专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08255346B2 Methods and systems for variable group selection and temporal causal modeling 有权
标题翻译：可变组选择和时间因果建模的方法和系统
公开(公告)号：US08255346B2
公开(公告)日：2012-08-28
申请号：US12616534
申请日：2009-11-11
申请人： Naoki Abe , Yan Liu , Aurelie C. Lozano , Saharon Rosset , Grzegorz Swirszcz
发明人： Naoki Abe , Yan Liu , Aurelie C. Lozano , Saharon Rosset , Grzegorz Swirszcz
IPC分类号： G06F15/18 , G06F7/60 , G06F17/50
CPC分类号： G06N5/003 , G06N7/005
摘要： A “variable group selection” system and method in which constructs are based upon a training data set, a regression modeling module that takes into account information on groups of related predictor variables given as input and outputs a regression model with selected variable groups. Optionally, the method can be employed as a component in methods of temporal causal modeling, which are applied on a time series training data set, and output a model of causal relationships between the multiple times series in the data.
摘要翻译：一种“可变组选择”系统和方法，其中构造基于训练数据集，回归建模模块考虑了作为输入给出的相关预测变量组的信息，并输出具有选定变量组的回归模型。可选地，该方法可以用作时间因果建模方法中的组件，其应用于时间序列训练数据集，并且输出数据中多次序列之间的因果关系模型。

2. 发明申请

US20110112998A1 METHODS AND SYSTEMS FOR VARIABLE GROUP SELECTION AND TEMPORAL CAUSAL MODELING 有权
标题翻译：可变组选择和时间建模的方法和系统
公开(公告)号：US20110112998A1
公开(公告)日：2011-05-12
申请号：US12616534
申请日：2009-11-11
申请人： Naoki Abe , Yan Liu , Aurelie C. Lozano , Saharon Rosset , Grzegorz Swirszcz
发明人： Naoki Abe , Yan Liu , Aurelie C. Lozano , Saharon Rosset , Grzegorz Swirszcz
IPC分类号： G06N3/12 , G06F15/18
CPC分类号： G06N5/003 , G06N7/005
摘要： A “variable group selection” system and method in which constructs are based upon a training data set, a regression modeling module that takes into account information on groups of related predictor variables given as input and outputs a regression model with selected variable groups. Optionally, the method can be employed as a component in methods of temporal causal modeling, which are applied on a time series training data set, and output a model of causal relationships between the multiple times series in the data.
摘要翻译：一种“可变组选择”系统和方法，其中构造基于训练数据集，回归建模模块考虑了作为输入给出的相关预测变量组的信息，并输出具有选定变量组的回归模型。可选地，该方法可以用作时间因果建模方法中的组件，其应用于时间序列训练数据集，并且输出数据中多次序列之间的因果关系模型。

3. 发明授权

US10360527B2 Casual modeling of multi-dimensional hierarchical metric cubes 有权
公开(公告)号：US10360527B2
公开(公告)日：2019-07-23
申请号：US12943316
申请日：2010-11-10
申请人： Naoki Abe , Jing Fu , Michael G. Gemmell , Shubir Kapoor , Floyd S. Kelly , David M. Loehr , Aurelie C. Lozano , Shilpa N. Mahatma , Bonnie K. Ray
发明人： Naoki Abe , Jing Fu , Michael G. Gemmell , Shubir Kapoor , Floyd S. Kelly , David M. Loehr , Aurelie C. Lozano , Shilpa N. Mahatma , Bonnie K. Ray
IPC分类号： G06Q10/06
摘要： A computing system initializes a first frontier to be a root of a multi-dimensional hierarchical data structure representing an entity. The system acquires first data corresponding to the first frontier. The system performs modeling on the first data to obtain a first model and a corresponding first statistic. The system expands a dimension of the first frontier. The system gathers second data corresponding to the expanded frontier. The system applies the data modeling on the second data to obtain a second model and a corresponding second statistic. The system compares the first statistic of the first model and the second statistic of the second model. The system sets the second model to be the first model in response to determining that the second model statistic is better than the first model statistic. The system outputs the first model.

