Motivated by the challenges in detecting extremely rare failures for sophisticated specifications in circuit design, we consider the problem of detecting regions of interest (ROIs) that consist of specifications with the value of a complex target function for the system performance being below or above a certain pre-specified threshold. Though Bayesian optimization (BO) has been applied to this problem, it is not effective in identifying multiple ROIs as it was originally designed for global optimization and tends to focus on searching the area where the global optimum is most likely to be. In this work, we propose a sampling strategy for fast ROI detection within a limited number of target function evaluations. The sampling distribution is designed so that the probability of a specification being sampled is proportional to the corresponding value of the acquisition function. Such an acquisition-guided sampling algorithm promotes a wider search of the sample space and a simpler incorporation of different criteria to determine the specifications to be evaluated next. To further improve the performance, we propose a new design of the acquisition function and two modifications of existing acquisition functions. Numerical studies on synthetic functions and a real-world circuit design application demonstrate that the proposed method can enjoy a stronger exploration ability provided by sampling and achieve faster ROI detection with higher coverage. Note to Practitioners—This study considers the extremely rare failure detection in automated circuit design, fabrication, packaging, and verification. Obtaining enough observations of interest within a given budget of evaluations is challenging due to the scarcity of extremely rare failures. Bayesian optimization (BO) has been adopted to tackle this problem, but it may not achieve satisfactory coverage of multiple failure regions, since its goal is to find the global optimum of the target function. In this paper, we propose a sampling-based rare event detection strategy tailored to efficiently detect regions of interest (ROIs) with high coverage, along with newly designed acquisition functions incorporating the pre-specified threshold and ideas of experimental design. This sampling strategy has greater robustness to the choice of acquisition function. Also, since multiple queries can be easily obtained through sampling, various criteria can be easily incorporated for determining the next batch of evaluation specifications without much increase in computational complexity.

In this paper, we study the problem of blood glucose forecasting and provide a deep personalized solution. Predicting blood glucose level in people with diabetes has significant value because health complications of abnormal glucose level are serious, sometimes even leading to death. Therefore, having a model that can accurately and quickly warn patients of potential problems is essential. To develop a better deep model for blood glucose forecasting, we analyze the data and detect important patterns. These observations helped us to propose a method that has several key advantages over existing methods: 1- it learns a personalized model for each patient as well as a global model; 2- it uses an attention mechanism and extracted time features to better learn long-term dependencies in the data; 3- it introduces a new, robust training procedure for time series data. We empirically show the efficacy of our model on a real dataset.

With increasing design complexity and stringent robustness requirements in application such as automotive electronics, analog and mixed-signal (AMS) verification becomes akey bottleneck. Rare failure detection in a high-dimensional parameter space using minimal expensive simulation data is a major challenge. We address this challenge under a Bayesian learning framework using Bayesian optimization (BO). We formulate the failure detection as a BO problem where a chosen acquisition function is optimized to select the next (set of) optimal simulation sampling point(s) such that rare failures may be detected using a small amount of data. While providing an attractive black-box solution to design verification, in practice BO is limited in its ability in dealing with high-dimensional problems. We propose to use random embedding to effectively reduce the dimensionality of a given verification problem to improve both the quality of BO-based optimal sampling and computational efficiency. We demonstrate the success of the proposed approach on detecting rare design failures under high-dimensional process variations which are completely missed by competitive smart sampling and BO techniques without dimension reduction.

Due to inherent complex behaviors and stringent requirements in analog and mixed-signal (AMS) systems, verification becomes a key bottleneck in the product development cycle. For the first time, we present a Bayesian optimization (BO) based approach to the challenging problem of verifying AMS circuits with stringent low failure requirements. At the heart of the proposed BO process is a delicate balancing between two competing needs: exploitation of the current statistical model for quick identification of highly-likely failures and exploration of undiscovered design space so as to detect hard-to-find failures within a large parametric space. To do so, we simultaneously leverage multiple optimized acquisition functions to explore varying degrees of balancing between exploitation and exploration. This makes it possible to not only detect rare failures which other techniques fail to identify, but also do so with significantly improved efficiency. We further build in a mechanism into the BO process to enable detection of multiple failure regions, hence providing a higher degree of coverage. Moreover, the proposed approach is readily parallelizable, further speeding up failure detection, particularly for large circuits for which acquisition of simulation/measurement data is very time-consuming. Our experimental study demonstrates that the proposed approach is very effective in finding very rare failures and multiple failure regions which existing statistical sampling techniques and other BO techniques can miss, thereby providing a more robust and cost-effective methodology for rare failure detection.

