Abstract: A controller is configured to receive raw signals from at least one gyroscope for at least two axes. The controller processes the raw signals through a BPF and output a filtered signal. The controller processes the filtered signal through an energy envelope estimator and determines an energy envelope signal for at least one axis. The controller then determines a nonswim activity in a segment based on the energy envelope signal through a detector. The energy envelope estimator is configured to generate the energy envelope signal using sliding window average of a preset window size over the filtered signal. The detector is configured to compare values of the energy envelope signal for at least one axis against respective threshold value, and classify the segment of the raw signals as non-swim activity upon satisfactory comparison.

Abstract: A controller is connected to receive an input signal from at least one accelerometer. The controller comprises an interface facilitating input and output pins/ports, and a filter module to filter the input signal from at least one accelerometer. The controller includes a stroke segmentation module configured to determine at least two parameters comprising a first parameter and a second parameter from the filtered input signal, generate an envelope signal using the at least two parameters and the filtered input signal, and determine the swim stroke of the swimmer based on the filtered input signal and the envelope signal. Further, an activity detection module is used in combination with the stroke segmentation module.

Abstract: The controller of a wearable device is used to determine swim characteristics of a swimmer. The controller is connected to at least one motion sensor selected from a group including a multi-axis gyroscope and a multi-axis accelerometer. The controller is adapted to detect input signals from the at least one motion sensor. The controller is further configured to perform dynamic stroke segmentations based on at least one of the input signals using a stroke segmentation module, extract feature vectors, using feature extraction module, from the at least one input signal based on the stroke segmentations, and determine the swim characteristics by using the feature vectors through a classifier module. The controller dynamically adapts to a style of the swimmer to detect the swim characteristics.

Abstract: A controller is configured to receive raw signals from at least one gyroscope for at least two axes. The controller processes the raw signals through a BPF and output a filtered signal. The controller processes the filtered signal through an energy envelope estimator and determines an energy envelope signal for at least one axis. The controller then determines a nonswim activity in a segment based on the energy envelope signal through a detector. The energy envelope estimator is configured to generate the energy envelope signal using sliding window average of a preset window size over the filtered signal. The detector is configured to compare values of the energy envelope signal for at least one axis against respective threshold value, and classify the segment of the raw signals as non-swim activity upon satisfactory comparison.

Abstract: A controller is connected to receive an input signal from at least one accelerometer. The controller comprises an interface facilitating input and output pins/ports, and a filter module to filter the input signal from at least one accelerometer. The controller includes a stroke segmentation module configured to determine at least two parameters comprising a first parameter and a second parameter from the filtered input signal, generate an envelope signal using the at least two parameters and the filtered input signal, and determine the swim stroke of the swimmer based on the filtered input signal and the envelope signal. Further, an activity detection module is used in combination with the stroke segmentation module.

Abstract: The controller of a wearable device is used to determine swim characteristics of a swimmer. The controller is connected to at least one motion sensor selected from a group including a multi-axis gyroscope and a multi-axis accelerometer. The controller is adapted to detect input signals from the at least one motion sensor. The controller is further configured to perform dynamic stroke segmentations based on at least one of the input signals using a stroke segmentation module, extract feature vectors, using feature extraction module, from the at least one input signal based on the stroke segmentations, and determine the swim characteristics by using the feature vectors through a classifier module. The controller dynamically adapts to a style of the swimmer to detect the swim characteristics.