4. 发明授权

US08275721B2 Methods and systems for cost-sensitive boosting 失效
标题翻译：成本敏感提升的方法和系统
公开(公告)号：US08275721B2
公开(公告)日：2012-09-25
申请号：US12190325
申请日：2008-08-12
申请人： Naoki Abe , Aurelie C. Lozano
发明人： Naoki Abe , Aurelie C. Lozano
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： Multi-class cost-sensitive boosting based on gradient boosting with “p-norm” cost functionals” uses iterative example weighting schemes derived with respect to cost functionals, and a binary classification algorithm. Weighted sampling is iteratively applied from an expanded data set obtained by enhancing each example in the original data set with as many data points as there are possible labels for any single instance, and where each non-optimally labeled example is given the weight equaling a half times the original misclassification cost for the labeled example times the p−1 norm of the average prediction of the current hypotheses. Each optimally labeled example is given the weight equaling the sum of the weights for all the non-optimally labeled examples for the same instance. Component classification algorithm is executed on a modified binary classification problem. A classifier hypothesis is output, which is the average of all the hypotheses output in the respective iterations.
摘要翻译：基于使用“p范数”成本函数梯度提升的多类成本敏感性提升“使用相对于成本函数导出的迭代示例加权方案和二进制分类算法。从通过增强原始数据集中的每个示例而获得的扩展数据集中的加权采样被迭代地应用于具有任何单一实例的可能标签的数据点数量，并且其中每个非最佳标记的示例给出权重等于一半乘以标记示例的原始错误分类成本乘以当前假设的平均预测的p-1范数。给出每个最佳标记的例子，其权重等于同一实例的所有非最佳标记的示例的权重之和。对修改的二进制分类问题执行组件分类算法。输出分类器假设，它是各自迭代中输出的所有假设的平均值。

5. 发明申请

US20120116850A1 CAUSAL MODELING OF MULTI-DIMENSIONAL HIERACHICAL METRIC CUBES 审中-公开
标题翻译：多维度数公式的原理建模
公开(公告)号：US20120116850A1
公开(公告)日：2012-05-10
申请号：US12943316
申请日：2010-11-10
申请人： Naoki Abe , Jing Fu , Michael G. Gemmell , Shubir Kapoor , Floyd S. Kelly , David M. Loehr , Aurelie C. Lozano , Shilpa N. Mahatma , Bonnie K. Ray
发明人： Naoki Abe , Jing Fu , Michael G. Gemmell , Shubir Kapoor , Floyd S. Kelly , David M. Loehr , Aurelie C. Lozano , Shilpa N. Mahatma , Bonnie K. Ray
IPC分类号： G06Q10/00
CPC分类号： G06Q10/067 , G06Q10/063 , G06Q10/0639
摘要： A computing system initializes a first frontier to be a root of a multi-dimensional hierarchical data structure representing an entity. The system acquires first data corresponding to the first frontier. The system performs modeling on the first data to obtain a first model and a corresponding first statistic. The system expands a dimension of the first frontier. The system gathers second data corresponding to the expanded frontier. The system applies the data modeling on the second data to obtain a second model and a corresponding second statistic. The system compares the first statistic of the first model and the second statistic of the second model. The system sets the second model to be the first model in response to determining that the second model statistic is better than the first model statistic. The system outputs the first model.
摘要翻译：计算系统将第一边界初始化为代表实体的多维分层数据结构的根。系统获取与第一边界对应的第一数据。系统对第一个数据执行建模以获得第一个模型和相应的第一个统计量。系统扩展了第一个边界的维度。系统收集对应于扩展边界的第二个数据。该系统对第二个数据应用数据建模以获得第二个模型和相应的第二个统计量。系统比较第一模型的第一个统计量和第二个模型的第二个统计量。响应于确定第二模型统计量优于第一模型统计量，系统将第二模型设置为第一模型。系统输出第一个模型。

