Hewlett-Packard Development Company, L.p.

Hitachi, Ltd.

Hsiu-Khuern Tang

Kemal Guler

Tongwei Liu

Abhay Mehta

Haiyan Wang

Hiroaki Ozaki

Alex Xin Zhang

Shuang Feng

Ren Wu

Fereydoon Safai

Kay-Yut Chen

Maojing Fu

Alan Hersh Karp

Chetan Kumar Gupta

Kave Eshghi

Bin Zhang

Dirk Manfred Beyer

Jun Yamazaki

Bo Yang

Cipriano A Santos

Ahmed Khairy Farahat

Song Wang

Pankaj K Garg

Leslie R Fine

Alex Wang

Laleh Jalali

Justin S Dyer

In some examples, a system may generate a plurality of care path patient profile models based on a plurality of care path patterns for a plurality of past patient admissions. For example, each care path patient profile model may include a trained classifier. Further, the system may receive information related to a new patient admission, and may generate features from the received information related to the new patient admission. The system may input the features generated from the received information related to the new patient admission into the plurality of care path patient profile models to obtain a respective probability of being classified in a respective care path based on an amount of similarity to the patients who have gone through each care path. In addition, the system may present, on a display, information related to at least one care path pattern in a graphical user interface.

Care path analysis and management platform

In some examples, a computing device may receive hierarchical data having a hierarchical structure including a plurality of levels. The computing device may determine a plurality of features based at least in part on the hierarchical data, and may select a subset of the features at a first level as candidates for consolidating to a next higher level in the hierarchical structure. The computing device may determine that a predicted loss of information from consolidating the subset of features is less than a threshold, and may revise the hierarchical structure to include a consolidated feature at the next higher level, rather than the subset of features. In some examples, a statistical model may be trained based on the revised hierarchical structure and used at least partially to make a determination, send a notification, and/or control a device.

Controlling devices based on hierarchical data

In some examples, a system may train a false positive reduction machine learning model (MLM) for nodule detection. The system may receive training data images including negative images and positive images, along with an indication of nodule locations in the positive images. The system may determine elliptical approximations for nodules in the positive images, and may determine respective binarized contours from the elliptical approximations. Further, the system may determine an elliptical approximation space for the binarized contours, and may determine a subspace angle between individual image samples in the positive images and the elliptical approximation space as at least one feature of the MLM. Subsequently, when applying the MLM during nodule detection, one or more images may be input to the MLM to determine whether an indication of a nodule is correct, and if so, a visualization of a location of the nodule may be provided.

Nodule detection with false positive reduction

In some examples, a computing device may receive sensor data associated with a plurality of patient devices that are associated with a plurality of patients. The computing device may further receive caregiver records corresponding at least partially to the sensor data. At least two groups of indicators may be determined from the caregiver records, such a based on a selected subject. Further, the computing device may determine a plurality of clusters from the sensor data. Based on the plurality of clusters and the at least two groups, the computing device may determine an indication of a discrepancy in care for a patient of the plurality of patients. Based on the indication of the discrepancy, the computing device may send at least one of a notification to a caregiver computing device, a notification to a monitoring computing device, or a control signal to one of the patient devices.

Managing patient devices based on sensor data

In some examples, a computing device may receive sensor data for a target and at least one of: log data for the target, or historical log data and historical sensor data for a plurality of other targets. The computing device may determine at least one event classified as a non-uniform event in at least one of the log data or the historical log data, and may determine combined features, such as a feature vector, based on the sensor data and the non-uniform event(s). The computing device may determine an analysis result from the combined features. Further, based on the analysis result, the computing device may send a control signal to a device associated with the target for controlling the device, and/or may send a communication related to the target to another computing device.

Controlling a device based on log and sensor data

Example implementations described herein are directed to a decision-support system for maintenance recommendation that uses analytics technology to evaluate the effectiveness of a maintenance action or a group of actions in improving the performance of equipment and its components, and provide recommendations on which maintenance actions or a group of maintenance actions should be pursued and which should be avoided.

System for maintenance recommendation based on maintenance effectiveness estimation

Example implementations described herein are directed to detection of anomalous events and locations on the transmission power system using phasor management unit (PMU) data, which provides information to grid operators for online decision support. From the high-resolution time synchronized PMU data, the transient abnormal events can be monitored and locations can be disclosed to operators for remedy actions. Utilization of PMU information for such decision support compliments operation practices relying on supervisory control and data acquisition (SCADA) measurements at much lower data resolution. Accurate identification of event locations can further advise grid operators the root cause of disturbances and illuminate possible cascading failures. Implementations of the proposed technology may improve the resilience and reliability of the transmission power systems.

