Sparse Projection Research Articles

A general adaptive unsupervised feature selection with auto-weighting

Feature selection (FS) is essential in machine learning and data mining as it makes handling high-dimensional data more efficient and reliable. More attention has been paid to unsupervised feature selection (UFS) due to the extra resources required to obtain labels for data in the real world. Most of the existing embedded UFS utilize a sparse projection matrix for FS. However, this may introduce additional regularization terms, and it is difficult to control the sparsity of the projection matrix well. Moreover, such methods may seriously destroy the original feature structure in the embedding space. Instead, avoiding projecting the original data into the low-dimensional embedding space and identifying features directly from the raw features that perform well in the process of making the data show a distinct cluster structure is a feasible solution. Inspired by this, this paper proposes a model called A General Adaptive Unsupervised Feature Selection with Auto-weighting (GAWFS), which utilizes two techniques, non-negative matrix factorization, and adaptive graph learning, to simulate the process of dividing data into clusters, and identifies the features that are most discriminative in the clustering process by a feature weighting matrix Θ. Since the weighting matrix is sparse, it also plays the role of FS or a filter. Finally, experiments comparing GAWFS with several state-of-the-art UFS methods on synthetic datasets and real-world datasets are conducted, and the results demonstrate the superiority of the GAWFS.

Neural Radiance Fields for Fisheye Driving Scenes Using Edge-Aware Integrated Depth Supervision.

Neural radiance fields (NeRF) have become an effective method for encoding scenes into neural representations, allowing for the synthesis of photorealistic views of unseen views from given input images. However, the applicability of traditional NeRF is significantly limited by its assumption that images are captured for object-centric scenes with a pinhole camera. Expanding these boundaries, we focus on driving scenarios using a fisheye camera, which offers the advantage of capturing visual information from a wide field of view. To address the challenges due to the unbounded and distorted characteristics of fisheye images, we propose an edge-aware integration loss function. This approach leverages sparse LiDAR projections and dense depth maps estimated from a learning-based depth model. The proposed algorithm assigns larger weights to neighboring points that have depth values similar to the sensor data. Experiments were conducted on the KITTI-360 and JBNU-Depth360 datasets, which are public and real-world datasets of driving scenarios using fisheye cameras. Experimental results demonstrated that the proposed method is effective in synthesizing novel view images, outperforming existing approaches.

A dual-domain cone beam computed tomography sparse-view reconstruction method based on generative projection interpolation

To propose a dual-domain CBCT reconstruction framework (DualSFR-Net) based on generative projection interpolation to reduce artifacts in sparse-view cone beam computed tomography (CBCT) reconstruction. The proposed method DualSFR-Net consists of a generative projection interpolation module, a domain transformation module, and an image restoration module. The generative projection interpolation module includes a sparse projection interpolation network (SPINet) based on a generative adversarial network and a full-view projection restoration network (FPRNet). SPINet performs projection interpolation to synthesize full-view projection data from the sparse-view projection data, while FPRNet further restores the synthesized full-view projection data. The domain transformation module introduces the FDK reconstruction and forward projection operators to complete the forward and gradient backpropagation processes. The image restoration module includes an image restoration network FIRNet that fine-tunes the domain-transformed images to eliminate residual artifacts and noise. Validation experiments conducted on a dental CT dataset demonstrated that DualSFR-Net was capable to reconstruct high-quality CBCT images under sparse-view sampling protocols. Quantitatively, compared to the current best methods, the DualSFR-Net method improved the PSNR by 0.6615 and 0.7658 and increased the SSIM by 0.0053 and 0.0134 under 2-fold and 4-fold sparse protocols, respectively. The proposed generative projection interpolation-based dual-domain CBCT sparse-view reconstruction method can effectively reduce stripe artifacts to improve image quality and enables efficient joint training for dual-domain imaging networks in sparse-view CBCT reconstruction.

