USA As Represented by Secretary of the Navy

Kai F Gong

Sherry E Hammel

David J Ferkinhoff

Kathleen D Keay

Marcus L Graham

Steven C Nardone

Chidambar Ganesh

John F MacDonald

Francis J O'Brien, Jr

Chung Tien Nguyen

John G Baylog

Neil A Jackson

Nixon A Pendergrass

Maria C Santos

Sherry E Hammell

John S Davis

A system for bearinqs-only contact state estimation in response to target bearing and ownship speed and course information provided for a plurality of observation legs at successive points in time, includes a plurality of neural networks and a data fusion circuit. Each of the neural networks generates range-normalized parameter estimate information for one of the observation legs in response to target bearing and ownship speed and course information for an associated one of the observation legs, provided thereto at each point in time and information generated for the previous point in time. The data fusion system receives the range-normalized parameter estimate information from the neural networks and generates the contact state estimate in response thereto.

System for bearing-only contact state estimation using recurrent neural networks

A fuzzy logic based model assessment system assesses models of physical phenomena and in one example, is used for contact tracking. The system uses measurement residual values representing the difference between a measured data sequence corresponding to the physical phenomena and an expected data sequence corresponding to the model to be assessed. The system includes a feature identification module for identifying one or more features or tracking anomalies in the measurement residual values, such as jump and drift, and for generating feature amplitude values and feature amplitude standard deviation values. An anomaly characterization module characterizes the features in one or more membership classes representing the strength of the identified feature and generates class membership intervals representing a range of degrees of membership in each of the classes (e.g., null, weak, moderate or strong). A hypothesis formulation and evaluation module determines one or more possible causes of mismodeling by applying fuzzy inferencing to the class memberships, and generates hypothesis certainty intervals representing a range of degrees of certainty of the mismodeling hypothesis based on the class membership intervals. A knowledge base of heuristic rules are used to infer the mismodeling hypotheses based upon the membership classes.

Fuzzy logic based model assessment system and method for contact tracking

A method for the selection of hypotheses for modeling physical phenomena, includes detecting if selected features are present by analyzing actual sensed data and parameter values of an initial physical phenomena model; comparing feature estimating hypotheses to the actual data for determining a belief probability assignment value (bpa) for each of the hypotheses which indicates the likelihood that the selected features exist in the actual data and the likelihood that such selected features cannot accurately be determined as existing due to the presence of noise; selecting a set of the hypotheses most accurately modeling the physical phenomena based on the bpa of each selected hypotheses meeting a predetermined criteria; generating evidential support values and lack of evidential support values for subsets of the set having non-zero subset bpa's; ranking the subsets having non-zero subset bpa's in order of decreasing subset bpa; unioning subsets of the power set for forming unioned subsets and determining support values and plausibility values for the unioned subsets; comparing the unioned evidential support values to a predefined threshold value; and using at least one of the unioned subsets having a unioned evidential support value most closely approximating or exceeding the threshold value for selecting alternate models having selected features which more closely approximate the actual data.

Hypothesis selection for evidential reasoning systems

The present invention relates to a method and a system for providing an estimate of the state of a contact. The method includes the steps of sensing the state of the contact; generating signals representative of the state of the contact; and processing the signals using a random search procedure to arrive at an estimate of the state of the contact. The random search procedure may employ the simulated annealing-based algorithm methodology or the genetic-based algorithm methodologies. The system includes sensors for sensing the state of the contact and a pre-programmed computer for generating the desired contact state estimates.

System and method for tracking vehicles using random search algorithms

The present invention relates to a system and a method for signal classification. The system comprises a sensor array for receiving a series of input signals such as acoustic signals, pixel-based image signal (such as from infrared images detectors), light signals, temperature signals, etc., a wavelet transform module for transforming the input signals so that characteristics of the signals are represented in the form of wavelet transform coefficients and an array of hybrid neural networks for classifying the signals into multiple distinct categories and generating a classification output signal. The hybrid neural networks each comprise a location neural network for processing data embedded in the frequency versus time location segment of the output of the transform module, a magnitude neural network for processing magnitude information embedded in the magnitude segment of the output of the transform module, and a classification neural network for processing the outputs from the location and magnitude neural networks. A method for processing the signal using the system of the present invention is also described.

Wavelet-based hybrid neurosystem for classifying a signal or an image

A system for providing an iterative method of assessing accuracy of selected models of physical phenomena and for determining selection of alternate models in response to a data sequence in the presence of noise. Initially, a residual sequence is generated reflecting difference values between in response to said data sequence and an expected data sequence as would be represented by a selected model. Feature estimate values of a plurality of predetermined data features in the residual sequence are then generated. In response to the feature estimate values, a threshold value is generated for each feature at an estimated ratio of data to noise power. Probability values are generated in response to the threshold value, representing the likelihood that the feature exists in the data sequence, does not exist in the data sequence, and that the existence or non-existence in the data sequence is not determinable, along with an amplitude probability value indicating the belief of the amplitude of the respective feature in the data sequence. Probability values are generated in response to the feature existence and amplitude probability values, representing the likelihood that various modelling hypotheses are represented by the observed features, or are not ruled out by the observed features in the presence of the given noise level. Finally, a model is selected in response to the probability values for use during a subsequent iteration.