This paper develops an efficient computational method for solving a Gaussian process (GP) regression for large spatial data sets using a collection of suitably defined local GP regressions. The conventional local GP approach first partitions a domain into multiple non-overlapping local regions, and then fits an independent GP regression for each local region using the training data belonging to the region. Two key issues with the local GP are (1) the prediction around the boundary of a local region is not as accurate as the prediction at interior of the local region, and (2) two local GP regressions for two neighboring local regions produce different predictions at the boundary of the two regions, creating undesirable discontinuity in the prediction. We address these issues by constraining the predictions of local GP regressions sharing a common boundary to satisfy the same boundary constraints, which in turn are estimated by the data. The boundary constrained local GP regressions are solved by a finite element method. Our approach shows competitive performance when compared with several state- of-the-art methods using two synthetic data sets and three real data sets.

This paper studies the problem of detecting the presence of nanoparticles in noisy transmission electron microscopic (TEM) images and then fitting each nanoparticle with an elliptic shape model. In order to achieve robustness while handling low contrast and high noise in the TEM images, we propose an approach to fuse two kinds of complementary image information, namely, the pixel intensity and the gradient (the first derivative in intensity). Our approach entails two main steps: 1) the first step is to, after necessary pre-processing, employ both intensity-based information and gradient-based information to process the same TEM image and produce two independent sets of results and 2) the subsequent step is to formulate a binary integer programming (BIP) problem for conflict resolution among the two sets of results. Solving the BIP problem determines the final nanoparticle identification. We apply our method to a set of TEM images taken under different microscopic resolutions and noise levels. The empirical results show the merit of the proposed method. It can process a TEM image of 1024×1024 pixels in a few minutes, and the processed outcomes appear rather robust.

Nonnegative matrix factorization (NMF), a popular part-based representation technique, does not capture the intrinsic local geometric structure of the data space. Graph regularized NMF (GNMF) was recently proposed to avoid this limitation by regularizing NMF with a nearest neighbor graph constructed from the input data set. However, GNMF has two main bottlenecks. First, using the original feature space directly to construct the graph is not necessarily optimal because of the noisy and irrelevant features and nonlinear distributions of data samples. Second, one possible way to handle the nonlinear distribution of data samples is by kernel embedding. However, it is often difficult to choose the most suitable kernel. To solve these bottlenecks, we propose two novel graph-regularized NMF methods, AGNMFFS and AGNMFMK, by introducing feature selection and multiple-kernel learning to the graph regularized NMF, respectively. Instead of using a fixed graph as in GNMF, the two proposed methods learn the nearest neighbor graph that is adaptive to the selected features and learned multiple kernels, respectively. For each method, we propose a unified objective function to conduct feature selection/multi-kernel learning, NMF and adaptive graph regularization simultaneously. We further develop two iterative algorithms to solve the two optimization problems. Experimental results on two challenging pattern classification tasks demonstrate that the proposed methods significantly outperform state-of-the-art data representation methods.

A combination of the sparse coding and transfer learning techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled from different underlying distributions, i.e., belong to different domains. The key assumption in such case is that in spite of the domain disparity, samples from different domains share some common hidden factors. Previous methods often assumed that all the objects in the target domain are unlabeled, and thus the training set solely comprised objects from the source domain. However, in real world applications, the target domain often has some labeled objects, or one can always manually label a small number of them. In this paper, we explore such possibility and show how a small number of labeled data in the target domain can significantly leverage classification accuracy of the state-of-the-art transfer sparse coding methods. We further propose a unified framework named supervised transfer sparse coding (STSC) which simultaneously optimizes sparse representation, domain transfer and classification. Experimental results on three applications demonstrate that a little manual labeling and then learning the model in a supervised fashion can significantly improve classification accuracy.