Temperature rise of high-speed bearing in gearbox of 5 MW wind turbine based on Bayesian-LightGBM and improved PSO-SVM troubleshooting

5MW wind turbine gearbox high-speed bearing temperature rise failure is one of the important factors affecting the stable operation of the wind turbine, accurate prediction and timely diagnosis can effectively improve the efficiency of the wind turbine. In this paper, a combined modelling wind turbine gearbox high-speed bearing temperature rise prediction method based on Bayesian-LightGBM and improved PSO-SVM is proposed with a 5 MW wind turbine as the research object. Firstly, the initial dimensionality reduction of SCADA data is performed by sparse random projection matrix, which reduces the redundant data. Secondly, feature selection is performed on the remaining data using Bayesian-LightGBM to identify 13 key input feature parameters. Then, the hyperparameters of the PSO algorithm are optimised using Bayesian algorithm and further, the optimised PSO algorithm is applied to identify the SVM parameters. Finally, a simulation experiment platform is established based on MATLAB to verify the temperature rise of high-speed bearings in gearboxes of wind turbines by example calculation and comparative analysis. The results show that the model established in this paper is effective, the prediction results are accurate and the performance is stable, and then compared with the algorithms such as PSO-SVM, SVM, BP, etc, the coefficient of determination of the algorithm is greater than 0.994 in both the training set and the test set, and the average decision percentage error is around 1.88% in both.

Evaluating the Geo-Environmental Conditions within a Working Face Using a Hybrid Intelligent Optimization Model

Geological anomalies within the working face likely induce geological disasters, such as water, gas, and coal mine roof fall, directly impacting the rational planning and safe mining of underground resources. Constrained by the conditions of underground closed spaces, effective reconstruction under incomplete and highly sparse projection is the central challenge when evaluating geo-environmental conditions. This work proposes a new hybrid intelligent optimization model (MPGA-SIRT) that integrates a multiple-population genetic algorithm (MPGA) with the simultaneous iterative reconstruction technique (SIRT) to finely reconstruct the geo-environmental conditions within a working face based on electromagnetic wave tomography theory. MPGA-SIRT can provide a more precise initial inversion model for the conventional linear reconstruction technique of SIRT, incorporating a local search property by leveraging the robust global search capacity of MPGA. The advantages of MPGA-SIRT have been demonstrated through numerical modeling, theoretical testing, and engineering practices on the 8208 working face in the Datong mining area, Shanxi Province. In comparison to individual SIRT inversion models, MPGA-SIRT reconstruction yields more accurate and stable performance, as demonstrated by the evolution curve of the objective function and the corresponding convergence tomography results. Consequently, the geomagnetic wave absorption coefficient within the area of reconstruction can be precisely ascertained through the use of our proposed technique. This innovation represents a groundbreaking strategy for assessing geological anomaly zones within a working face. The introduced method stands as a valuable theoretical instrument for confronting the complexities associated with geo-environmental reconstruction in underground engineering.

An Extremely Sparse Tomography Reconstruction of a Multispectral Temperature Field without Any a Priori Knowledge.

When undertaking optical sparse projection reconstruction, the reconstruction of the tested field often requires the utilization of a priori knowledge to compensate for the lack of information due to the sparse projection angle. In order to reconstruct the radiation field of unknown materials or in situations where a priori knowledge cannot be obtained, this paper proposes an extremely sparse tomography multispectral temperature field reconstruction algorithm that analyzes the similarity (the similarity here compares and calculates the Euclidean distance of the spectral emissivity values at various wavelengths between different spectral curves) of radiation characteristics of materials under the same pressure and concentration but different temperature, describes the similarity between the radiation information of the tested field using the dynamic time warping (DTW) algorithm, and uses the similarity sum of the radiation information among the subregions of the temperature field as the optimization objective. This is combined with the equation-constrained optimization algorithm and multispectral thermometry to establish the statistical law between the missing information and finally realize the reconstruction of the temperature field. Simulation experiments show that, without any a priori knowledge, the method in this paper can realize reconstruction of the temperature field with an accuracy of 1.53-12.05% under two projection angles and has fewer projection angles and stronger robustness than other methods.

