专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US07475047B1 Parallel grouping decomposition for fast training of large-scale support vector machines 有权
标题翻译：用于大规模支持向量机的快速训练的并行分组分解
公开(公告)号：US07475047B1
公开(公告)日：2009-01-06
申请号：US11081983
申请日：2005-03-16
申请人： Aleksey M. Urmanov , Anton A. Bougaev , Kenny C. Gross
发明人： Aleksey M. Urmanov , Anton A. Bougaev , Kenny C. Gross
IPC分类号： G06F15/18
CPC分类号： G06K9/6269 , G06N99/005 , Y10S706/924
摘要： One embodiment of the present invention provides a system that performs parallel grouping decomposition to facilitate expedited training of a support vector machine (SVM). During operation, the system receives a training dataset comprised of data vectors. The system then determines whether any data vector in the dataset violates conditions associated with a current SVM. Next, the system divides the violating data vectors into a number of subsets, thereby allowing parallel SVM training for each subset. The system subsequently builds an independent SVM for each subset in parallel based on the current SVM. The system then constructs a new SVM to replace the current SVM based on the SVMs built for each subset of violating data vectors.
摘要翻译：本发明的一个实施例提供一种执行并行分组分解以促进支持向量机（SVM）的加速训练的系统。在操作期间，系统接收由数据向量组成的训练数据集。然后，系统确定数据集中的任何数据向量是否违反与当前SVM相关联的条件。接下来，系统将违规数据向量划分成多个子集，从而允许每个子集的并行SVM训练。该系统随后基于当前SVM并行构建每个子集的独立SVM。然后，该系统构建新的SVM，以基于针对违规数据向量的每个子集构建的SVM来替换当前SVM。

32. 发明授权

US07447957B1 Dynamic soft-error-rate discrimination via in-situ self-sensing coupled with parity-space detection 有权
标题翻译：通过原位自感耦合奇偶校验空间检测的动态软错误率鉴别
公开(公告)号：US07447957B1
公开(公告)日：2008-11-04
申请号：US11194955
申请日：2005-08-01
申请人： John J. Cooley , Kenny C. Gross , Aleksey M. Urmanov
发明人： John J. Cooley , Kenny C. Gross , Aleksey M. Urmanov
IPC分类号： G11C29/00
CPC分类号： G11C29/56 , G06F11/1012 , G11C29/56008 , G11C2029/0409 , G11C2029/0411
摘要： A system that facilitates distinguishing between soft errors and the onset of hardware degradation in a computer system. During operation, the system receives notifications of correctable-error events from a plurality of memory components. The system then averages numbers of correctable-error events from the plurality of memory components to generate an average number of correctable-error events across the plurality of memory components. The system subtracts the number of correctable-error events for a given memory component in a given time interval from the average number of correctable-error events to generate a residual number of correctable-error events for the given memory component in the given time interval.
摘要翻译：一种有助于区分软错误和计算机系统硬件退化开始的系统。在操作期间，系统从多个存储器组件接收可纠正错误事件的通知。然后，该系统平均来自多个存储器组件的可纠正错误事件的数量，以在多个存储器组件之间生成平均数量的可校正错误事件。该系统在给定的时间间隔内从给定的时间间隔的平均数量减去给定存储器组件的可纠正错误事件的数量，以产生给定存储器组件的残留数量的可校正错误事件。

