A method for machine learning based artifact rejection is provided. The method may include applying a machine learning model to identify artefactual independent components in transcranial magnetic stimulation electroencephalogram data collected during a transcranial magnetic stimulation procedure. Clean transcranial magnetic stimulation electroencephalogram data is generated by removing, from the transcranial magnetic stimulation electroencephalogram data, the artefactual independent components. Real-time adjustments to parameters of the transcranial magnetic stimulation procedure may be performed based on the clean transcranial magnetic stimulation electroencephalogram data. Related systems and articles of manufacture, including computer program products, are also provided.

A data processing method for detecting and classifying a segment of a signal that is obtained from a single-channel EEG-recording as a target signal segment or as a non-target signal segment. The method includes a voting process to determine whether classification of a first detected segment of the signal as a target signal segment or classification of a second detected segment of the signal as a non-target signal segment is correct. A device and a system that are configured and arranged to perform the data processing method.

To perform urological diagnostics of a patient, detrusor pressure can be estimated using bladder pressure recordings from a single sensor. A signal comprising the bladder pressure data recorded by the sensor can be received. The bladder pressure data can include at least a detrusor pressure data component and a corrupting data component. An estimate of the corrupting data component can be extracted from the bladder pressure data. The detrusor pressure of the patient can be estimated based on the estimate of the corrupting data component and/or the estimate of the detrusor pressure data. An output indicative of the detrusor pressure of the patient can be provided based on the estimate of the detrusor pressure data component.

Methods, systems, and devices for signal analysis in an implanted cardiac monitoring and treatment device such as an implantable cardioverter defibrillator. In some examples, captured data including detected events is analyzed to identify likely overdetection of cardiac events. In some illustrative examples, when overdetection is identified, data may be modified to correct for overdetection, to reduce the impact of overdetection, or to ignore overdetected data. Several examples emphasize the use of morphology analysis using correlation to static templates and/or inter-event correlation analysis.

In a method and apparatus for swallowing impairment detection, a candidate executes one or more swallowing events, and dual axis accelerometry data is acquired representative thereof. Upon feature extraction and classification, vibrational data acquired in respect of each swallowing event is classified as indicative of one of normal or possibly impaired swallowing.

There is provided a device for measuring fatigue of a person, the device comprising a frame configured to be worn within the mouth of the person, a microphone mounted within the frame and configured to measure sound data, and a cavity located within the frame and adjacent to the microphone, wherein the cavity does not communicate with the environment surrounding the frame. There is also provided a computer-implemented method for determining a fatigue metric representing a level of physical fatigue of a person

A motion monitoring method (500) is provided, which includes: obtaining a movement signal of a user during motion, wherein the movement signal includes at least an electromyographic signal or an attitude signal (510); and monitoring a movement of the user during motion based at least on feature information corresponding to the electromyographic signal or the feature information corresponding to the attitude signal (520).

A non-contact facial blood pressure measurement method based on 3D CNN is disclosed, which belongs to the technical field of computer vision. The method includes the following steps. S110: collecting an actual face video sample and training a blood pressure prediction model based on face images using 3D CNN neural network. S120: obtaining a face video in real time through a HD camera. S130: recognizing face key points in the face video obtained in S120 through dlib face recognition model, selecting a face region of interest, and extracting face images from the region. S140: performing a wavelet transform operation on the face images extracted in S130 to remove noise. S150: inputting seven consecutive frames of the face images into the 3D CNN blood pressure prediction model trained in S110 to obtain a blood pressure value of the measured person. The disclosure realizes non-contact facial blood pressure measurement.

A method for monitoring thoracic tissue. The method comprises intercepting reflections of electromagnetic (EM) radiation reflected from thoracic tissue of a patient in radiation sessions during a period of at least 24 hours, detecting a change of a dielectric coefficient of the thoracic tissue by analyzing respective the reflections, and outputting a notification indicating the change. The reflections are changed as an outcome of thoracic movements which occur during the period.

A computer-implemented method for direct photoplethysmography or direct PPG comprises obtaining during a time interval plural PPG signals for respective sensors in a wearable device; and combining the plural PPG signals to thereby obtain a multi-sensor PPG signal.