LÓGICA DIFUSA

VolverVolver

Resultados 136 resultados LastUpdate Última actualización 22/02/2020 [15:12:00] pdf PDF

Solicitudes publicadas en los últimos 360 días / Applications published in the last 360 days

Página1 de 6 nextPage   por página


LEARNING SPARSITY-CONSTRAINED GAUSSIAN GRAPHICAL MODELS IN ANOMALY DETECTION

NºPublicación: US2020057956A1 20/02/2020

Solicitante:

IBM [US]

Resumen de: US2020057956A1

A first dependency graph is constructed based on a first data set by solving an objective function constrained with a maximum number of non-zeros and formulated with a regularization term comprising a quadratic penalty to control sparsity. The quadratic penalty in constructing the second dependency graph is determined as a function of the first data set. A second dependency graph is constructed based on a second data set by solving the objective function constrained with the maximum number of non-zeros and formulated with the regularization term comprising a quadratic penalty. The quadratic penalty in constructing the second dependency graph is determined as a function of the first data set and the second data set. An anomaly score is determined for each of a plurality of sensors based on comparing the first dependency graph and the second dependency graph, nodes of which represent sensors.

traducir

SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MACHINE-LEARNING-BASED TRAFFIC PREDICTION

NºPublicación: EP3610226A1 19/02/2020

Solicitante:

VISA INT SERVICE ASS [US]

US_2020033151_A1

Resumen de: WO2019245555A1

Described are a system, method, and computer program product for machine-learning-based traffic prediction. The method includes receiving historic transaction data including a plurality of transactions. The method also includes generating, using a machine-learning classification model, a transportation categorization for at least one consumer. The method further includes receiving at least one message associated with at least one transaction, identifying at least one geographic node of activity in the region, and generating an estimate of traffic intensity for the at least one geographic node of activity. The method further includes comparing the estimate of traffic intensity to a threshold of traffic intensity and, in response to determining that the estimate of traffic intensity satisfies the threshold: generating a communication configured to cause at least one navigation device to modify a navigation route; and communicating the communication to the at least one navigation device.

traducir

一种基于二元联系数的犹豫模糊多属性决策方法

NºPublicación: CN110796255A 14/02/2020

Solicitante:

\u6E56\u5DDE\u5E08\u8303\u5B66\u9662

Resumen de: CN110796255A

本发明提出了一种基于二元联系数的犹豫模糊多属性决策方法,通过把犹豫模糊决策值转换成二元联系数A+Bi,建立基于二元联系数的犹豫模糊多属性决策模型,借助二元联系数中i取不同值作m个方案在犹豫模糊环境下的优劣排序分析,配合二元联系数模的计算确定最优方案,根据不同排序给出不同条件下的决策建议。最终得到更为客观合理的最优备选方案及其他方案的优劣排序。该基于二元联系数的犹豫模糊多属性决策模型具有一定的通用性,不仅能客观确定出犹豫模糊性对m个方案排序影响条件下的最优方案,还能包容同一个犹豫模糊决策问题用其他方法的结果,有利于决策者根据不同的犹豫模糊条件做出针对性决策。

traducir

SYSTEMS AND METHODS FOR PROVIDING FLEXIBLE, MULTI-CAPACITY MODELS FOR USE OF DEEP NEURAL NETWORKS IN MOBILE DEVICES

NºPublicación: WO2020033898A1 13/02/2020

Solicitante:

UNIV MICHIGAN STATE [US]

Resumen de: WO2020033898A1

Systems and methods are disclosed which allow mobile devices, and other resource constrained applications, to more efficiently and effectively utilize deep learning neural networks using only (or primarily) local resources. These systems and methods take the dynamics of runtime resources into account to enable resource-aware, multi-tenant on-device deep learning for artificial intelligence functions for use in tasks like mobile vision systems. The multi-capacity framework enables deep learning models to offer flexible resource-accuracy trade-offs and other similar balancing of performance and resources consumed. At runtime, various systems disclosed herein may dynamically select the optimal resource-accuracy trade-off for each deep learning model to fit the model's resource demand to the system's available runtime resources and the needs of the task being performed by the model. In doing so, systems and methods disclosed herein can efficiently utilize the limited resources in mobile systems to maximize performance of multiple concurrently running neural network-based applications.

