Hierarchical Bayesian nonparametric models for knowledge discovery from electronic medical records

Electronic Medical Record (EMR) has established itself as a valuable resource for large scale analysis of health data. A hospital EMR dataset typically consists of medical records of hospitalized patients. A medical record contains diagnostic information (diagnosis codes), procedures performed (procedure codes) and admission details. Traditional topic models, such as latent Dirichlet allocation (LDA) and hierarchical Dirichlet process (HDP), can be employed to discover disease topics from EMR data by treating patients as documents and diagnosis codes as words. This topic modeling helps to understand the constitution of patient diseases and offers a tool for better planning of treatment. In this paper, we propose a novel and flexible hierarchical Bayesian nonparametric model, the word distance dependent Chinese restaurant franchise (wddCRF), which incorporates word-to-word distances to discover semantically-coherent disease topics. We are motivated by the fact that diagnosis codes are connected in the form of ICD-10 tree structure which presents semantic relationships between codes. We exploit a decay function to incorporate distances between words at the bottom level of wddCRF. Efficient inference is derived for the wddCRF by using MCMC technique. Furthermore, since procedure codes are often correlated with diagnosis codes, we develop the correspondence wddCRF (Corr-wddCRF) to explore conditional relationships of procedure codes for a given disease pattern. Efficient collapsed Gibbs sampling is derived for the Corr-wddCRF. We evaluate the proposed models on two real-world medical datasets - PolyVascular disease and Acute Myocardial Infarction disease. We demonstrate that the Corr-wddCRF model discovers more coherent topics than the Corr-HDP. We also use disease topic proportions as new features and show that using features from the Corr-wddCRF outperforms the baselines on 14-days readmission prediction. Beside these, the prediction for procedure codes based on the Corr-wddCRF also shows considerable accuracy.

A Bayesian nonparametric model for Taguchi's on-line quality monitoring procedure for attributes

A Bayesian nonparametric model for Taguchi's on-line quality monitoring procedure for attributes is introduced. The proposed model may accommodate the original single shift setting to the more realistic situation of gradual quality deterioration and allows the incorporation of an expert's opinion on the production process. Based on the number of inspections to be carried out until a defective item is found, the Bayesian operation for the distribution function that represents the increasing sequence of defective fractions during a cycle considering a mixture of Dirichlet processes as prior distribution is performed. Bayes estimates for relevant quantities are also obtained. © 2012 Elsevier B.V.

A Bayesian nonparametric model for Taguchi's on-line quality monitoring procedure for attributes

A Bayesian nonparametric model for Taguchi's on-line quality monitoring procedure for attributes is introduced. The proposed model may accommodate the original single shift setting to the more realistic situation of gradual quality deterioration and allows the incorporation of an expert's opinion on the production process. Based on the number of inspections to be carried out until a defective item is found, the Bayesian operation for the distribution function that represents the increasing sequence of defective fractions during a cycle considering a mixture of Dirichlet processes as prior distribution is performed. Bayes estimates for relevant quantities are also obtained. (C) 2012 Elsevier B.V. All rights reserved.

Sensor Planning for Bayesian Nonparametric Target Modeling

Bayesian nonparametric models, such as the Gaussian process and the Dirichlet process, have been extensively applied for target kinematics modeling in various applications including environmental monitoring, traffic planning, endangered species tracking, dynamic scene analysis, autonomous robot navigation, and human motion modeling. As shown by these successful applications, Bayesian nonparametric models are able to adjust their complexities adaptively from data as necessary, and are resistant to overfitting or underfitting. However, most existing works assume that the sensor measurements used to learn the Bayesian nonparametric target kinematics models are obtained a priori or that the target kinematics can be measured by the sensor at any given time throughout the task. Little work has been done for controlling the sensor with bounded field of view to obtain measurements of mobile targets that are most informative for reducing the uncertainty of the Bayesian nonparametric models. To present the systematic sensor planning approach to leaning Bayesian nonparametric models, the Gaussian process target kinematics model is introduced at first, which is capable of describing time-invariant spatial phenomena, such as ocean currents, temperature distributions and wind velocity fields. The Dirichlet process-Gaussian process target kinematics model is subsequently discussed for modeling mixture of mobile targets, such as pedestrian motion patterns.

