Deep Tensor Research Articles

Unsupervised Deep Tensor Network for Hyperspectral-Multispectral Image Fusion.

Fusing low-resolution (LR) hyperspectral images (HSIs) with high-resolution (HR) multispectral images (MSIs) is a significant technology to enhance the resolution of HSIs. Despite the encouraging results from deep learning (DL) in HSI-MSI fusion, there are still some issues. First, the HSI is a multidimensional signal, and the representability of current DL networks for multidimensional features has not been thoroughly investigated. Second, most DL HSI-MSI fusion networks need HR HSI ground truth for training, but it is often unavailable in reality. In this study, we integrate tensor theory with DL and propose an unsupervised deep tensor network (UDTN) for HSI-MSI fusion. We first propose a tensor filtering layer prototype and further build a coupled tensor filtering module. It jointly represents the LR HSI and HR MSI as several features revealing the principal components of spectral and spatial modes and a sharing code tensor describing the interaction among different modes. Specifically, the features on different modes are represented by the learnable filters of tensor filtering layers, the sharing code tensor is learned by a projection module, in which a co-attention is proposed to encode the LR HSI and HR MSI and then project them onto the sharing code tensor. The coupled tensor filtering module and projection module are jointly trained from the LR HSI and HR MSI in an unsupervised and end-to-end way. The latent HR HSI is inferred with the sharing code tensor, the features on spatial modes of HR MSIs, and the spectral mode of LR HSIs. Experiments on simulated and real remote-sensing datasets demonstrate the effectiveness of the proposed method.

Patch-Masked Visual Inspection via Parallel Deep Tensor Factorization in Industrial Internet of Things

Patch-Masked Visual Inspection via Parallel Deep Tensor Factorization in Industrial Internet of Things

TensorMap: A Deep RL-Based Tensor Mapping Framework for Spatial Accelerators

TensorMap: A Deep RL-Based Tensor Mapping Framework for Spatial Accelerators

Optimal depth and a novel approach to variational unitary quantum process tomography

In this work, we present two new methods for variational quantum circuit (VQC) process tomography (PT) onto n qubits systems: unitary PT based on VQCs (PT_VQC) and unitary evolution-based variational quantum singular value decomposition (U-VQSVD). Compared to the state of the art, PT_VQC halves in each run the required amount of qubits for unitary PT and decreases the required state initializations from 4 n to just 2 n , all while ensuring high-fidelity reconstruction of the targeted unitary channel U. It is worth noting that, for a fixed reconstruction accuracy, PT_VQC achieves faster convergence per iteration step compared to quantum deep neural network and tensor network schemes. The novel U-VQSVD algorithm utilizes variational singular value decomposition to extract eigenvectors (up to a global phase) and their associated eigenvalues from an unknown unitary representing a universal channel. We assess the performance of U-VQSVD by executing an attack on a non-unitary channel quantum physical unclonable function. By using U-VQSVD we outperform an uninformed impersonation attack (using randomly generated input states) by a factor of 2 to 5, depending on the qubit dimension. For the two presented methods, we propose a new approach to calculate the complexity of the displayed VQC, based on what we denote as optimal depth.

Classification of Ground‐Based Auroral Images by Learning Deep Tensor Feature Representation on Riemannian Manifold

AbstractAutomatically classifying a huge amount of ground‐based auroral images is essential to facilitate aurora morphology statistical research and aid in comprehending the magnetospheric dynamics. However, facing the challenge of insufficient labeled images, deep learning methods perform suboptimally on small auroral image data sets, and traditional machine learning methods based on handcrafted features heavily rely on expert knowledge. In this paper, we propose a novel method that leverages the merits of both traditional machine learning and deep learning methods by extracting deep second‐order tensor features to train a support vector machine (SVM). To improve compactness and discriminative ability of the features, we comply the intrinsic data geometry on Riemannian manifold to employ dimensionality reduction and map the dimensionality‐reduced features from Riemannian space to Euclidean space for the SVM classifier. Experimental results on small aurora data sets conclusively demonstrate the effectiveness of our method, exhibiting competitive performance with recent aurora classification methods.

