Knowledge discovery using multiple sources of biological data

The primary aim of this dissertation is to develop data mining tools for knowledge discovery in biomedical data when multiple (homogeneous or heterogeneous) sources of data are available. The central hypothesis is that, when information from multiple sources of data are used appropriately and effectively, knowledge discovery can be better achieved than what is possible from only a single source. ^ Recent advances in high-throughput technology have enabled biomedical researchers to generate large volumes of diverse types of data on a genome-wide scale. These data include DNA sequences, gene expression measurements, and much more; they provide the motivation for building analysis tools to elucidate the modular organization of the cell. The challenges include efficiently and accurately extracting information from the multiple data sources; representing the information effectively, developing analytical tools, and interpreting the results in the context of the domain. ^ The first part considers the application of feature-level integration to design classifiers that discriminate between soil types. The machine learning tools, SVM and KNN, were used to successfully distinguish between several soil samples. ^ The second part considers clustering using multiple heterogeneous data sources. The resulting Multi-Source Clustering (MSC) algorithm was shown to have a better performance than clustering methods that use only a single data source or a simple feature-level integration of heterogeneous data sources. ^ The third part proposes a new approach to effectively incorporate incomplete data into clustering analysis. Adapted from K-means algorithm, the Generalized Constrained Clustering (GCC) algorithm makes use of incomplete data in the form of constraints to perform exploratory analysis. Novel approaches for extracting constraints were proposed. For sufficiently large constraint sets, the GCC algorithm outperformed the MSC algorithm. ^ The last part considers the problem of providing a theme-specific environment for mining multi-source biomedical data. The database called PlasmoTFBM, focusing on gene regulation of Plasmodium falciparum, contains diverse information and has a simple interface to allow biologists to explore the data. It provided a framework for comparing different analytical tools for predicting regulatory elements and for designing useful data mining tools. ^ The conclusion is that the experiments reported in this dissertation strongly support the central hypothesis.^

Transforming Participation: A Case Study of an Introductory Physics Student in a Modeling Instruction Class

We present a case study on how participation of one student changed during her first semester of introductory physics class using Modeling Instruction. Using video recordings, we explore how her behavior is consistent with a change from thinking of group learning as a parallel activity to one that is collaborative.

Learning from Geometry

Subspaces and manifolds are two powerful models for high dimensional signals. Subspaces model linear correlation and are a good fit to signals generated by physical systems, such as frontal images of human faces and multiple sources impinging at an antenna array. Manifolds model sources that are not linearly correlated, but where signals are determined by a small number of parameters. Examples are images of human faces under different poses or expressions, and handwritten digits with varying styles. However, there will always be some degree of model mismatch between the subspace or manifold model and the true statistics of the source. This dissertation exploits subspace and manifold models as prior information in various signal processing and machine learning tasks.

A near-low-rank Gaussian mixture model measures proximity to a union of linear or affine subspaces. This simple model can effectively capture the signal distribution when each class is near a subspace. This dissertation studies how the pairwise geometry between these subspaces affects classification performance. When model mismatch is vanishingly small, the probability of misclassification is determined by the product of the sines of the principal angles between subspaces. When the model mismatch is more significant, the probability of misclassification is determined by the sum of the squares of the sines of the principal angles. Reliability of classification is derived in terms of the distribution of signal energy across principal vectors. Larger principal angles lead to smaller classification error, motivating a linear transform that optimizes principal angles. This linear transformation, termed TRAIT, also preserves some specific features in each class, being complementary to a recently developed Low Rank Transform (LRT). Moreover, when the model mismatch is more significant, TRAIT shows superior performance compared to LRT.

The manifold model enforces a constraint on the freedom of data variation. Learning features that are robust to data variation is very important, especially when the size of the training set is small. A learning machine with large numbers of parameters, e.g., deep neural network, can well describe a very complicated data distribution. However, it is also more likely to be sensitive to small perturbations of the data, and to suffer from suffer from degraded performance when generalizing to unseen (test) data.

