Apparatus, systems and methods for event recognition based on a wireless signal

A system having a processor, a memory communicatively coupled with the processor and a set of instructions stored in the memory for recognizing an event, comprising:

• a first transmitter in a venue and configured for:
• for each of at least one known event happening in the venue in a respective training time period , transmitting a respective training wireless signal through a wireless multipath channel impacted by the known event in the venue in the training time period associated with the known event;
• at least one first receiver in the venue, wherein each of the at least one first receiver is configured for:
• for each of the at least one known event happening in the venue,
• receiving asynchronously the respective training wireless signal through the wireless multipath channel,
• obtaining, asynchronously based on the respective training wireless signal, at least one time series of training channel information (training CI time series) of the wireless multipath channel between the first receiver and the first transmitter in the training time period associated with the known event, and
• pre-processing the at least one training CI time series;
• a second transmitter in the venue and configured for:
• for a current event happening in the venue in a current time period, transmitting a current wireless signal through the wireless multipath channel impacted by the current event in the venue in the current time period associated with the current event;
• at least one second receiver in the venue, wherein each of the at least one second receiver is configured for:
• for the current event happening in the venue in the current time period,
• receiving asynchronously the current wireless signal through the wireless multipath channel,
• obtaining, asynchronously based on the current wireless signal, at least one time series of current channel information (current CI time series) of the wireless multipath channel between the second receiver and the second transmitter in the current time period associated with the current event, and
• pre-processing the at least one current CI time series;
• and
• an event recognition engine configured for:
• training at least one classifier for the at least one known event based on the at least one training CI time series;
• and
• applying the at least one classifier to:
• classify at least one of:
• the at least one current CI time series, a portion of a particular current CI time series, and a combination of the portion of the particular current CI time series and a portion of an additional CI time series, and
• associate the current event with at least one of:
• a known event, an unknown event and another event, wherein a training CI time series associated with a first receiver and a current CI time series associated with a second receiver have at least one of:
• different starting times,
• different time durations,
• different stopping times,
• different counts of items in their respective time series,
• different sampling frequencies,
• different sampling periods between two consecutive items in their respective time series, and
• channel information (CI) with different features.

An event recognition engine of a wireless monitoring system, comprising:

• a processor;
• a memory communicatively coupled with the processor;
• and
• a set of instructions stored in the memory which, when executed, causes the processor to perform:
• for each of at least one known event happening in a venue in a respective training time period, obtaining, from each of at least one first receiver in the venue, at least one time series of training channel information (training CI time series) of a wireless multipath channel impacted by the known event, wherein the first receiver extracts the training CI time series from a respective training wireless signal received from a first transmitter in the venue through the wireless multipath channel between the first receiver and the first transmitter in the training time period associated with the known event,
• training at least one classifier for the at least one known event based on the at least one training CI time series,
• for a current event happening in the venue in a current time period, obtaining, from each of at least one second receiver in the venue, at least one time series of current channel information (current CI time series) of the wireless multipath channel impacted by the current event, wherein the second receiver extracts the current CI time series from a current wireless signal received from a second transmitter in the venue through the wireless multipath channel between the second receiver and the second transmitter in the current time period associated with the current event, and
• applying the at least one classifier to:
• classify at least one of:
• the at least one current CI time series, a portion of a particular current CI time series, and a combination of the portion of the particular current CI time series and a portion of an additional CI time series, and
• associate the current event with at least one of:
• a known event, an unknown event and another event, wherein a training CI time series associated with a first receiver and a current CI time series associated with a second receiver have at least one of:
• different starting times,
• different time durations,
• different stopping times,
• different counts of items in their respective time series,
• different sampling frequencies,
• different sampling periods between two consecutive items in their respective time series, and
• channel information (CI) with different features.

A receiver of a wireless monitoring system, comprising:

• a wireless circuitry configured to:
• for each of at least one known event happening in a venue in a respective training time period, receive a respective training wireless signal through a wireless multipath channel impacted by the known event, wherein the respective training wireless signal is transmitted by a first transmitter through the wireless multipath channel between the receiver and the first transmitter in the training time period associated with the known event, and
• for a current event happening in the venue in a current time period, receive a current wireless signal through the wireless multipath channel impacted by the current event, wherein the current wireless signal is transmitted by a second transmitter through the wireless multipath channel between the receiver and the second transmitter in the current time period associated with the current event;
• a processor communicatively coupled with the wireless circuitry;
• a memory communicatively coupled with the processor;
• and
• a set of instructions stored in the memory which, when executed, causes the processor to:
• for each of the at least one known event happening in the venue, obtain, asynchronously based on the respective training wireless signal, at least one time series of training channel information (training CI time series) of the wireless multipath channel, and
• for the current event happening in the venue in the current time period, obtain, asynchronously based on the current wireless signal, at least one time series of current channel information (current CI time series) of the wireless multipath channel, wherein:
• the at least one training CI time series is used by an event recognition engine of the wireless monitoring system to train at least one classifier for the at least one known event, and
• the at least one classifier is applied to:
• classify at least one of:
• the at least one current CI time series, a portion of a particular current CI time series, and a combination of the portion of the particular current CI time series and a portion of an additional CI time series, and
• associate the current event with at least one of:
• a known event, an unknown event and another event.