Ocean sound speed field reconstruction beyond tensor neural network

Obtaining accurate ocean sound speed fields (SSFs) across a three-dimensional (3D) geographic region is vital for various underwater acoustic tasks. However, the scarcity of measurements due to the high cost of underwater sensors, combined with the high dimensionality of complex 3D SSF, makes the reconstruction problem highly ill-conditioned, thus demanding advanced models and methods. Our recent work has analyzed the reconstruction error and identified one promising way: finding a representation model that is both concise and expressive. Following this path, we proposed a tensor neural network (TNN) model, which leverages the conciseness of tensor models and the expressive power of deep learning. However, existing TNN-based approaches have two limitations: (1) they are unable to capture long-range correlations within the SSF and (2) they can only handle discrete-indexed tensor data. To overcome these limitations and fully unleash the power of deep tensor learning, we seamlessly introduce attention schemes into the existing TNN framework without compromising its interpretability. Additionally, we employ Gaussian process models to evolve the original parameterized tensor model into a new functional tensor model, enabling reconstruction with a continuous grid. Numerical results obtained from real-life datasets demonstrate the superior performance of our approach compared to state-of-the-art methods.

Implementation of AI Based Model for Identification of Different Soil Types Using Tensorflow

AbstractThe agricultural industry is among the most important industry in the world and playing a critical part in human growth. Soil classification is becoming incredibly valuable, and recent study reveals that classification of images is proven as the preferred way of soil information for farmers. The testing of soil is the first step in construction planning to determine whether the plot of land is suitable for constructing any structure in order to prevent future disasters. In this work, the model has been proposed to address the visual classification of types of soil using the deep neural network (DNN) and tensor flow framework. Further, AI based sequential model has been created in python to classify the soil. This has been analyzed that with the use of proposed technique five types of soil viz. black, cinder, laterite, peat, and yellow soil has been classified while keeping the practical simplicity of the images. Far superior accuracy has been achieved using the CNN model on the above dataset. The model is useful for farmers to increase the crop production after identification of the appropriate soil type for respective crops.

Deep graph tensor learning for temporal link prediction

Knowledge discovery on dynamic graphs has received much attention in recent years. As a key task of dynamic graph research, the goal of temporal link prediction is to accurately predict the time-varying links in dynamic networks. Uncertainty in link emergence is a major challenge in this research, as it is not easy to learn stable and reliable link-level feature representations, which are usually readily available on static graphs. In order to adapt to the ever-changing graph structure, this paper proposes to construct a deep graph tensor learning model, which can capture the contextual characteristics of graph evolution from both the graph structure (spatial) mode and the link sequence (temporal) mode. Therefore, compared to link prediction on static graphs, temporal link prediction can benefit more from the link-level embedding representations coupled with spatio-temporal features. The experimental results on seven public dynamic graph datasets show that the prediction accuracy obtained by the new model is overall better than competing models such as GC-LSTM, EvolveGCN, and HTGN. In the meantime, as a result of getting rid of the traditional RNN learning paradigm, the new model is also significantly better than the traditional temporal graph learning model in terms of training efficiency.

Efficient and Effective NDVI Time-Series Reconstruction by Combining Deep Learning and Tensor Completion

Efficient and Effective NDVI Time-Series Reconstruction by Combining Deep Learning and Tensor Completion

Kiosk 9R-TC-06 - Accelerating DT-CMR with Deep Learning-based Tensor De-noising and Breath Hold Reduction

Kiosk 9R-TC-06 - Accelerating DT-CMR with Deep Learning-based Tensor De-noising and Breath Hold Reduction

Deep Tensor Evidence Fusion Network for Sentiment Classification

Recently, a multimodal sentiment analysis of social media has attracted increasing attention, and its core idea is to discovery heuristic fusion strategy to analyze the sentiment orientations over heterogeneous multimodal source from a learned compact multimodal representation. The existing multimodal fusion techniques not only struggle to achieve full heterogeneous data interaction, but also they are unable to dynamically assess the quality of various modal data to determine predictability. In this article, we present a novel deep tensor evidence fusion (DTEF) network for multimodal sentiment classification. First, we propose a common view evaluation network that uses a long short-term memory (LSTM) network and a tensor-based neural network to extract rich intermodal and intramodal information. Then, we propose a unique time cue evaluation network that takes advantage of the temporal granularity associated with numerous pattern sequences. To make reliable decisions, we finally incorporate uncertainty through the trusted fusion layer, which improves the accuracy and robustness of sentimental classification. Our model is validated using the CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) and CMU Multimodal Corpus of Sentiment Intensity (CMU-MOSI) datasets, and the experimental findings demonstrate the superior performance of the proposed network in terms of accuracy compared with the state-of-the-art methods.

