Search Results (63)

Hyperspectral image (HSI) denoising is an important preprocessing step for downstream applications. Fully characterizing the spatial-spectral priors of HSI is crucial for denoising tasks. In recent years, denoising methods based on low-rank subspaces have garnered widespread attention. In the low-rank matrix factorization framework, the restoration of HSI can be formulated as a task of recovering two subspace factors. However, hyperspectral images are inherently three-dimensional tensors, and transforming the tensor into a matrix for operations inevitably disrupts the spatial structure of the data. To address this issue and better capture the spatial-spectral priors of HSI, this paper proposes a modeling approach named low-rank Tucker decomposition with subspace implicit neural representation (LRTSINR). This data-driven and model-driven joint modeling mechanism has the following two advantages: (1) Tucker decomposition allows for the characterization of the low-rank properties across multiple dimensions of the HSI, leading to a more accurate representation of spectral priors; (2) Implicit neural representation enables the adaptive and precise characterization of the subspace factor continuity under Tucker decomposition. Extensive experiments demonstrate that our method outperforms a series of competing methods. Full article

Aiming at the limitations of existing multisensor fault diagnosis methods for rolling bearings in real industrial scenarios, this paper proposes an innovative intuitionistic fuzzy weighted least squares twin support higher-order tensor machine (IFW-LSTSHTM) model, which realizes a breakthrough in the noise robustness, adaptability to the working conditions, and the class imbalance processing capability. First, the multimodal feature tensor is constructed: the fourier synchro-squeezed transform is used to convert the multisensor time-domain signals into time–frequency images, and then the tensor is reconstructed to retain the three-dimensional structural information of the sensor coupling relationship and time–frequency features. The nonlinear feature mapping strategy combined with Tucker decomposition effectively maintains the high-order correlation of the feature tensor. Second, the adaptive sample-weighting mechanism is developed: an intuitionistic fuzzy membership score assignment scheme with global–local information fusion is proposed. At the global level, the class contribution is assessed based on the relative position of the samples to the classification boundary; at the local level, the topological structural features of the sample distribution are captured by K-nearest neighbor analysis; this mechanism significantly improves the recognition of noisy samples and the handling of class-imbalanced data. Finally, a dual hyperplane classifier is constructed in tensor space: a structural risk regularization term is introduced to enhance the model generalization ability and a dynamic penalty factor is set to set adaptive weights for different categories. A linear equation system solving strategy is adopted: the nonparallel hyperplane optimization is converted into matrix operations to improve the computational efficiency. The extensive experimental results on the two rolling bearing datasets have verified that the proposed method outperforms existing solutions in diagnostic accuracy and stability. Full article

The human functional connectome (FC) is a representation of the functional couplings between brain regions derived from blood oxygen level-dependent (BOLD) signals. Over the past decade, studies related to FC fingerprinting have sought to uncover functional patterns that enable uniquely identifying individuals across repeated scanning sessions, hence demonstrating the stability and distinctiveness of functional brain organization. In this study, it is hypothesized that tensor decomposition techniques, given their ability to project high-dimensional data into lower-dimensional spaces, enable detecting the brain fingerprint with high accuracy. A mathematical framework based on Tucker decomposition is presented to uncover the FC fingerprint of 426 unrelated participants from the Young-Adult Human Connectome Project (HCP) Dataset. An analysis of how brain parcellation granularity, decomposition rank, and scan length relate to within- and between-condition (resting state-task) fingerprinting was conducted. Relative to FC matrices as well as to Principal Components Analysis (PCA), tensor decomposition significantly increases the functional connectome’s fingerprint. For parcellation granularity of 214 in the within-condition setting, an improvement of 11–36% was seen across all fMRI conditions. Similarly, a substantial improvement, ranging from 43 to 72%, was observed in the between-condition setting relative to FC matrices. Compared to matching rates obtained directly on FCs and when applying other data-driven decomposition methods, Tucker decomposition led to higher or the same level of matching rates for all analyses. Furthermore, in the context of between-condition fingerprinting, results from the proposed framework suggest that partially sampling time points from resting-state time series is sufficient to uncover FC fingerprints with high accuracy. Full article

