Multidimensional Multivariate Multiple Sensor System

Abstract

Devices and methods for determining item-specific information for single or multiple items on one or multiple substrates are described. The method includes generating multiple sensor multiple dimensions array (MSMDA) data from multiple sensors, where each of the multiple sensors capture sensor data for one or more items in relation to a substrate. For each item, the method includes determining relationships between the multiple sensors based on characteristics of the MSMDA data, determining a location of the item on the substrate based on at least the determined relationships between the multiple sensors, determining an angular orientation of the item on the substrate based on at least the determined relationships between the multiple sensors, and determining a body position of the subject on the substrate based at least the determined relationships between the multiple sensors, the location of the subject, and the angular orientation of the item.

What is claimed is: 
     
         1 . A method for determining item specific parameters, the method comprising:
 generating multiple sensor multiple dimensions array (MSMDA) data from multiple sensors, wherein each of the multiple sensors capture sensor data for one or more items in relation to a substrate, and wherein an item is a subject or an object;   for each identified item:
 determining relationships between the multiple sensors based on characteristics of the MSMDA data; 
 determining a location of the item on the substrate based on at least the determined relationships between the multiple sensors; 
 determining an angular orientation of the item on the substrate based on at least the determined relationships between the multiple sensors; and 
 determining a body position of the item on the substrate based at least the determined relationships between the multiple sensors, the location of the subject, and the angular orientation of the item. 
   
     
     
         2 . The method of  claim 1 , further comprising:
 identifying a presence and an order of the presence of each item on the substrate.   
     
     
         3 . The method of  claim 1 , further comprising, for each item:
 determining weights based on characteristics of the MSMDA data.   
     
     
         4 . The method of  claim 3 , further comprising, for each item:
 comparing the weight against a threshold to determine a bed presence status for the item; and   issuing a bed presence status if the weight is greater than the threshold.   
     
     
         5 . The method of  claim 4 , wherein the threshold is multiple thresholds and each threshold of the multiple thresholds is different for subsequent items. 
     
     
         6 . The method of  claim 5 , further comprising, for each item:
 adjusting each threshold based on the location, angular orientation, and body position of for each identified item.   
     
     
         7 . The method of  claim 3 , further comprising, for each item:
 adjusting a threshold based on the location, angular orientation, and body position of each identified item;   performing a motion analysis based on characteristics of the MSMDA data; and   determining a bed presence status for the item based on the weight, the adjusted threshold, and the motion analysis.   
     
     
         8 . The method of  claim 1 , wherein the determining relationships further comprising:
 for each item:   determining, for a given combination of the multiple sensors:
 an amplitude change from the MSMDA data; 
 a rate of change from the MSMDA data; 
 a phase change from the MSMDA data; 
 a spectral change from the MSMDA data; 
 a time-frequency change from the MSMDA data; 
   sorting the combinations based on defined metrics; and   identifying, for each sorted combination, a determined relationship by:
 assigning a positive value to any other sorted combination which has at least one of a similar amplitude change, similar rate of change, similar phase of change, similar spectral change, or similar time-frequency change; and 
 assigning a negative value to any other sorted combination which has at least one of an opposite amplitude change, opposite rate of change, or opposite phase of change, opposite spectral change, or opposite time-frequency change, 
 wherein each determined relationship is a pair of combinations. 
   
     
     
         9 . The method of  claim 8 , wherein the determining a location further comprising:
 for each item:
 identifying determined relationships having one of a same directional change or an opposite directional change; 
 selecting directionally related determined relationships which represent a defined surface coverage area; and 
 mapping the selected directionally related determined relationships to a surface location map to determine the location of the identified item. 
   
     
     
         10 . The method of  claim 9 , wherein the determining an orientation further comprising:
 for each item:
 identifying determined relationships having strongest amplitude and opposite phase; 
 selecting identified determined relationships which represent corners of a defined surface coverage area; and 
 mapping the selected identified determined relationships to an orientation map to determine the orientation of the identified item. 
   
     
     
         11 . The method of  claim 8 , wherein the determining the body position further comprising:
 for each item:
 identifying determined relationships having same directional change or an opposite directional change at the location of the identified item and the angular orientation of the identified item; and 
 checking the identified determined relationships against a defined body position to determine the body position of the identified item. 
   
