公开(公告)号：US20150294230A1

公开(公告)日：2015-10-15

申请号：US14250407

申请日：2014-04-11

Applicant: Xerox Corporation

Inventor： Tridib Mukherjee ,  Sakyajit Bhattacharya ,  Koustuv Dasgupta

IPC: G06N7/00 ,  G06N99/00 ,  G06F17/30 ,  H04L29/08

CPC classification number: G06F16/285 ,  G06Q30/02 ,  G06Q50/01 ,  H04L67/306

Abstract: Some embodiments are directed to a system for identifying clusters from a plurality of users using cloud services. A behavior collection module is configured to obtain user preferences for the plurality of users, and an EM module to configured estimate at least one parameter of a distance-based model by the Expectation-Maximization (EM) algorithm for various values of G (number of clusters). A selection module is configured to compute Bayesian Information Criteria (BIC) with the at least one estimated parameter obtained from the EM module for various values of G, compare BICs obtained for various values of G, select the model with the highest BIC as the best model (best model including the plurality of clusters) and use estimated latent variables of the best model to build a classifier. A characterization module is configured to classify each user into a cluster of the best model using the classifier, and to determine ranking preference of each cluster.

Abstract translation: 一些实施例涉及用于使用云服务从多个用户中识别群集的系统。 行为收集模块被配置为获得多个用户的用户偏好，并且EM模块被配置为通过期望最大化（EM）算法估计基于距离的模型的至少一个参数，用于G的各种值 集群）。 选择模块被配置为使用从EM模块获得的各种G值的至少一个估计参数来计算贝叶斯信息准则（BIC），对于G的各种值获得的比较BIC，选择具有最高BIC的模型作为最佳 模型（包括多个集群的最佳模型），并使用最佳模型的估计潜在变量构建分类器。 表征模块被配置为使用分类器将每个用户分类为最佳模型的集群，并且确定每个集群的排名偏好。

公开(公告)号：US20150228015A1

公开(公告)日：2015-08-13

申请号：US14179775

申请日：2014-02-13

Applicant: Xerox Corporation

Inventor： Sakyajit Bhattacharya ,  Vaibhav Rajan

IPC: G06Q40/02

CPC classification number: G06Q40/025

Abstract: Disclosed are the embodiments for creating a model capable of identifying one or more clusters in a financial data. An input is received pertaining to a range of numbers. Each number in the range of numbers is representative of a number of clusters in the financial data. For a cluster, one or more first parameters of a distribution associated with the cluster are estimated. Thereafter, a threshold value is determined based on the one or more first parameters. An inverse cumulative distribution of each of one or more n-dimensional variables in the financial data is determined. The one or more first parameters are updated to generate one or more second parameters based on the estimated inverse cumulative distribution. A model is created for each number in the range of numbers based on the one or more second parameters.

Abstract translation: 公开了用于创建能够识别财务数据中的一个或多个集群的模型的实施例。 接收与数字范围有关的输入。 数字范围内的每个数字代表财务数据中的多个集群。 对于集群，估计与集群相关联的分发的一个或多个第一参数。 此后，基于一个或多个第一参数来确定阈值。 确定财务数据中的一个或多个n维变量中的每一个的逆累积分布。 更新一个或多个第一参数以基于估计的反向累积分布生成一个或多个第二参数。 基于一个或多个第二参数，为数字范围内的每个数字创建模型。

公开(公告)号：US20150220871A1

公开(公告)日：2015-08-06

申请号：US14171793

申请日：2014-02-04

Applicant: XEROX CORPORATION

Inventor： Vaibhav Rajan ,  Sakyajit Bhattacharya ,  Koustuv Dasgupta ,  Nischal Murthy Piratla ,  Laura Elisa Celis ,  Deepthi Chander ,  Saraschandra Karanam

IPC: G06Q10/06

CPC classification number: G06Q10/063112

Abstract: The disclosed embodiments illustrate methods and systems for scheduling a batch of tasks on one or more crowdsourcing platforms. The method includes generating one or more forecast models for each of the one or more crowdsourcing platforms based on historical data associated with each of the one or more crowdsourcing platforms and a robustness parameter. Thereafter, for a forecast model, from the one or more forecast models, associated with each of the one or more crowdsourcing platforms, a schedule is generated based on the forecast model and one or more parameters associated with the batch of tasks. Further, the schedule is executed on each of the one or more forecasts models associated with the one or more crowdsourcing platforms to determine a performance score of the schedule on each of the one or more forecast models. Finally, the schedule is recommended to a requestor based on the performance score.

