Biomarker detection is an indispensable part of the diagnosis and treatment of low-grade glioma (LGG). However, current LGG biomarker detection methods rely on expensive and complex molecular genetic testing, for which professionals are required to analyze the results, and intra-rater variability is often reported. To overcome these challenges, we propose an interpretable deep learning pipeline, named Multi-Biomarker Histomorphology Discoverer (Multi-Beholder), to predict the status of five biomarkers in LGG using only hematoxylin and eosin-stained whole slide images. Specifically, Multi-Beholder incorporates one-class classification into the multiple instance learning framework to achieve accurate instance-level pseudo-labeling, thereby complementing slide-level labels and improving prediction performance. Multi-Beholder demonstrates high performance on two LGG cohorts with diverse races and scanning protocols, with area under the receiver operating characteristic curve up to 0.973 on the internal-validated TCGA-LGG dataset and 0.820 on the external-validated Xiangya cohort. Moreover, the interpretability of Multi-Beholder allows for discovering quantitative and qualitative correlations between biomarker status and histomorphology characteristics. Our pipeline not only provides a novel approach for biomarker prediction, enhancing the applicability of molecular treatments for LGG patients but also facilitates the discovery of new mechanisms in molecular functionality and LGG progression. Code can be accessed athttps://github.com/Vison307/Multi-Beholder.

Recent developments have enabled the high-resolution inversion of the ionosphere using SAR signals. However, the accuracy of SAR-based ionospheric inversion has not been confirmed. This study analyzes the accuracy of SAR-derived ionospheric data in the polar region, characterized by increased ionospheric activity, using both global and regional ionospheric models. The results show an average difference of 1.9 TECU and a standard deviation of 0.5 TECU between SAR and GNSS ionosphere measurements, confirming the reliability of SAR inversion for high-resolution and high-accuracy ionosphere mapping. This work significantly contributes to the SAR-supported ionospheric detection and correction.

This article proposes a novel soft multiprototype clustering algorithm (SMP) for high-dimensional data clustering with noisy and complex structural patterns. SMP integrates dimensionality reduction, multiprototype clustering, and multiprototype merge clustering under a two-layer seminonnegative matrix factorization (semi-NMF) architecture. Specifically, the first semi-NMF layer performs multiprototype clustering, which solves the problem that a single prototype cannot represent complex data structures. Meanwhile, the multiprototype fuzzy clustering constraints ensure that the multiprototypes better characterize the original data structure. The second semi-NMF layer performs multiprototype merge clustering to mitigate the issues of heavy computation burden and poor antinoise performance of the spectral clustering algorithm. The introduction of the Laplace graph matrix regularization constraint in this layer assists SMP in completing the merging of multiprototypes with complex data structures. Comprehensive experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms.

Clustering noisy, high-dimensional, and structurally complex data have always been a challenging task. As most existing clustering methods are not able to deal with both the adverse impact of noisy samples and the complex structures of data, in this article, we propose a novel robust and sparse possibilistic K-subspace (RSPKS) clustering algorithm to integrate subspace recovery and possibilistic clustering algorithms under a unified sparse framework. First, the proposed method sparsifies the membership matrix and the subspace projection vector under a dual-sparse framework to handle high-dimensional noisy data. This unifies dimensionality reduction and clustering using one objective function for which the optimization can be realized through synchronous iteration. Second, the reconstruction error of each sample in the local subspace is used as the distance metric for classification. That is, each sample itself is treated as a clustering prototype so as not to be affected by the structure of the overall data distribution. Therefore, the clustering prototype construction problem of the data with complex structures can be better addressed. Finally, to deal with nonlinear regions, our RSPKS method is further extended into a kernelized version, namely the kernelized RSPKS clustering algorithm. The experimental results on both synthetic and real-world datasets demonstrate that our proposed method outperforms state-of-the-art algorithms in terms of clustering accuracy.

