发明名称 Sparse representation for dynamic sensor networks
摘要 A method, an apparatus and an article of manufacture for evaluating data from a network of sensors. The method includes analyzing data received from at least one sensor using exemplar-based sparse representation processing to create a sparse representation of the data, determining at least one discrete sparse characteristic of an event in the data received from the at least one sensor based on the sparse representation of the data, and evaluating the at least one discrete sparse characteristic of an event in the data to perform at least one task associated with the representation of the event in the data.
申请公布号 US9177215(B2) 申请公布日期 2015.11.03
申请号 US201213443289 申请日期 2012.04.10
申请人 International Business Machines Corporation 发明人 Ferre Wilfredo;Kanevsky Dimitri;Sainath Tara N.;Yvon Marc
分类号 G06F11/00;G06K9/00;G01N33/00;G06K9/62 主分类号 G06F11/00
代理机构 Ryan, Mason & Lewis, LLP 代理人 Ryan, Mason & Lewis, LLP
主权项 1. A method for evaluating data from a network of sensors, wherein the method comprises: capturing data from multiple physical sensors in the network of sensors, wherein said data comprises carbon dioxide-related data, and wherein said capturing comprises establishing a communicative link between the multiple physical sensors and a network sensor management module executing on a hardware processor of a computing device; analyzing the data received from the multiple physical sensors using exemplar-based sparse representation processing representing multiple categories of possible events to create a sparse representation of the data, wherein said analyzing comprises selecting a subset of at least one category from the multiple categories that represents the data received from the multiple physical sensors, and wherein said analyzing is carried out by a network data processing module, executing on the hardware processor of the computing device and communicatively linked to the network sensor management module; determining at least one discrete sparse characteristic of an event in the data received from the multiple physical sensors based on the sparse representation of the data; classifying the data into one of multiple event classifications based on evaluation of the at least one discrete sparse characteristic of an event in the data; and performing at least one task associated with the representation of the event in the data based on said classifying; wherein (i) said determining, (ii) said classifying, and (iii) said performing are carried out by a decision maker module, executing on the hardware processor of the computing device and communicatively linked to the network sensor management module and the network data processing module.
地址 Armonk NY US