With the rapid growth of streaming data, traditional tensor decomposition methods can hardly handle real-time, high-dimensional data of massive amounts in this scenario. In this paper, a two-level parallel incremental tensor Tucker decomposition method with multi-mode growth (TPITTD-MG) is proposed to address the low parallelism issue of the existing Tucker decomposition methods on large-scale, high-dimensional, dynamically growing data. TPITTD-MG involves two mechanisms, i.e., a parallel sub-tensor partitioning mechanism based on the dynamic programming (PSTPA-DP) and a two-level parallel update method for projection matrices and core tensors. The former can count the non-zero elements in a parallel manner and use dynamic programming to partition sub-tensors, which ensures more uniform task allocation. The latter updates the projection matrices or the core tensors by implementing the first level of parallel updates based on the parallel MTTKRP calculation strategy, followed by the second level of parallel updates of different projection matrices or tensors independently based on different classification of sub-tensors. The experimental results show that execution efficiency is improved by nearly 400% and the uniformity of partition results is improved by more than 20% when the data scale reaches an order of magnitude of tens of millions with a parallelism degree of 4, compared with existing algorithms. For third-order tensors, compared with the single-layer update algorithm, execution efficiency is improved by nearly 300%. Full article

Accurate temperature measurement in coal-fired power plants is crucial for optimizing combustion and achieving deep load regulation. While acoustic temperature measurement is an efficient and stable method, its practical application is limited to two-dimensional (2D) temperature fields, leading to poor reconstruction of complex 3D temperature fields due to limited measurement points. In this work, we propose a novel 3D temperature field reconstruction algorithm based on Tucker decomposition and acoustic thermometry. The key innovation lies in the use of Tucker decomposition to extract essential features from 3D time-of-flight (TOF) data, enabling efficient reconstruction of 3D temperature fields from a small number of single-layer TOF measurements. Our method achieves faster reconstruction speeds (approximately 4 s) and higher accuracy, reducing reconstruction errors by over 10% compared to traditional acoustic thermometry. Additionally, the algorithm demonstrates strong anti-noise capabilities and applicability to temperature fields beyond the a priori conditions, making it a valuable tool for combustion optimization and load adjustment in coal-fired power plants. Full article

The current development of machine learning has advanced many fields in applied sciences and industry, including remote sensing. In this area, deep neural networks are used to solve routine object detection problems, satisfying the required rules and conditions. However, the growing number and difficulty of such problems cause the developers to construct machine learning models with higher computational complexities, such as an increased number of hidden layers, epochs, learning rate, and rate decay. In this paper, we propose the Yolov8 architecture with decomposed layers via canonical polyadic and Tucker methods for accelerating the solving of the object detection problem in satellite images. Our positive–negative momentum approaches enabled a reduction in the loss in precision and recall assessments for the proposed neural network. The convolutional layer factorization reduces the shapes and accelerates the computations at kernel nodes in the proposed deep learning models. The advanced optimization algorithms achieve the global minimum of loss functions, which makes the precision and recall metrics superior to the ones for their known counterparts. We examined the proposed Yolov8 with decomposed layers, comparing it with the conventional Yolov8 on the DIOR and VisDrone 2020 datasets containing the UAV images. We verified the performance of the proposed and known neural networks on different optimizers. It is shown that the proposed neural network accelerates the solving object detection problem by 44–52%. The proposed Yolov8 with Tucker and canonical polyadic decompositions has greater precision and recall metrics than the usual Yolov8 with known analogs by 0.84–0.94 and 0.228–1.107 percentage points, respectively. Full article

Neural networks have become a cornerstone of computer vision applications, with tasks ranging from image classification to object detection. However, challenges such as hyperparameter optimization (HPO) and model compression remain critical for improving performance and deploying models on resource-constrained devices. In this work, we address these challenges using Tensor Network-based methods. For HPO, we propose and evaluate the TetraOpt algorithm against various optimization algorithms. These evaluations were conducted on subsets of the NATS-Bench dataset, including CIFAR-10, CIFAR-100, and ImageNet subsets. TetraOpt consistently demonstrated superior performance, effectively exploring the global optimization space and identifying configurations with higher accuracies. For model compression, we introduce a novel iterative method that combines CP, SVD, and Tucker tensor decompositions. Applied to ResNet-18 and ResNet-152, we evaluated our method on the CIFAR-10 and Tiny ImageNet datasets. Our method achieved compression ratios of up to $14.5\times$ for ResNet-18 and $2.5\times$ for ResNet-152. Additionally, the inference time for processing an image on a CPU remained largely unaffected, demonstrating the practicality of the method. Full article