DTLR-CS: Deep tensor low rank channel cross fusion neural network for reproductive cell segmentation.

In recent years, with the development of deep learning technology, deep neural networks have been widely used in the field of medical image segmentation. U-shaped Network(U-Net) is a segmentation network proposed for medical images based on full-convolution and is gradually becoming the most commonly used segmentation architecture in the medical field. The encoder of U-Net is mainly used to capture the context information in the image, which plays an important role in the performance of the semantic segmentation algorithm. However, it is unstable for U-Net with simple skip connection to perform unstably in global multi-scale modelling, and it is prone to semantic gaps in feature fusion. Inspired by this, in this work, we propose a Deep Tensor Low Rank Channel Cross Fusion Neural Network (DTLR-CS) to replace the simple skip connection in U-Net. To avoid space compression and to solve the high rank problem, we designed a tensor low-ranking module to generate a large number of low-rank tensors containing context features. To reduce semantic differences, we introduced a cross-fusion connection module, which consists of a channel cross-fusion sub-module and a feature connection sub-module. Based on the proposed network, experiments have shown that our network has accurate cell segmentation performance.

Deep Adversarial Tensor Completion for Accurate Network Traffic Measurement

Network trouble shooting, failure location, and anomaly detection rely heavily on network traffic measurement data. Due to the lack of measurement infrastructure, the high measurement cost, and the unavoidable transmission loss, network monitoring systems suffer from the problem that the network traffic data are incomplete. This article models the traffic data as a tensor to exploit its strong ability of feature extraction to recover the missing data. Different from traditional tensor completion which relies on tensor factorization, we design a novel Deep Adversarial Tensor Completion (DATC) scheme based on Deep Learning (DL) techniques. DATC is the first scheme that exploits the data reconstruction ability of autoencoder and the power of adversarial training from Generative Adversarial Networks to infer the missing data. Despite that DL techniques achieve great success in the image field, designing an algorithm based on DL techniques to recover the traffic data with missing entries faces additional challenges due to the skewed distribution and the sparsity of traffic data. To conquer these challenges, we propose the use of two techniques, adversarial training and missing data aware convolution. These techniques help DATC to learn the complex features of the traffic data and infer the missing data following the data distribution of traffic data. Our extensive experimental results using two public real-world network traffic datasets and running both offline and online demonstrate that DATC can achieve significantly better recovery accuracy while capturing the data distribution of the traffic data even when the sampling ratio is very low.

Deep low-rank tensor embedding for multi-view subspace clustering

Despite the good clustering performance, most of existing multi-view subspace clustering methods fail to consider the non-linear relationships of high-dimensional data, higher-order correlations of different views, and optimal local geometric structure of the latent embedding space simultaneously. To this end, we put forward a novel multi-view subspace clustering model, named deep low-rank tensor embedding (DLTE). In DLTE, we project the high-dimensional data into the low-dimensional embedding space by utilizing deep non-negative matrix factorization (NMF), which can efficiently capture the complex non-linear relationship of data. Moreover, in the deep embedding space, we utilize the weighted low-rank tensor constraint to capture the global structure and higher-order correlations of different views while considering the contributions of different views. Additionally, we introduce an optimal graph Laplacian to learn a more reasonable local geometric structure of data in the deep embedding space. At last, comprehensive experimental results on eleven datasets indicate the superiority and effectiveness of the proposed DLTE method.

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques.

