Classifying internet-of-things (IOT) gateways using principal component analysis
View Patent ↗Systems and methods for classifying Internet-of-Things (IoT) gateways using principal component analysis are described. In some embodiments, an Information Handling System (IHS) may be configured to: receive metadata from a plurality of IoT gateways in an IoT network, where the metadata describes hardware attributes of a given IoT gateway and hardware attributes of one or more IoT devices coupled the given IoT gateway, perform principal component analysis upon the metadata by performing an eigenvalue decomposition or a singular value decomposition of a matrix including the metadata, and classify the given IoT gateway based, at least in part, upon the principal component analysis.
1. An Information Handling System (IHS), comprising:
one or more processors; and
a memory coupled to the one or more processors, the memory comprising program instructions stored thereon that, upon execution by the one or more processors, cause the IHS to:
receive metadata from a plurality of IoT gateways in an IoT network, wherein the metadata from a given IoT gateway describes hardware attributes of the given IoT gateway and hardware attributes of one or more IoT devices coupled to the given IoT gateway;
perform principal component analysis upon the metadata by performing an eigenvalue decomposition or a singular value decomposition of a matrix comprising the metadata; and
classify the given IoT gateway based, at least in part, upon the principal component analysis.
2. The IHS of claim 1 , wherein each of the plurality of IoT gateways comprises a different instance of the same internal hardware.
3. The IHS of claim 1 , wherein the hardware attributes of the given IoT gateway are selected from the group consisting of: number of CPU cores, average CPU utilization, and average CPU frequency.
4. The IHS of claim 1 , wherein the hardware attributes of the given IoT gateway are selected from the group consisting of: USB device count, average USB block size, and average UBS throughput.
5. The IHS of claim 1 , wherein the hardware attributes of the given IoT gateway are selected from the group consisting of: serial device count and serial average throughput.
6. The IHS of claim 1 , wherein the hardware attributes of the given IoT gateway are selected from the group consisting of: video devices and average video throughput.
7. The IHS of claim 1 , wherein the hardware attributes of the IoT devices are selected from the group consisting of: movement sensors, power sensors, airflow sensors, temperature sensors, humidity sensors, GPS devices, RFID readers, door locks, compressor devices, valve devices, fan devices, pump devices, switch devices, thermostat devices, smoke alarm devices, and fire alarm devices.
8. The IHS of claim 1 , wherein classifying the given IoT gateway comprises assigning the given IoT gateway to a corresponding cluster of IoT gateways selected from the group consisting of: a video cluster, a building management cluster, an automation cluster, a transportation cluster, a security cluster, and an industrial cluster.
9. The IHS of claim 8 , wherein the program instructions, upon execution, further cause the IHS to:
determine location information for the classified IoT gateway; and
identify an inconsistency between the location information and the corresponding cluster of IoT gateways to which the classified IoT gateway is assigned.
10. The IHS of claim 9 , wherein identifying the inconsistency comprises determining that a number greater or smaller than an expected number of IoT gateways assigned to the corresponding cluster of IoT gateways is within a selected physical distance from each other, and wherein the program instructions, upon execution, further cause the IHS to re-classify the given IoT gateway based, at least in part, upon an updated principal component analysis.
11. The IHS of claim 8 , wherein the program instructions, upon execution, further cause the IHS to:
determine user information for the given IoT gateway; and
identify an inconsistency between the user information and the corresponding cluster of IoT gateways to which the given IoT gateway is assigned.
12. The IHS of claim 11 , wherein identifying the inconsistency comprises determining that a number greater or smaller than an expected number of IoT gateways assigned to the corresponding cluster of IoT gateways is being operated by users of a given category, and wherein the program instructions, upon execution, further cause the IHS to re-classify the given IoT gateway based, at least in part, upon an updated principal component analysis.
13. The IHS of claim 12 , wherein the category corresponds to a market vertical for customers, users, or resellers of a manufacturer of the given IoT gateway.
14. The IHS of claim 1 , wherein the program instructions, upon execution, further cause the IHS to receive updated metadata from at least one of plurality of IoT gateways due to a change in one or more IoT devices coupled the given IoT gateway.
15. The IHS of claim 14 , wherein the program instructions, upon execution, further cause the IHS to re-classify the given IoT gateway based, at least in part, upon an updated principal component analysis.
16. A hardware memory device having program instructions stored thereon that, upon execution by an Information Handling System (IHS), cause the IHS to:
receive metadata from a plurality of IoT gateways in an IoT network, wherein the metadata from a given IoT gateway describes hardware attributes of one or more IoT devices coupled the given IoT gateway;
perform principal component analysis upon the metadata by performing an eigenvalue decomposition or a singular value decomposition of a matrix comprising the metadata; and
classify the given IoT gateway based, at least in part, upon the principal component analysis.
17. The hardware memory device of claim 16 , wherein classifying the given IoT gateway comprises assigning the given IoT gateway to a corresponding cluster of IoT gateways selected from the group consisting of: a video cluster, a building management cluster, an automation cluster, a transportation cluster, a security cluster, and an industrial cluster.
18. A method, comprising:
receiving metadata from a plurality of IoT gateways in an IoT network, wherein the metadata from a given IoT gateway describes hardware attributes of the given IoT gateway;
performing principal component analysis upon the metadata by performing an eigenvalue decomposition or a singular value decomposition of a matrix comprising the metadata; and
classifying the given IoT gateway based, at least in part, upon the principal component analysis.
19. The method of claim 18 , wherein classifying the given IoT gateway comprises assigning the given IoT gateway to a corresponding cluster of IoT gateways selected from the group consisting of: a video cluster, a building management cluster, an automation cluster, a transportation cluster, a security cluster, and an industrial cluster.