公开(公告)号：US20060173923A1

公开(公告)日：2006-08-03

申请号：US11235336

申请日：2005-09-27

申请人： Naoki Abe

发明人： Naoki Abe

IPC分类号： G06F17/30

CPC分类号： G06F3/0643 ,  G06F3/0619 ,  G06F3/0676 ,  G06F3/0679

摘要： The file information write processing method according to the present invention is a file information write processing method wherein a computer executes a process for outputting instruction corresponding to a file information write instruction from an application to a device driver, wherein: searching clusters which are empty areas within an actual data area of a memory unit of the computer, and obtaining the search result; if clusters which are empty areas exist, writing information to overwrite to one or more clusters within the actual data area of the memory unit which is a target of the write instruction from the application, to the clusters which are empty areas; and freeing clusters which were to be overwritten by the information written to the empty area clusters.

公开(公告)号：US06973446B2

公开(公告)日：2005-12-06

申请号：US09730616

申请日：2000-12-06

申请人： Hiroshi Mamitsuka ,  Naoki Abe

发明人： Hiroshi Mamitsuka ,  Naoki Abe

IPC分类号： G06N99/00 ,  G06F9/44 ,  G06N5/02 ,  G06N5/04 ,  G06F15/18 ,  G06F17/30

CPC分类号： G06N5/025 ,  G06F2216/03

摘要： A general-purpose knowledge finding method for efficient knowledge finding by selectively sampling only data in large information amounts from a database. Learning means 104 causes a lower-order learning algorithm, inputted via an input unit 107, to perform learning on plural partial samples generated by sampling from data stored in a high-speed main memory 120, to obtain plural hypotheses. Data selection means 105 uses the hypotheses to estimate information amounts of respective candidate data read from a large-capacity data storage device 130, and additionally stores only data in large information amounts into the high-speed main memory 120. A control unit 106 repeats the processing a predetermined number of times, and stores obtained final hypotheses. A prediction unit 102 predicts a label value of unknown-labeled data inputted into the input unit 107 by the final hypotheses, and an output unit 101 outputs the predicted value.

摘要翻译： 通过有选择地只从数据库中抽取大量信息中的数据来高效地进行知识发现的通用知识发现方法。 学习装置104使得经由输入单元107输入的低阶学习算法通过从存储在高速主存储器120中的数据进行采样而产生的多个部分样本执行学习，以获得多个假设。 数据选择装置105使用假设来估计从大容量数据存储装置130读取的各个候选数据的信息量，并且仅将大量信息量的数据仅存储到高速主存储器120中。 控制单元106重复处理预定次数，并存储获得的最终假设。 预测单元102通过最终假设来预测输入到输入单元107的未知标签数据的标签值，并且输出单元101输出预测值。

公开(公告)号：US5587060A

公开(公告)日：1996-12-24

申请号：US527206

申请日：1995-09-12

申请人： Naoki Abe ,  Koji Mizuno ,  Masayuki Sumiyoshi ,  Katsuya Murakami ,  Kojiro Murayama ,  Koichi Sugiura ,  Fumio Kawahara ,  Mitsuru Tomono ,  Heijiro Ojima

发明人： Naoki Abe ,  Koji Mizuno ,  Masayuki Sumiyoshi ,  Katsuya Murakami ,  Kojiro Murayama ,  Koichi Sugiura ,  Fumio Kawahara ,  Mitsuru Tomono ,  Heijiro Ojima

IPC分类号： B01D21/01 ,  B01D17/06 ,  B01D21/00 ,  B01D21/28 ,  B01F17/00 ,  B01F17/22 ,  B01F17/38 ,  B01F17/42 ,  B03C5/00 ,  B03C5/02 ,  C02F1/465 ,  C02F1/48 ,  C02F1/68 ,  C02F9/00 ,  C09K3/00 ,  C22B3/02 ,  C22B3/20 ,  C22B3/44