6. 发明申请

US20100042561A1 METHODS AND SYSTEMS FOR COST-SENSITIVE BOOSTING 失效
标题翻译：成本敏感性升高的方法和系统
公开(公告)号：US20100042561A1
公开(公告)日：2010-02-18
申请号：US12190325
申请日：2008-08-12
申请人： Naoki Abe , Aurelie C. Lozano
发明人： Naoki Abe , Aurelie C. Lozano
IPC分类号： G06F15/16
CPC分类号： G06N99/005
摘要： Multi-class cost-sensitive boosting based on gradient boosting with “p-norm” cost functionals” uses iterative example weighting schemes derived with respect to cost functionals, and a binary classification algorithm. Weighted sampling is iteratively applied from an expanded data set obtained by enhancing each example in the original data set with as many data points as there are possible labels for any single instance, and where each non-optimally labeled example is given the weight equaling a half times the original misclassification cost for the labeled example times the p−1 norm of the average prediction of the current hypotheses. Each optimally labeled example is given the weight equaling the sum of the weights for all the non-optimally labeled examples for the same instance. Component classification algorithm is executed on a modified binary classification problem. A classifier hypothesis is output, which is the average of all the hypotheses output in the respective iterations.
摘要翻译：基于使用“p范数”成本函数梯度提升的多类成本敏感性提升“使用相对于成本函数导出的迭代示例加权方案和二进制分类算法。通过增加原始数据集中的每个示例获得的扩展数据集，对任何单个实例可能的标签具有尽可能多的数据点，并且每个非最佳标记的示例给出权重等于一半的加权采样乘以标记示例的原始错误分类成本乘以当前假设的平均预测的p-1范数。给出每个最佳标记的例子，其权重等于同一实例的所有非最佳标记的示例的权重之和。对修改的二进制分类问题执行组件分类算法。输出分类器假设，它是各自迭代中输出的所有假设的平均值。

7. 发明授权

US08285581B2 System and method for sequential decision making for customer relationship management 失效
标题翻译：用于客户关系管理的顺序决策系统和方法
公开(公告)号：US08285581B2
公开(公告)日：2012-10-09
申请号：US12140846
申请日：2008-06-17
申请人： Naoki Abe , Edwin P. D. Pednault
发明人： Naoki Abe , Edwin P. D. Pednault
IPC分类号： G06Q10/00
CPC分类号： G06Q30/02 , G06Q10/06375 , G06Q30/0201 , G06Q30/0202 , G06Q30/0204 , G06Q30/0226 , G06Q30/0234 , G06Q30/0239
摘要： A system and method for sequential decision-making for customer relationship management includes providing customer data including stimulus-response history data, and automatically generating actionable rules based on the customer data. Further, automatically generating actionable rules may include estimating a value function using reinforcement learning.
摘要翻译：用于客户关系管理的顺序决策的系统和方法包括提供包括刺激响应历史数据的客户数据，以及基于客户数据自动生成可操作的规则。此外，自动生成可操作规则可以包括使用强化学习估计值函数。

8. 发明授权

US08227238B2 Apparatus for producing pellets containing entrapped and immobilized microorganisms 有权
标题翻译：用于生产包含夹带和固定的微生物的颗粒的装置
公开(公告)号：US08227238B2
公开(公告)日：2012-07-24
申请号：US12382340
申请日：2009-03-13
申请人： Naoki Abe , Koutarou Aoyama , Tatsuo Sumino , Hiroyoshi Emori , Takayuki Kouno
发明人： Naoki Abe , Koutarou Aoyama , Tatsuo Sumino , Hiroyoshi Emori , Takayuki Kouno
IPC分类号： C12M1/00 , C12N11/02 , C12N11/04 , C12N1/04
CPC分类号： C02F3/108 , C02F3/348 , C12N11/04 , C12N11/08 , Y02W10/15
摘要： A large amount of entrapping immobilization pellets with highly stable quality are produced inexpensively by high-speed treatment. There is provided a process for producing entrapping immobilization pellets in which microorganisms are entrapped and immobilized in an immobilizing agent, the process comprising polymerizing a mixture containing the microorganisms and a solution of the immobilizing agent in a forming frame into a gel to prepare a pellet block.
摘要翻译：通过高速处理廉价地生产出大量具有高度稳定质量的捕获固定化丸粒。本发明提供了一种生产包埋固定化小球的方法，其中微生物被捕获并固定在固定剂中，该方法包括将含有微生物的混合物和固定剂溶液在成型框中聚合成凝胶以制备颗粒块。