33. 发明申请

US20080255819A1 High-accuracy virtual sensors for computer systems 有权
标题翻译：用于计算机系统的高精度虚拟传感器
公开(公告)号：US20080255819A1
公开(公告)日：2008-10-16
申请号：US11787604
申请日：2007-04-16
申请人： Kenny C. Gross , John J. Cooley , Aleksey M. Urmanov
发明人： Kenny C. Gross , John J. Cooley , Aleksey M. Urmanov
IPC分类号： G06F17/10 , G06G7/62
CPC分类号： G06F11/008
摘要： Embodiments of the present invention provide a system that estimates the value of a virtual sensor. The system first samples values for performance metrics using external sensors that are coupled to a system and internal sensors that are built into the system. Next, the system generates an inferential sensing model for the system from the sampled values. Then, during operation, the system samples values of performance metrics using the internal sensors and uses the inferential sensing model and the sampled values from the internal sensors to estimate the values of performance metrics for removed external sensors (i.e., virtual sensors).
摘要翻译：本发明的实施例提供一种估计虚拟传感器的值的系统。系统首先使用耦合到系统的外部传感器和内置于系统中的内部传感器对性能指标进行采样。接下来，系统从采样值生成用于系统的推理感知模型。然后，在运行期间，系统使用内部传感器对性能指标值进行采样，并使用推理感应模型和来自内部传感器的采样值来估计去除的外部传感器（即虚拟传感器）的性能指标值。

34. 发明申请

US20080228462A1 Generating synthetic workloads to measure power utilization in a computer system 有权
标题翻译：生成综合工作负载以测量计算机系统中的功率利用率
公开(公告)号：US20080228462A1
公开(公告)日：2008-09-18
申请号：US11725006
申请日：2007-03-15
申请人： Kenny C. Gross , Ramakrishna C. Dhanekula , Kalyanaraman Vaidyanathan
发明人： Kenny C. Gross , Ramakrishna C. Dhanekula , Kalyanaraman Vaidyanathan
IPC分类号： G06F9/45 , G06F11/30
CPC分类号： G06F11/30 , G01R21/133 , G06F11/3414 , Y02D10/34
摘要： One embodiment of the present invention provides a system that generates a synthetic workload to test power utilization in a computer system. During operation, the system monitors power utilization of a reference computer system while the reference computer system executes a workload-of interest, wherein the monitoring process produces a power profile. Next, the system determines characteristics of the workload-of-interest from the power profile. Finally, the system uses the determined characteristics to construct the synthetic workload, wherein the synthetic workload has similar power utilization to the workload-of-interest.
摘要翻译：本发明的一个实施例提供一种生成综合工作量以测试计算机系统中的功率利用的系统。在操作期间，系统监视参考计算机系统的功率利用，同时参考计算机系统执行感兴趣的工作负荷，其中监视过程产生功率分布。接下来，系统从功率分布确定感兴趣的工作负荷的特性。最后，系统使用确定的特征来构建合成工作负载，其中合成工作负载具有与利益的工作量相似的功率利用率。

35. 发明授权

US07391835B1 Optimizing synchronization between monitored computer system signals 有权
标题翻译：优化监控的计算机系统信号之间的同步
公开(公告)号：US07391835B1
公开(公告)日：2008-06-24
申请号：US10955195
申请日：2004-09-29
申请人： Kenny C. Gross , Yujuan Bao
发明人： Kenny C. Gross , Yujuan Bao
IPC分类号： H04L7/00
CPC分类号： G06F11/2294
摘要： One embodiment of the present invention provides a system that optimizes synchronization between monitored signals in a computer system. During operation, the system receives a number of monitored signals. The system then forms a number of signal pairs by grouping each signal with every other signal. Next, the system optimizes synchronization between the signals by iteratively perturbing the timing of each signal in an attempt to increase the value of an objective function which reflects the overall synchronization between all the signals.
摘要翻译：本发明的一个实施例提供了一种优化计算机系统中监视的信号之间的同步的系统。在操作期间，系统接收到多个监视信号。然后，系统通过将每个信号与每个其他信号分组来形成多个信号对。接下来，系统通过迭代地扰乱每个信号的定时来优化信号之间的同步，以试图增加反映所有信号之间的整体同步的目标函数的值。

