Performance tiers: Implementing comparative effectiveness analysis in the health care setting through operations research and spatial methods

This dissertation develops and tests a comparative effectiveness methodology utilizing a novel approach to the application of Data Envelopment Analysis (DEA) in health studies. The concept of performance tiers (PerT) is introduced as terminology to express a relative risk class for individuals within a peer group and the PerT calculation is implemented with operations research (DEA) and spatial algorithms. The analysis results in the discrimination of the individual data observations into a relative risk classification by the DEA-PerT methodology. The performance of two distance measures, kNN (k-nearest neighbor) and Mahalanobis, was subsequently tested to classify new entrants into the appropriate tier. The methods were applied to subject data for the 14 year old cohort in the Project HeartBeat! study.^ The concepts presented herein represent a paradigm shift in the potential for public health applications to identify and respond to individual health status. The resultant classification scheme provides descriptive, and potentially prescriptive, guidance to assess and implement treatments and strategies to improve the delivery and performance of health systems. ^

Generación automática de reglas de categorización de texto en un método híbrido basado en aprendizaje

En este artículo se evalúan diferentes técnicas para la generación automática de reglas que se emplean en un método híbrido de categorización automática de texto. Este método combina un algoritmo de aprendizaje computacional con diferentes sistemas basados en reglas en cascada empleados para el filtrado y reordenación de los resultados proporcionados por dicho modelo base. Aquí se describe una implementación realizada mediante el algoritmo kNN y un lenguaje básico de reglas basado en listas de términos que aparecen en el texto a clasificar. Para la evaluación se utiliza el corpus de noticias Reuters-21578. Los resultados demuestran que los métodos de generación de reglas propuestos producen resultados muy próximos a los obtenidos con la aplicación de reglas generadas manualmente y que el sistema híbrido propuesto obtiene una precisión y cobertura comparables a la de los mejores métodos del estado del arte.

Método híbrido para categorización de texto basado en aprendizaje y reglas

En este artículo se presenta un nuevo método híbrido de categorización automática de texto, que combina un algoritmo de aprendizaje computacional, que permite construir un modelo base de clasificación sin mucho esfuerzo a partir de un corpus etiquetado, con un sistema basado en reglas en cascada que se emplea para filtrar y reordenar los resultados de dicho modelo base. El modelo puede afinarse añadiendo reglas específicas para aquellas categorías difíciles que no se han entrenado de forma satisfactoria. Se describe una implementación realizada mediante el algoritmo kNN y un lenguaje básico de reglas basado en listas de términos que aparecen en el texto a clasificar. El sistema se ha evaluado en diferentes escenarios incluyendo el corpus de noticias Reuters-21578 para comparación con otros enfoques, y los modelos IPTC y EUROVOC. Los resultados demuestran que el sistema obtiene una precisión y cobertura comparables con las de los mejores métodos del estado del arte.

