Cardiomag Imaging, Inc.

Rensselaer Polytechnic Institute

Optimaret, Inc.

Boleslaw Szymanski

Mark Embrechts

Karsten Sternickel

Alexander Seth Ross

Shivkumar Kalyanaraman

Juong-Sik Lee

Ye Tao

David Harrison

Bin Mo

Biplab Sikdar

Jingjie Jiang

Long Han

Gang Chen

Amr Elsisy

Kenneth Vastola

Aamir Mandviwalla

A method of generating a synthetic network includes receiving, by a group structure identification module, anonymized input data related to an original network. The anonymized input data includes an anonymized list of nodes, a list of edges and a list of groups. The method further includes determining, by the group structure identification module, for each pair of nodes, a probability of an edge between the pair of nodes. A resulting list of probabilities corresponds to a summary group structure. The method further includes generating, by a synthetic random network generation module, at least one synthetic random network based, at least in part, on the determined probabilities.

Synthetic network generator for covert network analytics

The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.

Use of machine learning for classification of magneto cardiograms

The present invention includes a method and system for trading goods and services through recurring auctions. Recurring auctions are increasingly popular form of markets for perishable and time-sensitive resources. Traditional auctions strive to motivate bidders to bid their true valuation of the resources traded. Yet, when successful, they also quickly divide the recurring auction bidders into permanent winners and permanent losers. The latter have no incentive to stay in the market, so they leave, decreasing the competitive pressure and depressing pricing. The present invention introduces a novel winner selection method to maintain customers' interest in auction participation that employs participant retention mechanism in assigning traded resources to bidders. The winners are selected from a wider range of bidder ranks than in traditional auction mechanisms. For a group of bidders, winner selection takes into account bid values, allocation of resources and participation of each bidder in the previous auction rounds.

Apparatus and method for conducting a recurring auction using a participant retention mechanism

A novel Levenberg-Marquardt like second-order algorithm for tuning the Parzen window &#x3c3; in a Radial Basis Function (Gaussian) kernel. Each attribute has its own sigma parameter. The values of the optimized &#x3c3; are then used as a gauge for variable selection. Kernel Partial Least Squares (K-PLS) model is applied to several benchmark data sets to estimate effectiveness of second-order sigma tuning procedure for an RBF kernel. The variable subset selection method based on these sigma values is then compared with different feature selection procedures such as random forests and sensitivity analysis. The sigma-tuned RBF kernel model outperforms K-PLS and SVM models with a single sigma value. K-PLS models also compare favorably with Least Squares Support Vector Machines (LS-SVM), epsilon-insensitive Support Vector Regression and traditional PLS. Sigma tuning and variable selection is applied to industrial magnetocardiograph data for detection of ischemic heart disease from measurement of magnetic field around the heart.

Sigma tuning of gaussian kernels: detection of ischemia from magnetocardiograms

The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering. The results, similar for all three methods, were encouraging, exceeding the quality of classification achieved by the trained experts. Thus, a device and associated method for classifying cardiography data is disclosed, comprising applying a kernel transform to sensed data acquired from sensors sensing electromagnetic heart activity, resulting in transformed data, prior to classifying the transformed data using machine learning.

A collaborative on-line simulation system and method to provide automated and pro-active control functions for computer network. In a wide area network, clients communicate through one or several nodes (). Each node () contains routers which include control plane () and data plane (). Collaborative on-line simulators () are interfaced to the network nodes () and continuously monitor the surrounding network conditions, communicate with other simulators and execute collaborative on-line simulation. Based on the simulation results, the on-line simulators () continuously tune selected network parameters to a more efficient operation point to fit the current network conditions.

Network management and control using collaborative on-line simulation

Lookback is defined as the ability of a logical process to change its past locally (without involving other logical processes). Logical processes with lookback are able to process out-of-timestamp order events, enabling new synchronization protocols for the parallel discrete event simulation. Two of such protocols, LB-GVT (LookBack-Global Virtual Time) and LB-EIT (LookBack-Earliest Input Time), are presented and their performances on the Closed Queuing Network (CQN) simulation are compared with each other. Lookback can be used to reduce the rollback frequency in optimistic simulations. The relation between lookahead and lookback is also discussed in detail. Finally, it is shown that lookback allows conservative simulations to circumvent the speedup limit imposed by the critical path.

Growing community of inventors

Newtonville, NY, United States of America

Boleslaw Szymanski