Automatic fixture monitoring using mobile location and sensor data with smart meter data

A system comprising:

• one or more resource meters that each track resource usage data for a location;
• an electronic device that includes a plurality of sensor devices, wherein the electronic device:
• acquires one or more data streams from one or more resource meters and one or more electronic sensors;
• computes discrete events from each data stream;
• extracts a sequence of discrete sensor-meter event itemsets based on the events that occur together;
• discovers the frequent sensor-meter event itemsets that occur together, and computes a frequency of occurrence for each sensor-meter event itemset;
• matches rising and falling sensor-meter event itemsets based on appliance state models and the frequency of occurrence of each sensor-meter event itemset;
• identifies each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features;
• classifies each fixture cluster to a fixture category using a multi-modal fixture model trained on sensor and meter event features;
• and
• based on the matched fixture events, fixture clusters, and categories, determining resource usage information and associated user activities for each fixture usage event identified.

A non-transitory computer-readable medium having instructions which when executed on a computer perform a method comprising:

• acquiring one or more data streams from one or more resource meters and one or more electronic sensors;
• computing discrete events from each data stream;
• extracting a sequence of discrete sensor-meter event itemsets based on the events that occur together;
• discovering the frequent sensor-meter event itemsets that occur together, and determining a frequency of occurrence for each sensor-meter event itemset;
• matching rising and falling sensor-meter event itemsets based on appliance state models and the frequency of occurrence of each sensor-meter event itemset;
• identifying each individual fixture based on clustering the matched sensor-meter event itemsets using sensor-meter event features;
• classifying each fixture cluster to a fixture category using a multi-modal fixture model trained on sensor and meter event features;
• and
• based on the matched fixture events, fixture clusters, and categories, determining resource usage information and associated user activities for each fixture usage event identified.