As the research on deep learning methods gradually progresses, more and more classification models are applied in the classification of hyperspectral image. High-dimensional and low-resolution characteristics of hyperspectral image (HSI), however, make it difficult for conventional models to process its data effectively. In this paper, a novel HSI classification model, namely Spatial Spectral Pyramid Network (SSPN), is designed by combining 3D Convolutional Neural Network (3D CNN) with feature pyramid structure. SSPN taking advantage of 3D convolution coupled with multi-scale convolutional extraction is used to obtain a large set of diverse spatial-spectral features. Multi-scale interfusion is also applied in SSPN to enrich the features contained in a single feature map and to improve the sensitivity on HSI spatial-spectral information, allowing it to better learn spatial-spectral features. Moreover, the losses of each combination based on multi-scale interfusion are calculated via weighted average, which enables SSPN to avoid the excessive influence of single combination in the updating of model parameters. Four HSI public datasets and several comparison models are employed to validate the classification effect of SSPN. Experimental results show that SSPN achieves the highest overall accuracy (OA) in all datasets compared with other classification models, with 100%, 98.8%, 99.8% and 98.7% on the datasets of Chikusei, Pavia University, Botswana and Houston 2013, respectively. SSPN is demonstrated to possess higher classification accuracy and better generalization performance on HSI.

KNN has gained popularity in machine learning due to its simplicity and good performance. However, kNN faces two problems with classification tasks. The first is that an appropriate distance measurement is required to compute distances between test sample and training samples. The other is the highly computational complexity due to the requirement of searching the nearest neighbors in the whole training data. In order to mitigate these two problems, we propose a novel method named KCNN to enhance the performance of kNN. KCNN uses convolutional neural networks to learn a suitable distance metric as well as prototype reduction to learn a reduced set of prototypes which can represent the original set. It has several superiorities compared with related methods. The combination of CNN and kNN empowers it to extract discriminative hierarchical features with which kNN can easily classify. KCNN learns spatial information on an image instead of considering it as a vector to learn distance metric. Moreover, KCNN simultaneously learns a reduced set of prototypes, which help improve classification efficiency and avoid noisy samples of the massive training set. The proposed method has a better robustness and convergence than CNN, especially when projecting input data into a low-dimension space.

In recent years, various deep learning based methods have been successfully developed for change detection, such as Convolutional Neural Network (CNN) based U-Net and its variants, and Transformer based ones. However, CNNs lack the ability to effectively learn global representations, while Transformers neglect to learn local representations. Therefore, in this paper we propose a novel deep network, namely Multi-scale Attention based Transformer U-Net (MATU), to take advantages of CNNs and Transformers for learning both local and global features effectively. The backbone of our proposed MATU is a U-Net. In the encoder, a Siamese network is used to extract features from two input images, which is followed by a transformer module to further refine the feature pairs produced by the Siamese network. The difference of the refined feature pairs is fed into an Atrous Spatial Pyramid Pooling (ASSP) module to generate a distance map. Moreover, axial-attention blocks are integrated in the decoder with the corresponding multi-level feature differences of the encoder to progressively produce and improve the change map through attention upsampling. Extensive experiments on two widely used benchmark datasets SYSU-CD and LEVIR-CD demonstrate that the proposed MATU method achieves the state-of-the-art performance. Our code is available at https://github.com/easm002/MATU.

Federated Learning (FL) offers a novel distributed machine learning context whereby a global model is collaboratively learned through edge devices without violating data privacy. However, intrinsic data heterogeneity in the federated network can induce model heterogeneity, thus posing a great challenge to the server-side model aggregation performance. Existing FL algorithms widely adopt model-wise weighted averaging for client models to generate the new global model, which emphasizes the importance of the holistic model but ignores the importance of distinctions between internal parameters of various client models. In this paper, we propose a novel parameter-wise elastic weighted averaging aggregation approach to realize the rapid fusion of heterogeneous client models. Specifically, each client evaluates the importance of model internal parameters in the model update and obtains the corresponding parameter importance coefficient vector; the server implements the parameter-wise weighted averaging for each parameter based on their importance coefficient vectors, thereby aggregating a new global model. Extensive experiments on MNIST and CIFAR-10 datasets with diverse network architectures and hyper-parameter combinations show that our proposed algorithm outperforms the existing state-of-the-art FL algorithms on the performance of heterogeneous model fusion.