From the perspective of complexity of function classes, such a learning machine has a huge capacity (complexity), which tends to overfit. The manifold model provides us with a way of regularizing the learning machine, so as to reduce the generalization error, therefore mitigate overfiting. Two different overfiting-preventing approaches are proposed, one from the perspective of data variation, the other from capacity/complexity control. In the first approach, the learning machine is encouraged to make decisions that vary smoothly for data points in local neighborhoods on the manifold. In the second approach, a graph adjacency matrix is derived for the manifold, and the learned features are encouraged to be aligned with the principal components of this adjacency matrix. Experimental results on benchmark datasets are demonstrated, showing an obvious advantage of the proposed approaches when the training set is small.

Stochastic optimization makes it possible to track a slowly varying subspace underlying streaming data. By approximating local neighborhoods using affine subspaces, a slowly varying manifold can be efficiently tracked as well, even with corrupted and noisy data. The more the local neighborhoods, the better the approximation, but the higher the computational complexity. A multiscale approximation scheme is proposed, where the local approximating subspaces are organized in a tree structure. Splitting and merging of the tree nodes then allows efficient control of the number of neighbourhoods. Deviation (of each datum) from the learned model is estimated, yielding a series of statistics for anomaly detection. This framework extends the classical {\em changepoint detection} technique, which only works for one dimensional signals. Simulations and experiments highlight the robustness and efficacy of the proposed approach in detecting an abrupt change in an otherwise slowly varying low-dimensional manifold.

Bayesian Learning with Dependency Structures via Latent Factors, Mixtures, and Copulas

Bayesian methods offer a flexible and convenient probabilistic learning framework to extract interpretable knowledge from complex and structured data. Such methods can characterize dependencies among multiple levels of hidden variables and share statistical strength across heterogeneous sources. In the first part of this dissertation, we develop two dependent variational inference methods for full posterior approximation in non-conjugate Bayesian models through hierarchical mixture- and copula-based variational proposals, respectively. The proposed methods move beyond the widely used factorized approximation to the posterior and provide generic applicability to a broad class of probabilistic models with minimal model-specific derivations. In the second part of this dissertation, we design probabilistic graphical models to accommodate multimodal data, describe dynamical behaviors and account for task heterogeneity. In particular, the sparse latent factor model is able to reveal common low-dimensional structures from high-dimensional data. We demonstrate the effectiveness of the proposed statistical learning methods on both synthetic and real-world data.

Occupant location prediction in smart buildings using association rule mining

Heating, ventilation, air conditioning (HVAC) systems are significant consumers of energy, however building management systems do not typically operate them in accordance with occupant movements. Due to the delayed response of HVAC systems, prediction of occupant locations is necessary to maximize energy efficiency. We present an approach to occupant location prediction based on association rule mining, allowing prediction based on historical occupant locations. Association rule mining is a machine learning technique designed to find any correlations which exist in a given dataset. Occupant location datasets have a number of properties which differentiate them from the market basket datasets that association rule mining was originally designed for. This thesis adapts the approach to suit such datasets, focusing the rule mining process on patterns which are useful for location prediction. This approach, named OccApriori, allows for the prediction of occupants’ next locations as well as their locations further in the future, and can take into account any available data, for example the day of the week, the recent movements of the occupant, and timetable data. By integrating an existing extension of association rule mining into the approach, it is able to make predictions based on general classes of locations as well as specific locations.

Computational Methods for Identifying Hypertrophic Cardiomyopathy using 12-lead ECG

Hypertrophic cardiomyopathy (HCM) is a cardiovascular disease where the heart muscle is partially thickened and blood flow is - potentially fatally - obstructed. It is one of the leading causes of sudden cardiac death in young people. Electrocardiography (ECG) and Echocardiography (Echo) are the standard tests for identifying HCM and other cardiac abnormalities. The American Heart Association has recommended using a pre-participation questionnaire for young athletes instead of ECG or Echo tests due to considerations of cost and time involved in interpreting the results of these tests by an expert cardiologist. Initially we set out to develop a classifier for automated prediction of young athletes’ heart conditions based on the answers to the questionnaire. Classification results and further in-depth analysis using computational and statistical methods indicated significant shortcomings of the questionnaire in predicting cardiac abnormalities. Automated methods for analyzing ECG signals can help reduce cost and save time in the pre-participation screening process by detecting HCM and other cardiac abnormalities. Therefore, the main goal of this dissertation work is to identify HCM through computational analysis of 12-lead ECG. ECG signals recorded on one or two leads have been analyzed in the past for classifying individual heartbeats into different types of arrhythmia as annotated primarily in the MIT-BIH database. In contrast, we classify complete sequences of 12-lead ECGs to assign patients into two groups: HCM vs. non-HCM. The challenges and issues we address include missing ECG waves in one or more leads and the dimensionality of a large feature-set. We address these by proposing imputation and feature-selection methods. We develop heartbeat-classifiers by employing Random Forests and Support Vector Machines, and propose a method to classify full 12-lead ECGs based on the proportion of heartbeats classified as HCM. The results from our experiments show that the classifiers developed using our methods perform well in identifying HCM. Thus the two contributions of this thesis are the utilization of computational and statistical methods for discovering shortcomings in a current screening procedure and the development of methods to identify HCM through computational analysis of 12-lead ECG signals.

