A computer program recognizes selected patterns in time-series data like digitized samples of seismic or electrophysiological signals. The program implements an artificial neural network (ANN) and a set of N clocks for the purpose of determining whether N or more instances of a certain waveform, W, occur within a given time interval, T. The ANN must be trained to recognize W in the incoming stream of data. The first time the ANN recognizes W, it sets clock 1 to count down from T to zero; the second time it recognizes W, it sets clock 2 to count down from T to zero, and so forth through the Nth instance. On the N + 1st instance, the cycle is repeated, starting with clock 1. If any clock has not reached zero when it is reset, then N instances of W have been detected within time T, and the program so indicates. The program can readily be encoded in a field-programmable gate array or an application-specific integrated circuit that could be used, for example, to detect electroencephalographic or electrocardiographic waveforms indicative of epileptic seizures or heart attacks, respectively.
This program was written by Charles Hand of Caltech for NASA’s Jet Propulsion Laboratory.
This software is available for commercial licensing. Please contact Don Hart of the California Institute of Technology at (818) 393- 3425. Refer to NPO-30636.
This Brief includes a Technical Support Package (TSP).
Computer Program Recognizes Patterns in Time-Series Data
(reference NPO-30636) is currently available for download from the TSP library.
Don't have an account?
Overview
The document presents a technical support package detailing a computer program developed by Charles Hand at NASA's Jet Propulsion Laboratory (JPL) for the automatic detection of rhythmic patterns in time-series data, particularly in electrophysiological signals like Electroencephalograms (EEG) and Electrocardiograms (ECG). The program employs an artificial neural network (ANN) combined with a set of digital counters to identify specific waveforms within a defined time interval.
The core functionality of the program revolves around the ANN's ability to recognize a particular waveform, denoted as W. Once trained, the ANN monitors incoming data streams for instances of W. Upon detecting the first instance, it activates a countdown on the first clock; subsequent detections trigger countdowns on additional clocks. This process continues until N instances of W are recognized within the specified time interval T. If any clock has not reached zero when reset, it indicates that the required number of instances has been detected, signaling the presence of the rhythmic pattern.
The software is designed to be user-friendly and easily customizable, making it suitable for various applications. Its architecture allows for straightforward translation into hardware implementations, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). This adaptability is particularly beneficial for real-time monitoring systems in medical settings, where timely detection of conditions like epileptic seizures or heart attacks is critical.
The document emphasizes the program's accuracy and simplicity, addressing some of the challenges faced by traditional ANN approaches in recognizing rhythmic patterns. It highlights the potential for commercial licensing of the software, inviting interested parties to contact Don Hart at Caltech for further information.
Overall, this technical support package showcases an innovative solution for pattern recognition in time-series data, with significant implications for healthcare and other fields requiring precise monitoring of physiological signals. The work was conducted under NASA's sponsorship, and the document includes a disclaimer regarding the non-endorsement of specific commercial products or services.
