Richard J. Povinelli

Overview of BioCreative II gene mention recognition

Nineteen teams presented results for the Gene Mention Task at the BioCreative II Workshop. In this task participants designed systems to identify substrings in sentences corresponding to gene name mentions. A variety of different methods were used and the results varied with a highest achieved F1 score of 0.8721. Here we present brief descriptions of all the methods used and a statistical analysis of the results. We also demonstrate that, by combining the results from all submissions, an F score of 0.9066 is feasible, and furthermore that the best result makes use of the lowest scoring submissions.

Induction Machine Broken Bar and Stator Short-Circuit Fault Diagnostics Based on Three-Phase Stator Current Envelopes

A new method for the fault diagnosis of a broken rotor bar and interturn short circuits in induction machines (IMs) is presented. The method is based on the analysis of the three-phase stator current envelopes of IMs using reconstructed phase space transforms. The signatures of each type of fault are created from the three-phase current envelope of each fault. The resulting fault signatures for the new so-called ldquounseen signalsrdquo are classified using Gaussian mixture models and a Bayesian maximum likelihood classifier. The presented method yields a high degree of accuracy in fault identification as evidenced by the given experimental results, which validate this method.

Time series classification using Gaussian mixture models of reconstructed phase spaces

A new signal classification approach is presented that is based upon modeling the dynamics of a system as they are captured in a reconstructed phase space. The modeling is done using full covariance Gaussian mixture models of time domain signatures, in contrast with current and previous work in signal classification that is typically focused on either linear systems analysis using frequency content or simple nonlinear machine learning models such as artificial neural networks. The proposed approach has strong theoretical foundations based on dynamical systems and topological theorems, resulting in a signal reconstruction, which is asymptotically guaranteed to be a complete representation of the underlying system, given properly chosen parameters. The algorithm automatically calculates these parameters to form appropriate reconstructed phase spaces, requiring only the number of mixtures, the signals, and their class labels as input. Three separate data sets are used for validation, including motor current simulations, electrocardiogram recordings, and speech waveforms. The results show that the proposed method is robust across these diverse domains, significantly outperforming the time delay neural network used as a baseline.

A new temporal pattern identification method for characterization and prediction of complex time series events

A new method for analyzing time series data is introduced in this paper. Inspired by data mining, the new method employs time-delayed embedding and identifies temporal patterns in the resulting phase spaces. An optimization method is applied to search the phase spaces for optimal heterogeneous temporal pattern clusters that reveal hidden temporal patterns, which are characteristic and predictive of time series events. The fundamental concepts and framework of the method are explained in detail. The method is then applied to the characterization and prediction, with a high degree of accuracy, of the release of metal droplets from a welder. The results of the method are compared to those from a Time Delay Neural Network and the C4.5 decision tree algorithm.

Statistical models of reconstructed phase spaces for signal classification

This paper introduces a novel approach to the analysis and classification of time series signals using statistical models of reconstructed phase spaces. With sufficient dimension, such reconstructed phase spaces are, with probability one, guaranteed to be topologically equivalent to the state dynamics of the generating system, and, therefore, may contain information that is absent in analysis and classification methods rooted in linear assumptions. Parametric and nonparametric distributions are introduced as statistical representations over the multidimensional reconstructed phase space, with classification accomplished through methods such as Bayes maximum likelihood and artificial neural networks (ANNs). The technique is demonstrated on heart arrhythmia classification and speech recognition. This new approach is shown to be a viable and effective alternative to traditional signal classification approaches, particularly for signals with strong nonlinear characteristics.