CPC分类号： B01D21/283 ,  B01D17/06 ,  B01D21/0009 ,  B01D21/0018 ,  B01D21/01 ,  B01D21/2433 ,  B01F17/0042 ,  B01F17/0057 ,  C02F1/465 ,  C02F1/487 ,  C02F1/547 ,  C02F1/683 ,  C02F9/00 ,  C22B3/02 ,  C22B3/205 ,  C22B3/44 ,  C02F2101/20 ,  C02F2305/04 ,  Y02P10/234 ,  Y10S204/13

摘要： Disclosed herein is a technique of removing metal contained in a solution through chelation, which makes it possible to preclude undesired aggregation and permit effective aggregation through an aggregating process. A surface active agent containing a hydrophobic group, a hydrophilic group and a chelating group is added to the solution to be processed, and subsequently an aggregating process is carried out. The chelating group chelates metal, the hydrophilic group prevents undesired aggregation, and the hydrophobic group is effectively aggregated in the aggregating process. Various uses are possible by selecting the charge of ligand.

摘要翻译： 本文公开了通过螯合除去溶液中所含金属的技术，这使得可以排除不期望的聚集并允许通过聚集过程的有效聚集。 将含有疏水基团，亲水基团和螯合基团的表面活性剂加入待处理的溶液中，随后进行聚集过程。 螯合基团螯合金属，亲水基团防止不希望的聚集，并且疏水基团在聚集过程中有效聚集。 可以通过选择配体的电荷来进行各种用途。

公开(公告)号：US08468290B2

公开(公告)日：2013-06-18

申请号：US12212439

申请日：2008-09-17

申请人： Naoki Abe

发明人： Naoki Abe

IPC分类号： G06F17/30

CPC分类号： G06F3/0643 ,  G06F3/0619 ,  G06F3/0676 ,  G06F3/0679

摘要： The file information write processing method according to the present invention is a file information write processing method wherein a computer executes a process for outputting instruction corresponding to a file information write instruction from an application to a device driver, wherein: searching clusters which are empty areas within an actual data area of a memory unit of the computer, and obtaining the search result; if clusters which are empty areas exist, writing information to overwrite to one or more clusters within the actual data area of the memory unit which is a target of the write instruction from the application, to the clusters which are empty areas; and freeing clusters which were to be overwritten by the information written to the empty area clusters.

摘要翻译： 根据本发明的文件信息写入处理方法是文件信息写入处理方法，其中计算机执行用于将与文件信息写入指令相对应的指令从应用程序输出到设备驱动程序的处理，其中：搜索作为空区域的群集 在计算机的存储器单元的实际数据区域内，并获得搜索结果; 如果存在作为空区域的簇，则写入信息以覆盖作为来自应用的写指令的目标的存储器单元的实际数据区域内的一个或多个簇到作为空区域的簇; 并释放被写入空区域的信息覆盖的簇。

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。

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。

公开(公告)号：US07978987B2

公开(公告)日：2011-07-12

申请号：US12211889

申请日：2008-09-17

申请人： Naoki Abe

发明人： Naoki Abe

IPC分类号： G03G15/00

CPC分类号： G03G15/5008 ,  G03G15/0189 ,  G03G15/0194 ,  G03G2215/0141 ,  G03G2215/0158

摘要： In an image forming apparatus, an image forming portion forms an image on a rotator. A storage portion stores change characteristics information relevant to correction parameters corresponding to phase points of the rotator. A designating portion sequentially designates the correction parameters based on the change characteristics information. A correcting portion corrects an image forming position on the rotator based on the correction parameter designated by the designating portion. When it is determined, based on a detecting phase point of the rotator detected by a detecting portion, that the current phase of the rotator corresponds to a gradual phase point at which the correction parameter changes at a rate equal to or lower than a predetermined value, the designation by said designating portion is shifted to the correction parameter corresponding to the gradual phase point.