Codificador de voz MIDI

El presente proyecto tiene el objetivo de facilitar la composición de canciones mediante la creación de las distintas pistas MIDI que la forman. Se implementan dos controladores. El primero, con objeto de transcribir la parte melódica, convierte la voz cantada o tarareada a eventos MIDI. Para ello, y tras el estudio de las distintas técnicas del cálculo del tono (pitch), se implementará una técnica con ciertas variaciones basada en la autocorrelación. También se profundiza en el segmentado de eventos, en particular, una técnica basada en el análisis de la derivada de la envolvente. El segundo, dedicado a la base rítmica de la canción, permite la creación de la percusión mediante el golpe rítmico de objetos que disponga el usuario, que serán asignados a los distintos elementos de percusión elegidos. Los resultados de la grabación de estos impactos serán señales de corta duración, no lineales y no armónicas, dificultando su discriminación. La herramienta elegida para la clasificación de los distintos patrones serán las redes neuronales artificiales (RNA). Se realizara un estudio de la metodología de diseño de redes neuronales especifico para este tipo de señales, evaluando la importancia de las variables de diseño como son el número de capas ocultas y neuronas en cada una de ellas, algoritmo de entrenamiento y funciones de activación. El estudio concluirá con la implementación de dos redes de diferente naturaleza. Una red de Elman, cuyas propiedades de memoria permiten la clasificación de patrones temporales, procesará las cualidades temporales analizando el ataque de su forma de onda. Una red de propagación hacia adelante feed-forward, que necesitará de robustas características espectrales y temporales para su clasificación. Se proponen 26 descriptores como los derivados de los momentos del espectro: centroide, curtosis y simetría, los coeficientes cepstrales de la escala de Mel (MFCCs), y algunos temporales como son la tasa de cruces por cero y el centroide de la envolvente temporal. Las capacidades de discriminación inter e intra clase de estas características serán evaluadas mediante un algoritmo de selección, habiéndose elegido RELIEF, un método basado en el algoritmo de los k vecinos mas próximos (KNN). Ambos controladores tendrán función de trabajar en tiempo real y offline, permitiendo tanto la composición de canciones, como su utilización como un instrumento más junto con mas músicos. ABSTRACT. The aim of this project is to make song composition easier by creating each MIDI track that builds it. Two controllers are implemented. In order to transcribe the melody, the first controler converts singing voice or humming into MIDI files. To do this a technique based on autocorrelation is implemented after having studied different pitch detection methods. Event segmentation has also been dealt with, to be more precise a technique based on the analysis of the signal's envelope and it's derivative have been used. The second one, can be used to make the song's rhythm . It allows the user, to create percussive patterns by hitting different objects of his environment. These recordings results in short duration, non-linear and non-harmonic signals. Which makes the classification process more complicated in the traditional way. The tools to used are the artificial neural networks (ANN). We will study the neural network design to deal with this kind of signals. The goal is to get a design methodology, paying attention to the variables involved, as the number of hidden layers and neurons in each, transfer functions and training algorithm. The study will end implementing two neural networks with different nature. Elman network, which has memory properties, is capable to recognize sequences of data and analyse the impact's waveform, precisely, the attack portion. A feed-forward network, needs strong spectral and temporal features extracted from the hit. Some descriptors are proposed as the derivates from the spectrum moment as centroid, kurtosis and skewness, the Mel-frequency cepstral coefficients, and some temporal features as the zero crossing rate (zcr) and the temporal envelope's centroid. Intra and inter class discrimination abilities of those descriptors will be weighted using the selection algorithm RELIEF, a Knn (K-nearest neighbor) based algorithm. Both MIDI controllers can be used to compose, or play with other musicians as it works on real-time and offline.

Hierarchical indexing structure for efficient similarity search in video retrieval

With the rapid increase in both centralized video archives and distributed WWW video resources, content-based video retrieval is gaining its importance. To support such applications efficiently, content-based video indexing must be addressed. Typically, each video is represented by a sequence of frames. Due to the high dimensionality of frame representation and the large number of frames, video indexing introduces an additional degree of complexity. In this paper, we address the problem of content-based video indexing and propose an efficient solution, called the Ordered VA-File (OVA-File) based on the VA-file. OVA-File is a hierarchical structure and has two novel features: 1) partitioning the whole file into slices such that only a small number of slices are accessed and checked during k Nearest Neighbor (kNN) search and 2) efficient handling of insertions of new vectors into the OVA-File, such that the average distance between the new vectors and those approximations near that position is minimized. To facilitate a search, we present an efficient approximate kNN algorithm named Ordered VA-LOW (OVA-LOW) based on the proposed OVA-File. OVA-LOW first chooses possible OVA-Slices by ranking the distances between their corresponding centers and the query vector, and then visits all approximations in the selected OVA-Slices to work out approximate kNN. The number of possible OVA-Slices is controlled by a user-defined parameter delta. By adjusting delta, OVA-LOW provides a trade-off between the query cost and the result quality. Query by video clip consisting of multiple frames is also discussed. Extensive experimental studies using real video data sets were conducted and the results showed that our methods can yield a significant speed-up over an existing VA-file-based method and iDistance with high query result quality. Furthermore, by incorporating temporal correlation of video content, our methods achieved much more efficient performance.