9. 发明授权

US08006157B2 Resource-light method and apparatus for outlier detection 失效
标题翻译：资源光法和异常检测装置
公开(公告)号：US08006157B2
公开(公告)日：2011-08-23
申请号：US11863704
申请日：2007-09-28
申请人： Naoki Abe , John Langford
发明人： Naoki Abe , John Langford
IPC分类号： H04L1/00 , G06F11/30 , H03M13/00
CPC分类号： G06N99/005 , Y10S707/99936 , Y10S707/99943
摘要： Outlier detection methods and apparatus have light computational resources requirement, especially on the storage requirement, and yet achieve a state-of-the-art predictive performance. The outlier detection problem is first reduced to that of a classification learning problem, and then selective sampling based on uncertainty of prediction is applied to further reduce the amount of data required for data analysis, resulting in enhanced predictive performance. The reduction to classification essentially consists in using the unlabeled normal data as positive examples, and randomly generated synthesized examples as negative examples. Application of selective sampling makes use of an underlying, arbitrary classification learning algorithm, the data labeled by the above procedure, and proceeds iteratively. Each iteration consisting of selection of a smaller sub-sample from the input data, training of the underlying classification algorithm with the selected data, and storing the classifier output by the classification algorithm. The selection is done by essentially choosing examples that are harder to classify with the classifiers obtained in the preceding iterations. The final output hypothesis is a voting function of the classifiers obtained in the iterations of the above procedure.
摘要翻译：异常值检测方法和装置具有较轻的计算资源需求，特别是对存储要求的要求，而且具有最先进的预测性能。异常值检测问题首先降低到分类学习问题，然后应用基于预测不确定度的选择性抽样来进一步减少数据分析所需的数据量，从而提高预测性能。归类分类主要在于使用未标记的正常数据作为正例，随机生成合成实例作为阴性实例。选择性抽样的应用使用了基础的，任意的分类学习算法，由上述过程标记的数据，并且迭代地进行。每个迭代包括从输入数据中选择较小的子样本，对所选数据训练底层分类算法，以及通过分类算法存储分类器输出。选择是通过基本上选择难以对上述迭代中获得的分类器进行分类的示例来完成的。最终输出假设是在上述过程的迭代中获得的分类器的投票函数。

10. 发明授权

US07897042B2 Entrapping immobilization pellets for purifying breeding water, process and apparatus for purifying breeding water, and aquarium set 有权
标题翻译：用于净化繁殖水的包埋固定颗粒，用于净化繁殖水的方法和装置以及水族箱
公开(公告)号：US07897042B2
公开(公告)日：2011-03-01
申请号：US12382740
申请日：2009-03-23
申请人： Shinichi Yoshikawa , Naoki Abe , Kazuichi Isaka
发明人： Shinichi Yoshikawa , Naoki Abe , Kazuichi Isaka
IPC分类号： A01K63/04 , C02F3/08 , C12N11/04 , C12N11/08
CPC分类号： A01K63/045 , A01K63/04 , C02F3/108 , C12N11/08 , Y02W10/15
摘要： Entrapping immobilization pellets for purifying breeding water in an aquarium to breed aquatic animals, wherein the entrapping immobilization pellets have a phosphorus content of 0.05 mass % or less.
摘要翻译：包埋固定化颗粒，用于净化水族箱中的繁殖水以繁殖水生动物，其中所述包埋固定化沉淀物的磷含量为0.05质量％以下。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式