Hidden Structure Of Data Research Articles

BPVSE: Publicly Verifiable Searchable Encryption for Cloud-Assisted Electronic Health Records

Cloud-assisted electronic health records (EHRs) provide convenient medical services for patients by storing and analyzing medical data records in the cloud, but searching for sensitive data (e.g., identity, medical history) in the cloud conflicts with privacy protection requirements. Searchable encryption (SE) is a good cryptographic primitive for solving this conflict, which allows the user to store their encrypted data in the cloud and search them later in encrypted domain. However, the direct applications of most existing SE schemes in cloud-assisted EHRs may result in challenges, for example in terms of functionality, security and efficiency. In this paper, we propose BPVSE, a new verifiable and dynamic SE scheme for cloud-assisted EHR. BPVSE has the following advantages over existing approaches. First, leveraging blockchain and hash-proof chain, BPVSE allows the user to publicly verify the search result returned by the cloud without a trusted authority. Second, BPVSE supports dynamic datasets with forward and backward security, using our newly designed new hidden data structure. Third, BPVSE enables the user to launch parallel search with efficient encryption. We formally prove the security of the proposed BPVSE, and also conduct theoretical comparison and experimental evaluation to show its superiority of functionality, security, and efficiency.

Time-Enabled and Verifiable Secure Search for Blockchain-Empowered Electronic Health Record Sharing in IoT

The collection and sharing of electronic health records (EHRs) via the Internet of Things (IoT) can enhance the accuracy of disease diagnosis. However, it is challenging to guarantee the secure search of EHR during the sharing process. The advent of blockchain is a promising solution to address the issues, owing to its remarkable features such as immutability and anonymity. In this paper, we propose a novel blockchain-based secure sharing system over searchable encryption and hidden data structure via IoT devices. EHR ciphertexts of data owners are stored in the interplanetary file system (IPFS). A user with proper access permissions can search for the desired data with the data owner’s time-bound authorization and verify the authenticity of the search result. After that, the data user can access the relevant EHR ciphertext from IPFS using a symmetric key. The scheme jointly uses searchable encryption and smart contract to realize secure search, time control, verifiable keyword search, fast search, and forward privacy in IoT scenarios. Performance analysis and proof demonstrate that the proposed protocol can satisfy the design goals. In addition, performance evaluation shows the high scalability and feasibility of the proposed scheme.

Scalable Fuzzy Clustering With Anchor Graph

Fuzzy clustering algorithms have been widely used to reveal the possible hidden structure of data. However, with the increasing of data amount, large scale data has brought genuine challenges for fuzzy clustering. Most fuzzy clustering algorithms suffer from the long time-consumption problem since a large amount of distance calculations are involved to update the solution per iteration. To address this problem, we introduce the popular anchor graph technique into fuzzy clustering and propose a scalable fuzzy clustering algorithm referred to as Scalable Fuzzy Clustering with Anchor Graph (SFCAG). The main characteristic of SFCAG is that it addresses the scalability issue plaguing fuzzy clustering from two perspectives: anchor graph construction and membership matrix learning. Specifically, we select a small number of anchors and construct a sparse anchor graph, which is beneficial to reduce the computational complexity. We then formulate a trace ratio model, which is parameter-free, to learn the membership matrix of anchors to speed up the clustering procedure. In addition, the proposed method enjoys linear time complexity with the data size. Extensive experiments performed on both synthetic and real world datasets demonstrate the superiority (both effectiveness and scalability) of the proposed method over some representative large scale clustering methods.

Does non-linear factorization of financial returns help build better and stabler portfolios?

A portfolio allocation method based on linear and non-linear latent constrained conditional factors is presented. The factor loadings are constrained to always be positive in order to obtain long-only portfolios, which is not guaranteed by classical factor analysis or PCA. In addition, the factors are to be uncorrelated among clusters in order to build long-only portfolios. Our approach is based on modern machine learning tools: convex Non-negative Matrix Factorization (NMF) and autoencoder neural networks, designed in a specific manner to enforce the learning of useful hidden data structure such as correlation between the assets' returns. Our technique finds lowly correlated linear and non-linear conditional latent factors which are used to build outperforming global portfolios consisting of cryptocurrencies and traditional assets, similar to hierarchical clustering method. We study the dynamics of the derived non-linear factors in order to forecast tail losses of the portfolios and thus build more stable ones.