Determining the time before or after a galaxy merger event

Aims. This work aims to reproduce the time before or after a merger event of merging galaxies from the IllustrisTNG cosmological simulation using machine learning. Methods. Images of merging galaxies were created in the u, g, r, and i bands from IllustrisTNG. The merger times were determined using the time difference between the last simulation snapshot where the merging galaxies were tracked as two galaxies and the first snapshot where the merging galaxies were tracked as a single galaxy. This time was then further refined using simple gravity simulations. These data were then used to train a residual network (ResNet50), a Swin Transformer (Swin), a convolutional neural network (CNN), and an autoencoder (using a single latent neuron) to reproduce the merger time. The full latent space of the autoencoder was also studied to see if it reproduces the merger time better than the other methods. This was done by reducing the latent space dimensions using Isomap, linear discriminant analysis (LDA), neighbourhood components analysis, sparse random projection, truncated singular value decomposition, and uniform manifold approximation and projection. Results. The CNN is the best of all the neural networks. The performance of the autoencoder was close to the CNN, with Swin close behind the autoencoder. ResNet50 performed the worst. The LDA dimensionality reduction performed the best of the six methods used. The exploration of the full latent space produced worse results than the single latent neuron of the autoencoder. For the test data set, we found a median error of 190 Myr, comparable to the time separation between snapshots in IllustrisTNG. Galaxies more than ≈625 Myr before a merger have poorly recovered merger times, as well as galaxies more than ≈125 Myr after a merger event.

The Experimental Method of Sparse Measurement Based on Target’s Radar Cross Section Data

In experiments of testing targets’ radar cross section (RCS), RCS is a measure of the target’s ability to reflect radar signals in the direction of radar reception. In order to take non blurry spatial-domain imaging of the target, sampling or measuring the target’s RCS signal must meet the Nyquist sampling theorem. However, RCS testing in microwave darkroom would produce a significant amount of sampling data, which requires a very long testing period. Based on the sparsity of spatial-domain RCS data after sparsifying transformation, a sparse projection measurement experimental method is designed for frequency-domain RCS data by sparsely sampling frequency-domain signals, fully utilizing the correlation between row and column information of two-dimensional frequency-domain data and the global sparsity of two-dimensional spatial-domain data. Finally, based on sparsely sampled data in the frequency-domain, the original RCS data is reconstructed by reconstruction algorithms, achieving the goal of effectively reducing RCS sampling data in RCS testing experiments.

Multi-View Synthesis of Sparse Projection of Absorption Spectra Based on Joint GRU and U-Net

Tunable diode laser absorption spectroscopy (TDLAS) technology, combined with chromatographic imaging algorithms, is commonly used for two-dimensional temperature and concentration measurements in combustion fields. However, obtaining critical temperature information from limited detection data is a challenging task in practical engineering applications due to the difficulty of deploying sufficient detection equipment and the lack of sufficient data to invert temperature and other distributions in the combustion field. Therefore, we propose a sparse projection multi-view synthesis model based on U-Net that incorporates the sequence learning properties of gated recurrent unit (GRU) and the generalization ability of residual networks, called GMResUNet. The datasets used for training all contain projection data with different degrees of sparsity. This study shows that the synthesized full projection data had an average relative error of 0.35%, a PSNR of 40.726, and a SSIM of 0.997 at a projection angle of 4. At projection angles of 2, 8, and 16, the average relative errors of the synthesized full projection data were 0.96%, 0.19%, and 0.18%, respectively. The temperature field reconstruction was performed separately for sparse and synthetic projections, showing that the application of the model can significantly improve the reconstruction accuracy of the temperature field of high-energy combustion.