Learning to Interpret and Generate Instructional Recipes

Thesis (Ph.D.)--University of Washington, 2016-08

A review of Parkinson’s disease cardinal and dyskinetic motor symptoms assessment methods using sensor systems

This paper is reviewing objective assessments of Parkinson’s disease(PD) motor symptoms, cardinal, and dyskinesia, using sensor systems. It surveys the manifestation of PD symptoms, sensors that were used for their detection, types of signals (measures) as well as their signal processing (data analysis) methods. A summary of this review’s finding is represented in a table including devices (sensors), measures and methods that were used in each reviewed motor symptom assessment study. In the gathered studies among sensors, accelerometers and touch screen devices are the most widely used to detect PD symptoms and among symptoms, bradykinesia and tremor were found to be mostly evaluated. In general, machine learning methods are potentially promising for this. PD is a complex disease that requires continuous monitoring and multidimensional symptom analysis. Combining existing technologies to develop new sensor platforms may assist in assessing the overall symptom profile more accurately to develop useful tools towards supporting better treatment process.

Convex Optimization Algorithms and Statistical Bounds for Learning Structured Models

Thesis (Ph.D.)--University of Washington, 2016-08

IoT Based Pain Management using Physiological Parameters

The continuous technology evaluation is benefiting our lives to a great extent. The evolution of Internet of things and deployment of wireless sensor networks is making it possible to have more connectivity between people and devices used extensively in our daily lives. Almost every discipline of daily life including health sector, transportation, agriculture etc. is benefiting from these technologies. There is a great potential of research and refinement of health sector as the current system is very often dependent on manual evaluations conducted by the clinicians. There is no automatic system for patient health monitoring and assessment which results to incomplete and less reliable heath information. Internet of things has a great potential to benefit health care applications by automated and remote assessment, monitoring and identification of diseases. Acute pain is the main cause of people visiting to hospitals. An automatic pain detection system based on internet of things with wireless devices can make the assessment and redemption significantly more efficient. The contribution of this research work is proposing pain assessment method based on physiological parameters. The physiological parameters chosen for this study are heart rate, electrocardiography, breathing rate and galvanic skin response. As a first step, the relation between these physiological parameters and acute pain experienced by the test persons is evaluated. The electrocardiography data collected from the test persons is analyzed to extract interbeat intervals. This evaluation clearly demonstrates specific patterns and trends in these parameters as a consequence of pain. This parametric behavior is then used to assess and identify the pain intensity by implementing machine learning algorithms. Support vector machines are used for classifying these parameters influenced by different pain intensities and classification results are achieved. The classification results with good accuracy rates between two and three levels of pain intensities shows clear indication of pain and the feasibility of this pain assessment method. An improved approach on the basis of this research work can be implemented by using both physiological parameters and electromyography data of facial muscles for classification.

Techniques for batch reinforcement learning in robotics

This thesis addresses the Batch Reinforcement Learning methods in Robotics. This sub-class of Reinforcement Learning has shown promising results and has been the focus of recent research. Three contributions are proposed that aim to extend the state-of-art methods allowing for a faster and more stable learning process, such as required for learning in Robotics. The Q-learning update-rule is widely applied, since it allows to learn without the presence of a model of the environment. However, this update-rule is transition-based and does not take advantage of the underlying episodic structure of collected batch of interactions. The Q-Batch update-rule is proposed in this thesis, to process experiencies along the trajectories collected in the interaction phase. This allows a faster propagation of obtained rewards and penalties, resulting in faster and more robust learning. Non-parametric function approximations are explored, such as Gaussian Processes. This type of approximators allows to encode prior knowledge about the latent function, in the form of kernels, providing a higher level of exibility and accuracy. The application of Gaussian Processes in Batch Reinforcement Learning presented a higher performance in learning tasks than other function approximations used in the literature. Lastly, in order to extract more information from the experiences collected by the agent, model-learning techniques are incorporated to learn the system dynamics. In this way, it is possible to augment the set of collected experiences with experiences generated through planning using the learned models. Experiments were carried out mainly in simulation, with some tests carried out in a physical robotic platform. The obtained results show that the proposed approaches are able to outperform the classical Fitted Q Iteration.