Robust Jointly Sparse Fuzzy Clustering With Neighborhood Structure Preservation

Fuzzy clustering techniques, especially fuzzy C-means (FCM) and its weighted variants, are typical partitive clustering models that are widely used for revealing possible hidden structures in data. Although they can quantitatively depict the overlapping areas with a partition matrix, their performances deteriorate when dealing with high-dimensional data because the distance computations may be negatively impacted by the irrelevant features, and then the concentration effect may arise. Moreover, they are sensitive to noisy environments. To tackle these obstacles, a robust jointly sparse fuzzy clustering method (RJSFC) is proposed in this study. The representative prototypes, sparse membership grades, and an orthogonal projection matrix are simultaneously learnt when optimizing RJSFC. The obtained low-dimensional embeddings can preserve the local neighborhood structure, and the clustering is conducted in the transformed lower dimensional space rather than the original space, which improves the capability of fuzzy clustering for dealing with high-dimensional scenarios. Furthermore, <inline-formula><tex-math notation="LaTeX">${L_{2,1}}$</tex-math></inline-formula>-norm is exploited as the basic metric for both loss and regularization parts in RJSFC, the robustness of the model and the interpretability of the extracted features are enhanced. The notions of fuzzy clustering, neighborhood structure preservation, and feature extraction are seamlessly integrated into a unified model. The limitation of the previous two-stage clustering framework when dealing with high-dimensional data entailing dimensionality reduction and clustering procedures separately can be effectively addressed. Extensive experimental results on various well-known datasets demonstrate the usefulness of RJSFC when comparing with some state-of-the-art methods.

Deep learning black hole metrics from shear viscosity

Based on AdS/CFT correspondence, we build a deep neural network to learn black hole metrics from the complex frequency-dependent shear viscosity. The network architecture provides a discretized representation of the holographic renormalization group flow of the shear viscosity and can be applied to a large class of strongly coupled field theories. Given the existence of the horizon and guided by the smoothness of spacetime, we show that Schwarzschild and Reissner-Nordstr\"{o}m metrics can be learned accurately. Moreover, we illustrate that the generalization ability of the deep neural network can be excellent, which indicates that by using the black hole spacetime as a hidden data structure, a wide spectrum of the shear viscosity can be generated from a narrow frequency range. These results are further generalized to an Einstein-Maxwell-dilaton black hole. Our work might not only suggest a data-driven way to study holographic transports but also shed some light on holographic duality and deep learning.

Infinite ShapeOdds: Nonparametric Bayesian Models for Shape Representations

Learning compact representations for shapes (binary images) is important for many applications. Although neural network models are very powerful, they usually involve many parameters, require substantial tuning efforts and easily overfit small datasets, which are common in shape-related applications. The state-of-the-art approach, ShapeOdds, as a latent Gaussian model, can effectively prevent overfitting and is more robust. Nonetheless, it relies on a linear projection assumption and is incapable of capturing intrinsic nonlinear shape variations, hence may leading to inferior representations and structure discovery. To address these issues, we propose Infinite ShapeOdds (InfShapeOdds), a Bayesian nonparametric shape model, which is flexible enough to capture complex shape variations and discover hidden cluster structures, while still avoiding overfitting. Specifically, we use matrix Gaussian priors, nonlinear feature mappings and the kernel trick to generalize ShapeOdds to a shape-variate Gaussian process model, which can grasp various nonlinear correlations among the pixels within and across (different) shapes. To further discover the hidden structures in data, we place a Dirichlet process mixture (DPM) prior over the representations to jointly infer the cluster number and memberships. Finally, we exploit the Kronecker-product structure in our model to develop an efficient, truncated variational expectation-maximization algorithm for model estimation. On synthetic and real-world data, we show the advantage of our method in both representation learning and latent structure discovery.

Map Reduce based REmoving Dependency on K and Initial Centroid Selection MR-REDIC Algorithm for clustering of Mixed Data

In machine learning, clustering is recognized as widely used task to find hidden structure of data. While handling the massive amount of data, the traditional clustering algorithm degrades in performance due to size and mixed type of at-tributes. The Removal Dependency on K and Initial Centroid Selection (REDIC) algorithm is designed to handle mixed data with frequency based dissimilarity measurement for categorical attributes. The selection of initial centroids and prior decision for number of cluster improves the efficiency of REDIC algorithm. To deal with the large scale data, the REDIC algorithm is migrated to Map Reduce paradigm,and Map Reduce based REDIC( MR-REDIC) algorithm is proposed. The large amount of data is divided into small chunks and parallel approach is used to reduce the execution time of algorithm.The proposed algorithm inherits the feature of REDIC algorithm to cluster the data.The algorithm is implemented in Hadoop environment with three different configuration and evaluated using five bench mark data sets. Experimental results show that the Speed up value of data is gradually shifting towards linear by increasing number of data nodes from one to four. The algorithm also achieves the near to closer value for Scale up parameter, while maintaining the accuracy of algorithm.

