arXiv subjects

Feng Yan

Publications and source records attributed to Feng Yan.

96 records · Page 6Linked to original sources

arXiv2014

Accuracy of Homology based Coverage Hole Detection for Wireless Sensor Networks on Sphere

Homology theory has attracted great attention because it can provide novel and powerful solutions to address coverage problems in wireless sensor networks. They usually use an easily computable algebraic object, Rips complex, to detect coverage holes. But Rips complex may miss some coverage holes in some cases. In this paper, we investigate homology-based coverage hole detection for wireless sensor networks on sphere. The situations when Rips complex may miss coverage holes are first presented. Then we choose the proportion of the area of coverage holes missed by Rips complex as a metric to evaluate the accuracy of homology-based coverage hole detection approaches. Three different cases are considered for the computation of accuracy. For each case, closed-form expressions for lower and upper bounds of the accuracy are derived. Simulation results are well consistent with the analytical lower and upper bounds, with maximum differences of 0.5% and 3% respectively. Furthermore, it is shown that the radius of sphere has little impact on the accuracy if it is much larger than communication and sensing radii of each sensor.

cs.NI↗

arXiv2012

Sparse matrix-variate Gaussian process blockmodels for network modeling

We face network data from various sources, such as protein interactions and online social networks. A critical problem is to model network interactions and identify latent groups of network nodes. This problem is challenging due to many reasons. For example, the network nodes are interdependent instead of independent of each other, and the data are known to be very noisy (e.g., missing edges). To address these challenges, we propose a new relational model for network data, Sparse Matrix-variate Gaussian process Blockmodel (SMGB). Our model generalizes popular bilinear generative models and captures nonlinear network interactions using a matrix-variate Gaussian process with latent membership variables. We also assign sparse prior distributions on the latent membership variables to learn sparse group assignments for individual network nodes. To estimate the latent variables efficiently from data, we develop an efficient variational expectation maximization method. We compared our approaches with several state-of-the-art network models on both synthetic and real-world network datasets. Experimental results demonstrate SMGBs outperform the alternative approaches in terms of discovering latent classes or predicting unknown interactions.

cs.LG↗

arXiv2012

Infinite Tucker Decomposition: Nonparametric Bayesian Models for Multiway Data Analysis

Tensor decomposition is a powerful computational tool for multiway data analysis. Many popular tensor decomposition approaches---such as the Tucker decomposition and CANDECOMP/PARAFAC (CP)---amount to multi-linear factorization. They are insufficient to model (i) complex interactions between data entities, (ii) various data types (e.g. missing data and binary data), and (iii) noisy observations and outliers. To address these issues, we propose tensor-variate latent nonparametric Bayesian models, coupled with efficient inference methods, for multiway data analysis. We name these models InfTucker. Using these InfTucker, we conduct Tucker decomposition in an infinite feature space. Unlike classical tensor decomposition models, our new approaches handle both continuous and binary data in a probabilistic framework. Unlike previous Bayesian models on matrices and tensors, our models are based on latent Gaussian or $t$ processes with nonlinear covariance functions. To efficiently learn the InfTucker from data, we develop a variational inference technique on tensors. Compared with classical implementation, the new technique reduces both time and space complexities by several orders of magnitude. Our experimental results on chemometrics and social network datasets demonstrate that our new models achieved significantly higher prediction accuracy than the most state-of-art tensor decomposition

cs.LG↗

arXiv2011

EigenNet: A Bayesian hybrid of generative and conditional models for sparse learning

It is a challenging task to select correlated variables in a high dimensional space. To address this challenge, the elastic net has been developed and successfully applied to many applications. Despite its great success, the elastic net does not explicitly use correlation information embedded in data to select correlated variables. To overcome this limitation, we present a novel Bayesian hybrid model, the EigenNet, that uses the eigenstructures of data to guide variable selection. Specifically, it integrates a sparse conditional classification model with a generative model capturing variable correlations in a principled Bayesian framework. We reparameterize the hybrid model in the eigenspace to avoid overfiting and to increase the computational efficiency of its MCMC sampler. Furthermore, we provide an alternative view to the EigenNet from a regularization perspective: the EigenNet has an adaptive eigenspace-based composite regularizer, which naturally generalizes the $l_{1/2}$ regularizer used by the elastic net. Experiments on synthetic and real data show that the EigenNet significantly outperforms the lasso, the elastic net, and the Bayesian lasso in terms of prediction accuracy, especially when the number of training samples is smaller than the number of variables.

cs.LG↗

arXiv2011

Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties

Online learning has become increasingly popular on handling massive data. The sequential nature of online learning, however, requires a centralized learner to store data and update parameters. In this paper, we consider online learning with {\em distributed} data sources. The autonomous learners update local parameters based on local data sources and periodically exchange information with a small subset of neighbors in a communication network. We derive the regret bound for strongly convex functions that generalizes the work by Ram et al. (2010) for convex functions. Most importantly, we show that our algorithm has \emph{intrinsic} privacy-preserving properties, and we prove the sufficient and necessary conditions for privacy preservation in the network. These conditions imply that for networks with greater-than-one connectivity, a malicious learner cannot reconstruct the subgradients (and sensitive raw data) of other learners, which makes our algorithm appealing in privacy sensitive applications.

cs.LG↗

arXiv2004

Multipixel characterization of imaging CZT detectors for hard X-ray imaging and spectroscopy

We report our in-depth study of Cd-Zn-Te (CZT) crystals to determine an optimum pixel and guard band configuration for Hard X-ray imaging and spectroscopy. We tested 20x20x5mm crystals with 8x8 pixels on a 2.46mm pitch. We have studied different types of cathode / anode contacts and different pixel pad sizes. We present the measurements of leakage current as well as spectral response for each pixel. Our I-V measurement setup is custom designed to allow automated measurements of the I-V curves sequentially for all 64 pixels, whereas the radiation properties measurement setup allows for interchangeable crystals with the same XAIM3.2 ASIC readout from IDEAS. We have tested multiple crystals of each type, and each crystal in different positions to measure the variation between individual crystals and variation among the ASIC channels. We also compare the same crystals with and without a grounded guard band deposited on the crystal side walls vs. a floating guard band and compare results to simulations. This study was carried out to find the optimum CZT crystal configuration for prototype detectors for the proposed Black-Hole Finder mission, EXIST.

astro-ph↗