36. 发明授权

US07349823B2 Using a genetic technique to optimize a regression model used for proactive fault monitoring 有权
标题翻译：使用遗传技术优化用于主动故障监测的回归模型
公开(公告)号：US07349823B2
公开(公告)日：2008-03-25
申请号：US11359672
申请日：2006-02-22
申请人： Keith A. Whisnant , Ramakrishna C. Dhanekula , Kenny C. Gross
发明人： Keith A. Whisnant , Ramakrishna C. Dhanekula , Kenny C. Gross
IPC分类号： G06F11/00
CPC分类号： G06F11/0751 , G06F11/0748
摘要： Embodiments of the present invention provides a system that optimizes a regression model which predicts a signal as a function of a set of available signals. These embodiments use a genetic technique to optimize the regression model, which involves using a portion of the sample signals used to generate each parent regression model from a pair of best-fit parent regression models to generate a child regression model. In addition, in embodiments of the present invention, the system introduces “mutations” to the set of sample signals used to create the child regression model in an attempt to create more robust child regression models during the optimization process.
摘要翻译：本发明的实施例提供了一种优化回归模型的系统，该回归模型预测作为一组可用信号的函数的信号。这些实施例使用遗传技术来优化回归模型，其包括使用用于从一对最佳拟合父回归模型生成每个父回归模型的样本信号的一部分以生成子回归模型。此外，在本发明的实施例中，系统将“突变”引入用于创建儿童回归模型的样本信号集合，以在优化过程中创建更健壮的儿童回归模型。

37. 发明授权

US07330325B2 Proactive fault monitoring of disk drives through phase-sensitive surveillance 有权
标题翻译：通过相位敏感监控对磁盘驱动器进行主动故障监控
公开(公告)号：US07330325B2
公开(公告)日：2008-02-12
申请号：US11452702
申请日：2006-06-13
申请人： Dan Vacar , David K. McElfresh , Kenny C. Gross , Aleksey M. Urmanov
发明人： Dan Vacar , David K. McElfresh , Kenny C. Gross , Aleksey M. Urmanov
IPC分类号： G11B19/02
CPC分类号： G11B19/048
摘要： One embodiment of the present invention provides a system that proactively monitors a disk drive to detect an impending disk drive failure. During operation, the system obtains a time-varying electrical signal which is generated by the spindle rotation during operation of the disk drive. Next, the system extracts one or more inferential parameters associated with the spindle rotation from the time-varying electrical signal using a phase-sensitive detection. The system then performs proactive fault detection on the inferential parameters to detect an impending failure of the disk drive.
摘要翻译：本发明的一个实施例提供了一种主动监视磁盘驱动器以检测即将发生的磁盘驱动器故障的系统。在操作期间，系统获得在磁盘驱动器的操作期间由主轴旋转产生的时变电信号。接下来，系统使用相敏检测从时变电信号中提取与主轴旋转相关联的一个或多个推理参数。然后，系统对推理参数执行主动故障检测，以检测即将发生的磁盘驱动器故障。

38. 发明申请

US20080001776A1 Method and apparatus for camouflaging business-activity information in a telemetry signal 有权
标题翻译：在遥测信号中伪装业务活动信息的方法和装置
公开(公告)号：US20080001776A1
公开(公告)日：2008-01-03
申请号：US11471203
申请日：2006-06-20
申请人： Kenny C. Gross , Jon D. Greaves , Keith A. Whisnant
发明人： Kenny C. Gross , Jon D. Greaves , Keith A. Whisnant
IPC分类号： G08C19/16
CPC分类号： H04Q9/00
摘要： One embodiment of the present invention provides a system that camouflages business-activity information in telemetry signals from a computer system. During operation, the system monitors telemetry signals from the computer system to obtain a time series containing a telemetry metric which provides business-activity information. Next, for each telemetry-metric value contained in the time series, the system compares the telemetry-metric value with a predetermined threshold level. If the telemetry-metric value is below the predetermined threshold level, the system then generates artificial activity associated with the telemetry metric in the computer system, so that the artificial activity causes the telemetry-metric value to exceed the predetermined threshold level.
摘要翻译：本发明的一个实施例提供一种从计算机系统伪装遥测信号中的业务活动信息的系统。在操作期间，系统监视来自计算机系统的遥测信号，以获得包含提供业务活动信息的遥测度量的时间序列。接下来，对于包含在时间序列中的每个遥测度量值，系统将遥测度量值与预定阈值水平进行比较。如果遥测度量值低于预定阈值水平，则系统然后产生与计算机系统中的遥测度量相关联的人为活动，使得人为活动导致遥测度量值超过预定阈值水平。