Towards Proactive Context-aware Computing and Systems

A primary goal of context-aware systems is delivering the right information at the right place and right time to users in order to enable them to make effective decisions and improve their quality of life. There are three key requirements for achieving this goal: determining what information is relevant, personalizing it based on the users’ context (location, preferences, behavioral history etc.), and delivering it to them in a timely manner without an explicit request from them. These requirements create a paradigm that we term as “Proactive Context-aware Computing”. Most of the existing context-aware systems fulfill only a subset of these requirements. Many of these systems focus only on personalization of the requested information based on users’ current context. Moreover, they are often designed for specific domains. In addition, most of the existing systems are reactive - the users request for some information and the system delivers it to them. These systems are not proactive i.e. they cannot anticipate users’ intent and behavior and act proactively without an explicit request from them. In order to overcome these limitations, we need to conduct a deeper analysis and enhance our understanding of context-aware systems that are generic, universal, proactive and applicable to a wide variety of domains. To support this dissertation, we explore several directions. Clearly the most significant sources of information about users today are smartphones. A large amount of users’ context can be acquired through them and they can be used as an effective means to deliver information to users. In addition, social media such as Facebook, Flickr and Foursquare provide a rich and powerful platform to mine users’ interests, preferences and behavioral history. We employ the ubiquity of smartphones and the wealth of information available from social media to address the challenge of building proactive context-aware systems. We have implemented and evaluated a few approaches, including some as part of the Rover framework, to achieve the paradigm of Proactive Context-aware Computing. Rover is a context-aware research platform which has been evolving for the last 6 years. Since location is one of the most important context for users, we have developed ‘Locus’, an indoor localization, tracking and navigation system for multi-story buildings. Other important dimensions of users’ context include the activities that they are engaged in. To this end, we have developed ‘SenseMe’, a system that leverages the smartphone and its multiple sensors in order to perform multidimensional context and activity recognition for users. As part of the ‘SenseMe’ project, we also conducted an exploratory study of privacy, trust, risks and other concerns of users with smart phone based personal sensing systems and applications. To determine what information would be relevant to users’ situations, we have developed ‘TellMe’ - a system that employs a new, flexible and scalable approach based on Natural Language Processing techniques to perform bootstrapped discovery and ranking of relevant information in context-aware systems. In order to personalize the relevant information, we have also developed an algorithm and system for mining a broad range of users’ preferences from their social network profiles and activities. For recommending new information to the users based on their past behavior and context history (such as visited locations, activities and time), we have developed a recommender system and approach for performing multi-dimensional collaborative recommendations using tensor factorization. For timely delivery of personalized and relevant information, it is essential to anticipate and predict users’ behavior. To this end, we have developed a unified infrastructure, within the Rover framework, and implemented several novel approaches and algorithms that employ various contextual features and state of the art machine learning techniques for building diverse behavioral models of users. Examples of generated models include classifying users’ semantic places and mobility states, predicting their availability for accepting calls on smartphones and inferring their device charging behavior. Finally, to enable proactivity in context-aware systems, we have also developed a planning framework based on HTN planning. Together, these works provide a major push in the direction of proactive context-aware computing.