A Hybrid and Parameter-Free Clustering Algorithm for Large Data Sets

As an important unsupervised learning method, clustering can find the hidden structures in data effectively. With the amount of data grows larger, clustering of large data sets is a challenging task. Many clustering algorithms have been developed to deal with small data sets, but they are often inefficient when the data sets are large. Meanwhile, most clustering algorithms require some extra parameters as input, which may not be easy to obtain in practical applications. This paper proposed a new clustering algorithm called hybrid and parameter-free clustering method (HPFCM). HPFCM is able to rapidly perform clustering on large data sets without knowing the number of clusters in advance. HPFCM is based on sampling on large data sets (MMRS* sampling), assessing the clustering tendency on samples (eVAT), determining the number of clusters (EPB), forming different partitions (MST tree cutting), and extending the results to the rest of the data sets. We compare HPFCM with the other three methods, which are popular in clustering large data sets. Several numerical and real-world experiments have been conducted to verify our algorithm. The results show the great potential and effectiveness of HPFCM for clustering large data sets.

Imbalanced classification by learning hidden data structure

ABSTRACTApproaches to solve the imbalanced classification problem usually focus on rebalancing the class sizes, neglecting the effect of the hidden structure within the majority class. The purpose of this article is to first highlight the effect of sub-clusters within the majority class on the detection of the minority instances and then handle the imbalanced classification problem by learning the structure in the data. We propose a decomposition-based approach to a two-class imbalanced classification problem. This approach works by first learning the hidden structure of the majority class using an unsupervised learning algorithm and thus transforming the classification problem into several classification sub-problems. The base classifier is constructed on each sub-problem. The ensemble is tuned to increase its sensitivity toward the minority class. We also provide a metric for selecting the clustering algorithm by comparing estimates of the stability of the decomposition, which appears necessary for good classifier performance. We demonstrate the performance of the proposed approach through various real data sets.

Semi-Supervised Fuzzy Clustering with Feature Discrimination.

Semi-supervised clustering algorithms are increasingly employed for discovering hidden structure in data with partially labelled patterns. In order to make the clustering approach useful and acceptable to users, the information provided must be simple, natural and limited in number. To improve recognition capability, we apply an effective feature enhancement procedure to the entire data-set to obtain a single set of features or weights by weighting and discriminating the information provided by the user. By taking pairwise constraints into account, we propose a semi-supervised fuzzy clustering algorithm with feature discrimination (SFFD) incorporating a fully adaptive distance function. Experiments on several standard benchmark data sets demonstrate the effectiveness of the proposed method.

Transforming Scagnostics to Reveal Hidden Features.

Scagnostics (Scatterplot Diagnostics) were developed by Wilkinson et al. based on an idea of Paul and John Tukey, in order to discern meaningful patterns in large collections of scatterplots. The Tukeys' original idea was intended to overcome the impediments involved in examining large scatterplot matrices (multiplicity of plots and lack of detail). Wilkinson's implementation enabled for the first time scagnostics computations on many points as well as many plots. Unfortunately, scagnostics are sensitive to scale transformations. We illustrate the extent of this sensitivity and show how it is possible to pair statistical transformations with scagnostics to enable discovery of hidden structures in data that are not discernible in untransformed visualizations.

Cascade model with Dirichlet process for analyzing multiple dyadic matrices

Dyadic matrices are natural data representations in a wide range of domains. A dyadic matrix often involves two types of abstract objects and is based on observations of pairs of elements with one element from each object. Owing to the increasing needs from practical applications, dyadic data analysis has recently attracted increasing attention and many techniques have been developed. However, most existing approaches, such as co-clustering and relational reasoning, only handle a single dyadic table and lack flexibility to perform prediction using multiple dyadic matrices. In this article, we propose a general nonparametric Bayesian framework with a cascaded structure to model multiple dyadic matrices and then describe an efficient hybrid Gibbs sampling algorithm for posterior inference and analysis. Empirical evaluations using both synthetic data and real data show that the proposed model captures the hidden structure of data and generalizes the predictive inference in a unique way.

Tree-structured analysis of treatment effects with large observational data

Treatment effect in an observational study of relatively large scale can be described as a mixture of effects among subgroups. In particular, analysis for estimating the treatment effect at the level of an entire sample potentially involves not only differential effects across subgroups of the entire study cohort, but also differential propensities – probabilities of receiving treatment given study subjects’ pretreatment history. Such complex heterogeneity is of great research interest because the analysis of treatment effects can substantially depend on the hidden data structure for effect sizes and propensities. To uncover the unseen data structure, we propose a likelihood-based regression tree method which we call marginal tree (MT). The MT method is aimed at a simultaneous assessment of differential effects and propensity scores so that both become homogeneous within each terminal node of the resultant tree structure. We assess simulation performances of the MT method by comparing it with other existing tree methods and illustrate its use with a simulated data set, where the objective is to assess the effects of dieting behavior on its subsequent emotional distress among adolescent girls.