Novel information theoretic functions are developed for these introduced Bayesian nonparametric target kinematics models to represent the expected utility of measurements as a function of sensor control inputs and random environmental variables. A Gaussian process expected Kullback Leibler divergence is developed as the expectation of the KL divergence between the current (prior) and posterior Gaussian process target kinematics models with respect to the future measurements. Then, this approach is extended to develop a new information value function that can be used to estimate target kinematics described by a Dirichlet process-Gaussian process mixture model. A theorem is proposed that shows the novel information theoretic functions are bounded. Based on this theorem, efficient estimators of the new information theoretic functions are designed, which are proved to be unbiased with the variance of the resultant approximation error decreasing linearly as the number of samples increases. Computational complexities for optimizing the novel information theoretic functions under sensor dynamics constraints are studied, and are proved to be NP-hard. A cumulative lower bound is then proposed to reduce the computational complexity to polynomial time.

Three sensor planning algorithms are developed according to the assumptions on the target kinematics and the sensor dynamics. For problems where the control space of the sensor is discrete, a greedy algorithm is proposed. The efficiency of the greedy algorithm is demonstrated by a numerical experiment with data of ocean currents obtained by moored buoys. A sweep line algorithm is developed for applications where the sensor control space is continuous and unconstrained. Synthetic simulations as well as physical experiments with ground robots and a surveillance camera are conducted to evaluate the performance of the sweep line algorithm. Moreover, a lexicographic algorithm is designed based on the cumulative lower bound of the novel information theoretic functions, for the scenario where the sensor dynamics are constrained. Numerical experiments with real data collected from indoor pedestrians by a commercial pan-tilt camera are performed to examine the lexicographic algorithm. Results from both the numerical simulations and the physical experiments show that the three sensor planning algorithms proposed in this dissertation based on the novel information theoretic functions are superior at learning the target kinematics with

little or no prior knowledge

Bayesian nonparametric latent variable models

L’un des problèmes importants en apprentissage automatique est de déterminer la complexité du modèle à apprendre. Une trop grande complexité mène au surapprentissage, ce qui correspond à trouver des structures qui n’existent pas réellement dans les données, tandis qu’une trop faible complexité mène au sous-apprentissage, c’est-à-dire que l’expressivité du modèle est insuffisante pour capturer l’ensemble des structures présentes dans les données. Pour certains modèles probabilistes, la complexité du modèle se traduit par l’introduction d’une ou plusieurs variables cachées dont le rôle est d’expliquer le processus génératif des données. Il existe diverses approches permettant d’identifier le nombre approprié de variables cachées d’un modèle. Cette thèse s’intéresse aux méthodes Bayésiennes nonparamétriques permettant de déterminer le nombre de variables cachées à utiliser ainsi que leur dimensionnalité. La popularisation des statistiques Bayésiennes nonparamétriques au sein de la communauté de l’apprentissage automatique est assez récente. Leur principal attrait vient du fait qu’elles offrent des modèles hautement flexibles et dont la complexité s’ajuste proportionnellement à la quantité de données disponibles. Au cours des dernières années, la recherche sur les méthodes d’apprentissage Bayésiennes nonparamétriques a porté sur trois aspects principaux : la construction de nouveaux modèles, le développement d’algorithmes d’inférence et les applications. Cette thèse présente nos contributions à ces trois sujets de recherches dans le contexte d’apprentissage de modèles à variables cachées. Dans un premier temps, nous introduisons le Pitman-Yor process mixture of Gaussians, un modèle permettant l’apprentissage de mélanges infinis de Gaussiennes. Nous présentons aussi un algorithme d’inférence permettant de découvrir les composantes cachées du modèle que nous évaluons sur deux applications concrètes de robotique. Nos résultats démontrent que l’approche proposée surpasse en performance et en flexibilité les approches classiques d’apprentissage. Dans un deuxième temps, nous proposons l’extended cascading Indian buffet process, un modèle servant de distribution de probabilité a priori sur l’espace des graphes dirigés acycliques. Dans le contexte de réseaux Bayésien, ce prior permet d’identifier à la fois la présence de variables cachées et la structure du réseau parmi celles-ci. Un algorithme d’inférence Monte Carlo par chaîne de Markov est utilisé pour l’évaluation sur des problèmes d’identification de structures et d’estimation de densités. Dans un dernier temps, nous proposons le Indian chefs process, un modèle plus général que l’extended cascading Indian buffet process servant à l’apprentissage de graphes et d’ordres. L’avantage du nouveau modèle est qu’il admet les connections entres les variables observables et qu’il prend en compte l’ordre des variables. Nous présentons un algorithme d’inférence Monte Carlo par chaîne de Markov avec saut réversible permettant l’apprentissage conjoint de graphes et d’ordres. L’évaluation est faite sur des problèmes d’estimations de densité et de test d’indépendance. Ce modèle est le premier modèle Bayésien nonparamétrique permettant d’apprendre des réseaux Bayésiens disposant d’une structure complètement arbitraire.