Hierarchical decomposed dual-domain deep learning for sparse-view CT reconstruction

Objective. X-ray computed tomography employing sparse projection views has emerged as a contemporary technique to mitigate radiation dose. However, due to the inadequate number of projection views, an analytic reconstruction method utilizing filtered backprojection results in severe streaking artifacts. Recently, deep learning (DL) strategies employing image-domain networks have demonstrated remarkable performance in eliminating the streaking artifact caused by analytic reconstruction methods with sparse projection views. Nevertheless, it is difficult to clarify the theoretical justification for applying DL to sparse view computed tomography (CT) reconstruction, and it has been understood as restoration by removing image artifacts, not reconstruction. Approach. By leveraging the theory of deep convolutional framelets (DCF) and the hierarchical decomposition of measurement, this research reveals the constraints of conventional image and projection-domain DL methodologies, subsequently, the research proposes a novel dual-domain DL framework utilizing hierarchical decomposed measurements. Specifically, the research elucidates how the performance of the projection-domain network can be enhanced through a low-rank property of DCF and a bowtie support of hierarchical decomposed measurement in the Fourier domain. Main results. This study demonstrated performance improvement of the proposed framework based on the low-rank property, resulting in superior reconstruction performance compared to conventional analytic and DL methods. Significance. By providing a theoretically justified DL approach for sparse-view CT reconstruction, this study not only offers a superior alternative to existing methods but also opens new avenues for research in medical imaging. It highlights the potential of dual-domain DL frameworks to achieve high-quality reconstructions with lower radiation doses, thereby advancing the field towards safer and more efficient diagnostic techniques. The code is available at https://github.com/hanyoseob/HDD-DL-for-SVCT.

Sparse-view cone-beam computed tomography iterative reconstruction based on new multi-gradient direction total variation.

The accurate reconstruction of cone-beam computed tomography (CBCT) from sparse projections is one of the most important areas for study. The compressed sensing theory has been widely employed in the sparse reconstruction of CBCT. However, the total variation (TV) approach solely uses information from the i-coordinate, j-coordinate, and k-coordinate gradients to reconstruct the CBCT image. It is well recognized that the CBCT image can be reconstructed more accurately with more gradient information from different directions. Thus, this study introduces a novel approach, named the new multi-gradient direction total variation minimization method. The method uses gradient information from the ij-coordinate, ik-coordinate, and jk-coordinate directions to reconstruct CBCT images, which incorporates nine different types of gradient information from nine directions. This study assessed the efficacy of the proposed methodology using under-sampled projections from four different experiments, including two digital phantoms, one patient's head dataset, and one physical phantom dataset. The results indicated that the proposed method achieved the lowest RMSE index and the highest SSIM index. Meanwhile, we compared the voxel intensity curves of the reconstructed images to assess the edge structure preservation. Among the various methods compared, the curves generated by the proposed method exhibited the highest level of consistency with the gold standard image curves. In summary, the proposed method showed significant potential in enhancing the quality and accuracy of CBCT image reconstruction.

Optimized signal of calcifications in wide-angle digital breast tomosynthesis: a virtual imaging trial.