This paper presents a method of exercises recommendation based on machine learning. This method can recommend more suitable exercises to students according to the category they belong to. Firstly, we use linear regression and EM algorithm to accurately model the students' mastery of each knowledge point. For each knowledge point, students are divided into several categories according to their mastery of the knowledge point and their average mastery of all knowledge points. For each knowledge point, according to the student history answer record, find out the exercise that can make each kind of student get bigger promotion respectively. For the students who need to recommend the exercises that contain the specified knowledge points, we first use the k-nearest neighbor algorithm to classify the students, and then recommend the exercises suitable for the students. It has been proved by experiments that this method can help students to achieve greater improvement in the same number of exercises.

In conventional unsupervised multi-view clustering (MVC), learning of representations from heterogeneous multiview data and its subsequent clustering are often separately optimized. The disparate optimization would lead to suboptimal performance because multi-view representation learning is not goal-directed. In this paper, we unify unsupervised multi-view learning and deep clustering in a novel discriminative Self-supervised Deep Correlational Multi-view Clustering (SDC-MVC) network. A new unified loss function is proposed to incorporate consensus information into discriminative representations, in which, the former is learnt by maximizing the canonical correlation among multi-view representations projected by neural networks, and the later is achieved through using confident clustering assignments as supervision. Further, multi-view representations are harnessed by our proposed Deep Serial Feature-level (DSF) Fusion layer. Experiments on three public datasets demonstrated that our method outperforms six state-of-the-art correlation-based MVC algorithms in terms of three evaluation metrics.

Data samples of complicated geometry and nonlinear separability are considered as common challenges to clustering algorithms. In this article, we first construct Mahalanobis distance in the kernel space and then propose a novel fuzzy clustering model with a kernelized Mahalanobis distance, namely KMD-FC. The key contributions of KMD-FC include: first, the construction of KMD matrix is innovatively transformed from the Euclidean distance kernel matrix, which is able to effectively avoid the problem of “curse of dimensionality” posed by explicitly calculating the sample covariance matrix in the kernel space; second, for the first time, the kernelized Gustafson–Kessel (GK) fuzzy C-means algorithm is achieved, which is critically important to extend the applications of the GK algorithm to the nonlinear classification tasks; finally, taking account of the overall distribution of samples in the kernel space after kernel mapping to improve the generalizability of the proposed KMD-FC clustering method. Comprehensive experiments conducted on a wide range of datasets, including synthetic datasets and machine learning repository (UCI) datasets, have validated that the proposed clustering algorithm outperformed the state-of-the-art methods in comparison.

Clustering is increasingly important for multiview data analytics and current algorithms are either based on the collaborative learning of local partitions or directly derived global clustering from multikernel learning. In this paper, we innovate a clustering model that unifies the local partitions and global clustering in a collaborative learning framework. We first construct a common multikernel space from a set of basis kernels to better reflect clustering information of each individual view. Then, considering that joint local partitions would conform to the global clustering, we fuse the local partitions and global clustering guidance as a single objective function in accordance with fuzzy clustering form. The collaborative learning strategy enables the mutual and interactive clustering from local partitions and global clustering. The validation was performed over two synthetic and four public databases and the clustering accuracy was measured by normalized mutual information and rand index. The experimental results demonstrated that the proposed algorithm outperformed the related state-of-the-art algorithms in comparison, which included multitask, multikernel, and multiview clustering approaches.

The classical fuzzy discriminant analysis with kernel methods (KFDA) is an effective method of solving nonlinearity pattern analysis problem. In some complicated cases, the kernel machine constituted by a single kernel function is not able to meet some practical application requirements, such as heterogeneous information or unnormalised data, non-flat distribution of samples, etc. By searching for an appropriate linear combination of base kernel functions or matrices, multiple kernel learning (MKL) is able to improve the performance in some extent. So it is a necessary choice to introduce multiple kernel learning into KFDA in order to get better results. In this study, multiple kernel fuzzy discriminant analysis (MKFDA) is proposed. Our method obtains the projection matrix from fuzzy discriminant analysis with multiple kernel, and then feature extraction and classification are made based on the projection matrix. The experiment on the AVIRIS image was performed, and the results showed that the performance of fuzzy discriminant analysis with multiple kernels is better than that of fuzzy discriminant with single kernel for the Hyperspectral images' feature extraction and classification.

