Machine Learning and Data Mining, Signal Processing, Dynamical Systems and Chaos
Speech Recognition, Energy Demand Forecasting, Financial Event Prediction
Speech Recognition using Dynamical Systems Models
Participants: Michael T. Johnson, Ph.D., Andrew Lindgren, Xiaolin Liu, Felice Roberts, Jinjin Ye
This project focuses on the creation of a stochastic representation for the
phase-space embeddings of dynamical systems, for application to the task of
speech classification and recognition. The research team will develop a general
stochastic model for such signal embeddings, test the model through classification
simulations, then apply the technique to both isolated and continuous speech
recognition. The goal of the research is to discover time-domain analysis
techniques using dynamical systems methods that will lead to improved analysis
of speech signals and to improvements in speech recognition accuracy. This
approach represents the integration of two traditionally distinct research
fields: statistical signal processing and chaotic systems. Since signal processing
is fundamentally based on linear systems theory and the study of chaos is
inherently non-linear, these fields have little or no overlap outside of the
fact that both attempt to model the behavior of physical systems. This research
integrates these different fields by applying stochastic analysis and modeling
tools from the signal processing field to the problem of analyzing embedded
phase spaces obtained from chaotic systems analysis of time-series signals.
Visit the project web page
Automatic Identification of Heart Arrythmias
Participants: Felice Roberts
Changes in the normal rhytmicity of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart when sustained over long periods of time. The ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment, as well as for understanding the electrophysiological mechanisms of the arrhythmias. This project focuses on novel approaches to efficiently and accurately identify normal sinus rhythm and various ventricular arrhythmias through phase space reconstruction and machine learning techniques.
Induction Motor Asynchronous Drive Fault Prediction
Participants: Michael T. Johnson, Ph.D., Edwin Yaz, Ph.D., Nabeel Demerdash, Ph.D.
Induction motor-drive systems are used throughout industry. In many applications they are the motor-drives of choice. They are used in a wide variety of motor-drive applications such as industrial plant control, propulsion systems, and medical diagnostic equipment. Failure of such motor-drive systems have serious impact on the equipment they are part of including shutdown of the larger system. In industrial applications the impact can be dangerous and costly, but in medical applications such failure can even have fatal effects.
Accurate diagnostics and fault predictive will increase the reliability of motor-drive systems and minimize the problem of their failure in the field. A dual track approach is proposed to developing a comprehensive diagnostic system for motor-drive systems. We address two fundamental problems in developing such a diagnostic system, namely the difficulty and cost of obtaining large amounts of mtoor-drive system failure data and the difficulty in developing accurate, robust, fast, and effective diagnostic techniques. The dual track is a combination of time stepping coupled finite element state space (TSCFE-SS) techniques for generating accurate, but inexpensive, fault data with a reconstructed phase space based approach for modeling system trajectories for creating effective fault signatures.
- Participants: David Diggs, Regis DiGiacomo
- Former Participants: Minglei Duan
Predicting stock market behavior is a challenging and sometimes impossible task. There are many factors that influence the changes in value of stocks, and nobody knows exactly how each of these factors will impact the market. This project approaches this problem with a combination of proven time series anaylsis methods and novel evaluation techniques. In the strategies used here, only the past stock price information is used to predict the future behavior of the stock. A model of the stock price time series is learned and then evaluated using a metric that determines the confidence level of the accuracy of the model. Stocks can be traded at times when the model predicts success, and the model is evaluated at a high confidence level. This way, the number of trades, and the commissions that go along with them, can be limited, while still employing a successful market prediction strategy.