Estimating the locations of power system events using PMU measurements

System, including method, apparatus, and computer-readable media, for evaluating client status for a likelihood of churn. Client data may be received, with the client data representing events from a set of different event types performed by clients. Parameters of a statistical model that describes client behavior may be estimated using a computer and based on the client data. A churn type of event may be encoded in the statistical model as an absorbing state of a stochastic process, with a time of transition to the absorbing state modeled as being infinite. At least one of the parameters may correspond to the churn type of event. A likelihood of churn may be calculated for a plurality of the clients at one or more time points using the statistical model and its estimated parameters.

Evaluation of client status for likelihood of churn

A system and method comprises simulating a multiple lot auction using a sequencing rule until bidding on all lots is closed, simulating the multiple lot auction using a different sequencing rule until bidding on all lots is closed, and comparing results of the simulated auctions with both sequencing rules.

System and method for comparing results of multiple lot auctions using different sequencing rules

Methods and associated apparatus comprise, among other features, organizing previously acquired auction data into a plurality of sub-samples, each sub-sample comprising bid data associated with auctions having a common number of bidders, applying an inverse bid function to at least two sub-samples, pooling results from applying the inverse bid function to form a first pool, applying a direct bid function on the first pool to generate sample bids, matching bids from at least one sub-sample to the sample bids, and pooling results from the matching with the first pool to form a second pool.

Analyzing auction data having a varying number of bidders

A computer-implemented automated decision support system for designing an auction for a given item includes a structure extractor that estimates unknown elements of market structure of the auction based on auction characteristics data extracted from historical auctions for similar items and a bidding model matching the extracted auction characteristics data. The decision support system also includes a bidding behavior predictor that predicts bidding behaviors of bidders in the auction based on the estimated unknown elements of market structure and characteristics of the auction. In addition, the system includes an optimizer that employs an evaluation criterion to generate an evaluation of the auction based on (1) the estimated unknown elements of market structure and (2) the predicted bidding behavior of bidders. A method of providing an automated auction analysis is also described.

Automated decision support system for designing auctions

An automated estimation and optimization solution for selecting the best auction format by determining the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements. Structural analysis of bid data from prior auctions is used to identify and estimate the distributions of bidders' private signals conditional on observable bidder characteristics. The estimated signal distributions, identified by the structural analysis, are used to evaluate alternative auction formats and to select the best format from among a given set of candidates. The present invention provides decision support tools to select an auction format based on structural econometric analysis of available data on the market environment. A decision-maker may estimate the unobservable private signals of the bidders and to determine the best auction format the decision maker can employ to sell a given set of items.

Method and system for selecting an optimal auction format

A method for extracting an implied value of a component associated with a plurality of product packages is disclosed. One embodiment of the method includes receiving data associated with a plurality of product packages. It is noted that the data comprises product package price data associated with the plurality of product packages. The data is processed utilizing a mathematical optimization to produce first output data. The first output data is processed with a statistical regression to produce second output data. The second output data includes an estimated value and its standard error of a component associated with the plurality of product packages.

Extracting an implied value of a component associated with a plurality of product packages

The present invention provides an automated estimation and optimization solution for selecting the optimal bid for an item in an auction. The characteristics of the auction are selected (e.g., auction format, reserve price). A relevant bidding model, based on the characteristics of the auction, is selected. The structure of the auction is estimated based on the relevant bidding model. A bid function is determined based on the auction structure and user inputs regarding the item being bid on and the characteristics of the rival bidders. An optimal bid is determined based on the bid function and user-defined evaluation criterion. An embodiment of the present invention provides a method and system that determines the latent elements of the auction environment taking into account the strategic and information conditions with minimal assumptions on the distributions of unobserved random elements. The present invention allows a bidder to estimate the unobservable private signals of rival bidders and to determine the optimal bid the bidder can employ to optimize their evaluation criterion.

Method and system for automated bid advice for auctions

One embodiment of the present invention provides a method and system that computes the optimal level of the reserve price for an auction, with respect to a multiplicity of possible evaluation criteria that the end user of the system may specify. In one embodiment, structural elements characterizing the auction situation are estimated from bid data available on past auctions. The estimated structural elements are then used in the formulation of the user's expected payoff as a function of the reserve price. This objective function is then optimized to obtain the best level of the reserve price. In one embodiment, this method is implemented by a process executed on a computer system, under the control of software and firmware directing the operation of its processors and components. In one embodiment, a computer readable medium causes a computer system to execute the steps in a process for implementing the method.

Growing community of inventors

Menlo Park, CA, United States of America

Hsiu-Khuern Tang