Bayesian nonparametric learning of contexts and activities from pervasive signals

This thesis develops machine learning techniques to discover activities and contexts from pervasive sensor data. These techniques are especially suitable for streaming sensor data as they can infer the context space automatically. They are applicable in many real world applications such as activity monitoring or organization management.

Bayesian nonparametric multilevel modelling and applications

Our research aims at contributing to the multilevel modeling in data analytics. We address the task of multilevel clustering, multilevel regression, and classification. We provide state of the art solution for the critical problem.

Scalable nonparametric Bayesian multilevel clustering

Multilevel clustering problems where the con-tent and contextual information are jointly clustered are ubiquitous in modern datasets. Existing works on this problem are limited to small datasets due to the use of the Gibbs sampler. We address the problem of scaling up multi-level clustering under a Bayesian nonparametric setting, extending the MC2 model proposed in (Nguyen et al., 2014). We ground our approach in structured mean-field and stochastic variational inference (SVI) and develop a tree-structured SVI algorithm that exploits the interplay between content and context modeling. Our new algorithm avoids the need to repeatedly go through the corpus as in Gibbs sampler. More crucially, our method is immediately amendable to parallelization, facilitating a scalable distributed implementation on the Apache Spark platform. We conduct extensive experiments in a variety of domains including text, images, and real-world user application activities. Direct comparison with the Gibbs-sampler demonstrates that our method is an order-of-magnitude faster without loss of model quality. Our Spark-based implementation gains an-other order-of-magnitude speedup and can scale to large real-world datasets containing millions of documents and groups.

Nonparametric discovery of learning patterns and autism subgroups from therapeutic data

Autism Spectrum Disorder (ASD) is growing at a staggering rate, but, little is known about the cause of this condition. Inferring learning patterns from therapeutic performance data, and subsequently clustering ASD children into subgroups, is important to understand this domain, and more importantly to inform evidence-based intervention. However, this data-driven task was difficult in the past due to insufficiency of data to perform reliable analysis. For the first time, using data from a recent application for early intervention in autism (TOBY Play pad), whose download count is now exceeding 4500, we present in this paper the automatic discovery of learning patterns across 32 skills in sensory, imitation and language. We use unsupervised learning methods for this task, but a notorious problem with existing methods is the correct specification of number of patterns in advance, which in our case is even more difficult due to complexity of the data. To this end, we appeal to recent Bayesian nonparametric methods, in particular the use of Bayesian Nonparametric Factor Analysis. This model uses Indian Buffet Process (IBP) as prior on a binary matrix of infinite columns to allocate groups of intervention skills to children. The optimal number of learning patterns as well as subgroup assignments are inferred automatically from data. Our experimental results follow an exploratory approach, present different newly discovered learning patterns. To provide quantitative results, we also report the clustering evaluation against K-means and Nonnegative matrix factorization (NMF). In addition to the novelty of this new problem, we were able to demonstrate the suitability of Bayesian nonparametric models over parametric rivals.