Video Object Tracking (VOT) is a critical task in computer vision. While Siamese-based and Transformer-based trackers are widely used in VOT, they struggle to perform well on the OTB100 benchmark due to the lack of dedicated training sets. This challenge highlights the difficulty of effectively generalizing to unknown data. To address this issue, this paper proposes an innovative method that utilizes tensor decomposition, an underexplored concept in object-tracking research. By applying L1-norm tensor decomposition, video sequences are represented as four-mode tensors, and a real-time background subtraction algorithm is introduced, allowing for effective modeling of the target–background relationship and adaptation to environmental changes, leading to accurate and robust tracking. Additionally, the paper integrates an improved multi-kernel correlation filter into a single frame, locating and tracking the target by comparing the correlation between the target template and the input image. To further enhance localization precision and robustness, the paper also incorporates Tucker2 decomposition to integrate appearance and motion patterns, generating composite heatmaps. The method is evaluated on the OTB100 benchmark dataset, showing significant improvements in both performance and speed compared to traditional methods. Experimental results demonstrate that the proposed method achieves a 15.8% improvement in AUC and a ten-fold increase in speed compared to typical deep learning-based methods, providing an efficient and accurate real-time tracking solution, particularly in scenarios with similar target–background characteristics, high-speed motion, and limited target movement. Full article

To address the issue of efficiently reusing the massive amount of unstructured knowledge generated during the handling of track circuit equipment faults and to automate the construction of knowledge graphs in the railway maintenance domain, it is crucial to leverage knowledge extraction techniques to efficiently extract relational triplets from fault maintenance text data. Given the current lag in joint extraction technology within the railway domain and the inefficiency in resource utilization, this paper proposes a joint extraction model for track circuit entities and relations, integrating Global Pointer and tensor learning. Taking into account the associative characteristics of semantic relations, the nesting of domain-specific terms in the railway sector, and semantic diversity, this research views the relation extraction task as a tensor learning process and the entity recognition task as a span-based Global Pointer search process. First, a multi-layer dilate gated convolutional neural network with residual connections is used to extract key features and fuse the weighted information from the 12 different semantic layers of the RoBERTa-wwm-ext model, fully exploiting the performance of each encoding layer. Next, the Tucker decomposition method is utilized to capture the semantic correlations between relations, and an Efficient Global Pointer is employed to globally predict the start and end positions of subject and object entities, incorporating relative position information through rotary position embedding (RoPE). Finally, comparative experiments with existing mainstream joint extraction models were conducted, and the proposed model’s excellent performance was validated on the English public datasets NYT and WebNLG, the Chinese public dataset DuIE, and a private track circuit dataset. The F1 scores on the NYT, WebNLG, and DuIE public datasets reached 92.1%, 92.7%, and 78.2%, respectively. Full article

Cooperative MIMO communication systems play an important role in the development of future sixth-generation (6G) wireless systems incorporating new technologies such as massive MIMO relay systems, dual-polarized antenna arrays, millimeter-wave communications, and, more recently, communications assisted using intelligent reflecting surfaces (IRSs), and unmanned aerial vehicles (UAVs). In a companion paper, we provided an overview of cooperative communication systems from a tensor modeling perspective. The objective of the present paper is to provide a comprehensive tutorial on semi-blind receivers for MIMO one-way two-hop relay systems, allowing the joint estimation of transmitted symbols and individual communication channels with only a few pilot symbols. After a reminder of some tensor prerequisites, we present an overview of tensor models, with a detailed, unified, and original description of two classes of tensor decomposition frequently used in the design of relay systems, namely nested CPD/PARAFAC and nested Tucker decomposition (TD). Some new variants of nested models are introduced. Uniqueness and identifiability conditions, depending on the algorithm used to estimate the parameters of these models, are established. Two families of algorithms are presented: iterative algorithms based on alternating least squares (ALS) and closed-form solutions using Khatri–Rao and Kronecker factorization methods, which consist of SVD-based rank-one matrix or tensor approximations. In a second part of the paper, the overview of cooperative communication systems is completed before presenting several two-hop relay systems using different codings and configurations in terms of relaying protocol (AF/DF) and channel modeling. The aim of this presentation is firstly to show how these choices lead to different nested tensor models for the signals received at destination. Then, by capitalizing on these models and their correspondence with the generic models studied in the first part, we derive semi-blind receivers to jointly estimate the transmitted symbols and the individual communication channels for each relay system considered. In a third part, extensive Monte Carlo simulation results are presented to compare the performance of relay systems and associated semi-blind receivers in terms of the symbol error rate (SER) and channel estimate normalized mean-square error (NMSE). Their computation time is also compared. Finally, some perspectives are drawn for future research work. Full article