Toward efficient multifeature query processing

In many advanced applications, data are described by multiple high-dimensional features. Moreover, different queries may weight these features differently; some may not even specify all the features. In this paper, we propose our solution to support efficient query processing in these applications. We devise a novel representation that compactly captures f features into two components: The first component is a 2D vector that reflects a distance range ( minimum and maximum values) of the f features with respect to a reference point ( the center of the space) in a metric space and the second component is a bit signature, with two bits per dimension, obtained by analyzing each feature's descending energy histogram. This representation enables two levels of filtering: The first component prunes away points that do not share similar distance ranges, while the bit signature filters away points based on the dimensions of the relevant features. Moreover, the representation facilitates the use of a single index structure to further speed up processing. We employ the classical B+-tree for this purpose. We also propose a KNN search algorithm that exploits the access orders of critical dimensions of highly selective features and partial distances to prune the search space more effectively. Our extensive experiments on both real-life and synthetic data sets show that the proposed solution offers significant performance advantages over sequential scan and retrieval methods using single and multiple VA-files.

Exploring composite acoustic features for efficient music similarity query

Music similarity query based on acoustic content is becoming important with the ever-increasing growth of the music information from emerging applications such as digital libraries and WWW. However, relative techniques are still in their infancy and much less than satisfactory. In this paper, we present a novel index structure, called Composite Feature tree, CF-tree, to facilitate efficient content-based music search adopting multiple musical features. Before constructing the tree structure, we use PCA to transform the extracted features into a new space sorted by the importance of acoustic features. The CF-tree is a balanced multi-way tree structure where each level represents the data space at different dimensionalities. The PCA transformed data and reduced dimensions in the upper levels can alleviate suffering from dimensionality curse. To accurately mimic human perception, an extension, named CF+-tree, is proposed, which further applies multivariable regression to determine the weight of each individual feature. We conduct extensive experiments to evaluate the proposed structures against state-of-art techniques. The experimental results demonstrate superiority of our technique.

Experiments with two Approaches for Tracking Drifting Concepts

This paper addresses the task of learning classifiers from streams of labelled data. In this case we can face the problem that the underlying concepts can change over time. The paper studies two mechanisms developed for dealing with changing concepts. Both are based on the time window idea. The first one forgets gradually, by assigning to the examples weight that gradually decreases over time. The second one uses a statistical test to detect changes in concept and then optimizes the size of the time window, aiming to maximise the classification accuracy on the new examples. Both methods are general in nature and can be used with any learning algorithm. The objectives of the conducted experiments were to compare the mechanisms and explore whether they can be combined to achieve a synergetic e ect. Results from experiments with three basic learning algorithms (kNN, ID3 and NBC) using four datasets are reported and discussed.

AllerTOP v.2 - a server for in silico prediction of allergens

Allergy is an overreaction by the immune system to a previously encountered, ordinarily harmless substance - typically proteins - resulting in skin rash, swelling of mucous membranes, sneezing or wheezing, or other abnormal conditions. The use of modified proteins is increasingly widespread: their presence in food, commercial products, such as washing powder, and medical therapeutics and diagnostics, makes predicting and identifying potential allergens a crucial societal issue. The prediction of allergens has been explored widely using bioinformatics, with many tools being developed in the last decade; many of these are freely available online. Here, we report a set of novel models for allergen prediction utilizing amino acid E-descriptors, auto- and cross-covariance transformation, and several machine learning methods for classification, including logistic regression (LR), decision tree (DT), naïve Bayes (NB), random forest (RF), multilayer perceptron (MLP) and k nearest neighbours (kNN). The best performing method was kNN with 85.3% accuracy at 5-fold cross-validation. The resulting model has been implemented in a revised version of the AllerTOP server (http://www.ddg-pharmfac.net/AllerTOP). © Springer-Verlag 2014.

