Adaptable radiation monitoring system and method
    1.
    发明授权
    Adaptable radiation monitoring system and method 有权
    适应性辐射监测系统及方法

    公开(公告)号:US07064336B2

    公开(公告)日:2006-06-20

    申请号:US10874127

    申请日:2004-06-21

    IPC分类号: G01T1/24 G01J1/00

    摘要: A portable radioactive-material detection system capable of detecting radioactive sources moving at high speeds. The system has at least one radiation detector capable of detecting gamma-radiation and coupled to an MCA capable of collecting spectral data in very small time bins of less than about 150 msec. A computer processor is connected to the MCA for determining from the spectral data if a triggering event has occurred. Spectral data is stored on a data storage device, and a power source supplies power to the detection system. Various configurations of the detection system may be adaptably arranged for various radiation detection scenarios. In a preferred embodiment, the computer processor operates as a server which receives spectral data from other networked detection systems, and communicates the collected data to a central data reporting system.

    摘要翻译: 一种便携式放射性物质检测系统,能够检测高速运动的放射源。 该系统具有至少一个能够检测伽马辐射并耦合到能够在小于约150毫秒的非常小的时间段中收集光谱数据的MCA的辐射检测器。 计算机处理器连接到MCA,用于根据光谱数据确定是否发生触发事件。 光谱数据存储在数据存储设备上,电源向检测系统供电。 检测系统的各种配置可以适用于各种辐射检测场景。 在优选实施例中,计算机处理器作为从其他联网检测系统接收频谱数据并将收集的数据传送到中央数据报告系统的服务器。

    Discriminant Forest Classification Method and System
    3.
    发明申请
    Discriminant Forest Classification Method and System 有权
    判别森林分类方法与系统

    公开(公告)号:US20090281981A1

    公开(公告)日:2009-11-12

    申请号:US12436667

    申请日:2009-05-06

    IPC分类号: G06N7/02

    CPC分类号: G06K9/6282 G06N99/005

    摘要: A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

    摘要翻译: 混合机器学习方法和分类系统,将经典随机森林(RF)方法与判别分析(DA)技术相结合,提供增强的分类能力。 使用使用对象的特征测量来预测其类成员资格(例如线性判别分析(LDA)或者安徒生 - 巴多尔线性判别技术(AB))的DA技术来分割每个分类树中的每个节点上的数据 培育和种植树木和森林。 当训练完成时,产生一组基于判别式森林的基于DA的决策树,用于预测未知类别的新样本的分类。

    Actively driven thermal radiation shield
    4.
    发明授权
    Actively driven thermal radiation shield 失效
    积极驱动的热辐射屏蔽

    公开(公告)号:US06396061B1

    公开(公告)日:2002-05-28

    申请号:US09406913

    申请日:1999-09-24

    IPC分类号: G12B1500

    CPC分类号: G01J5/061

    摘要: A thermal radiation shield for cooled portable gamma-ray spectrometers. The thermal radiation shield is located intermediate the vacuum enclosure and detector enclosure, is actively driven, and is useful in reducing the heat load to mechanical cooler and additionally extends the lifetime of the mechanical cooler. The thermal shield is electrically-powered and is particularly useful for portable solid-state gamma-ray detectors or spectrometers that dramatically reduces the cooling power requirements. For example, the operating shield at 260K (40K below room temperature) will decrease the thermal radiation load to the detector by 50%, which makes possible portable battery operation for a mechanically cooled Ge spectrometer.

    摘要翻译: 用于冷却便携式γ射线光谱仪的热辐射屏蔽。 热辐射屏蔽位于真空外壳和检测器外壳的中间,被主动驱动,并且可用于减少机械冷却器的热负荷,并且还可延长机械冷却器的使用寿命。 热屏蔽是电动的,对于便携式固态γ射线检测器或光谱仪特别有用,可显着降低冷却功率要求。 例如,260K(40K低于室温)的操作屏蔽将使检测器的热辐射负载降低50%,这使得机械冷却Ge光谱仪的便携式电池运行成为可能。

    Discriminant forest classification method and system
    5.
    发明授权
    Discriminant forest classification method and system 有权
    判别森林分类方法和系统

    公开(公告)号:US08306942B2

    公开(公告)日:2012-11-06

    申请号:US12436667

    申请日:2009-05-06

    IPC分类号: G06F15/00 G06F15/18

    CPC分类号: G06K9/6282 G06N99/005

    摘要: A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

    摘要翻译: 混合机器学习方法和分类系统,将经典随机森林(RF)方法与判别分析(DA)技术相结合,提供增强的分类能力。 使用使用对象的特征测量来预测其类成员资格(例如线性判别分析(LDA)或者安徒生 - 巴多尔线性判别技术(AB))的DA技术来分割每个分类树中的每个节点上的数据 培育和种植树木和森林。 当训练完成时,产生一组基于判别式森林的基于DA的决策树,用于预测未知类别的新样本的分类。