System and method for performing distributed signal classification for a multi-hop cognitive communication device
A system and method for cognitive communication device operation. In accordance with the system and method, a node ( 102, 106, 107 ) that communicates in a wireless multihopping communication network ( 100 ) uses a receiver ( 302, 402, 502, 602 ) to acquire a digital sample of a communication signal, and extracts at least one feature of the digital sample. The node ( 102, 106, 107 ) employs a classifier ( 306, 406, 506 ) to determine the signal type, and a transmitter ( 108 ) to send feature vectors including information representing the signal type to other nodes ( 102, 106, 107 ) in the network ( 100 ).
1. A method for performing distributed signal classification within a wireless multi-hop communication network, the method comprising:
operating each of a plurality of multi-hop nodes within the wireless multi-hop communication network to:
receive at least one respective signal and acquire a sample of the signal;
extract at least one feature of the signal from the sample;
assign a feature vector to the signal based on the at least one feature;
classify the signal the signal as a certain type of signal based on the at least one feature;
change an operation of the multi-hop node based on the signal classification; and
transmit the feature vector including the signal type to other multi-hop nodes in the wireless multi-hopping communication network.
2. A method as claimed in claim 1 , further comprising:
operating each of the plurality of multi-hop nodes in the wireless multi-hop communication network to receive at least one respective signal and acquire a sample of the signal;
operating each of the multi-hop nodes to extract at least one feature of the signal from the sample;
operating each of the multi-hop nodes to classify the signal as a certain type of signal based on the at least one feature;
operating each of the multi-hop nodes to assign a feature vector to the signal based on the at least one feature;
operating each of the multi-hop nodes to change an operation of the multi-hop node based on the signal classification; and
operating each of the multi-hop nodes to transmit to each of the other multi-hop nodes the feature vector including the signal type.
3. A method as claimed in claim 1 , further comprising:
operating each of the multi-hop nodes to transmit to a single multi-hop node respective information pertaining to the respective types of classified signals.
4. A method as claimed in claim 1 , wherein:
the acquiring step comprises operating the multi-hop node to receive a plurality of signals and to acquire a respective sample of each of the plurality of signals;
the extracting step comprises operating the multi-hop node to extract at least one respective feature of each of the signals from their respective sample; and
the classifying step comprises operating the multi-hop node to classify each of the respective signals as one of a plurality of types of signals based on the respective features.
5. A method as claimed in claim 1 , wherein:
the sample is a digital sample; and
the extracting step comprises operating the multi-hop node to perform a Fourier transform operation on the digital sample to extract the at least one feature.
6. A method as claimed in claim 1 , wherein extracting at least one feature of the signal from the sample includes measuring at least one of: a Fourier transform of the signal, an average signal power of the signal, and one or more Media Access Control (MAC) headers of the signal.
7. A method as claimed in claim 1 , wherein classifying the signal as a certain type of signal comprises classifying the received signal as an IEEE standard 802.x signal, a Bluetooth signal, or an unknown signal.
8. A method as claimed in claim 7 , further comprising operating the node to analyze the received signal or ignore the received signal based on a higher layer rule, when the signal is classified as an unknown signal.
9. The method as claimed in claim 1 , further comprising;
operating a next hop node within the communication network to:
receive the feature vector including the signal type;
receive the signal and acquire a sample of the signal;
extract at least one feature of the signal from the sample;
assign a feature vector to the signal based on the at least one feature;
classify the signal the signal as a certain type of signal based on the at least one feature;
change an operation of the next hop node based on the signal classification; and transmit the feature vector including the signal type to other multi-hop nodes in the wireless multi-hopping communication network.
10. A method as claimed in claim 1 , wherein the signal is one of a known signal and an unknown signal.
11. A method as claimed in claim 10 , further comprises:
transmitting the unknown signal with a preamble, wherein the preamble is based on the at least one feature of the signal.
12. A node, operating in a wireless multi-hop communication network having a plurality of nodes, the node comprising:
a receiver, for receiving at least one signal and acquire a sample of the signal;
a feature extractor, for extracting at least one feature of the signal from the sample;
a classifier, for classifying the signal as a certain type of signal based on the at least one feature and for assigning a feature vector to the signal based on the at least one feature;
a decision component, for instructing the node to change an operation of the node based on the signal classification; and
a transmitter, for transmitting to each of the other nodes, the feature vector including the signal type.
13. A node as claimed in claim 12 , wherein:
the receiver for receiving a plurality of signals and to acquire a respective sample of each of the plurality of signals;
the extractor for extracting at least one respective feature of each of the signals from their respective sample; and
the classifier for classifying each of the respective signals as one of a plurality of types of signals based on the respective features.
14. A node as claimed in claim 12 , wherein:
the sample is a digital sample; and
the extractor for performing a Fourier transform operation on the digital sample to extract the at least one feature.
15. A node as claimed in claim 12 , further comprising:
a demodulator, for demodulating the signal based on the at least one feature.
16. A node as claimed in claim 12 , wherein:
the receiver comprises a plurality of receivers, for monitoring different frequency bands for receipt of a signal.
17. A node as claimed in claim 12 , wherein:
the decision component determines an operation of the node based on the type of signal as classified by the classifier.
18. A wireless communication network, comprising:
a plurality of nodes, each of the plurality of nodes comprising a receiver, for receiving at least one signal and acquire a sample of the signal, a feature extractor, for extracting at least one feature of the signal from the sample, a classifier, for classifying the signal as a certain type of signal based on the at least one feature and for assigning a feature vector to the signal based on the at least one feature, a decision component, for instructing the node to change an operation of the node based on the signal classification, and a transmitter, for transmitting to other nodes the feature vector including the signal type.
19. A wireless communication network as claimed in claim 18 , wherein:
at least one of the nodes is an access point, for providing at least one of the other nodes with access to a network other than the wireless communication network; and
at least one of the nodes is a wireless router, for routing data packets between other of the nodes in the network.
20. A wireless communication network as claimed in claim 18 , wherein:
each of the nodes for transmitting to other nodes respective information pertaining to the respective type of classified signal that the node received and classified.
21. A wireless communication network as claimed in claim 18 , wherein:
each of the nodes to transmit to a single one of the nodes respective information pertaining to the respective type of classified signal that node received and classified.
22. A node as claimed in claim 12 , wherein the signal is one of a known signal and an unknown signal.
23. A node as claimed in claim 12 , wherein:
the transmitter, transmits the unknown signal with a preamble, wherein the preamble is based on the at least one feature of the signal.