AllerTOP - a server for in silico prediction of allergens

Background: Allergy is a form of hypersensitivity to normally innocuous substances, such as dust, pollen, foods or drugs. Allergens are small antigens that commonly provoke an IgE antibody response. There are two types of bioinformatics-based allergen prediction. The first approach follows FAO/WHO Codex alimentarius guidelines and searches for sequence similarity. The second approach is based on identifying conserved allergenicity-related linear motifs. Both approaches assume that allergenicity is a linearly coded property. In the present study, we applied ACC pre-processing to sets of known allergens, developing alignment-independent models for allergen recognition based on the main chemical properties of amino acid sequences.Results: A set of 684 food, 1,156 inhalant and 555 toxin allergens was collected from several databases. A set of non-allergens from the same species were selected to mirror the allergen set. The amino acids in the protein sequences were described by three z-descriptors (z1, z2 and z3) and by auto- and cross-covariance (ACC) transformation were converted into uniform vectors. Each protein was presented as a vector of 45 variables. Five machine learning methods for classification were applied in the study to derive models for allergen prediction. The methods were: discriminant analysis by partial least squares (DA-PLS), logistic regression (LR), decision tree (DT), naïve Bayes (NB) and k nearest neighbours (kNN). The best performing model was derived by kNN at k = 3. It was optimized, cross-validated and implemented in a server named AllerTOP, freely accessible at http://www.pharmfac.net/allertop. AllerTOP also predicts the most probable route of exposure. In comparison to other servers for allergen prediction, AllerTOP outperforms them with 94% sensitivity.Conclusions: AllerTOP is the first alignment-free server for in silico prediction of allergens based on the main physicochemical properties of proteins. Significantly, as well allergenicity AllerTOP is able to predict the route of allergen exposure: food, inhalant or toxin. © 2013 Dimitrov et al.; licensee BioMed Central Ltd.

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.^

Statistical analysis and meta-analysis of microarray data

The microarray technology provides a high-throughput technique to study gene expression. Microarrays can help us diagnose different types of cancers, understand biological processes, assess host responses to drugs and pathogens, find markers for specific diseases, and much more. Microarray experiments generate large amounts of data. Thus, effective data processing and analysis are critical for making reliable inferences from the data. ^ The first part of dissertation addresses the problem of finding an optimal set of genes (biomarkers) to classify a set of samples as diseased or normal. Three statistical gene selection methods (GS, GS-NR, and GS-PCA) were developed to identify a set of genes that best differentiate between samples. A comparative study on different classification tools was performed and the best combinations of gene selection and classifiers for multi-class cancer classification were identified. For most of the benchmarking cancer data sets, the gene selection method proposed in this dissertation, GS, outperformed other gene selection methods. The classifiers based on Random Forests, neural network ensembles, and K-nearest neighbor (KNN) showed consistently god performance. A striking commonality among these classifiers is that they all use a committee-based approach, suggesting that ensemble classification methods are superior. ^ The same biological problem may be studied at different research labs and/or performed using different lab protocols or samples. In such situations, it is important to combine results from these efforts. The second part of the dissertation addresses the problem of pooling the results from different independent experiments to obtain improved results. Four statistical pooling techniques (Fisher inverse chi-square method, Logit method. Stouffer's Z transform method, and Liptak-Stouffer weighted Z-method) were investigated in this dissertation. These pooling techniques were applied to the problem of identifying cell cycle-regulated genes in two different yeast species. As a result, improved sets of cell cycle-regulated genes were identified. The last part of dissertation explores the effectiveness of wavelet data transforms for the task of clustering. Discrete wavelet transforms, with an appropriate choice of wavelet bases, were shown to be effective in producing clusters that were biologically more meaningful. ^