Nonparametric discovery of movement patterns from accelerometer signals

Monitoring daily physical activity plays an important role in disease prevention and intervention. This paper proposes an approach to monitor the body movement intensity levels from accelerometer data. We collect the data using the accelerometer in a realistic setting without any supervision. The ground-truth of activities is provided by the participants themselves using an experience sampling application running on their mobile phones. We compute a novel feature that has a strong correlation with the movement intensity. We use the hierarchical Dirichlet process (HDP) model to detect the activity levels from this feature. Consisting of Bayesian nonparametric priors over the parameters the model can infer the number of levels automatically. By demonstrating the approach on the publicly available USC-HAD dataset that includes ground-truth activity labels, we show a strong correlation between the discovered activity levels and the movement intensity of the activities. This correlation is further confirmed using our newly collected dataset. We further use the extracted patterns as features for clustering and classifying the activity sequences to improve performance.

Bayesian Analysis of Linear Inverse Problems with Applications in Economics and Finance

In my PhD thesis I propose a Bayesian nonparametric estimation method for structural econometric models where the functional parameter of interest describes the economic agent's behavior. The structural parameter is characterized as the solution of a functional equation, or by using more technical words, as the solution of an inverse problem that can be either ill-posed or well-posed. From a Bayesian point of view, the parameter of interest is a random function and the solution to the inference problem is the posterior distribution of this parameter. A regular version of the posterior distribution in functional spaces is characterized. However, the infinite dimension of the considered spaces causes a problem of non continuity of the solution and then a problem of inconsistency, from a frequentist point of view, of the posterior distribution (i.e. problem of ill-posedness). The contribution of this essay is to propose new methods to deal with this problem of ill-posedness. The first one consists in adopting a Tikhonov regularization scheme in the construction of the posterior distribution so that I end up with a new object that I call regularized posterior distribution and that I guess it is solution of the inverse problem. The second approach consists in specifying a prior distribution on the parameter of interest of the g-prior type. Then, I detect a class of models for which the prior distribution is able to correct for the ill-posedness also in infinite dimensional problems. I study asymptotic properties of these proposed solutions and I prove that, under some regularity condition satisfied by the true value of the parameter of interest, they are consistent in a "frequentist" sense. Once I have set the general theory, I apply my bayesian nonparametric methodology to different estimation problems. First, I apply this estimator to deconvolution and to hazard rate, density and regression estimation. Then, I consider the estimation of an Instrumental Regression that is useful in micro-econometrics when we have to deal with problems of endogeneity. Finally, I develop an application in finance: I get the bayesian estimator for the equilibrium asset pricing functional by using the Euler equation defined in the Lucas'(1978) tree-type models.

Nonparametric discovery and analysis of learning patterns and autism subgroups from therapeutic data

The spectrum nature and heterogeneity within autism spectrum disorders (ASD) pose as a challenge for treatment. Personalisation of syllabus for children with ASD can improve the efficacy of learning by adjusting the number of opportunities and deciding the course of syllabus. We research the data-motivated approach in an attempt to disentangle this heterogeneity for personalisation of syllabus. With the help of technology and a structured syllabus, collecting data while a child with ASD masters the skills is made possible. The performance data collected are, however, growing and contain missing elements based on the pace and the course each child takes while navigating through the syllabus. Bayesian nonparametric methods are known for automatically discovering the number of latent components and their parameters when the model involves higher complexity. We propose a nonparametric Bayesian matrix factorisation model that discovers learning patterns and the way participants associate with them. Our model is built upon the linear Poisson gamma model (LPGM) with an Indian buffet process prior and extended to incorporate data with missing elements. In this paper, for the first time we have presented learning patterns deduced automatically from data mining and machine learning methods using intervention data recorded for over 500 children with ASD. We compare the results with non-negative matrix factorisation and K-means, which being parametric, not only require us to specify the number of learning patterns in advance, but also do not have a principle approach to deal with missing data. The F1 score observed over varying degree of similarity measure (Jaccard Index) suggests that LPGM yields the best outcome. By observing these patterns with additional knowledge regarding the syllabus it may be possible to observe the progress and dynamically modify the syllabus for improved learning.

