System and method for processing signals for the real-time detection of a functional cyclic activity

A system for processing signals for the real-time detection of a cyclic functional activity, the processing system comprising:

• a signal acquisition means forming an instrumental network including at least two sensors;
• one or more processing devices configured to:
• simultaneously receive signals acquired by the signal acquisition means,
• record and preprocess the acquired signals during a plurality of consecutive processing cycles,
• identify event combinations from recordings from the acquired signals, enabling a calibration to be carried out by the one or more processing devices, the calibration being carried out by:
• identifying a plurality of events in the acquired signals, each one of the events corresponding to an activation of a muscle and each acquired signal of the signal acquisition means including a plurality of identified events,
• defining a model of the cyclic functional activity, the model being a timing chart consisting of a time order of the plurality of identified events and mean delays between the identified events,
• defining a detection time window from the model of the cyclic functional activity, and
• detecting events into the detection time window taking into account the model of the cyclic functional activity;
• and
• a monitoring device configured to monitor the cyclic functional activity for a last full cycle, the monitoring device configured to:
• calculate a sliding mean of the delays between the events detected into the signals acquired during a plurality of consecutive monitoring cycles, the plurality of consecutive monitoring cycles comprising the last full cycle,
• display the sliding mean of the delays,
• compare the sliding mean of the delays to the mean of the delays calculated during the calibration in order to detect an anomaly, and
• generate and transmit an alert signal when the anomaly is detected.