Abstract translation: 所公开的实施例示出了用于在一个或多个众包平台上调度一批任务的方法和系统。 该方法包括基于与一个或多个众包平台中的每一个相关联的历史数据和鲁棒性参数为一个或多个众包平台中的每一个生成一个或多个预测模型。 此后，对于与一个或多个众包平台中的每一个相关联的一个或多个预测模型的预测模型，基于预测模型和与该批次任务相关联的一个或多个参数来生成调度。 此外，对与一个或多个众包平台相关联的一个或多个预测模型中的每一个执行日程表，以确定该一个或多个预测模型中的每个预测模型上的日程表的绩效分数。 最后，根据绩效分数向请求者推荐日程表。

公开(公告)号：US20170278009A1

公开(公告)日：2017-09-28

申请号：US15077049

申请日：2016-03-22

Applicant: XEROX CORPORATION

Inventor： Vaibhav Rajan ,  Sakyajit Bhattacharya ,  Vijay Huddar ,  Abhishek Sengupta ,  James D. Kirkendall ,  Stephen Fullerton ,  Katerina Sinclair ,  Bhupendra Singh Solanki ,  Prathosh Aragulla Prasad

IPC: G06N99/00 ,  G06N7/00 ,  G06F17/30 ,  H04W4/00

CPC classification number: G06N20/00 ,  G06F16/24578 ,  G06N7/005 ,  H04W4/70

Abstract: A method and a system for predicting admission of a human subject to a first ward in a medical center are disclosed. A patient dataset is generated based on at least a measure of one or more physiological parameters associated with one or more first human subjects and a first information pertaining to the admission of each of the one or more first human subjects to the first ward. For a first human subject of the one or more first human subjects, a first score at each of the one or more first time instants is determined. Further, one or more second time instants from the one or more first time instants are identified. Further, a second score at each of the one or more second time instants is determined. In an embodiment, the first classifier is trained based on at least the second score, and the first information.

公开(公告)号：US20170270429A1

公开(公告)日：2017-09-21

申请号：US15075691

申请日：2016-03-21

Applicant: Xerox Corporation

Inventor： Sakyajit Bhattacharya ,  Vaibhav Rajan

IPC: G06N99/00 ,  G06N7/00

CPC classification number: G06N20/00

Abstract: A method and system for data classification using machine learning comprises collecting a dataset with a data collection module, receiving the dataset at a classification module configured for machine learning, dividing the dataset into a plurality of vectors, transforming the plurality of vectors into a plurality of variables wherein each variable is assigned a label, and classifying the variables.

公开(公告)号：US20170262596A1

公开(公告)日：2017-09-14

申请号：US15063558

申请日：2016-03-08

Applicant: XEROX CORPORATION

Inventor： Abhishek Sengupta ,  Vaibhav Rajan ,  Sakyajit Bhattacharya ,  Gosala Raja Kukkuta Sarma

IPC: G06F19/00 ,  G06N7/00 ,  G06N99/00

CPC classification number: G16H50/20 ,  G06N7/005 ,  G06N20/00

Abstract: A method and a system are provided for prediction of an outcome of a stroke event associated with a first human subject. The method receives a first score, one or more first observations, and one or more second observations associated with the first human subject. The method predicts one or more second scores at the second time instant based on a training of a probabilistic model. The method further selects a second score from the one or more second scores at the second time instant. The second score corresponds to the outcome of the stroke event associated with the first human subject. The second score corresponds to the highest value from the one or more second scores.

公开(公告)号：US09471876B2

公开(公告)日：2016-10-18

申请号：US14273566

申请日：2014-05-09

Applicant: Xerox Corporation

Inventor： Sakyajit Bhattacharya ,  Tridib Mukherjee ,  Koustuv Dasgupta ,  Shruti Kunde

IPC: G06F17/00 ,  G06N5/02 ,  G06N5/04 ,  H04L29/08 ,  G06N99/00

CPC classification number: G06N5/04 ,  G06N99/005 ,  H04L67/10

Abstract: Methods and systems for creating one or more statistical classifiers. A first set of performance parameters, corresponding to the one or more applications and the one or more computing infrastructures, is extracted from a historical data pertaining to the execution of the one or more applications on the one or more computing infrastructures. Further, a set of application-specific and a set of infrastructure-specific parameters are selected, from the first set of performance parameters, based on one or more statistical techniques. A similarity between each pair of the applications, each pair of the computing infrastructures, and each pair of possible combinations of an application and a computing infrastructure is determined. One or more statistical classifiers are created, based on the determined similarity.

Abstract translation: 用于创建一个或多个统计分类器的方法和系统。 从与一个或多个计算基础设施上的一个或多个应用的​​执行有关的历史数据中提取对应于一个或多个应用和一个或多个计算基础设施的第一组性能参数。 此外，基于一种或多种统计技术，从第一组性能参数中选择一组特定应用和一组基础设施特定参数。 确定每对应用程序，每对计算基础设施之间的相似性以及应用程序和计算基础设施的每对可能的组合。 基于所确定的相似度，创建一个或多个统计分类器。