Interturn Fault Diagnosis in Induction Motors Using the Pendulous Oscillation Phenomenon

A robust interturn fault diagnostic approach based on the concept of magnetic field pendulous oscillation, which occurs in induction motors under faulty conditions, is introduced in this paper. This approach enables one to distinguish and classify an unbalanced voltage power supply and machine manufacturing/construction imperfections from an interturn fault. The experimental results for the two case studies of a set of 5-hp and 2-hp induction motors verify the validity of the proposed approach. Moreover, it can be concluded from the experimental results that if the circulating current level in the shorted loop increases beyond the phase current level, an interturn fault can be easily detected using the proposed approach even in the presence of the existence of motor manufacturing imperfection effects

Identifying Temporal Patterns for Characterization and Prediction of Financial Time Series Events

The novel Time Series Data Mining (TSDM) framework is applied to analyzing financial time series. The TSDM framework adapts and innovates data mining concepts to analyzing time series data. In particular, it creates a set of methods that reveal hidden temporal patterns that are characteristic and predictive of time series events. This contrasts with other time series analysis techniques, which typically characterize and predict all observations. The TSDM framework and concepts are reviewed, and the applicable TSDM method is discussed. Finally, the TSDM method is applied to time series generated by a basket of financial securities. The results show that statistically significant temporal patterns that are both characteristic and predictive of events in financial time series can be identified.

Speech recognition using reconstructed phase space features

The paper presents a novel method for speech recognition by utilizing nonlinear/chaotic signal processing techniques to extract time-domain based phase space features. By exploiting the theoretical results derived in nonlinear dynamics, a processing space called a reconstructed phase space can be generated where a salient model (the natural distribution of the attractor) can be extracted for speech recognition. To discover the discriminatory power of these features, isolated phoneme classification experiments were performed using the TIMIT corpus and compared to a baseline classifier that uses MFCC (Mel frequency cepstral coefficient) features. The results demonstrate that phase space features contain substantial discriminatory power, even though MFCC features outperformed the phase space features on direct comparisons. The authors conjecture that phase space and MFCC features used in combination within a classifier may yield increased accuracy for various speech recognition tasks.

Time-domain isolated phoneme classification using reconstructed phase spaces

This paper introduces a novel time-domain approach to modeling and classifying speech phoneme waveforms. The approach is based on statistical models of reconstructed phase spaces, which offer significant theoretical benefits as representations that are known to be topologically equivalent to the state dynamics of the underlying production system. The lag and dimension parameters of the reconstruction process for speech are examined in detail, comparing common estimation heuristics for these parameters with corresponding maximum likelihood recognition accuracy over the TIMIT data set. Overall accuracies are compared with a Mel-frequency cepstral baseline system across five different phonetic classes within TIMIT, and a composite classifier using both cepstral and phase space features is developed. Results indicate that although the accuracy of the phase space approach by itself is still currently below that of baseline cepstral methods, a combined approach is capable of increasing speaker independent phoneme accuracy.

Synergistic Use of Compound Properties and Docking Scores in Neural Network Modeling of CYP2D6 Binding: Predicting Affinity and Conformational Sampling

Cytochrome P450 2D6 (CYP2D6) is used to develop an approach for predicting affinity and relevant binding conformation(s) for highly flexible binding sites. The approach combines the use of docking scores and compound properties as attributes in building a neural network (NN) model. It begins by identifying segments of CYP2D6 that are important for binding specificity, based on structural variability among diverse CYP enzymes. A family of distinct, low-energy conformations of CYP2D6 are generated using simulated annealing (SA) and a collection of 82 compounds with known CYP2D6 affinities are docked. Interestingly, docking poses are observed on the backside of the heme as well as in the known active site. Docking scores for the active site binders, along with compound-specific attributes, are used to train a neural network model to properly bin compounds as strong binders, moderate binders, or nonbinders. Attribute selection is used to preselect the most important scores and compound-specific attributes for the model. A prediction accuracy of 85+/-6% is achieved. Dominant attributes include docking scores for three of the 20 conformations in the ensemble as well as the compounds formal charge, number of aromatic rings, and AlogP. Although compound properties were highly predictive attributes (12% improvement over baseline) in the NN-based prediction of CYP2D6 binders, their combined use with docking score attributes is synergistic (net increase of 23% above baseline). Beyond prediction of affinity, attribute selection provides a way to identify the most relevant protein conformation(s), in terms of binding competence. In the case of CYP2D6, three out of the ensemble of 20 SA-generated structures are found to be the most predictive for binding.