Privacy-preserving data publication problem has attracted more and more attentions in recent years. A lot of related research works have been done towards dataset with single sensitive attribute. However, usually, ori...
详细信息
There’re many effective architectures of the artificial neural network(ANN). For which the training is a hard work. The cost for training an ANN increases exponentially when the ANN gets deeper or wider. We therefore...
详细信息
There’re many effective architectures of the artificial neural network(ANN). For which the training is a hard work. The cost for training an ANN increases exponentially when the ANN gets deeper or wider. We therefore propose a novel architecture, the Hybrid Learning Network(HLN), to achieve a fast learning with good stablity. The HLN can learn from both labeled data and unlabeled data at the same time in a hybrid learning manner. It uses a Self Organizing Map unified by the specially designed nonlinear function as the sparsity mask for a hidden layer to improve the training speed. We experiment our architecture on a synthetic dataset to test its regression capability against the traditional architecture, the result is promising.
This paper extends frequency domain quantitative electroencephalography (qEEG) methods pursuing higher sensitivity to detect Brain Developmental Disorders. Prior qEEG work lacked integration of cross-spectral informat...
详细信息
This paper extends frequency domain quantitative electroencephalography (qEEG) methods pursuing higher sensitivity to detect Brain Developmental Disorders. Prior qEEG work lacked integration of cross-spectral information omitting important functional connectivity descriptors. Lack of geographical diversity precluded accounting for site-specific variance, increasing qEEG nuisance variance. We ameliorate these weaknesses. (i) Create lifespan Riemannian multinational qEEG norms for cross-spectral tensors. These norms result from the HarMNqEEG project fostered by the Global Brain Consortium. We calculate the norms with data from 9 countries, 12 devices, and 14 studies, including 1564 subjects. Instead of raw data, only anonymized metadata and EEG cross spectral tensors were shared. After visual and automatic quality control, developmental equations for the mean and standard deviation of qEEG traditional and Riemannian DPs were calculated using additive mixed-effects models. We demonstrate qEEG "batch effects " and provide methods to calculate harmonized z-scores. (ii) We also show that harmonized Riemannian norms produce z-scores with increased diagnostic accuracy predicting brain dysfunction produced by malnutrition in the first year of life and detecting COVID induced brain dysfunction. (iii) We offer open code and data to calculate different individual z-scores from the HarMNqEEG dataset. These results contribute to developing bias-free, low-cost neuroimaging technologies applicable in various health settings.
Join is one of the most important operations in data analytics systems. Prior works focus mainly on join optimization using GPUs, but little is known about performance impact on the MICs. In order to investigate poten...
详细信息
—In order to retrieve unlabeled images by textual queries, cross-media similarity computation is a key ingredient. Although novel methods are continuously introduced, little has been done to evaluate these methods to...
详细信息
Attribute reduction is an inevitable problem in machine learning and statistical learning. To improve the traditional rough set reduction, statistical rough sets is then proposed by introducing random sampling into th...
详细信息
This paper strives to find amidst a set of sentences the one best describing the content of a given image or video. Different from existing works, which rely on a joint subspace for their image and video caption retri...
详细信息
This paper proposes a novel method for cross-modal retrieval. Different from vector (text)-to-vector (image) framework of the traditional cross-modal methods, we adopt a vector (text)-to-matrix (image) framework. We a...
详细信息
ISBN:
(纸本)9781509060689
This paper proposes a novel method for cross-modal retrieval. Different from vector (text)-to-vector (image) framework of the traditional cross-modal methods, we adopt a vector (text)-to-matrix (image) framework. We assume that compared with vectors, matrices can directly represent images and characterize the structure of feature space. Furthermore, we propose a Metric based on Multi-order spaces (MMs). Multi-order statistic features are used to represent images for enriching the semantic information, and metrics among the multi-spaces are jointly learned to measure the similarity between two different modalities. Specifically, there are three steps for MMs. First, we jointly use the bags of visual features (zero-order), mean (first-order) and covariance (second-order) to characterize each image. Second, considering that covariance matrices and vectors lie on a Riemannian manifold and an Euclidean space respectively, we embed multi-order spaces into their corresponding Hilbert spaces to reduce the heterogeneity among the original spaces. Finally, the similarity between two different modalities can be measured by learning multiple transformations from the different Hilbert spaces to a common subspace. The performance of the proposed method over the state-of-the-art has been demonstrated through the experiments on two public datasets.
We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e...
详细信息
ISBN:
(纸本)9781509020218
We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e., heat) for the point. The heat map provides a global view on the influence distribution in the space, and hence supports exploratory analyses in many applications such as marketing and resource management. To construct such a heat map, we first reduce it to a problem called Region Coloring (RC), which divides the space into disjoint regions within which all the points have the same RNN set. We then propose a novel algorithm named CREST that efficiently solves the RC problem by labeling each region with the heat value of its containing points. In CREST, we propose innovative techniques to avoid processing expensive RNN queries and greatly reduce the number of region labeling operations. We perform detailed analyses on the complexity of CREST and lower bounds of the RC problem, and prove that CREST is asymptotically optimal in the worst case. Extensive experiments with both real and synthetic data sets demonstrate that CREST outperforms alternative algorithms by several orders of magnitude.
暂无评论