Random function priors for exchangeable arrays with applications to graphs and relational data

A fundamental problem in the analysis of structured relational data like graphs, networks, databases, and matrices is to extract a summary of the common structure underlying relations between individual entities. Relational data are typically encoded in the form of arrays; invariance to the ordering of rows and columns corresponds to exchangeable arrays. Results in probability theory due to Aldous, Hoover and Kallenberg show that exchangeable arrays can be represented in terms of a random measurable function which constitutes the natural model parameter in a Bayesian model. We obtain a flexible yet simple Bayesian nonparametric model by placing a Gaussian process prior on the parameter function. Efficient inference utilises elliptical slice sampling combined with a random sparse approximation to the Gaussian process. We demonstrate applications of the model to network data and clarify its relation to models in the literature, several of which emerge as special cases.

Exploiting side information in distance dependent Chinese restaurant processes for data clustering

Multimedia contents often possess weakly annotated data such as tags, links and interactions. The weakly annotated data is called side information. It is the auxiliary information of data and provides hints for exploring the link structure of data. Most clustering algorithms utilize pure data for clustering. A model that combines pure data and side information, such as images and tags, documents and keywords, can perform better at understanding the underlying structure of data. We demonstrate how to incorporate different types of side information into a recently proposed Bayesian nonparametric model, the distance dependent Chinese restaurant process (DD-CRP). Our algorithm embeds the affinity of this information into the decay function of the DD-CRP when side information is in the form of subsets of discrete labels. It is flexible to measure distance based on arbitrary side information instead of only the spatial layout or time stamp of observations. At the same time, for noisy and incomplete side information, we set the decay function so that the DD-CRP reduces to the traditional Chinese restaurant process, thus not inducing side effects of noisy and incomplete side information. Experimental evaluations on two real-world datasets NUS WIDE and 20 Newsgroups show exploiting side information in DD-CRP significantly improves the clustering performance.

Extraction of latent patterns and contexts from social honest signals using hierarchical Dirichlet processes

A fundamental task in pervasive computing is reliable acquisition of contexts from sensor data. This is crucial to the operation of smart pervasive systems and services so that they might behave efficiently and appropriately upon a given context. Simple forms of context can often be extracted directly from raw data. Equally important, or more, is the hidden context and pattern buried inside the data, which is more challenging to discover. Most of existing approaches borrow methods and techniques from machine learning, dominantly employ parametric unsupervised learning and clustering techniques. Being parametric, a severe drawback of these methods is the requirement to specify the number of latent patterns in advance. In this paper, we explore the use of Bayesian nonparametric methods, a recent data modelling framework in machine learning, to infer latent patterns from sensor data acquired in a pervasive setting. Under this formalism, nonparametric prior distributions are used for data generative process, and thus, they allow the number of latent patterns to be learned automatically and grow with the data - as more data comes in, the model complexity can grow to explain new and unseen patterns. In particular, we make use of the hierarchical Dirichlet processes (HDP) to infer atomic activities and interaction patterns from honest signals collected from sociometric badges. We show how data from these sensors can be represented and learned with HDP. We illustrate insights into atomic patterns learned by the model and use them to achieve high-performance clustering. We also demonstrate the framework on the popular Reality Mining dataset, illustrating the ability of the model to automatically infer typical social groups in this dataset. Finally, our framework is generic and applicable to a much wider range of problems in pervasive computing where one needs to infer high-level, latent patterns and contexts from sensor data.