Microblogging Temporal Summarization: Filtering Important Twitter Updates for Breaking News

While news stories are an important traditional medium to broadcast and consume news, microblogging has recently emerged as a place where people can dis- cuss, disseminate, collect or report information about news. However, the massive information in the microblogosphere makes it hard for readers to keep up with these real-time updates. This is especially a problem when it comes to breaking news, where people are more eager to know “what is happening”. Therefore, this dis- sertation is intended as an exploratory effort to investigate computational methods to augment human effort when monitoring the development of breaking news on a given topic from a microblog stream by extractively summarizing the updates in a timely manner. More specifically, given an interest in a topic, either entered as a query or presented as an initial news report, a microblog temporal summarization system is proposed to filter microblog posts from a stream with three primary concerns: topical relevance, novelty, and salience. Considering the relatively high arrival rate of microblog streams, a cascade framework consisting of three stages is proposed to progressively reduce quantity of posts. For each step in the cascade, this dissertation studies methods that improve over current baselines. In the relevance filtering stage, query and document expansion techniques are applied to mitigate sparsity and vocabulary mismatch issues. The use of word embedding as a basis for filtering is also explored, using unsupervised and supervised modeling to characterize lexical and semantic similarity. In the novelty filtering stage, several statistical ways of characterizing novelty are investigated and ensemble learning techniques are used to integrate results from these diverse techniques. These results are compared with a baseline clustering approach using both standard and delay-discounted measures. In the salience filtering stage, because of the real-time prediction requirement a method of learning verb phrase usage from past relevant news reports is used in conjunction with some standard measures for characterizing writing quality. Following a Cranfield-like evaluation paradigm, this dissertation includes a se- ries of experiments to evaluate the proposed methods for each step, and for the end- to-end system. New microblog novelty and salience judgments are created, building on existing relevance judgments from the TREC Microblog track. The results point to future research directions at the intersection of social media, computational jour- nalism, information retrieval, automatic summarization, and machine learning.

Requirement Risk Level Forecast Using Bayesian Networks Classifiers

Requirement engineering is a key issue in the development of a software project. Like any other development activity it is not without risks. This work is about the empirical study of risks of requirements by applying machine learning techniques, specifically Bayesian networks classifiers. We have defined several models to predict the risk level for a given requirement using three dataset that collect metrics taken from the requirement specifications of different projects. The classification accuracy of the Bayesian models obtained is evaluated and compared using several classification performance measures. The results of the experiments show that the Bayesians networks allow obtaining valid predictors. Specifically, a tree augmented network structure shows a competitive experimental performance in all datasets. Besides, the relations established between the variables collected to determine the level of risk in a requirement, match with those set by requirement engineers. We show that Bayesian networks are valid tools for the automation of risks assessment in requirement engineering.

EXAMINING THE IMPACT OF TEACHER PRACTICE ON STUDENT LEARNING IN INTERACTIVE RADIO INSTRUCTION (IRI) CLASSROOMS: LESSONS FROM NEW DELHI AND RAJASTHAN (INDIA)

This quantitative study examines the impact of teacher practices on student achievement in classrooms where the English is Fun Interactive Radio Instruction (IRI) programs were being used. A contemporary IRI design using a dual-audience approach, the English is Fun IRI programs delivered daily English language instruction to students in grades 1 and 2 in Delhi and Rajasthan through 120 30-minute programs via broadcast radio (the first audience) while modeling pedagogical techniques and behaviors for their teachers (the second audience). Few studies have examined how the dual-audience approach influences student learning. Using existing data from 32 teachers and 696 students, this study utilizes a multivariate multilevel model to examine the role of the primary expectations for teachers (e.g., setting up the IRI classroom, following instructions from the radio characters and ensuring students are participating) and the role of secondary expectations for teachers (e.g., modeling pedagogies and facilitating learning beyond the instructions) in promoting students’ learning in English listening skills, knowledge of vocabulary and use of sentences. The study finds that teacher practice on both sets of expectations mattered, but that practice in the secondary expectations mattered more. As expected, students made the smallest gains in the most difficult linguistic task (sentence use). The extent to which teachers satisfied the primary and secondary expectations was associated with gains in all three skills – confirming the relationship between students’ English proficiency and teacher practice in a dual-audience program. When it came to gains in students’ scores in sentence use, a teacher whose focus was greater on primary expectations had a negative effect on student performance in both states. In all, teacher practice clearly mattered but not in the same way for all three skills. An optimal scenario for teacher practice is presented in which gains in all three skills are maximized. These findings have important implications for the way the classroom teacher is cast in IRI programs that utilize a dual-audience approach and in the way IRI programs are contracted insofar as the role of the teacher in instruction is minimized and access is limited to instructional support from the IRI lessons alone.