Quality of experience evaluation of voice communication: an affect-based approach

Voice communication systems such as Voice-over IP (VoIP), Public Switched Telephone Networks, and Mobile Telephone Networks, are an integral means of human tele-interaction. These systems pose distinctive challenges due to their unique characteristics such as low volume, burstiness and stringent delay/loss requirements across heterogeneous underlying network technologies. Effective quality evaluation methodologies are important for system development and refinement, particularly by adopting user feedback based measurement. Presently, most of the evaluation models are system-centric (Quality of Service or QoS-based), which questioned us to explore a user-centric (Quality of Experience or QoE-based) approach as a step towards the human-centric paradigm of system design. We research an affect-based QoE evaluation framework which attempts to capture users' perception while they are engaged in voice communication. Our modular approach consists of feature extraction from multiple information sources including various affective cues and different classification procedures such as Support Vector Machines (SVM) and k-Nearest Neighbor (kNN). The experimental study is illustrated in depth with detailed analysis of results. The evidences collected provide the potential feasibility of our approach for QoE evaluation and suggest the consideration of human affective attributes in modeling user experience.

Event mining for system and service management

Modern IT infrastructures are constructed by large scale computing systems and administered by IT service providers. Manually maintaining such large computing systems is costly and inefficient. Service providers often seek automatic or semi-automatic methodologies of detecting and resolving system issues to improve their service quality and efficiency. This dissertation investigates several data-driven approaches for assisting service providers in achieving this goal. The detailed problems studied by these approaches can be categorized into the three aspects in the service workflow: 1) preprocessing raw textual system logs to structural events; 2) refining monitoring configurations for eliminating false positives and false negatives; 3) improving the efficiency of system diagnosis on detected alerts. Solving these problems usually requires a huge amount of domain knowledge about the particular computing systems. The approaches investigated by this dissertation are developed based on event mining algorithms, which are able to automatically derive part of that knowledge from the historical system logs, events and tickets. ^ In particular, two textual clustering algorithms are developed for converting raw textual logs into system events. For refining the monitoring configuration, a rule based alert prediction algorithm is proposed for eliminating false alerts (false positives) without losing any real alert and a textual classification method is applied to identify the missing alerts (false negatives) from manual incident tickets. For system diagnosis, this dissertation presents an efficient algorithm for discovering the temporal dependencies between system events with corresponding time lags, which can help the administrators to determine the redundancies of deployed monitoring situations and dependencies of system components. To improve the efficiency of incident ticket resolving, several KNN-based algorithms that recommend relevant historical tickets with resolutions for incoming tickets are investigated. Finally, this dissertation offers a novel algorithm for searching similar textual event segments over large system logs that assists administrators to locate similar system behaviors in the logs. Extensive empirical evaluation on system logs, events and tickets from real IT infrastructures demonstrates the effectiveness and efficiency of the proposed approaches.^

Labeling large scale social media data using budget-driven One-class SVM classification

The social media classification problems draw more and more attention in the past few years. With the rapid development of Internet and the popularity of computers, there is astronomical amount of information in the social network (social media platforms). The datasets are generally large scale and are often corrupted by noise. The presence of noise in training set has strong impact on the performance of supervised learning (classification) techniques. A budget-driven One-class SVM approach is presented in this thesis that is suitable for large scale social media data classification. Our approach is based on an existing online One-class SVM learning algorithm, referred as STOCS (Self-Tuning One-Class SVM) algorithm. To justify our choice, we first analyze the noise-resilient ability of STOCS using synthetic data. The experiments suggest that STOCS is more robust against label noise than several other existing approaches. Next, to handle big data classification problem for social media data, we introduce several budget driven features, which allow the algorithm to be trained within limited time and under limited memory requirement. Besides, the resulting algorithm can be easily adapted to changes in dynamic data with minimal computational cost. Compared with two state-of-the-art approaches, Lib-Linear and kNN, our approach is shown to be competitive with lower requirements of memory and time.