Modular control of the muscle, which is called muscle synergy, simplifies control of the movement by the central nervous system. The purpose of this study was to explore the synergy in both the frequency and movement domains based on the non-negative Tucker decomposition (NTD) method. Surface electromyography (sEMG) data of 8 upper limb muscles in 10 healthy subjects under wrist flexion (WF) and wrist extension (WE) were recorded. NTD was selected for exploring the multi-domain muscle synergy from the sEMG data. The results showed two synergistic flexor pairs, Palmaris longus–Flexor Digitorum Superficialis (PL-FDS) and Extensor Carpi Radialis–Flexor Carpi Radialis (ECR-FCR), in the WF stage. Their spectral components are mainly in the respective bands 0–20 Hz and 25–50 Hz. And the spectral components of two extensor pairs, Extensor Digitorum–Extensor Carpi Ulnar (ED-ECU) and Extensor Carpi Radialis–Brachioradialis (ECR-B), are mainly in the respective bands 0–20 Hz and 7–45 Hz in the WE stage. Additionally, further analysis showed that the Biceps Brachii (BB) muscle was a shared muscle synergy module of the WE and WF stage, while the flexor muscles FCR, PL and FDS were the specific synergy modules of the WF stage, and the extensor muscles ED, ECU, ECR and B were the specific synergy modules of the WE stage. This study showed that NTD is a meaningful method to explore the multi-domain synergistic characteristics of multi-channel sEMG signals. The results can help us to better understand the frequency features of muscle synergy and shared and specific synergies, and expand the study perspective related to motor control in the nervous system. Full article

Deep convolutional neural networks have a large number of parameters and require a significant number of floating-point operations during computation, which limits their deployment in situations where the storage space is limited and computational resources are insufficient, such as in mobile phones and small robots. Many network compression methods have been proposed to address the aforementioned issues, including pruning, low-rank decomposition, quantization, etc. However, these methods typically fail to achieve a significant compression ratio in terms of the parameter count. Even when high compression rates are achieved, the network’s performance is often significantly deteriorated, making it difficult to perform tasks effectively. In this study, we propose a more compact representation for neural networks, named Quantized Low-Rank Tensor Decomposition (QLTD), to super compress deep convolutional neural networks. Firstly, we employed low-rank Tucker decomposition to compress the pre-trained weights. Subsequently, to further exploit redundancies within the core tensor and factor matrices obtained through Tucker decomposition, we employed vector quantization to partition and cluster the weights. Simultaneously, we introduced a self-attention module for each core tensor and factor matrix to enhance the training responsiveness in critical regions. The object identification results in the CIFAR10 experiment showed that QLTD achieved a compression ratio of 35.43×, with less than 1% loss in accuracy and a compression ratio of 90.61×, with less than a 2% loss in accuracy. QLTD was able to achieve a significant compression ratio in terms of the parameter count and realize a good balance between compressing parameters and maintaining identification accuracy. Full article

