Search

Using brain activity directly as input for assistive tool control can circumventmuscular dysfunction and increase functional independence for physically impaired people. The motor cortex is commonly targeted for recordings, while growing evidence shows that there exists decodable movement-related neural activity outside of the motor cortex. Several decoding studies demonstrated significant decoding from distributed areas separately. Here, we combine information from all recorded non-motor brain areas and decode executed and imagined movements using a Riemannian decoder. We recorded neural activity from 8 epilepsy patients implanted with stereotactic-electroencephalographic electrodes (sEEG), while they performed an executed and imagined grasping tasks. Before decoding, we excluded all contacts in or adjacent to the central sulcus. The decoder extracts a low-dimensional representation of varying number of components, and classified move/no-move using a minimum-distance-to-geometric-mean Riemannian classifier. We show that executed and imagined movements can be decoded from distributed non-motor brain areas using a Riemannian decoder, reaching an area under the receiver operator characteristic of 0.83 ± 0.11. Furthermore, we highlight the distributedness of the movement-related neural activity, as no single brain area is the main driver of performance. Our decoding results demonstrate a first application of a Riemannian decoder on sEEG data and show that it is able to decode from distributed brain-wide recordings outside of the motor cortex. This brief report highlights the perspective to explore motor-related neural activity beyond the motor cortex, as many areas contain decodable information. [ABSTRACT FROM AUTHOR]

Using brain activity directly as input for assistive tool control can circumventmuscular dysfunction and increase functional independence for physically impaired people. The motor cortex is commonly targeted for recordings, while growing evidence shows that there exists decodable movement-related neural activity outside of the motor cortex. Several decoding studies demonstrated significant decoding from distributed areas separately. Here, we combine information from all recorded non-motor brain areas and decode executed and imagined movements using a Riemannian decoder. We recorded neural activity from 8 epilepsy patients implanted with stereotactic-electroencephalographic electrodes (sEEG), while they performed an executed and imagined grasping tasks. Before decoding, we excluded all contacts in or adjacent to the central sulcus. The decoder extracts a low-dimensional representation of varying number of components, and classified move/no-move using a minimum-distance-to-geometric-mean Riemannian classifier. We show that executed and imagined movements can be decoded from distributed non-motor brain areas using a Riemannian decoder, reaching an area under the receiver operator characteristic of 0.83 ± 0.11. Furthermore, we highlight the distributedness of the movement-related neural activity, as no single brain area is the main driver of performance. Our decoding results demonstrate a first application of a Riemannian decoder on sEEG data and show that it is able to decode from distributed brain-wide recordings outside of the motor cortex. This brief report highlights the perspective to explore motor-related neural activity beyond the motor cortex, as many areas contain decodable information.

• A new method named stacked-ISASP is proposed for subspace clustering. • The proposed method can efficiently capture the low-dimensional informative features within data. • Better low-dimensional structure can be learned from data. Sparse subspace clustering (SSC) method has gained considerable attention in recent decades owing to its advantages in the fields of clustering. In essence, SSC is to learn a sparse affinity matrix followed by striving for a low-dimensional representation of data. However, the SSC and its variants mainly focus on building high-quality affinity matrix while ignoring the importance of low-dimensional feature derived from the affinity matrix. Moreover, due to their intrinsic linearity of models, they cannot efficiently handle data with the nonlinear distribution. In this paper, we propose a stacked independent subspace analysis (ISA) with sparse prior information called stacked-ISASP to deal with these two issues. Powered by handling data with nonlinear structure, our method aims at seeking a low-dimensional feature from the image data. Concretely, the model can stack the modified independent subspace analysis networks by incorporating the prior subspace information from the original data. To validate the efficiency of the proposed method, we compare our proposed stacked-ISASP method with the state-of-the-art methods on real datasets. Experimental results show that our approach can not only learn a better low-dimensional structure from the data but also achieve better performance for the classification task. [ABSTRACT FROM AUTHOR]