Although handcrafted radiomics features (RF) are commonly extracted via radiomics software, employing deep features (DF) extracted from deep learning (DL) algorithms merits significant investigation. Moreover, a "tensor'' radiomics paradigm where various flavours of a given feature are generated and explored can provide added value. We aimed to employ conventional and tensor DFs, and compare their outcome prediction performance to conventional and tensor RFs. 408 patients with head and neck cancer were selected from TCIA. PET images were first registered to CT, enhanced, normalized, and cropped. We employed 15 image-level fusion techniques (e.g., dual tree complex wavelet transform (DTCWT)) to combine PET and CT images. Subsequently, 215 RFs were extracted from each tumor in 17 images (or flavours) including CT only, PET only, and 15 fused PET-CT images through the standardized-SERA radiomics software. Furthermore, a 3 dimensional autoencoder was used to extract DFs. To predict the binary progression-free-survival-outcome, first, an end-to-end CNN algorithm was employed. Subsequently, we applied conventional and tensor DFs vs. RFs as extracted from each image to three sole classifiers, namely multilayer perceptron (MLP), random-forest, and logistic regression (LR), linked with dimension reduction algorithms. DTCWT fusion linked with CNN resulted in accuracies of 75.6 ± 7.0% and 63.4 ± 6.7% in five-fold cross-validation and external-nested-testing, respectively. For the tensor RF-framework, polynomial transform algorithms + analysis of variance feature selector (ANOVA) + LR enabled 76.67 ± 3.3% and 70.6 ± 6.7% in the mentioned tests. For the tensor DF framework, PCA + ANOVA + MLP arrived at 87.0 ± 3.5% and 85.3 ± 5.2% in both tests. This study showed that tensor DF combined with proper machine learning approaches enhanced survival prediction performance compared to conventional DF, tensor and conventional RF, and end-to-end CNN frameworks.

Unsupervised Deep Tensor Multitask Anomaly Detection With Rule Adaptation for Online Early Fault Evaluation

This paper tries to solve the problem of online early fault detection (EFD) with unlabeled streaming data by addressing the following challenges: 1) no state information is available for online data; 2) online working condition is not determined in advance; 3) False alarm should be avoided. This paper first proposes a deep tensor multi-task anomaly detection model (Tensor-MAD) with rule adaptation for the online EFD. Running on multi-task learning architecture, Tensor-MAD builds a new tensorized pooling filter to keep the essential information of each task’s operating status from noisy data. With hypersphere-based one-class detection rule representation, Tensor-MAD further constructs a new rule adaptation mechanism to transfer the detection rule from offline labeled data to the online unlabeled data. A training algorithm with an alternating minimization scheme is also provided to update tensor decomposition and rule adaptation. Then the optimal information filter level and the rule adaptation degree can be determined. Based on the obtained anomalies, this paper proposes a non-parametric alarm threshold setting method based on the sequential accumulation of anomaly probability. This threshold can be adaptively chosen once an expected false alarm rate is given. A rationality proof is also provided. Experimental results on the IEEE PHM Challenge 2012 bearing dataset demonstrate that the proposed approach can adaptively and accurately evaluate the early fault occurrence from unlabeled streaming data. More importantly, the proposed approach has a much lower false alarm rate and a faster convergence speed, providing an easy-to-deploy and reliable solution for online EFD.

Heterogeneous data-driven measurement method for FeO content of sinter based on deep learning and tensor decomposition

FeO content is an important index reflecting the reducibility and drum strength of sinter, which is of great significance to the subsequent iron-making process. However, due to the time delay of chemical analysis method, FeO content cannot be obtained in real-time, which promotes the research on online measurement methods. Based on deep learning and information fusion, this paper proposes an intelligent heterogeneous data-driven method to accurately measure the level of FeO content in real time. Firstly, in view of the interference information such as background and furnace contour, the region proposal network is adopted to detect the burning ore region in the cross-section image of sintering machine. Secondly, a split attention-based deep convolutional neural network is constructed to extract deep image features. In particular, a fuzzy labeling strategy is proposed aiming at the problem of dividing images at the junction of different levels. In the end, the image features and the sintering process variables are fused through a bilinear model, and tensor decomposition is introduced to obtain the final fusion feature. Experimental results on actual industrial data demonstrate the effectiveness of the proposed method for measuring the level of FeO content, achieving an excellent accuracy of 98.35%.