Evaluate microcalcification detectability in digital breast tomosynthesis (DBT) and synthetic 2D mammography (SM) for different acquisition setups using a virtual imaging trial (VIT) approach. Medio-lateral oblique (MLO) DBT acquisitions on eight patients were performed at twice the automatic exposure controlled (AEC) dose. The noise was added to the projections to simulate a given dose trajectory. Virtual microcalcification models were added to a given projection set using an in-house VIT framework. Three setups were evaluated: (1) standard acquisition with 25 projections at AEC dose, (2) 25 projections with a convex dose distribution, and (3) sparse setup with 13 projections, every second one over the angular range. The total scan dose and angular range remained constant. DBT volume reconstruction and synthetic mammography image generation were performed using a Siemens prototype algorithm. Lesion detectability was assessed through a Jackknife-alternative free-response receiver operating characteristic (JAFROC) study with six observers. For DBT, the area under the curve (AUC) was 0.97 ± 0.01 for the standard, 0.95 ± 0.02 for the convex, and 0.89 ± 0.03 for the sparse setup. There was no significant difference between standard and convex dose distributions (p = 0.309). Sparse projections significantly reduced detectability (p = 0.001). Synthetic images had a higher AUC with the convex setup, though not significantly (p = 0.435). DBT required four times more reading time than synthetic mammography. A convex setup did not significantly improve detectability in DBT compared to the standard setup. Synthetic images exhibited a non-significant increase in detectability with the convex setup. Sparse setup significantly reduced detectability in both DBT and synthetic mammography. This virtual imaging trial study allowed the design and efficient testing of different dose distribution trajectories with real mammography images, using a dose-neutral protocol. • In DBT, a convex dose distribution did not increase the detectability of microcalcifications compared to the current standard setup but increased detectability for the SM images. • A sparse setup decreased microcalcification detectability in both DBT and SM images compared to the convex and current clinical setups. • Optimal microcalcification cluster detection in the system studied was achieved using either the standard or convex dose setting, with the default number of projections.

Laplacian adaptive weighted discriminant analysis for semi-supervised multi-class classification

A multi-class discriminant analysis via adaptive weighted scheme (MDAAWS) has been proposed for supervised learning, which can deal with the issue that some classes may be vanished in the subspace. However, the acquisition of labeled data is expensive and time-consuming, while the unlabeled data is easy to obtained. To achieve a wide application, we propose a novel semi-supervised multi-class dimensionality reduction method based on MDAAWS, named Laplacian adaptive weighted discriminant analysis (LapAWDA), by applying manifold regularization to labeled and unlabeled data. This method inherits the merit of MDAAWS, assigning each pairwise class with an adaptive weight to avoid the issue of class vanishing. To enhance the robustness, we introduce the ℓ2,1 norm into LapAWDA to obtain a sparse discriminant projection matrix. Moreover, an alternative and iterative scheme is designed to find the solution of LapAWDA. Extensive experiments on several synthetic and real-world datasets demonstrate the excellent performance of LapAWDA.

Industrial defect detection and location based on greedy particle swarm optimization algorithm

ABSTRACT Particle swarm optimization algorithm is a branch of evolutionary computing and can search for a better solution in a given feature space. This paper introduces the particle swarm optimization algorithm and greedy strategy for the defect detection and location of industrial components and then proposes a greedy particle swarm optimization algorithm. This paper employs sparse random projection to map the vast high-dimensional information to the low-dimensional space while maintaining the relative distance between the data. This employment helps to accelerate the training and prediction speed of the model and remove some unimportant features or noise. This algorithm first adopts particle swarm optimization (PSO) to initialize the cluster centers in an effort to minimize the maximum distance between all unlabeled data points and these centers. The algorithm then utilizes the greedy strategy to select a batch of data points to represent the corresponding features of the normal image, thereby improving the coverage of the model to the data. Experiments have shown that the results of most categories of data sets are close to or better than the current existing methods, especially in defect detection. In terms of defect localization for object categories, our method achieves a pixel-level anomaly localization index (AUROC) of 98.3% on the MVTec AD dataset.

