Separated application security management

Abstract

A set of data is identified that includes a plurality of observed values generated by a plurality of sensor devices located in a plurality of different locations. For each of the plurality of observed values, a modality of the value, a spatial location of the value, and a timestamp of the value is determined. Values for one or more missing values in the set of data are determined from the modalities, spatial locations, and timestamps of the plurality of observed values.

1 . At least one machine accessible storage medium having code stored thereon, the code when executed on a machine, causes the machine to:
 identify a set of data comprising a plurality of observed values generated by a plurality of sensor devices, wherein the plurality of sensor devices are located in a plurality of different locations;   determine, for each of the plurality of observed values, a modality of the value, a spatial location of the value, and a timestamp of the value; and   determine values for one or more missing values in the set of data from the modalities, spatial locations, and timestamps of the plurality of observed values.   
     
     
         2 . The storage medium of  claim 1 , wherein the plurality of sensor devices comprise sensors of a plurality of different sensor types. 
     
     
         3 . The storage medium of  claim 2 , wherein the plurality of observed values comprise values of a plurality of different value types, and each of the sensor types corresponds to at least a respective one of the value types. 
     
     
         4 . The storage medium of  claim 1 , wherein the code, when executed, further causes a machine to determine one or more tensors for the set of data based on the modalities, spatial locations, and timestamps of the plurality of observed values, wherein the values for the one or more missing values in the set of data are determined using the tensor. 
     
     
         5 . The storage medium of  claim 4 , wherein the tensor incorporates spatial coherence among the plurality of observed values, temporal coherence among the plurality of observed values, and multi-modal coherence among the plurality of observed values. 
     
     
         6 . The storage medium of  claim 5 , wherein at least one of the spatial coherence, temporal coherence, and multi-model coherence is non-continuous. 
     
     
         7 . The storage medium of  claim 4 , wherein the missing values are determined using tensor factorization. 
     
     
         8 . The storage medium of  claim 7 , wherein the tensor factorization comprises parallel factor (PARAFAC) decomposition. 
     
     
         9 . The storage medium of  claim 4 , wherein determining the tensor comprises normalizing the multi-modal values. 
     
     
         10 . The storage medium of  claim 4 , wherein the tensor comprises a three-dimensional tensor. 
     
     
         11 . The storage medium of  claim 4 , wherein the code, when executed, further causes a machine to:
 identify a subset of the missing values falling outside the tensor; and   perform interpolation to derive the subset of missing values.   
     
     
         12 . The storage medium of  claim 11 , wherein the subset of missing values corresponds to a plane within the tensor in which no values exist. 
     
     
         13 . The storage medium of  claim 11 , wherein interpolation is performed in response to identifying existence of missing values falling outside the tensor. 
     
     
         14 . The storage medium of  claim 11 , wherein the interpolation is performed using the one or more missing values determined from the tensor. 
     
     
         15 . The storage medium of  claim 14 , wherein the interpolation is performed using one or more of the plurality of observed values. 
     
     
         16 . The storage medium of  claim 4 , wherein determining the one or more missing values comprises learning latent values of the tensor. 
     
     
         17 . The storage medium of  claim 1 , wherein the missing values comprises more than 50 percent of the values of the data set. 
     
     
         18 . The storage medium of  claim 17 , wherein the missing values comprises more than 80 percent of the values of the data set. 
     
     
         19 . The storage medium of  claim 1 , wherein modality corresponds to a sensor type used to generate the value, spatial location corresponds to physical location of the sensor used to generate the value, and the time stamp indicates when the value was recorded. 
     
     
         20 . (canceled) 
     
     
         21 . (canceled) 
     
     
         22 . (canceled) 
     
     
         23 . (canceled) 
     
     
         24 . (canceled) 
     
     
         25 . (canceled) 
     
     
         26 . (canceled) 
     
     
         27 . (canceled)