Search Results (13)

In structural health monitoring (SHM), ensuring data completeness is critical for enhancing the accuracy and reliability of structural condition assessments. SHM data are prone to random missing values due to signal interference or connectivity issues, making precise data imputation essential. A latent factorization of tensor (LFT)-based method has proven effective for such problems, with optimization typically achieved via stochastic gradient descent (SGD). However, SGD-based LFT models and other imputation methods exhibit significant sensitivity to learning rates and slow tail-end convergence. To address these limitations, this study proposes an RMSprop-incorporated latent factorization of tensor (RLFT) model, which integrates an adaptive learning rate mechanism to dynamically adjust step sizes based on gradient magnitudes. Experimental validation on a scaled bridge accelerometer dataset demonstrates that RLFT achieves faster convergence and higher imputation accuracy compared to state-of-the-art models including SGD-based LFT and the long short-term memory (LSTM) network, with improvements of at least 10% in both imputation accuracy and convergence rate, offering a more efficient and reliable solution for missing data handling in SHM. Full article

In forestry data management and analysis, data integrity and analytical accuracy are of critical importance. However, existing techniques face a dual challenge: first, sensor failures, data transmission interruptions, and human errors lead to the prevalence of missing data in forestry datasets; second, the multidimensional heterogeneity and environmental complexity of forestry systems not only increase the difficulty of missing value estimation, but also significantly affect the accuracy of resolving the potential correlations among data. In order to solve the above problems, we proposed the $L^2$ model using the aspen woodland as the experimental object. The $L^2$ model consists of a complementary model and a predictive model. The $L^2$ complementary model integrates low tensor tensor kernel norm minimisation (LRTC-TNN) to capture global consistency and local trends, and combines long and short-term memory and convolutional neural network (LSTM-CNN) to extract temporal and spatial features, which is effective in accurately reconstructing the missing values in forestry time-series data. We also optimised the LRTC-TNN model to handle multi-class data and incorporated a self-attention mechanism into the LSTM-CNN framework to improve performance in the case of complex missing data. The $L^2$ prediction model adopts a dual attention mechanism (temporal attention mechanism and feature attention mechanism) based on LSTM to construct a stem diameter prediction model, which achieves high-precision prediction of stem diameter variation. Then we further analyzed the effects of various factors on stem diameter using SHAP (Shapley Additive Explanations). Experimental results demonstrate that our $L^2$ significantly improves data completion accuracy while preserving the original structure and key characteristics of the data. Moreover, it enables a more precise analysis of the factors affecting stem diameter, providing a robust foundation for advanced forestry data analysis and informed decision making. Full article

The prediction of lithium-ion battery capacity degradation is crucial for enhancing the reliability, efficiency, and sustainability of energy storage systems. This study proposes a data-driven approach to model capacity degradation in 18650 lithium-ion cells, supporting the long-term performance and responsible management of battery technologies. A systematic search was conducted to identify publicly available experimental datasets reporting charge/discharge processes, leading to the selection of the MIT-BIT Battery Degradation Dataset (Fixed Current Profiles and Arbitrary Use Profiles). This dataset was chosen for its extensive degradation data, variability, and adaptability to real-world applications. Of the 77 tested cells, 73 were included after filtering data completeness; cells with missing critical information, such as temperature, were excluded. A subset of cells tested under a 1C–2C charge/discharge profile was analyzed, and cell 52 was selected for its comprehensive structure. Using this dataset, a predictive model was developed to estimate the battery capacity based on the current, voltage, and temperature, with capacity as the target variable. A neural network was implemented using TensorFlow and Keras, incorporating ReLU activation, Adam optimization, and multiple loss functions. The dataset was standardized using MinMaxScaler, StandardScaler, and RobustScaler, and the training–test split was 75–25%. The model achieved a prediction error of 3.35% during training and 3.48% during validation, demonstrating robustness and efficiency. These results highlight the potential of data-driven models in accurately predicting lithium-ion battery degradation and underscore their relevance for promoting sustainable energy systems through improved battery health forecasting, optimized second-life use, and extended operational lifetimes of storage technologies. Full article

Tensor restoration finds applications in various fields, including data science, image processing, and machine learning, where the global low-rank property is a crucial prior. As the convex relaxation to the tensor rank function, the traditional tensor nuclear norm is used by directly adding all the singular values of a tensor. Considering the variations among singular values, nonconvex regularizations have been proposed to approximate the tensor rank function more effectively, leading to improved recovery performance. In addition, the local characteristics of the tensor could further improve detail recovery. Currently, the gradient tensor is explored to effectively capture the smoothness property across tensor dimensions. However, previous studies considered the gradient tensor only within the context of the nuclear norm. In order to better simultaneously represent the global low-rank property and local smoothness of tensors, we propose a novel regularization, the Tensor-Correlated Total Variation (TCTV), based on the nonconvex Geman norm and total variation. Specifically, the proposed method minimizes the nonconvex Geman norm on singular values of the gradient tensor. It enhances the recovery performance of a low-rank tensor by simultaneously reducing estimation bias, improving approximation accuracy, preserving fine-grained structural details and maintaining good computational efficiency compared to traditional convex regularizations. Based on the proposed TCTV regularization, we develop TC-TCTV and TRPCA-TCTV models to solve completion and denoising problems, respectively. Subsequently, the proposed models are solved by the Alternating Direction Method of Multipliers (ADMM), and the complexity and convergence of the algorithm are analyzed. Extensive numerical results on multiple datasets validate the superior recovery performance of our method, even in extreme conditions with high missing rates. Full article