traducir

MAPPING DATA SOURCES TO STORAGE DEVICES BASED ON FUZZY LOGIC-BASED CLASSIFICATIONS

NºPublicación: US2020050372A1 13/02/2020

Solicitante:

ENTIT SOFTWARE LLC [US]

Resumen de: US2020050372A1

A technique includes, for each storage device of a plurality of storage devices, applying, by a processor, fuzzy logic to assign the plurality of storage devices to respective storage classes based on the weights that are assigned to the plurality of storage devices. The technique includes assigning, by the processor, weights to attributes of a data source. In response to an operation to backup data of the data source, mapping, by the processor, the data source to a given storage device based on the weights that are assigned to the attributes of the data source and the storage class that is associated with the given storage device.

traducir

Fraud detection system and method

NºPublicación: AU2018301643A1 06/02/2020

Solicitante:

VAIL SYSTEMS INC [US]

WO_2019013974_A1

Resumen de: AU2018301643A1

A system and method for fraud detection for a telephony platform based on an analysis of call detail records (CDRs) that are generated by the telephony platform. The analysis is based on collecting, organizing, transforming, analyzing, and quantifying the CDR data into a plurality of data analytics and data correlations and then applying fuzzy logic to the data analytics to generate a fraud risk rating for each incoming call into the platform.

traducir

一种滚动直线导轨综合性能模糊评价方法

NºPublicación: CN110750940A 04/02/2020

Solicitante:

\u5927\u8FDE\u7406\u5DE5\u5927\u5B66

Resumen de: CN110750940A

本发明公开了一种滚动直线导轨综合性能模糊评价方法。该方法的具体步骤为:建立滚动直线导轨综合性能模糊评价层次结构模型;通过三尺度法建立比较矩阵,由比较矩阵得到层级内各指标的权重系数;进行层级单一排序和总体排序以及一致性检验;利用折中规划法和平均功率法建立滚动直线导轨静态性能、动态性能以及综合性能模糊评价函数;依据评价函数对滚动直线导轨的静、动态性能和综合性能进行评价,得到评价结果。本方法解决了传统静态和动态性能单目标评价以及评价指标的权重系数难以确定的问题,能够合理描述滚动直线导轨的静动综合性能,具有较高的工程实用性。

traducir

一种基于遗传算法的云制造多视角协同调度优化方法

NºPublicación: CN110751292A 04/02/2020

Solicitante:

\u6D59\u6C5F\u8D22\u7ECF\u5927\u5B66

Resumen de: CN110751292A

本发明公开了一种基于遗传算法的云制造多视角协同调度优化方法,用于从用户、制造企业和制造平台三个视角的相关属性优化调度方案,用户的相关属性包括时间、成本和可靠性,制造企业的相关属性包括外包,制造平台的相关属性包括能耗,基于遗传算法的云制造多视角协同调度优化方法,包括:采用三角模糊数表示时间、成本、可靠性和能耗的模糊属性值,以时间、成本、可靠性和能耗的模糊属性值以及外包建立FMILP模型;利用基于区间直觉模糊熵权法的遗传算法求解FMILP模型。本发明从用户、制造企业和制造平台三个视角优化调度方案,并且采用区间直觉模糊熵权法设置FMILP模型的相关参数,考虑了QoS属性权重和任务权重,以得到更优的调度方案。

traducir

一种视角约减的多视角TSK模糊系统

NºPublicación: CN110728369A 24/01/2020

Solicitante:

\u5357\u901A\u5927\u5B66

Resumen de: CN110728369A

本发明公开了一种视角约减的多视角TSK模糊系统,该多视角TSK模糊系统的目标函数包含2个部分,第一部分为协同学习机制,第二部分为视角约减机制,在该模型的目标函数中,引入误差约束项,使得当前视角的决策结果与其他视角决策结果的均值之差最小,从而实现多视角协同学习;另外,引入“变体信息熵”,学习各视角的权重,并设计约减规则,剔除噪声视角或弱相关视角。这对于提高多视角数据的分类精度有着非常重要的作用。

traducir

一种电力二次设备差异化改造方案选择方法

NºPublicación: CN110727912A 24/01/2020

Solicitante:

\u6CB3\u6D77\u5927\u5B66

Resumen de: CN110727912A

本发明公开了一种电力二次设备差异化改造方案选择方法,通过根据二次设备使用历史信息与相关规范和标准构建了包括方案层、准则层和目标层的层次分析结构,随后给出上述各指标的计算模型和量化方法,采用三角直觉模糊数理论,将所有指标模糊化处理;通过定义新的得分函数改进模糊层次分析法,基于模糊数运算法则求取各指标权重,并进行分层排序。本发明基于三角直觉模糊理论进行电力二次设备差异化改造方案选择,相比其他线性评估排序方�x6CD5;,解决了评估过程中存在界定不清的模糊性和统计信息的不完整性问题,同时保留有效信息,降低主观因素的影响,提高变电站进行精准的二次设备差异化技术改造的能力。

traducir

利用模糊聚类的基因网络分析方法

NºPublicación: CN110717541A 21/01/2020

Solicitante:

\u5409\u6797\u5927\u5B66

Resumen de: CN110717541A

本发明提供一种利用模糊聚类的基因网络分析方法,该方法将现有基因网络分析中硬聚类替换为模糊聚类。本发明由于模糊聚类具有簇之间非斥的特点,即对象可以同时属于多个簇,而簇之间可以有交集,这与系统生物学中基因参与多种生物功能子系统的运作的观点很契合,进而使得簇的划分更准确和更符合生物学逻辑,从而达到从生物学角度优化基因网络分析算法的目的。

traducir

METHOD AND SYSTEM FOR MUTING CLASSIFIED INFORMATION FROM AN AUDIO

NºPublicación: US2020020340A1 16/01/2020

Solicitante:

TATA CONSULTANCY SERVICES LTD [IN]

EP_3598444_A1

Resumen de: US2020020340A1

This disclosure relates generally to a method and system for muting of classified information from an audio using a fuzzy approach. The method comprises converting the received audio signal into text using a speech recognition engine to identify a plurality of classified words from the text to obtain a first set of parameters. Further, a plurality of subwords associated with each classified word are identified to obtain a second set of parameters associated with each subword of corresponding classified word. A relative score is computed for each subword associated with the classified word based on a plurality of similar pairs for the corresponding classified word. A fuzzy muting function is generated using the first set of parameters, the second set of parameters and the relative score associated with each subword. The plurality of subwords associated with each classified word is muted in accordance with the generated fuzzy muting function.

traducir

一种非线性模糊逻辑决策算法

NºPublicación: CN110689132A 14/01/2020

Solicitante:

\u53A6\u95E8\u949B\u5C1A\u4EBA\u5DE5\u667A\u80FD\u79D1\u6280\u6709\u9650\u516C\u53F8

Resumen de: CN110689132A

本发明提供一种非线性模糊逻辑决策算法,涉及家居厨房领域。该非线性模糊逻辑决策算法,包括以下步骤:S1:采集移动数据,记录对应时间下的相关参数,统计出关于时间的特征值;S2:将统计的特征值进行分段处理,以时间参数为节点,设置对应的特征区间;S3:将精确量转换为标准论域上的模糊单点集,精确量经对应关系转换为标准论域上的基本元素。通过建立非线性模糊化模型,训练非线性模糊化算法,使得运动模糊决策中能够有相关的有效算法计算出运动员非线性的模糊加速度变化,对模糊值进行推理,决策出精确值之后,得到最终精准量输出,在一定程度上让运动过程分析更加真实有效。

traducir

基于FAHP与规划图融合的Web服务组合方法

NºPublicación: CN110691000A 14/01/2020

Solicitante:

\u5C71\u4E1C\u7406\u5DE5\u5927\u5B66

Resumen de: CN110691000A

本发明涉及Web服务组合技术领域,具体涉及一种基于FAHP与规划图融合的Web服务组合方法。它包括输入用户请求和Web服务存储库中的服务;通过FAHP方法分别计算每个服务的归一化QoS值;执行规划图的向前扩展阶段;根据用户请求执行规划图向后搜索阶段,所述向后搜索阶段包括根据用户需要寻找的每一个目标输出g,在A层中寻找满足最多功能性需求且归一化QoS值最高的服务ws;将服务ws的输入参数作为P层中的目标状态,重复此过程直至到达初始状态层;将得到的该最佳服务组合路径输出。本方法可以匹配出能够实现用户复杂需求的服务组合,也能准确反应候选服务对于用户偏好的综合QoS水平。

traducir

一种基于图像模糊集的多属性决策系统

NºPublicación: CN110674945A 10/01/2020

Solicitante:

\u5B89\u9633\u5E08\u8303\u5B66\u9662

Resumen de: CN110674945A

一种基于图像模糊集的多属性决策系统,包括:获取模块从输入端获取决策矩阵;数据判断模块从所述获取模块中获取所述决策矩阵并对其进行规范化判断;规范化处理模块从所述数据判断模块中获取非规范决策矩阵并进行规范化处理;相对值计算模块计算各个方案的图像模糊相对贴近度;绝对值计算模块计算各个方案的图像模糊绝对贴近度;融合计算模块计算各个方案的图像模糊综合贴近度;决策模块从所述融合计算模块中获取各个方案的图像模糊综合贴近度,并以此对方案进行优劣排序后确定图像模糊综合贴近度最大的方案为最优方案;显示模块从所述决策模块中获取所述最优方案并进行显示。

traducir

一种基于双向投影的图像模糊多属性决策方法

NºPublicación: CN110674946A 10/01/2020

Solicitante:

\u5B89\u9633\u5E08\u8303\u5B66\u9662

Resumen de: CN110674946A

本发明公开了一种基于双向投影的图像模糊多属性决策方法。根据TOPSIS方法,构造基于双向投影的图像模糊相对贴近度公式,在多属性决策问题中,考虑方案和图像模糊绝对正理想解、图像模糊绝对负理想解的关系,构造图像模糊权重绝对正则投影模型,以及基于双向投影的图像模糊绝对贴近度公式。然后,将基于双向投影的图像模糊相对贴近度公式和图像模糊绝对贴近度公式融合并建立图像模糊综合贴近度公式。最后,利用方案的图像模糊综合贴近度数值的大小对方案集进行优劣排序,并确定图像模糊综合贴近度最大的方案为最优方案,实现精准分析和决策。

traducir

一种基于直觉模糊的软件质量评价方法

NºPublicación: CN110659213A 07/01/2020

Solicitante:

\u90D1\u5DDE\u822A\u7A7A\u5DE5\u4E1A\u7BA1\u7406\u5B66\u9662

Resumen de: CN110659213A

本发明涉及一种基于直觉模糊的软件质量评价方法,包括以下步骤:由用户提供待评价软件A,A,L,A,L A构成待评价软件集合A={A,A,L,A,L A};选取合适的软件质量评价指标;由经验丰富的多名专家或使用过这些试用软件的客户对软件做出评价;引入模糊数来表示专家对软件各个属性的评价结果;专家或使用过试用软件的客户对软件质量属性进行评价;采用直觉模糊熵权法确定各个指标的权重;对打分所得的直觉模糊数进行集成运算;计算集成直觉模糊集合的得分进而得出排序;根据得分函数的大小对各个软件进行质量排序。本发明的有益效果是:符合人们犹豫不决的思维,并允许弃权的情况发生。采用客观的直觉模糊熵权法对属性赋权,克服了其他赋权方法的主观性。

traducir

基于模糊层次分析法的电力通信运维安全风险评估的方法

NºPublicación: CN110648072A 03/01/2020

Solicitante:

\u56FD\u7F51\u5B89\u5FBD\u7701\u7535\u529B\u6709\u9650\u516C\u53F8\u4FE1\u606F\u901A\u4FE1\u5206\u516C\u53F8,
\u5357\u4EAC\u5357\u745E\u4FE1\u606F\u901A\u4FE1\u79D1\u6280\u6709\u9650\u516C\u53F8,
\u5357\u4EAC\u534E\u82CF\u79D1\u6280\u6709\u9650\u516C\u53F8

Resumen de: CN110648072A

本发明涉及一种基于模糊层次分析法的电力通信运维安全风险评估的方法,包括以下步骤:(1)建立系统的风险指标体系;(2)确定因素集:根据步骤(1)中根据建立的风险指标体系确定因素集;并根据因素的不同层次,划分处理;(3)模糊权重集的确定:将评价因素按重要程度排序,从而确定因素的模糊权重;(4)评语集的确定:将划分在3~7级的因素汇集并设为评语集;(5)模糊评价矩阵的建立:根据所评因素的数据,确定所评因素的等级,再统计评价结果,得到评价结果统计表;再通过所述评价结果统计表求出各因素不同等级评语的隶属度,然后建立模糊评价矩阵;(6)计算综合评价结果:采用算法计算风险并得出综合评价结果。

traducir

一种超声换能器的输出控制方法及相关设备

NºPublicación: CN110646518A 03/01/2020

Solicitante:

\u676D\u5DDE\u7535\u529B\u8BBE\u5907\u5236\u9020\u6709\u9650\u516C\u53F8,
\u56FD\u7F51\u6D59\u6C5F\u676D\u5DDE\u5E02\u4F59\u676D\u533A\u4F9B\u7535\u6709\u9650\u516C\u53F8,
\u56FD\u7F51\u6D59\u6C5F\u7701\u7535\u529B\u6709\u9650\u516C\u53F8\u676D\u5DDE\u4F9B\u7535\u516C\u53F8

Resumen de: CN110646518A

本申请公开了一种超声换能器的输出控制方法、装置、电子设备及计算机可读存储介质,该输出控制方法包括:获取所述超声换能器在PI控制下的输入数据和输出数据;基于模糊理论,根据所述输入数据和所述输出数据建立所述超声换能器的逆模型;同时启动PI控制以及基于所述逆模型的模糊控制,对所述超声换能器进行输出控制。本申请结合使用了直接逆模型控制与PI控制,并具体是根据超声波换能器的输入数据和输出数据来进行逆系统的参数辨识,建立精确的模糊系统构建逆模型,可有效提高和改善对超声波换能器输出电压的控制精度。

traducir

一种基于改进熵权法的空气质量评价方法

NºPublicación: CN110633449A 31/12/2019

Solicitante:

\u90D1\u5DDE\u822A\u7A7A\u5DE5\u4E1A\u7BA1\u7406\u5B66\u9662

Resumen de: CN110633449A

本发明涉及一种基于改进熵权法的空气质量评价方法,本发明充分考虑各污染物之间的相互作用关系和众多因素相互动态作用的影响,得到的结论更加符合实际;考虑到各因素对整个评价体系的贡献程度不同,本方法基于改进熵权法确定污染因子的权重,传统的熵权法在计算熵值时未考虑各指标熵值趋近于1的情况,本发明运用改进熵权法公式可以避免此类指标权重的成倍变化,且确定权重仅依赖于数据离散性,突出各评价因子的局部差异,通过分析离散程度以及指标信息量客观地确定指标权重,进而突出主要污染物的重要性,充分考虑不同污染物在不同限值下的差异性,从而在一定程度上避免了受专家主观因素的影响,可为制定有效的区域污染控制措施提供理论依据。

