Anomaly detection in a sensor network
AssigneeInternational Business Machines Corporation
InventorsYu Ling Zheng, Xiao Xing Liang, Yu Chen Zhou, Ning Zhang
Life of this patent
Estimating the term…
Abstract
A method, system, and computer product for anomaly detection in a sensor network. The method comprises: receiving measurements from a plurality of sensors in the sensor network. The method further comprises performing a graph Fourier transform on the measurements to obtain a spectrum. The graph Fourier transform is defined by a graph structure generated from the plurality of sensors. The method further comprises generating an anomaly alert in response to high frequency components of the spectrum exceeding a first threshold.
Claims20
A computer-implemented method for anomaly detection in a sensor network, the method comprising:
- receiving a plurality of measurements from a plurality of sensors in the sensor network, wherein the sensor network is a local internet of things network;
- generating a graph structure comprising relationships of the plurality of sensors;
- performing, based on the graph structure, a graph Fourier transform on the plurality of measurements to obtain a spectrum;
- analyzing the spectrum to detect a plurality of high frequency components;
- generating an anomaly alert in response to one or more of the plurality of high frequency components exceeding a first threshold;
- and
- determining a location of the anomaly within the sensor network.
A system for anomaly detection in a sensor network, the system comprising:
- one or more processors;
- a memory coupled to at least one of the one or more processors;
- a set of computer program instructions stored in the memory and executed by at least one of the one or more processors in order to perform actions of:
- receiving a plurality of measurements from a plurality of sensors in the sensor network, wherein the sensor network is a local internet of things network;
- generating a graph structure comprising relationships of the plurality of sensors;
- performing, based on the graph structure, a graph Fourier transform on the plurality of measurements to obtain a spectrum;
- analyzing the spectrum to detect a plurality of high frequency components;
- generating an anomaly alert in response to one or more of the plurality of high frequency components exceeding a first threshold;
- and
- determining a location of the anomaly within the sensor network.
A computer program product for anomaly detection in a sensor network, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the program instructions being executable by a device to cause the device to perform a method comprising:
- receiving a plurality of measurements from a plurality of sensors in the sensor network, wherein the sensor network is a local internet of things network;
- generating a graph structure comprising relationships of the plurality of sensors;
- performing, based on the graph structure, a graph Fourier transform on the plurality of measurements to obtain a spectrum;
- analyzing the spectrum to detect a plurality of high frequency components;
- generating an anomaly alert in response to one or more of the plurality of high frequency components exceeding a first threshold;
- and
- determining a location of the anomaly within the sensor network.
Dependencies are inferred from the claim text.