Tensor-DAAD: When tensor meets online early fault detection with transfer learning

This paper tries to address the concerns about online early fault detection in non-stop scenarios: (1) no information of running status and operating condition is available for online data; (2) False alarms are raised by irregular noise. This paper proposes a new self-supervised deep tensor domain-adversarial anomaly detection model, named Tensor-DAAD. A contrastive learning network is first built to generate pre-trained features and pseudo-labels for online data. Second, a new tensor hypersphere-adversarial network is designed. By calculating core tensors of two domains’ features, this network builds hypersphere-based one-class detection rules from noisy data, and then realizes rule adaptation between the domains through adversarial training. Finally, a training algorithm with alternating minimization scheme is proposed to seek the optimal tensor decomposition and domain-invariant feature representation. Results on the two widely-used bearing datasets demonstrate that Tensor-DAAD can find early fault occurrence in an earlier location with a much lower false alarm rate.

A New Deep Tensor Autoencoder Network for Unsupervised Health Indicator Construction and Degradation State Evaluation of Metro Wheel

For metro vehicles, wheel performance degradation is inevitable due to the continuous wear of tread and rim. It is of significant value to apply machine learning techniques to evaluate the wheel’s degradation state with vibration signals, as it can lessen expert dependence and optimize repair strategy. In the real metro operation process, however, the wheels’ vibration signal is easily disturbed by irregular noise from many factors, such as load, road condition, and temperature, etc., and lacks essential tendency characteristics for the intelligent state evaluation. To solve this problem, this paper proposes a new unsupervised degradation state evaluation method for metro wheels against irregular noise disturbance. First, a new deep tensor autoencoder (TAE) network is proposed based on the merit of tensor representation in exploring the intrinsic information from raw signals. By extracting the core tensor from hidden features via Tucker decomposition, a new decoding process is rebuilt and a tensorized tendency regularizer is designed with the core tensor. Moreover, a new training algorithm with alternating minimization scheme is constructed to seek the optimal tensor representation and unsupervised feature extraction. Second, a health indicator (HI) of the degradation process is built with the extracted features. A HI-based state assessment algorithm is further proposed to adaptively determine the interval of state change in order to substitute the first/second warning in the current maintenance strategy. A set of comparative experiments are conducted using the wheel data from Beijing Subway. The results demonstrate that TAE can extract features with good monotonicity and tendency from the raw signals under irregular noise disturbance. More importantly, the obtained warning positions can precisely match the wheel diameter’s change in the actual repair record, which offers an easy-to-deploy and intelligent solution for the health management of metro wheels.

Self-Supervised Deep Tensor Domain-Adversarial Regression Adaptation for Online Remaining Useful Life Prediction Across Machines

With deep transfer learning techniques, this paper focuses on the online remaining useful life (RUL) prediction problem across different machines, and tries to address the following concerns: 1) The effect of transfer learning decreases significantly due to considerable divergence of degradation characteristic; 2) A high computational cost is raised by re-training whole model with online data; 3) Error accumulation occurs because of lacking label information of online data. In this paper, a self-supervised deep tensor domain-adversarial regression adaptation approach is proposed. In the pre-training stage, a novel tensor domain-adversarial network, with a tensorized domain discriminator, is constructed using the offline whole-life degradation data and early fault data of the target machine. A new training algorithm with an alternating minimization scheme is then built to seek the optimal core tensor and domain-invariant feature representation. In the online stage, a new self-supervised fine-tuning strategy is designed for the target network initialized from the pre-trained network. The core tensor-formed self-supervised information, extracted from the monotonicity of online degradation process, and the pseudo-supervised information from the pre-trained network are integrated to realize fast and adaptive RUL prediction. This paper takes rolling bearing as an example, and runs both cross-conditions and cross-machines experiments on three rolling bearings datasets, i.e., IEEE PHM Challenge 2012, XJTU-SY and our test rig. The results verify the use of tensor representation can facilitate regression adversarial training, and demonstrate the proposed approach can effectively improve predictive accuracy and stability under unknown online conditions.