Feature representation plays a critical role in speech emotion recognition (SER). As a method of data dimensionality reduction, Non-negative Matrix Factorization (NMF) can obtain the low-dimensional representation of data by matrix decomposition, and make the data more distinguishable. In order to improve the recognition ability of NMF for SER, we conduct a potential study on NMF and propose a supervised NMF model, called joint discrimination ability and similarity constraint of NMF (DSNMF). This model incorporates the discriminative information and similarity information of samples into basic NMF as prior knowledge, so that the original data can be decomposed into more distinguished low-dimensional data. Specifically, on the one hand, the labels of the training set are used to improve the discriminative ability of the model; on the other hand, with the similarity of the training samples, the data of similar samples are more highly aggregated in the low-dimensional space. In addition, the convergence of DSNMF is proved theoretically and experimentally. Extensive experiments on EMODB and IEMOCAP corpora show that the proposed approach has a better classification effect on low-dimensional representation data than other NMF models. • A supervised NMF model is proposed for Speech Emotion Recognition in this work. • This model makes full use of the label information of the data. • This work gives a strategy by introducing a projection matrix obtained by NMF. • Experimental results demonstrate that the effectiveness of proposed model. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) is a widely used tool for dimensionality reduction and feature extraction in the field of computer vision. Traditional PCA is sensitive to outliers which are common in empirical applications. Therefore, in recent years, massive efforts have been made to improve the robustness of PCA. However, many emerging PCA variants developed in the direction have some weaknesses. First, few of them pay attention to the 2D structure of error matrix. Second, to estimate data mean from sample set with outliers by averaging is usually biased. Third, if some elements of a sample are disturbed, to extract principal components (PCs) by directly projecting data with transformation matrix causes incorrect mapping of sample to its genuine location in low-dimensional feature subspace. To alleviate these problems, we present a novel robust method, called nuclear norm-based on PCA (N-PCA) to take full advantage of the structure information of error image. Meanwhile, it is developed under a novel unified framework of PCA to remedy the bias of computing data mean and the low-dimensional representation of a sample both of which are treated as unknown variables in a single model together with projection matrix. To solve N-PCA, we propose an iterative algorithm, which has a closed-form solution in each iteration. Experimental results on several open databases demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In the past few decades, the number and variety of genomic and proteomic data available have increased dramatically. Molecular or functional interaction networks are usually constructed according to high-throughput data and the topological structure of these interaction networks provide a wealth of information for inferring the function of genes or proteins. It is a widely used way to mine functional information of genes or proteins by analyzing the association networks. However, it remains still an urgent but unresolved challenge how to combine multiple heterogeneous networks to achieve more accurate predictions. In this paper, we present a method named ReprsentConcat to improve function inference by integrating multiple interaction networks. The low-dimensional representation of each node in each network is extracted, then these representations from multiple networks are concatenated and fed to gcForest, which augment feature vectors by cascading and automatically determines the number of cascade levels. We experimentally compare ReprsentConcat with a state-of-the-art method, showing that it achieves competitive results on the datasets of yeast and human. Moreover, it is robust to the hyperparameters including the number of dimensions.

Patterns in expression data conserved across multiple independent disease studies are likely to represent important molecular events underlying the disease. We present the INSPIRE method to infer modules of co-expressed genes and the dependencies among the modules from multiple expression datasets that may contain different sets of genes. We show that INSPIRE infers more accurate models than existing methods to extract low-dimensional representation of expression data. We demonstrate that applying INSPIRE to nine ovarian cancer datasets leads to a new marker and potential driver of tumor-associated stroma, HOPX, followed by experimental validation. The implementation of INSPIRE is available at http://inspire.cs.washington.edu. [ABSTRACT FROM AUTHOR]

In this paper, a new dimensionality reduction based temperature distribution sensing (TDS) method is proposed to reconstruct the temperature distribution via the limited number of the scattered temperature measurement data. The projective nonnegative matrix factorization (PNMF) method is developed to exact the basis vectors, and the augmented Lagrangian multipliers (ALM) method is proposed to solve the proposed PNMF model. A dimensionality reduction model is obtained via projecting the original temperature distribution onto the spaces spanned by a set of basis. An objective functional that considers the inaccurate properties of the reconstruction model and the measurement data, the Shearlet regularization and the total variation (TV) method is proposed to convert the TDS task into an optimization problem, where the temperature distribution is indirectly reconstructed via solving a low-dimensional vector. An iteration scheme is developed to solve the objective functional. Numerical simulation results validate the feasibility of the proposed reconstruction algorithm. [ABSTRACT FROM AUTHOR]

The detection of multiple changes (i.e., different kinds of change) in multitemporal remote sensing images is a complex problem. When multispectral images having B spectral bands are considered, an effective solution to this problem is to exploit all available spectral channels in the framework of supervised or partially supervised approaches. However, in many real applications, it is difficult/impossible to collect ground truth information for either multitemporal or single-date images. On the opposite, unsupervised methods available in the literature are not effective in handling the full information present in multispectral and multitemporal images. They usually consider a simplified subspace of the original feature space having small dimensionality and, thus, characterized by a possible loss of change information. In this paper, we present a framework for the detection of multiple changes in bitemporal and multispectral remote sensing images that allows one to overcome the limits of standard unsupervised methods. The framework is based on the following: 1) a compressed yet efficient 2-D representation of the change information and 2) a two-step automatic decision strategy. The effectiveness of the proposed approach has been tested on two bitemporal and multispectral data sets having different properties. Results obtained on both data sets confirm the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

In the past few decades, the number and variety of genomic and proteomic data available have increased dramatically. Molecular or functional interaction networks are usually constructed according to high-throughput data and the topological structure of these interaction networks provide a wealth of information for inferring the function of genes or proteins. It is a widely used way to mine functional information of genes or proteins by analyzing the association networks. However, it remains still an urgent but unresolved challenge how to combine multiple heterogeneous networks to achieve more accurate predictions. In this paper, we present a method named ReprsentConcat to improve function inference by integrating multiple interaction networks. The low-dimensional representation of each node in each network is extracted, then these representations from multiple networks are concatenated and fed to gcForest, which augment feature vectors by cascading and automatically determines the number of cascade levels. We experimentally compare ReprsentConcat with a state-of-the-art method, showing that it achieves competitive results on the datasets of yeast and human. Moreover, it is robust to the hyperparameters including the number of dimensions. [ABSTRACT FROM AUTHOR]