Abstract: A system of networked sensors designed to predict the onset of chronic obstructive pulmonary disease (COPD) symptoms is disclosed. The system is worn by an individual and the sensors collect data correlated with COPD symptoms. The collected sensor data is transmitted from the device to the user's mobile device for analysis. The results of the analysis may be forwarded to a health care provider.

Abstract: A smart multi-modal telehealth IoT system for respiratory analysis. Such a system includes a body area sensor network comprised of meshed wireless sensor nodes and advanced machine learning techniques. The system may be used to remotely diagnose a user's respiratory illness and monitor their health.

Abstract: A wearable garment with sensors attached to obtain physiological data. The sensors are incorporated to form a body area sensor network to obtain the data. This provides patients with improved health monitoring by aggregating multiple interconnected nodes on a human body for sensorimotor measurements and provides patients with quantitative measurements of their progress. The data is obtained in a way that allows for the number of transmissions to be reduced thereby conserving the energy of the wearable devices. This is made possible by each sensor reducing the number of samples by eliminating predictable samples and configuring the sensors to pack the data efficiently. A neural network can determine whether a sample can be skipped or needs to be reported. A long short term memory architecture creates a waveform for a given snapshot of samples based on the previous samples regardless of whether these samples were reported or predicted.

Abstract: An embodiment of the invention provides a method where input is received in sensors on a glove, where the sensors include a force sensor, a flex sensor, and/or a range-of-motion IMU sensor. The input is sent from the sensors on the glove to a processor on the glove. The input is analyzed with the processor to determine an exercise being performed by a user of the glove. A trained neural network is used to analyze the input from the sensors; and, the orientation of the glove is recognized with the trained neural network. The input and the orientation are classified as a grip exercise and/or a rotation exercise.

Abstract: An embodiment of the invention provides a method where input is received in sensors on a glove, where the sensors include a force sensor, a flex sensor, and/or a range-of-motion IMU sensor. The input is sent from the sensors on the glove to a processor on the glove. The input is analyzed with the processor to determine an exercise being performed by a user of the glove. A trained neural network is used to analyze the input from the sensors; and, the orientation of the glove is recognized with the trained neural network. The input and the orientation are classified as a grip exercise and/or a rotation exercise.