Recovering incomplete high-dimensional data to create complete and valuable datasets is the main focus of tensor completion research, which lies at the intersection of mathematics and information science. Researchers typically apply various linear and nonlinear transformations to the original tensor, using regularization terms like the nuclear norm for low-rank approximation. However, relying solely on the tensor nuclear norm can lead to suboptimal solutions because of the convex relaxation of tensor rank, which strays from the original outcomes. To tackle these issues, we introduce the low-rank approximation nonconvex nonlinear transformation (LRANNT) method. By employing nonconvex norms and nonlinear transformations, we can more accurately capture the intrinsic structure of tensors, providing a more effective solution to the tensor completion problem. Additionally, we propose the proximal alternating minimization (PAM) algorithm to solve the model, demonstrating its convergence. Tests on publicly available datasets demonstrate that our method outperforms the current state-of-the-art approaches, even under extreme conditions with a high missing rate of up to 97.5%. Full article

The multi-modal knowledge graph completion (MMKGC) task aims to automatically mine the missing factual knowledge from the existing multi-modal knowledge graphs (MMKGs), which is crucial in advancing cross-modal learning and reasoning. However, few methods consider the adverse effects caused by different missing modal information in the model learning process. To address the above challenges, we innovatively propose a Modal Equilibrium Relational Graph framEwork, called MERGE. By constructing three modal-specific directed relational graph attention networks, MERGE can implicitly represent missing modal information for entities by aggregating the modal embeddings from neighboring nodes. Subsequently, a fusion approach based on low-rank tensor decomposition is adopted to align multiple modal features in both the explicit structural level and the implicit semantic level, utilizing the structural information inherent in the original knowledge graphs, which enhances the interpretability of the fused features. Furthermore, we introduce a novel interpolation re-ranking strategy to adjust the importance of modalities during inference while preserving the semantic integrity of each modality. The proposed framework has been validated on four publicly available datasets, and the experimental results have demonstrated the effectiveness and robustness of our method in the MMKGC task. Full article

Array sensor failure poses a serious challenge to robust direction-of-arrival (DOA) estimation in complicated environments. Although existing matrix completion methods can successfully recover the damaged signals of an impaired sensor array, they cannot preserve the multi-way signal characteristics as the dimension of arrays expands. In this paper, we propose a structural-missing tensor completion algorithm for robust DOA estimation with uniform rectangular array (URA), which exhibits a high robustness to non-ideal sensor failure conditions. Specifically, the signals received at the impaired URA are represented as a three-dimensional incomplete tensor, which contains whole fibers or slices of missing elements. Due to this structural-missing pattern, the conventional low-rank tensor completion becomes ineffective. To resolve this issue, a spatio-temporal dimension augmentation method is developed to transform the structural-missing tensor signal into a six-dimensional Hankel tensor with dispersed missing elements. The augmented Hankel tensor can then be completed with a low-rank regularization by solving a Hankel tensor nuclear norm minimization problem. As such, the inverse Hankelization on the completed Hankel tensor recovers the tensor signal of an unimpaired URA. Accordingly, a completed covariance tensor can be derived and decomposed for robust DOA estimation. Simulation results verify the effectiveness of the proposed algorithm. Full article

Changes in the deflection of cable-stayed bridges due to thermal effects may adversely affect the bridge structure and reflect the degradation of bridge performance. Therefore, complete deflection field data are important for bridge health monitoring. A strong linear correlation has been found between temperature-induced deflections in different positions of the same span of a cable-stayed bridge in many studies, which make the deflection data matrix/tensor have a low-rank structure. Therefore, it is appropriate to use a low-rank matrix/tensor learning to model the temperature–deflection field of a cable-stayed bridge. Moreover, to avoid disturbing the recovery results via abnormal data (e.g., baseline shift and outliers), a Bayesian robust tensor learning method is proposed to extract the spatio-temporal characteristics of the bridge temperature–deflection field. The missing data recovery and abnormal data cleaning are achieved simultaneously in the process of reconstructing the temperature-induced field via tensor learning. The performance of the method is verified with actual continuous monitoring data from a cable-stayed bridge. The experimental results show that low-order tensor (i.e., matrix) learning has a good recovery and cleaning performance. The extension to higher-order tensor learning is proposed to extract the spatial symmetry of the sensor locations, which is experimentally proven to have better missing recovery and abnormal data cleaning performance. Full article

Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is the task of inferring missing facts based on existing ones. Knowledge graph embedding, representing entities and relations in the knowledge graphs with high-dimensional vectors, has made significant progress in link prediction. The tensor decomposition models are an embedding family with good performance in link prediction. The previous tensor decomposition models do not consider the problem of attribute separation. These models mainly explore particular regularization to improve performance. No matter how sophisticated the design of tensor decomposition models is, the performance is theoretically under the basic tensor decomposition model. Moreover, the unnoticed task of attribute separation in the traditional models is just handed over to the training. However, the amount of parameters for this task is tremendous, and the model is prone to overfitting. We investigate the design approaching the theoretical performance of tensor decomposition models in this paper. The observation that measuring the rationality of specific triples means comparing the matching degree of the specific attributes associated with the relations is well-known. Therefore, the comparison of actual triples needs first to separate specific attribute dimensions, which is ignored by existing models. Inspired by this observation, we design a novel tensor ecomposition model based on Separating Attribute space for knowledge graph completion (SeAttE). The major novelty of this paper is that SeAttE is the first model among the tensor decomposition family to consider the attribute space separation task. Furthermore, SeAttE transforms the learning of too many parameters for the attribute space separation task into the structure’s design. This operation allows the model to focus on learning the semantic equivalence between relations, causing the performance to approach the theoretical limit. We also prove that RESCAL, DisMult and ComplEx are special cases of SeAttE in this paper. Furthermore, we classify existing tensor decomposition models for subsequent researchers. Experiments on the benchmark datasets show that SeAttE has achieved state-of-the-art among tensor decomposition models. Full article

In recent years, as photovoltaic (PV) power generation has rapidly increased on a global scale, there is a growing need for a highly accurate power generation forecasting model that is easy to implement for a wide range of electric utilities. Against this background, this study proposes a PV power forecasting model based on the generalized additive model (GAM) and compares its forecasting accuracy with four popular machine learning methods: k-nearest neighbor, artificial neural networks, support vector regression, and random forest. The empirical analysis provides an intuitive interpretation of the multidimensional smooth trends estimated by the GAM as tensor product splines and confirms the validity of the proposed modeling structure. The effectiveness of GAM is particularly evident in trend completion for missing data, where it is able to flexibly express the tangled trend structure inherent in time series data, and thus has an advantage not only in interpretability but also in improving forecast accuracy. Full article

Matrix completion, the problem of completing missing entries in a data matrix with low-dimensional structure (such as rank), has seen many fruitful approaches and analyses. Tensor completion is the tensor analog that attempts to impute missing tensor entries from similar low-rank type assumptions. In this paper, we study the tensor completion problem when the sampling pattern is deterministic and possibly non-uniform. We first propose an efficient weighted Higher Order Singular Value Decomposition (HOSVD) algorithm for the recovery of the underlying low-rank tensor from noisy observations and then derive the error bounds under a properly weighted metric. Additionally, the efficiency and accuracy of our algorithm are both tested using synthetic and real datasets in numerical simulations. Full article

Multispectral sensors constitute a core Earth observation image technology generating massive high-dimensional observations. To address the communication and storage constraints of remote sensing platforms, lossy data compression becomes necessary, but it unavoidably introduces unwanted artifacts. In this work, we consider the encoding of multispectral observations into high-order tensor structures which can naturally capture multi-dimensional dependencies and correlations, and we propose a resource-efficient compression scheme based on quantized low-rank tensor completion. The proposed method is also applicable to the case of missing observations due to environmental conditions, such as cloud cover. To quantify the performance of compression, we consider both typical image quality metrics as well as the impact on state-of-the-art deep learning-based land-cover classification schemes. Experimental analysis on observations from the ESA Sentinel-2 satellite reveals that even minimal compression can have negative effects on classification performance which can be efficiently addressed by our proposed recovery scheme. Full article

This work contributes to the techniques used for SCADA (Supervisory Control and Data Acquisition) system data completion in databases containing historical water sensor signals from a water supplier company. Our approach addresses the data restoration problem in two stages. In the first stage, we treat one-dimensional signals by estimating missing data through the combination of two linear predictor filters, one working forwards and one backwards. In the second stage, the data are tensorized to take advantage of the underlying structures at five minute, one day, and one week intervals. Subsequently, a low-range approximation of the tensor is constructed to correct the first stage of the data restoration. This technique requires an offset compensation to guarantee the continuity of the signal at the two ends of the burst. To check the effectiveness of the proposed method, we performed statistical tests by deleting bursts of known sizes in a complete tensor and contrasting different strategies in terms of their performance. For the type of data used, the results show that the proposed data completion approach outperforms other methods, the difference becoming more evident as the size of the bursts of missing data grows. Full article