Many spectral unmixing approaches ranging from geometry, algebra to statistics have been proposed, in which nonnegative matrix factorization (NMF)-based ones form an important family. The original NMF-based unmixing algorithm loses the spectral and spatial information between mixed pixels when stacking the spectral responses of the pixels into an observed matrix. Therefore, various constrained NMF methods are developed to impose spectral structure, spatial structure, and spectral-spatial joint structure into NMF to enforce the estimated endmembers and abundances preserve these structures. Compared with matrix format, the third-order tensor is more natural to represent a hyperspectral data cube as a whole, by which the intrinsic structure of hyperspectral imagery can be losslessly retained. Extended from NMF-based methods, a matrix-vector nonnegative tensor factorization (NTF) model is proposed in this paper for spectral unmixing. Different from widely used tensor factorization models, such as canonical polyadic decomposition CPD) and Tucker decomposition, the proposed method is derived from block term decomposition, which is a combination of CPD and Tucker decomposition. This leads to a more flexible frame to model various application-dependent problems. The matrix-vector NTF decomposes a third-order tensor into the sum of several component tensors, with each component tensor being the outer product of a vector (endmember) and a matrix (corresponding abundances). From a formal perspective, this tensor decomposition is consistent with linear spectral mixture model. From an informative perspective, the structures within spatial domain, within spectral domain, and cross spectral-spatial domain are retreated interdependently. Experiments demonstrate that the proposed method has outperformed several state-of-the-art NMF-based unmixing methods.

Since most System-on-Chips (SoCs) consist of heterogeneous IP core(s), application-specific Network on Chip (NoC) architectures are appropriate to meet the design requirements. The energy and performance optimization in the NoC design will continue to be the main design goal in nanoscale technologies. In this paper, we present a new hierarchal partitioning approach considering not only the reduction of wire length among cores, but also the optimization of switching power consumption subject to performance constraints. The experimental results on different benchmarks showed that our NoC topology synthesis algorithm can effectively save power and improve performance.

In this paper, we investigate thermal via (T-via) planning during three-dimensional (3-D) floorplanning. First, we consider the temperature constrained T-via planning (TVP) problem on a given 3-D floorplan. Second, we integrate dynamic TVP into 3-D floorplanning process. Our main contribution and results can be summarized as follows. We solve the temperature constrained TVP problem by solving a sequence of simplified interlayer and intralayer TVP subproblems. Each subproblem is formulated as convex programming problem and we derive nearly optimal solution for detailed T-via distribution. Based on the TVP solution, we implement the integrated TVP and 3-D floorplanning algorithm in a two-stage approach. Before floorplanning, blocks are assigned into different layers by solving a sequence of knapsack problems. During floorplanning, T-vias are allocated with white space redistribution to optimize T-via insertion. Experimental results show that our TVP approach can reduce T-vias by 12% compared with a recent published work (J. Cong and Y. Zhang, "Thermal via planning for 3-D ICs," in Proc. Int. Conf. Comput.-Aided Des., Nov. 2005, pp.745-752). Compared with the postfloorplanning optimization approach, integrating TVP into floorplanning process can reduce T-vias by 16% with 21% runtime overhead

Incorporating thermal vias into 3D ICs is a promising way to reduce circuit temperature by lowering down the thermal resistances between device layers. In this paper, we integrate dynamic thermal via planning into 3D floorplanning process. Our 3D floorplanning and thermal via planning approaches are implemented in a two-stage approach. Before floorplanning, the temperature-constrained vertical thermal via planning is formulated as a convex programming problem. Based on the analytical solution, blocks are assigned into different layers by solving a sequence of knapsack problems. Then a SA engine is used to generate floorplans of all these layers simultaneously. During floorplanning, thermal vias are distributed horizontally in each layer with white space redistribution to optimize thermal via insertion. Experimental results show that compared to a recent published result from [14], our method can reduce thermal vias by 15% with 38% runtime overhead.