会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 6. 发明申请
    • Spot finding algorithm using image recognition software
    • 使用图像识别软件的现货发现算法
    • US20050008212A1
    • 2005-01-13
    • US10822035
    • 2004-04-08
    • William EwingDuane DeSienoRhett Affleck
    • William EwingDuane DeSienoRhett Affleck
    • G01N31/00G06F20060101G06K9/00G06T7/00
    • G06T7/75G06T2207/30004
    • A plurality of samples are tested for their ability to enhance or inhibit a biological process in a multiplexed diffusive assay. The assay is imaged after the biological process has produced spots in a medium that indicate the tested enhancing or inhibiting ability of the samples. The image containing the resulting spots are evaluated to determine which samples caused the spots to form. The location of spots are identified by user selection or through a gradient triangulation technique that determines spot locations by analyzing the slope of pixel intensities in numerous subimages. The spots may also be analyzed by parametrically modeling the spots and comparing the spot characteristics in the image to a spot function, to determine the location of hit spots in the image. The hit spot locations, corresponding to the location of tested samples in the assay that enhanced or inhibited the biological process, are output to facilitate further analysis of the test samples.
    • 测试多个样品在多重扩散测定中增强或抑制生物过程的能力。 在生物学过程在培养基中产生指示样品的增强或抑制能力的斑点之后,测定成像。 评估含有所得斑点的图像,以确定哪些样品导致斑点形成。 斑点的位置通过用户选择或通过梯度三角测量技术来识别,其通过分析许多子图像中像素强度的斜率来确定点位置。 也可以通过对斑点进行参数建模和将图像中的斑点特征与斑点函数进行比较来分析斑点,以确定图像中命中点的位置。 输出对应于增强或抑制生物过程的测定中测试样品的位置的命中点位置,以便于进一步分析测试样品。
    • 7. 发明授权
    • Method for selecting medical and biochemical diagnostic tests using neural network-related applications
    • 使用神经网络相关应用程序选择医学和生化诊断测试的方法
    • US06678669B2
    • 2004-01-13
    • US08912133
    • 1997-08-14
    • Jerome LapointeDuane DeSieno
    • Jerome LapointeDuane DeSieno
    • G06N302
    • G16H50/20G06F19/00G16H10/20G16H10/60G16H15/00G16H50/70
    • Methods are provided for developing medical diagnostic tests using decision-support systems, such as neural networks. Patient data or information, typically patient history or clinical data, are analyzed by the decision-support systems to identify important or relevant variables and decision-support systems are trained on the patient data. Patient data are augmented by biochemical test data, or results, where available, to refine performance. The resulting decision-support systems are employed to evaluate specific observation values and test results, to guide the development of biochemical or other diagnostic tests, too assess a course of treatment, to identify new diagnostic tests and disease markers, to identify useful therapies, and to provide the decision-support functionality for the test. Methods for identification of important input variables for a medical diagnostic tests for use in training the decision-support systems to guide the development of the tests, for improving the sensitivity and specificity of such tests, and for selecting diagnostic tests that improve overall diagnosis of, or potential for, a disease state and that permit the effectiveness of a selected therapeutic protocol to be assessed are provided. The methods for identification can be applied in any field in which statistics are used to determine outcomes. A method for evaluating the effectiveness of any given diagnostic test is also provided.
    • 提供了使用决策支持系统(如神经网络)开发医疗诊断测试的方法。 患者数据或信息(通常为患者病史或临床数据)由决策支持系统进行分析,以确定重要或相关变量,并对患者数据进行培训。 患者数据通过生物化学测试数据或结果(如果可用)来增强,以提高性能。 由此产生的决策支持系统用于评估具体的观察值和测试结果,指导生物化学或其他诊断测试的开发,同时评估治疗过程,确定新的诊断测试和疾病标志物,以确定有用的治疗方法,以及 为测试提供决策支持功能。 识别用于培训决策支持系统的医学诊断测试的重要输入变量的方法,以指导测试的开发,用于提高这些测试的灵敏度和特异性,以及选择改善整体诊断的诊断测试, 或潜在的疾病状态,并且允许评估所选择的治疗方案的有效性。 识别方法可以应用于统计学用于确定结果的任何领域。 还提供了用于评估任何给定诊断测试的有效性的方法。
    • 8. 发明授权
    • Detecting, classifying, and tracking abnormal data in a data stream
    • 检测,分类和跟踪数据流中的异常数据
    • US08306931B1
    • 2012-11-06
    • US12462634
    • 2009-08-06
    • Christopher BowmanDuane DeSieno
    • Christopher BowmanDuane DeSieno
    • G06E1/00G06E3/00G06F15/18G06G7/00G06N3/04
    • G06N3/0454
    • The present invention extends to methods, systems, and computer program products for detecting, classifying, and tracking abnormal data in a data stream. Embodiments include an integrated set of algorithms that enable an analyst to detect, characterize, and track abnormalities in real-time data streams based upon historical data labeled as predominantly normal or abnormal. Embodiments of the invention can detect, identify relevant historical contextual similarity, and fuse unexpected and unknown abnormal signatures with other possibly related sensor and source information. The number, size, and connections of the neural networks all automatically adapted to the data. Further, adaption appropriately and automatically integrates unknown and known abnormal signature training within one neural network architecture solution automatically. Algorithms and neural networks architecture are data driven, resulting more affordable processing. Expert knowledge can be incorporated to enhance the process, but sufficient performance is achievable without any system domain or neural networks expertise.
    • 本发明扩展到用于检测,分类和跟踪数据流中的异常数据的方法,系统和计算机程序产品。 实施例包括使得分析者能够基于标记为主要正常或异常的历史数据来检测,表征和跟踪实时数据流中的异常的集成算法。 本发明的实施例可以检测,识别相关的历史背景相似性,并且将意外和未知的异常签名与其他可能相关的传感器和源信息融合。 神经网络的数量,大小和连接都自动适应数据。 此外,自适应适应并自动将未知和已知的异常签名训练集成在一个神经网络架构解决方案中。 算法和神经网络架构是数据驱动的,从而实现更加实惠的处理。 可以结合专家知识来增强过程,但是没有任何系统领域或神经网络专长就可以实现足够的性能。
    • 9. 发明授权
    • Graded learning device and method
    • 分级学习设备和方法
    • US4933871A
    • 1990-06-12
    • US287877
    • 1988-12-21
    • Duane DeSieno
    • Duane DeSieno
    • G06F15/18G05B13/02G06N3/00G06N3/08G06N99/00
    • G06N3/08G05B13/027
    • A graded-learning processing network which grades its performance as it maps the input-output relationship during a training period. At the end of an operation of the Processing Newtork, its performance is graded and network variables are adjusted or amended, and the processing network is operated again and its performance is graded. The order or direction of performance grades (e.g. better or worse) are noted and the adjustments or amendments of the processing network may proceed in the same direction (or opposite direction) depending upon the grading of subsequent performances. This obviates the need for information about a desired response on output performance of the processing network at any given time, and is conducive to efficient learning for improved performance in a processing environment in which the operational parameters are not known.
    • 一个渐进式学习处理网络,在培训期间映射输入 - 输出关系,对其绩效进行评分。 在处理Newtork的操作结束时,其性能分级,网络变量进行调整或修改,处理网络再次运行,其性能等级。 注意性能等级(例如更好或更差)的顺序或方向,并且根据后续性能的分级,处理网络的调整或修改可以沿相同方向(或相反方向)进行。 这消除了在任何给定时间需要关于处理网络的输出性能的期望响应的信息,并且有助于在不知道操作参数的处理环境中改进性能的有效学习。