Reducing image artifacts in sparse projection CT using conditional generative adversarial networks

Reducing the amount of projection data in computed tomography (CT), specifically sparse-view CT, can reduce exposure dose; however, image artifacts can occur. We quantitatively evaluated the effects of conditional generative adversarial networks (CGAN) on image quality restoration for sparse-view CT using simulated sparse projection images and compared them with autoencoder (AE) and U-Net models. The AE, U-Net, and CGAN models were trained using pairs of artifacts and original images; 90% of patient cases were used for training and the remaining for evaluation. Restoration of CT values was evaluated using mean error (ME) and mean absolute error (MAE). The image quality was evaluated using structural image similarity (SSIM) and peak signal-to-noise ratio (PSNR). Image quality improved in all sparse projection data; however, slight deformation in tumor and spine regions was observed, with a dispersed projection of over 5°. Some hallucination regions were observed in the CGAN results. Image resolution decreased, and blurring occurred in AE and U-Net; therefore, large deviations in ME and MAE were observed in lung and air regions, and the SSIM and PSNR results were degraded. The CGAN model achieved accurate CT value restoration and improved SSIM and PSNR compared to AE and U-Net models.

Unsupervised Feature Selection With Flexible Optimal Graph.

In the unsupervised feature selection method based on spectral analysis, constructing a similarity matrix is a very important part. In existing methods, the linear low-dimensional projection used in the process of constructing the similarity matrix is too hard, it is very challenging to construct a reliable similarity matrix. To this end, we propose a method to construct a flexible optimal graph. Based on this, we propose an unsupervised feature selection method named unsupervised feature selection with flexible optimal graph and l2,1 -norm regularization (FOG-R). Unlike other methods that use linear projection to approximate the low-dimensional manifold of the original data when constructing a similarity matrix, FOG-R can learn a flexible optimal graph, and by combining flexible optimal graph learning and feature selection into a unified framework to get an adaptive similarity matrix. In addition, an iterative algorithm with a strict convergence proof is proposed to solve FOG-R. l2,1 -norm regularization will introduce an additional regularization parameter, which will cause parameter-tuning trouble. Therefore, we propose another unsupervised feature selection method, that is, unsupervised feature selection with a flexible optimal graph and l2,0 -norm constraint (FOG-C), which can avoid tuning additional parameters and obtain a more sparse projection matrix. Most critically, we propose an effective iterative algorithm that can solve FOG-C globally with strict convergence proof. Comparative experiments conducted on 12 public datasets show that FOG-R and FOG-C perform better than the other nine state-of-the-art unsupervised feature selection algorithms.

Fusion recognition of palmprint and palm vein based on modal correlation.

Biometric authentication prevents losses from identity misuse in the artificial intelligence (AI) era. The fusion method integrates palmprint and palm vein features, leveraging their stability and security and enhances counterfeiting prevention and overall system efficiency through multimodal correlations. However, most of the existing multi-modal palmprint and palm vein feature extraction methods extract only feature information independently from different modalities, ignoring the importance of the correlation between different modal samples in the class to the improvement of recognition performance. In this study, we addressed the aforementioned issues by proposing a feature-level joint learning fusion approach for palmprint and palm vein recognition based on modal correlations. The method employs a sparse unsupervised projection algorithm with a "purification matrix" constraint to enhance consistency in intra-modal features. This minimizes data reconstruction errors, eliminating noise and extracting compact, and discriminative representations. Subsequently, the partial least squares algorithm extracts high grayscale variance and category correlation subspaces from each modality. A weighted sum is then utilized to dynamically optimize the contribution of each modality for effective classification recognition. Experimental evaluations conducted for five multimodal databases, composed of six unimodal databases including the Chinese Academy of Sciences multispectral palmprint and palm vein databases, yielded equal error rates (EER) of 0.0173%, 0.0192%, 0.0059%, 0.0010%, and 0.0008%. Compared to some classical methods for palmprint and palm vein fusion recognition, the algorithm significantly improves recognition performance. The algorithm is suitable for identity recognition in scenarios with high security requirements and holds practical value.

FDEPCA: A Novel Adaptive Nonlinear Feature Extraction Method via Fruit Fly Olfactory Neural Network for IoMT Anomaly Detection.