Contact management model assessment system for contact tracking in the

An adaptive statistical filter system for receiving a data stream comprising a series of data values from a sensor associated with successive points in time. Each data value includes a data component representative of the motion of a target and a noise component, with the noise components of data values associated with proximate points in time being correlated. The adaptive statistical filter system includes a prewhitener module, a plurality of statistical filters of different orders and a selection module. The prewhitener module receives the data stream from the sensor and generates a corrected data stream comprising a series of corrected data values each associated with a data value of the data stream, each including a data component and a noise component with the noise components of data values associated with proximate points in time being decorrelated. The plural statistical filters are coupled to receive the corrected data stream in parallel from the prewhitener. Each statistical filter generates coefficient values to fit the corrected data stream to a polynomial of corresponding order and fit values representative of the degree of fit of corrected data stream to the polynomial. The selection module receives the fit values and coefficient values from the plural statistical filters and selects coefficient values from one of the filters in response to the fit values. The coefficient values are coupled to target motion analysis module which determines position and velocity of the target.

Enhanced adaptive statistical filter providing improved performance for

A system for compensating for noise induced in a sensor data stream from a sensor array towed by a towing device includes a towing device motion data input receives a towed motion data stream representative of towing motion of the towing device. A sensor array input for receiving the sensor data stream. An adaptive filter connected to the towing device motion data input and the sensor array input for receiving the towed motion data stream from the towing device motion data input and the sensor data stream from the sensor array input and for generating a corrected sensor data stream representing sensor array data with ship motion noise attenuated therefrom.

System and method for compensating for towed array motion induced errors

A trajectory estimation system for estimating a trajectory of a target in sponse to a series of data items which generated in response to motion of the target. The trajectory estimation system includes a data segmentation means and a trajectory selection means. The data segmentation means processes the series of data items in accordance with a regression/multiple-hypothesis methodology to generate a plurality of segments, each having associated data items which have similar features. The trajectory selection means for processing said segments in accordance with a multiple-model hypothesis methodology to generate a corresponding statistically-supportable candidate trajectory motion estimate of target motion thereby to provide indicia of an overall trajectory of the target.

System and method for rapidly tracking highly dynamic vehicles

A system for facilitating the tracking of a target vehicle in connection h successively-received acoustic sensor signal data items. A fast Fourier transform operation is performed in connection with each successive acoustic sensor signal data item to generate a phase and amplitude beam map reflecting spectral signal energy in the received acoustic sensor signal data item. If the beam map for a acoustic sensor signal data item indicates that the item represents a signal having a signal-to-noise ratio above a first predetermined threshold value, a beam map generated for a previous acoustic sensor signal data item is used to generate a bounded beam map, a determination is made as to whether the bounded beam map represents a signal having a second predetermined signal-to-noise ratio. In response to a positive determination for the latter signal-to-noise determination, both the beam maps are used to generate tracking information for the target vehicle.

System and method for rapidly tracking vehicles of special utility in

A system having a device for comparing incoming data with hypotheses prevsly formed from prior data for providing new hypotheses on target information. It has application when the data source is from either single or multiple targets. The incoming datum to the system forms new hypotheses assuming the incoming datum is invalid, forms new hypotheses assuming the new datum begins a new segment of information, and forms new hypotheses assuming the new datum is associated with segments in prior retained hypotheses. The one hypothesis of the thusly formed new hypotheses with the greatest likelihood of target information is then selected for further analyzation and the hypothesis selected and other hypotheses are retained for further processing with new incoming datum.

Automatic data segmentation module for target motion analysis

A system for providing an iterative method of assessing accuracy of selec models of physical phenomena and for determining selection of alternate models in response to a data sequence in the presence of noise. Initially, a residual sequence is generated reflecting difference values between in response to said data sequence and an expected data sequence as would be represented by a selected model. Feature estimate values of a plurality of predetermined data features in the residual sequence are then generated. In response to the feature estimate values, a threshold value is generated for each feature at an estimated ratio of data to noise. Probability values are generated in response to the threshold value, representing the likelihood that the feature exists in the data sequence, does not exist in the data sequence, and that the existence or non-existence in the data sequence is not determinable. Finally, a model is selected in response to the probability values for use during a subsequent iteration.

Growing community of inventors

Pawtucket, RI, United States of America

Kai F Gong