traducir

СПОСОБ ПОЛУЧЕНИЯ ЗАКЛЮЧЕНИЯ ОБРАТНОГО НЕЧЕТКОГО ЛОГИЧЕСКОГО ВЫВОДА, СООТВЕТСТВУЮЩЕГО ПОСЫЛКЕ ПРЯМОГО ВЫВОДА

NºPublicación: EA201800355A1 30/12/2019

Solicitante:

\u041E\u0411\u0429\u0415\u0421\u0422\u0412\u041E \u0421 \u041E\u0413\u0420\u0410\u041D\u0418\u0427\u0415\u041D\u041D\u041E\u0419 \u041E\u0422\u0412\u0415\u0422\u0421\u0422\u0412\u0415\u041D\u041D\u041E\u0421\u0422\u042C\u042E \"\u0418\u0422-\u0410\u0413\u0420\u041E\"

一种基于告警大数据信息的电力设备状态评估方法

NºPublicación: CN110619467A 27/12/2019

Solicitante:

\u7535\u5B50\u79D1\u6280\u5927\u5B66

Resumen de: CN110619467A

本发明公开了一种基于告警大数据信息的电力设备状态评估方法,通过电力系统的实际运行情况确定影响设备的因素,然后利用层次分析(AHP)法求取各状态量对设备状态影响大小的组合权重,并进行一致性检验,然后在得到组合权重的基础上,运用模糊综合评价法对设备的状态进行综合分析和评价,得到评估结果。

traducir

SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MACHINE-LEARNING-BASED TRAFFIC PREDICTION

NºPublicación: WO2019245555A1 26/12/2019

Solicitante:

VISA INT SERVICE ASS [US]

US_2020033151_A1

Resumen de: WO2019245555A1

Described are a system, method, and computer program product for machine-learning-based traffic prediction. The method includes receiving historic transaction data including a plurality of transactions. The method also includes generating, using a machine-learning classification model, a transportation categorization for at least one consumer. The method further includes receiving at least one message associated with at least one transaction, identifying at least one geographic node of activity in the region, and generating an estimate of traffic intensity for the at least one geographic node of activity. The method further includes comparing the estimate of traffic intensity to a threshold of traffic intensity and, in response to determining that the estimate of traffic intensity satisfies the threshold: generating a communication configured to cause at least one navigation device to modify a navigation route; and communicating the communication to the at least one navigation device.

traducir

SYSTEMS AND METHODS FOR OPTIMIZED COMPUTER VISION USING DEEP NEURAL NETWORKS AND LIPSCHITZ ANALYSIS

NºPublicación: WO2019241775A1 19/12/2019

Solicitante:

INSURANCE SERVICES OFFICE INC [US]

US_2019385013_PA

Resumen de: WO2019241775A1

Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

traducir

METHOD FOR LARGE-SCALE DISTRIBUTED MACHINE LEARNING USING FORMAL KNOWLEDGE AND TRAINING DATA

Nº publicación: US2019385087A1 19/12/2019

Solicitante:

MARTIN MAROTO FERNANDO [US]

WO_2019143774_PA

Resumen de: US2019385087A1

A method for large-scale distributed machine learning using input data comprising formal knowledge and/or training data. The method consisting of independently calculating discrete algebraic models of the input data in one or many computing devices, and in sharing indecomposable components of the algebraic models among the computing devices without constraints on when or on how many times the sharing needs to happen. The method uses an asynchronous communication among machines or computing threads, each working in the same or related learning tasks. Each computing device improves its algebraic model every time it receives new input data or the sharing from other computing devices, thereby providing a solution to the scaling-up problem of machine learning systems.

traducir

Página1 de 6 nextPage por página

punteroimgVolver