With the rapid development of 5G communication technology, the data in the Internet of Medical Things (IoMT) application systems exhibits complex characteristics such as large volume, high dimensionality, nonlinearity, and diversity, which significantly affect the efficiency and detection performance of anomaly detection tasks. How to efficiently extract nonlinear features from high-dimensional data in the context of the IoMT while minimizing information distortion in data objects are challenging problems in recent academic research. A novel adaptive nonlinear feature extraction method via fruit fly olfactory neural network (Fly dimension expansion projection and remain main components by PCA, FDEPCA) is proposed, where 1) the data are mean-centered; 2) a binary sparse random projection matrix is used for dimension expansion projection; and 3) PCA is used to extract principal component information. The proposed method overcomes the problems of present nonlinear feature extraction in the face of high-dimensional outliers where the intrinsic geometric structure of the data is severely distorted and computationally expensive. The dataset after nonlinear feature extraction by the FDEPCA algorithm is applied to specific anomaly detection models, using ROC curves and AUC as evaluation metrics for classification performance. Extensive comparison experiments are conducted on eight publicly available datasets, and experimental results show that compared with the popular nonlinear feature extraction algorithms, the FDEPCA algorithm has better classification performance and projection time advantage. When applied to proximity-based, probability-based, and ensemble-based different anomaly detection models respectively, the FDEPCA algorithm exhibits strong applicability in different types of anomaly detection classifiers.

DPI-MoCo: Deep Prior Image Constrained Motion Compensation Reconstruction for 4D CBCT.

4D cone-beam computed tomography (CBCT) plays a critical role in adaptive radiation therapy for lung cancer. However, extremely sparse sampling projection data will cause severe streak artifacts in 4D CBCT images. Existing deep learning (DL) methods heavily rely on large labeled training datasets which are difficult to obtain in practical scenarios. Restricted by this dilemma, DL models often struggle with simultaneously retaining dynamic motions, removing streak degradations, and recovering fine details. To address the above challenging problem, we introduce a Deep Prior Image Constrained Motion Compensation framework (DPI-MoCo) that decouples the 4D CBCT reconstruction into two sub-tasks including coarse image restoration and structural detail fine-tuning. In the first stage, the proposed DPI-MoCo combines the prior image guidance, generative adversarial network, and contrastive learning to globally suppress the artifacts while maintaining the respiratory movements. After that, to further enhance the local anatomical structures, the motion estimation and compensation technique is adopted. Notably, our framework is performed without the need for paired datasets, ensuring practicality in clinical cases. In the Monte Carlo simulation dataset, the DPI-MoCo achieves competitive quantitative performance compared to the state-of-the-art (SOTA) methods. Furthermore, we test DPI-MoCo in clinical lung cancer datasets, and experiments validate that DPI-MoCo not only restores small anatomical structures and lesions but also preserves motion information.

Consistency and Complementarity Jointly Regularized Subspace Support Vector Data Description for Multimodal Data

The one‐class classification (OCC) problem has always been a popular topic because it is difficult or expensive to obtain abnormal data in many practical applications. Most of OCC methods focused on monomodal data, such as support vector data description (SVDD) and its variants, while we often face multimodal data in reality. The data come from the same task in multimodal learning, and thus, the inherent structures among all modalities should be hold, which is called the consistency principle. However, each modality contains unique information that can be used to repair the incompleteness of other modalities. It is called the complementarity principle. To follow the above two principles, we designed a multimodal graph–regularized term and a sparse projection matrix–regularized term. The former aims to preserve the within‐modal structural and between‐modal relationships, while the latter aims to richly use the complementarity information hidden in multimodal data. Further, we follow the multimodal subspace (MS) SVDD architecture and use two regularized terms to regularize SVDD. Consequently, a novel OCC method for multimodal data is proposed, called the consistency and complementarity jointly regularized subspace SVDD (CCS‐SVDD). Extensive experimental results demonstrate that our approach is more effective and competitive than other algorithms. The source codes are available at https://github.com/wongchuang/CCS_SVDD.