of array processing scenarios, including radar, sonar, and wireless communications. Full article

Gearbox failure represents one of the most time-consuming maintenance challenges in wind turbine operations. Abnormal temperature variations in the gearbox high-speed shaft (GHSS) serve as reliable indicators of potential faults. This study proposes a Spatio-Temporal Attentive (STA) synergistic architecture for GHSS fault detection and early warning by utilizing the in situ monitoring data from a wind farm. This comprehensive architecture involves five modules: data preprocessing, multi-dimensional spatial feature extraction, temporal dependency modeling, global relationship learning, and hyperparameter optimization. It was achieved by using real-time monitoring data to predict the GHSS temperature in 10 min, with an accuracy of 1 °C. Compared to the long short-term memory (LSTM) and convolutional neural network and LSTM hybrid models, the STA architecture reduces the root mean square error of the prediction by approximately 37% and 13%, respectively. Furthermore, the architecture establishes a normal operating condition model and provides benchmark eigenvalues for subsequent fault warnings. The model was validated to issue early warnings up to seven hours before the fault alert is triggered by the supervisory control and data acquisition system of the wind turbine. By offering reliable, cost-effective prognostics without additional hardware, this approach significantly improves wind turbine health management and fault prevention. Full article

The chlorophyll content is an important index reflecting the growth status and nutritional level of plants. The rapid, accurate and nondestructive monitoring of the SPAD content of apple trees can provide a basis for large-scale monitoring and scientific management of the growth status of apple trees. In this study, the canopy leaves of apple trees at different growth stages in the same year were taken as the research object, and remote sensing images of fruit trees in different growth stages (flower-falling stage, fruit-setting stage, fruit expansion stage, fruit-coloring stage and fruit-maturing stage) were acquired via a DJI MAVIC 3 multispectral unmanned aerial vehicle (UAV). Then, the spectral reflectance was extracted to calculate 15 common vegetation indexes as eigenvalues, the 5 vegetation indexes with the highest correlation were screened out through Pearson correlation analysis as the feature combination, and the measured SPAD values in the leaves of the fruit trees were gained using a handheld chlorophyll meter in the same stages. The estimation models for the SPAD values in different growth stages were, respectively, established through five machine learning algorithms: multiple linear regression (MLR), partial least squares regression (PLSR), support vector regression (SVR), random forest (RF) and extreme gradient boosting (XGBoost). Additionally, the model performance was assessed by selecting the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). The results show that the SPAD estimation results vary from stage to stage, where the best estimation model for the flower-falling stage, fruit-setting stage and fruit-maturing stage is RF and those for the fruit expansion stage and fruit-coloring stage are PLSR and MLR, respectively. Among the estimation models in the different growth stages, the model accuracy for the fruit expansion stage is the highest, with R² = 0.787, RMSE = 0.87 and MAE = 0.644. The RF model, which outperforms the other models in terms of the prediction effect in multiple growth stages, can effectively predict the SPAD value in the leaves of apple trees and provide a reference for the growth status monitoring and precise management of orchards. Full article

Superheat degree (SD) is an important indicator for identifying the status of aluminum electrolytic cells. The fire hole video of the aluminum electrolytic cell captured by an industrial camera is an important basis for identifying SD. This article proposes a novel method that VideoMamba enhances with attention and learnable Fourier transform (CFVM) for SD identification. With a lower computational complexity and feature extraction capabilities comparable to transformers, VideoMamba offers the CFVM model a stronger feature extraction basis. The channel attention mechanism (CAM) block can achieve information exchange between channels. Through matrix eigenvalue manipulation, the learnable nonlinear Fourier transform (LNFT) block may guarantee stable convergence of the model. Furthermore, the LNFT block can efficiently use mixed frequency domain channels to capture global dependency information. The model is trained using the aluminum electrolysis fire hole dataset. Compared with recent fire hole identification models that primarily rely on neural networks, the method proposed in this paper is based on the concept of state space modeling, offering lower model complexity and enhanced feature extraction capability. Experimental results demonstrate that the proposed model achieves competitive performance in fire hole video identification tasks, reaching an identification accuracy of 85.7% on the test set. Full article