The quick development of machine learning techniques provides a superior capability for manufacturing enterprises to make effective decisions about inventory management based on spare parts demand (SPD) data. Since SPD sequences in practical maintenance applications usually show an intermittent distribution, it is not easy to represent the demand pattern of such sequences. Meanwhile, there are some aspects like manual report errors, environmental interference, sudden project changes, etc., that bring large and unexpected fluctuations to SPD sequences, i.e., anomalous demands. The inventory decision made based on the SPD sequences with anomalous demands is not trusted by enterprise engineers. For such SPD data, there are two great concerns, i.e., false alarms in which sparse demands are recognized to be anomalous and missing alarms in which the anomalous demands are categorized as normal due to their adjacent demands having extreme values. To address these concerns, a new unsupervised anomaly-detection method for intermittent time series is proposed based on a dual-tailed probability. First, the multi-way delay embedding transform (MDT) was applied on the raw SPD sequences to obtain higher-order tensors. Through Tucker tensor decomposition, the disturbance of extreme demands can be effectively reduced. For the reconstructed SPD sequences, then, the tail probability at each time point, as well as the empirical cumulative distribution function were calculated based on the probability of the demand occurrence. Second, to lessen the disturbance of sparse demand, the non-zero demand sequence was distilled from the raw SPD sequence, with the tail probability at each time point being calculated. Finally, the obtained dual-tailed probabilities were fused to determine the anomalous degree of each demand. The proposed method was validated on the two actual SPD datasets, which were collected from a large engineering manufacturing enterprise and a large vehicle manufacturing enterprise in China, respectively. The results demonstrated that the proposed method can effectively lower the false alarm rate and missing alarm rate with no supervised information provided. The detection results were trustworthy enough and, more importantly, computationally inexpensive, showing significant applicability to large-scale after-sales parts management. Full article

The deployment of Electronic Toll Collection (ETC) gantry systems marks a transformative advancement in the journey toward an interconnected and intelligent highway traffic infrastructure. The integration of these systems signifies a leap forward in streamlining toll collection and minimizing environmental impact through decreased idle times. To solve the problems of missing sensor data in an ETC gantry system with large volumes and insufficient traffic detection among ETC gantries, this study constructs a high-order tensor model based on the analysis of the high-dimensional, sparse, large-volume, and heterogeneous characteristics of ETC gantry data. In addition, a missing data completion method for the ETC gantry data is proposed based on an improved dynamic tensor flow model. This study approximates the decomposition of neighboring tensor blocks in the high-order tensor model of the ETC gantry data based on tensor Tucker decomposition and the Laplacian matrix. This method captures the correlations among space, time, and user information in the ETC gantry data. Case studies demonstrate that our method enhances ETC gantry data quality across various rates of missing data while also reducing computational complexity. For instance, at a less than 5% missing data rate, our approach reduced the RMSE for time vehicle distance by 0.0051, for traffic volume by 0.0056, and for interval speed by 0.0049 compared to the MATRIX method. These improvements not only indicate a potential for more precise traffic data analysis but also add value to the application of ETC systems and contribute to theoretical and practical advancements in the field. Full article

Efficient logistics and transport at the port heavily relies on efficient AGV scheduling and planning for container transshipment. This paper presents a comprehensive approach to address the challenges in AGV path planning and coordination within the domain of intelligent transportation systems. We propose an enhanced graph search method for constructing the global path of a single AGV that mitigates the issues associated with paths closely aligned with obstacle corner points. Moreover, a centralized global planning module is developed to facilitate planning and scheduling. Each individual AGV establishes real-time communication with the upper layers to accurately determine its position at complex intersections. By computing its priority sequence within a coordination circle, the AGV effectively treats the high-priority trajectories of other vehicles as dynamic obstacles for its local trajectory planning. The feasibility of trajectory information is ensured by solving the online real-time Optimal Control Problem (OCP). In the trajectory planning process for a single AGV, we incorporate a linear programming-based obstacle avoidance strategy. This strategy transforms the obstacle avoidance optimization problem into trajectory planning constraints using Karush-Kuhn-Tucker (KKT) conditions. Consequently, seamless and secure AGV movement within the port environment is guaranteed. The global planning module encompasses a global regulatory mechanism that provides each AGV with an initial feasible path. This approach not only facilitates complexity decomposition for large-scale problems, but also maintains path feasibility through continuous real-time communication with the upper layers during AGV travel. A key advantage of our progressive solution lies in its flexibility and scalability. This approach readily accommodates extensions based on the original problem and allows adjustments in the overall problem size in response to varying port cargo throughput, all without requiring a complete system overhaul. Full article