BACKGROUND: Protein-ligand binding is important for some proteins to perform their functions. Protein-ligand binding sites are the residues of proteins that physically bind to ligands. Despite of the recent advances in computational prediction for protein-ligand binding sites, the state-of-the-art methods search for similar, known structures of the query and predict the binding sites based on the solved structures. However, such structural information is not commonly available. RESULTS: In this paper, we propose a sequence-based approach to identify protein-ligand binding residues. We propose a combination technique to reduce the effects of different sliding residue windows in the process of encoding input feature vectors. Moreover, due to the highly imbalanced samples between the ligand-binding sites and non ligand-binding sites, we construct several balanced data sets, for each of which a random forest (RF)-based classifier is trained. The ensemble of these RF classifiers forms a sequence-based protein-ligand binding site predictor. CONCLUSIONS: Experimental results on CASP9 and CASP8 data sets demonstrate that our method compares favorably with the state-of-the-art protein-ligand binding site prediction methods.

The characteristics of low minor allele frequency (MAF) and weak individual effects make genome-wide association studies (GWAS) for rare variant single nucleotide polymorphisms (SNPs) more difficult when using conventional statistical methods. By aggregating the rare variant effects belonging to the same gene, collapsing is the most common way to enhance the detection of rare variant effects for association analyses with a given trait. In this paper, we propose a novel framework of MAF-based logistic principal component analysis (MLPCA) to derive aggregated statistics by explicitly modeling the correlation between rare variant SNP data, which is categorical. The derived aggregated statistics by MLPCA can then be tested as a surrogate variable in regression models to detect the gene-environment interaction from rare variants. In addition, MLPCA searches for the optimal linear combination from the best subset of rare variants according to MAF that has the maximum association with the given trait. We compared the power of our MLPCA-based methods with four existing collapsing methods in gene-environment interaction association analysis using both our simulation data set and Genetic Analysis Workshop 17 (GAW17) data. Our experimental results have demonstrated that MLPCA on two forms of genotype data representations achieves higher statistical power than those existing methods and can be further improved by introducing the appropriate sparsity penalty. The performance improvement by our MLPCA-based methods result from the derived aggregated statistics by explicitly modeling categorical SNP data and searching for the maximum associated subset of SNPs for collapsing, which helps better capture the combined effect from individual rare variants and the interaction with environmental factors.

Despite considerable progress in the past decades, protein structure prediction remains one of the major unsolved problems in computational biology. Angular-sampling-based methods have been extensively studied recently due to their ability to capture the continuous conformational space of protein structures. The literature has focused on using a variety of parametric models of the sequential dependencies between angle pairs along the protein chains. In this article, we present a thorough review of angular-sampling-based methods by assessing three main questions: What is the best distribution type to model the protein angles? What is a reasonable number of components in a mixture model that should be considered to accurately parameterize the joint distribution of the angles? and What is the order of the local sequence-structure dependency that should be considered by a prediction method? We assess the model fits for different methods using bivariate lag-distributions of the dihedral/planar angles. Moreover, the main information across the lags can be extracted using a technique called Lag singular value decomposition (LagSVD), which considers the joint distribution of the dihedral/planar angles over different lags using a nonparametric approach and monitors the behavior of the lag-distribution of the angles using singular value decomposition. As a result, we developed graphical tools and numerical measurements to compare and evaluate the performance of different model fits. Furthermore, we developed a web-tool (http://www.stat.tamu.edu/∼madoliat/LagSVD) that can be used to produce informative animations.

This paper presents a method that enables automated morphology analysis of partially overlapping nanoparticles in electron micrographs. In the undertaking of morphology analysis, three tasks appear necessary: separate individual particles from an agglomerate of overlapping nano-objects; infer the particle's missing contours; and ultimately, classify the particles by shape based on their complete contours. Our specific method adopts a two-stage approach: the first stage executes the task of particle separation, and the second stage conducts simultaneously the tasks of contour inference and shape classification. For the first stage, a modified ultimate erosion process is developed for decomposing a mixture of particles into markers, and then, an edge-to-marker association method is proposed to identify the set of evidences that eventually delineate individual objects. We also provided theoretical justification regarding the separation capability of the first stage. In the second stage, the set of evidences become inputs to a Gaussian mixture model on B-splines, the solution of which leads to the joint learning of the missing contour and the particle shape. Using twelve real electron micrographs of overlapping nanoparticles, we compare the proposed method with seven state-of-the-art methods. The results show the superiority of the proposed method in terms of particle recognition rate.