摘要翻译： 在图像形成装置中，图像形成部在旋转体上形成图像。 存储部存储与对应于旋转体的相位点的校正参数相关的变化特性信息。 指定部分根据变化特征信息依次指定校正参数。 校正部根据由指定部指定的校正参数来校正旋转体上的图像形成位置。 当基于由检测部检测到的旋转体的检测相位点确定旋转器的当前相位对应于校正参数以等于或低于预定值的速率变化的逐渐相位点时 ，所述指定部分的指定被移动到对应于逐渐相位点的校正参数。

公开(公告)号：US07847810B2

公开(公告)日：2010-12-07

申请号：US12401868

申请日：2009-03-11

申请人： Naoki Abe

发明人： Naoki Abe

IPC分类号： B41J2/385

CPC分类号： H04N1/0473 ,  G03G15/0194 ,  G03G15/043 ,  G03G2215/0158 ,  H04N2201/04748 ,  H04N2201/04767

摘要： An image forming apparatus is provided. A second photoconductor is disposed at a downstream side of a first photoconductor in a moving direction of a medium. First and second exposure units form first and second electrostatic latent images on the first and second photoconductors line by line at first and second exposure timing intervals in first and second exposure enabling time periods based on successive lines of first and second image data, respectively. A correction unit corrects at least one of the first and second exposure timing intervals. A change unit changes the second exposure enabling time period so as to suppress a difference between the number of the successive lines of the first image data and the number of the successive lines of the second image data.

摘要翻译： 提供一种图像形成装置。 第二感光体在介质的移动方向上设置在第一感光体的下游侧。 第一和第二曝光单元分别基于第一和第二图像数据的连续行，分别在第一和第二曝光允许时间段中的第一和第二曝光时间间隔上逐行地在第一和第二光电导体上形成第一和第二静电潜像。 校正单元校正第一和第二曝光定时间隔中的至少一个。 改变单元改变第二曝光使能时间段，以便抑制第一图像数据的连续行数与第二图像数据的连续行数之间的差异。

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。

公开(公告)号：US07561158B2

公开(公告)日：2009-07-14

申请号：US11329437

申请日：2006-01-11

申请人： Naoki Abe ,  Edwin Peter Dawson Pednault ,  Fateh Ali Tipu

发明人： Naoki Abe ,  Edwin Peter Dawson Pednault ,  Fateh Ali Tipu

IPC分类号： G06T11/20

CPC分类号： G06T11/206

摘要： Feature importance information available in a predictive model with correlation information among the variables is presented to facilitate more flexible choices of actions by business managers. The displayed feature importance information combines feature importance information available in a predictive model with correlational information among the variables. The displayed feature importance information may be presented as a network structure among the variables as a graph, and regression coefficients of the variables indicated on the corresponding nodes in the graph. To generate the display, a regression engine is called on a set of training data that outputs importance measures for the explanatory variables for predicting the target variable. A graphical model structural learning module is called that outputs a graph on the explanatory variables of the above regression problem representing the correlational structure among them. The feature importance measure, output by the regression engine, is displayed for each node in the graph, as an attribute, such as color, size, texture, etc, of that node in the graph output by the graphical model structural learning module.

摘要翻译： 提供了具有变量之间相关性信息的预测模型中的特征重要度信息，以便企业管理者更灵活地选择行动。 显示的特征重要性信息将预测模型中可用的特征重要性信息与变量之间的相关信息相结合。 所显示的特征重要性信息可以作为图形中的变量之间的网络结构呈现，并且在图中的相应节点上指示的变量的回归系数。 为了生成显示，在一组训练数据上调用回归引擎，该训练数据输出用于预测目标变量的解释变量的重要度量。 一个图形模型结构学习模块被称为输出上述回归问题的解释变量的图表，表示它们之间的相关性结构。 由图形模型结构学习模块输出的图形中的该节点的颜色，大小，纹理等属性显示图形中每个节点的回归引擎输出的特征重要性度量。