A monitoring device for monitoring of vital signs of a living organism comprises at least two electrode pins for receiving an electrical activity of the living organism and an optical sensor for sensing a pulse of the living organism, wherein the monitoring device has a compact form and the at least two electrode pins and the optical sensor are integrated in the monitoring device.

In some embodiments, the present disclosure relates to a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, including forming an imaging dataset having imaging data corresponding to one or more radiological images of a patient having a bowel disease; operating upon the imaging data with one or more convolutional neural network (CNN) segments configured to generate a plurality of CNN outputs, the one or more CNN segments respectively including a convolution layer configured to perform a convolution on the imaging data; and applying a wavelet network to the plurality of CNN outputs to generate a plurality of convolution wavelet network (CWN) outputs, the wavelet network being configured to decompose the plurality of CNN outputs according to a mother wavelet. A predictive signature associated with disease response or risk is constructed using the plurality of CWN outputs.

A sleep estimation system (1) according to an embodiment includes: an input device (14, 16) configured to receive blood flow data on a user; and a controller (11) configured to calculate output data (19) indicating a sleep state of the user on the basis of the blood flow data, in which the controller includes an approximator (17) capable of calculating the output data on the basis of the blood flow data.

A method and a system for analyzing electrocardiographic segments previously derived from a cardiac device so as to help to discriminate true positives episodes, including abnormal heart rhythms, from false positives episodes, including normal heart rhythms. Each episode received includes at least one segment of electrocardiographic signal, and each segment is segmented into sub-segments. Score vectors are obtained for each sub-segment to classify the episode so as to discriminate true positive episodes from false positive episodes, and the classification results, which include at least the true positive episodes, are output.

A method is described, which provides electrical stimulation to a person, where the current flows from a subcranial electrode, through a target brain region, through a separate conductive path, and back to a subcutaneous electrode, and where the parameters of the electric current pulses are set to influence the resonant properties of the brain.

The exemplified methods and systems provide a phase space volumetric object in which the dynamics of a complex, quasi-periodic system, such as the electrical conduction patterns of the heart, or other biophysical-acquired signals of other organs, are represented as an image of a three dimensional volume having both a volumetric structure (e.g., a three dimensional structure) and a color map to which features can be extracted that are indicative the presence and/or absence of pathologies, e.g., ischemia relating to significant coronary arterial disease (CAD). In some embodiments, the phase space volumetric object can be assessed to extract topographic and geometric parameters that are used in models that determine indications of presence or non-presence of significant coronary artery disease.

A method for generating a feature associated with input data includes receiving the input data; projecting the input data with a set of square functions ψ.sub.nh.sup.2 of the Schrödinger operator; selecting the feature to be a number of the negative eigenvalues λ.sub.nh of the Schrödinger operator; and classifying the input data based on the feature.

A disease diagnosing method and a disease diagnosing system are provided in the disclosure. The disease diagnosing method includes: obtaining continuous images of a body skin and generating a time domain signal according to an average pixel value of a region of interest in each frame of the continuous images; transforming the time domain signal to a frequency domain signal and combining the time domain signal and the frequency domain signal to a time frequency signal; retrieving multiple first features of a first high dimensional space of the time frequency signal to obtain multiple second features of a second high dimensional space; and use the second features as feature vectors to map to a high dimension feature space, and classifying the second features as one of the multiple categories of a disease corresponding to the region of interest in the body skin according to a hyperplane of the high dimension feature space.

A fiber-optic sensor matt detects movements of a person on the matt that cause microbending of a fiber-optic cable that is arranged into a symmetric pair of radial ring groups within the matt. There are no cross-over points or overlapping of the fiber-optic cable within the symmetric pair of radial ring groups that could cause fiber wear and noisy readings. Microbending of the fiber-optic cable pressed into a mesh modulates the light intensity received, which is analyzed to extract both respiration and heart BallistoCardioGram (BCG) waveforms by convolution with Daubechies dB5 wavelet and scaling functions. The reconstructed level-4 detail waveform is output as the extracted BCG, while the reconstructed level-6 approximation waveform is output as the extracted respiration waveform. Respiration and heart rates and variations can be generated from the extracted waveforms. An integrated Fast Wavelet Transform (FWT) using dB5 wavelet thus generates both respiration rate and heart rate.

Methods, computer systems, and computer readable media are provided for promoting positive activity patterns for users and facilitate long-term adherence to the activity patterns, such as by providing alerts or electronic reminders to ambulate in a fashion that is responsive to an individual's actual activity patterns and behaviors and compatible with routine activities in the workplace and home. In particular, embodiments of the present invention are directed to measuring physical activity patterns during the waking hours of a human, and in some embodiments continuously measuring these activity patterns; automatically ascertaining whether the patterns exhibit sufficient frequency and variability of activity such as confers certain health benefits; and if the patterns do not manifest such features, to adaptively provide sensible reminders at irregular within-day intervals such as are likely to establish healthy patterns of ambulation and other light activity.