Unsupervised Multi-Level Non-Negative Matrix Factorization Model: Binary Data Case

Rank determination issue is one of the most significant issues in non-negative matrix factorization (NMF) research. However, rank determination problem has not received so much emphasis as sparseness regularization problem. Usually, the rank of base matrix needs to be assumed. In this paper, we propose an unsupervised multi-level non-negative matrix factorization model to extract the hidden data structure and seek the rank of base matrix. From machine learning point of view, the learning result depends on its prior knowledge. In our unsupervised multi-level model, we construct a three-level data structure for non-negative matrix factorization algorithm. Such a construction could apply more prior knowledge to the algorithm and obtain a better approximation of real data structure. The final bases selection is achieved through L2-norm optimization. We implement our experiment via binary datasets. The results demonstrate that our approach is able to retrieve the hidden structure of data, thus determine the correct rank of base matrix.

Explorative data analysis techniques and unsupervised clustering methods to support clinical assessment of Chronic Obstructive Pulmonary Disease (COPD) phenotypes

Chronic Obstructive Pulmonary Disease (COPD) is the fourth leading cause of death worldwide and represents one of the major causes of chronic morbidity. Cigarette smoking is the most important risk factor for COPD. In these patients, the airflow limitation is caused by a mixture of small airways disease and parenchyma destruction, the relative contribution of which varies from person to person. The twofold nature of the pathology has been studied in the past and according to some authors each patient should be classified as presenting a predominantly bronchial or emphysematous phenotype. In this study we applied various explorative analysis techniques (PCA, MCA, MDS) and recent unsupervised clustering methods (KHM) to study a large dataset, acquired from 415 COPD patients, to assess the presence of hidden structures in data corresponding to the different COPD phenotypes observed in clinical practice. In order to validate our methods, we compared the results obtained from a training set of 415 patients with lung density data acquired in a test set of 93 patients who underwent HRCT (High Resolution Computerized Tomography).

Statistical evaluation of aerosol data from Ben Macdhui mountain, South Africa

The aim of this study is re-evaluation of the data collected during Ben Macdhui High Altitude Trace Gas and Aerosols Transport Experiment (BHATTEX) to identify the dominant species of aerosols and their interactions in the atmosphere. Particularly, investigations of seasonal variations, the origin of sulphates and the formation of the ammonia sulphate were essential topics of this study. Such analyses were done by application of unique combination of supervised and unsupervised learning classification methods. Namely discriminant function analysis (DFA) for simple identification of parameters and principal component analysis (PCA) for the further investigations on hidden structure of data has been applied. The analysis shows that sulphate concentration and C,N isotopic ratios can classify winter and summer patterns of data. Differences between sulphate concentrations in summer and winter samples indicated by second PCA component were probably related to meteorological conditions over that region. The relations between anthropogenic compounds and ammonia or sulphate were much more stronger in summer samples than in winter ones, that is related with seasonal transport of that particles from industry to the investigated regions. The hypothesis of competitive reaction between sulphates, nitrates and ammonia ions has been also proven by application of simple regression analysis. Moreover the analysis of correlations coefficients shows that those relations are independent on seasons.

Enhancement of fuzzy clustering by mechanisms of partial supervision

Semi-supervised (or partial) fuzzy clustering plays an important and unique role in discovering hidden structure in data realized in presence of a certain quite limited fraction of labeled patterns. The objective of this study is to investigate and quantify the effect of various distance functions (distances) on the performance of the clustering mechanisms. The underlying goal of endowing the clustering algorithms with a higher level of flexibility is done via the use of various distances. The enhancement of this character is evaluated by means of a comprehensive assessment of quality of clusters, their ensuing discrimination abilities and the accuracy of clusters themselves. In addition to the standard Euclidean distance being commonly exploited in fuzzy clustering, three more versatile and adaptive distance measures are considered such as its weighted version, a full adaptive distance, and a kernel-based distance. Using Fuzzy C-Means (FCM) coming in its generic format, we show its semi-supervised enhancements, derive detailed formulas and analyze their effectiveness. The improvements of semi-supervised clustering are empirically evaluated and numerically quantified with the use of several Machine Learning data sets.

Testing for non-linearity in an artificial financial market: a recurrence quantification approach

In this paper, earlier work on testing for non-linear dynamics on realizations from an artificial financial market is extended in two ways. On the one hand, Hinich’s bispectral test and White’s neural network test are computed. On the other hand, a recently developed methodology to test for hidden structures in data, inherited from Physics, is successfully applied on the realizations of the artificial market. Results among alternative tests are compared.