39. 发明申请

US20070291390A1 Dynamically controlling a temperature profile in a disk drive for a temperature-dependent reliability study 有权
标题翻译：动态控制磁盘驱动器中的温度曲线，以进行温度依赖性可靠性研究
公开(公告)号：US20070291390A1
公开(公告)日：2007-12-20
申请号：US11471206
申请日：2006-06-20
申请人： Kalyanaraman Vaidyanathan , Kenny C. Gross , Roger E. Blythe
发明人： Kalyanaraman Vaidyanathan , Kenny C. Gross , Roger E. Blythe
IPC分类号： G11B5/09 , G11B19/02 , G11B21/02
CPC分类号： G11B5/455 , G11B5/4555 , G11B19/048
摘要： One embodiment of the present invention provides a system that dynamically controls a temperature profile within a disk drive by generating disk drive activity. During operation, the system first receives a desired temperature profile. Next, the system generates a load profile based on the desired temperature profile, wherein the load profile specifies read/write operations on the disk drive. The system then applies the load profile to the disk drive to generate disk drive activity, wherein the disk activity causes the temperature in the disk drive to track the desired temperature profile.
摘要翻译：本发明的一个实施例提供了一种系统，其通过产生磁盘驱动器活动来动态地控制磁盘驱动器内的温度分布。在操作期间，系统首先接收所需的温度曲线。接下来，系统基于期望的温度曲线生成负载曲线，其中负载曲线指定对盘驱动器的读/写操作。然后，系统将负载配置文件应用于磁盘驱动器以生成磁盘驱动器活动，其中磁盘活动导致磁盘驱动器中的温度跟踪所需的温度曲线。

40. 发明授权

US07296132B1 Method and apparatus for storing performance parameters in a limited storage space 有权
标题翻译：用于在有限的存储空间中存储性能参数的方法和装置
公开(公告)号：US07296132B1
公开(公告)日：2007-11-13
申请号：US11598607
申请日：2006-11-13
申请人： Kenny C. Gross , Keith A. Whisnant , Aleksey M. Urmanov
发明人： Kenny C. Gross , Keith A. Whisnant , Aleksey M. Urmanov
IPC分类号： G06F12/00 , G06F7/00 , G06F13/00
CPC分类号： G06F11/3476 , Y10S707/99942
摘要： A system that records performance parameters from a computer system. During operation, the system periodically monitors performance parameters from the computer system and records the monitored performance parameters in a first storage space. Next, the system recurrently compresses the recorded performance parameters. This involves: (1) compressing the recorded performance parameters from the first storage space; (2) if insufficient space is available in a second storage space which is used to store compressed performance parameters, further compressing data in the second storage space to make room for the compressed performance parameters from the first storage space; and (3) storing the compressed performance parameters from the first storage space in the second storage space.
摘要翻译：从计算机系统记录性能参数的系统。在操作期间，系统定期监视来自计算机系统的性能参数，并将监视的性能参数记录在第一存储空间中。接下来，系统重复地压缩记录的性能参数。这涉及：（1）从第一存储空间压缩记录的性能参数; （2）如果在用于存储压缩性能参数的第二存储空间中没有足够的空间可用，则进一步压缩第二存储空间中的数据以为来自第一存储空间的压缩性能参数腾出空间; 以及（3）将来自第一存储空间的压缩性能参数存储在第二存储空间中。

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