     
     
         12 . The method of  claim 1 , further comprising:
 training a classifier based on the MSMDA data to generate at least a location classifier, an angular orientation classifier, and a body position classifier; and   making classifications on non-classified MSMDA data using at least the location classifier, the angular orientation classifier, and the body position classifier.   
     
     
         13 . The method of  claim 12 , further comprising:
 updating classifiers associated with other multiple sensors with at least the location classifier, the angular orientation classifier, and the body position classifier,   wherein the other multiple sensors and the multiple sensors are associated with different substrates.   
     
     
         14 . A device comprising:
 a substrate configured to support an item, wherein the item is a subject or an object;   a plurality of sensors configured to capture sensor data from item actions with respect to the substrate;   a processor in connection with the plurality of sensors, the processor configured to:   generate multiple sensor multiple dimensions array (MSMDA) data from sensed sensor data;   for each identified item:
 determine relationships between the plurality of sensors based on characteristics of the MSMDA data; 
 determine a location of the identified item on the substrate based on at least the determined relationships between the plurality of sensors; 
 determine an angular orientation of the identified item on the substrate based on at least the determined relationships between the plurality of sensors; and 
 determine a body position of the identified item on the substrate based at least the determined relationships between the plurality of sensors, the location of the identified item and the angular orientation of the identified item. 
   
     
     
         15 . The device of  claim 14 , the processor further configured to:
 identify a presence of each item and the order of the presence on the substrate.   
     
     
         16 . The device of  claim 14 , the processor further configured to:
 for each item:
 determine a weight based on characteristics of the MSMDA data; 
 compare the weight against threshold to determine a bed presence status for the identified item; and 
 issue a bed presence status if the weight is greater than the threshold. 
   
     
     
         17 . The method of  claim 16 , wherein the threshold is multiple thresholds and each threshold of the multiple thresholds is different for subsequent items. 
     
     
         18 . The device of  claim 16 , the processor further configured to:
 for each item:
 adjust the threshold based on the location of the identified item. 
   
     
     
         19 . The device of  claim 14 , the processor further configured to:
 for each item:
 determine a weight based on characteristics of the MSMDA data; 
 adjust a threshold based on the location of the identified item; 
 perform a motion analysis based on characteristics of the MSMDA data; and 
 determine a bed presence status for the identified item based on the weight, the adjusted threshold, and the motion analysis. 
   
     
     
         20 . The device of  claim 14 , the processor further configured to:
 for each item:
 determine, for a given combination of the plurality of sensors:
 an amplitude change from the MSMDA data; 
 a rate of change from the MSMDA data; 
 a phase change from the MSMDA data; 
 a spectral change from the MSMDA data; 
 a time-frequency change from the MSMDA data; 
 
 sort the combinations based on a defined metric; and 
 identify, for each sorted combination, a determined relationship by:
 assignment of a positive value to any other sorted combination which has at least one of a similar amplitude change, similar rate of change, or similar phase of change; and 
 assignment of a negative value to any other sorted combination which has at least one of an opposite amplitude change, opposite rate of change, or opposite phase of change, 
 
 wherein each determined relationship is a pair of combinations. 
   
     
     
         21 . The device of  claim 14 , the processor further configured to, for each item:
 identify determined relationships having one of a same directional change or an opposite directional change;   select directionally related determined relationships which represent a defined surface coverage area; and   map the selected directionally related determined relationships to a surface location map to determine the location of the identified item.   
     
     
         22 . The device of  claim 14 , the processor further configured to, for each item:
 identify determined relationships having strongest amplitude and opposite phase;   select identified determined relationships which represent corners of a defined surface coverage area; and   map the selected identified determined relationships to an orientation map to determine the angular orientation of the identified item.   
     
     
         23 . The device of  claim 14 , the processor further configured to, for each item:
 identify determined relationships having same directional change or an opposite directional change at the location of the identified item and the angular orientation of the identified item; and   check the identified determined relationships against a defined body position to determine the body position of the identified item.   
     
     
         24 . The device of  claim 14 , further comprising:
 a classifier configured to make classifications on non-classified MSMDA data using at least a location classifier, an angular orientation classifier, and a body position classifier,   wherein each of the location classifier, the angular orientation classifier, and the body position classifier is trained and generated based on the MSMDA data.