Bed having sleep stage detecting feature
A first bed includes a first mattress, a first pressure sensor, and a first controller in data communication with the first pressure sensor, the first controller configured to receive pressure readings and to transmit the first pressure readings to a remote server. The system further includes a second bed that includes a second mattress having an inflatable chamber. The system further includes a second pressure sensor in fluid communication with the second mattress inflatable chamber to sense pressure applied to the second mattress of the inflatable chamber. The system further includes a second controller in data communication with the second pressure sensor, the controller configured to receive the one or more sleep-state classifiers and to run the received sleep-state classifiers in order to collect one or more sleep-state votes. The second controller is further configured to determine a sleep-state and operate the bed system according to the determined sleep-state.
1. A bed system comprising:
a first bed comprising:
a first mattress;
a first pressure sensor in communication with the first mattress to sense pressure applied to the first mattress; and
a first controller in data communication with the first pressure sensor, the first controller configured to:
receive, from the first pressure sensor, first pressure readings indicative of the sensed pressure of the first mattress; and
transmit the first pressure readings to a remote server such that the remote server is able to generate one or more sleep-state classifiers that, when run by a controller on incoming pressure readings, provide a sleep-state vote;
a second bed comprising:
a second mattress;
a second pressure sensor in communication with the second mattress to sense pressure applied to the second mattress; and
a second controller in data communication with the second pressure sensor, the controller configured to:
receive the one or more sleep-state classifiers;
run the received sleep-state classifiers on second pressure readings in order to collect one or more sleep-state votes from the running sleep-state classifiers;
determine, from the one or more sleep-state votes, a sleep-state of a user on the second bed;
responsive to the determined sleep-state, operate the bed system according to the determined sleep-state.
2. The bed system of claim 1 , wherein operating the bed system according to the determined sleep-state comprises one of the list comprising turning on a light, turning off a light, turning on a warming feature, changing bed temperature, changing HVAC temperature, changing firmness of the second mattress, and articulating a foundation of the bed system.
3. The bed system of claim 1 , the bed system further comprising the remote server.
4. The bed system of claim 3 , wherein the remote server is physically remote from the first controller and the second controller; and
wherein the remote server is in data communication with the first controller and the second controller.
5. The bed system of claim 3 , wherein the remote server is configured to:
generate training data from the first pressure data;
generate, from the training data, the one or more sleep-state classifiers; and
send, to the second controller, the one or more sleep-state classifiers.
6. The bed system of claim 5 , wherein generating, from the training data, the one or more sleep-state classifiers comprises:
generating a feature set from the training data;
mapping the training data to a kernel space;
training a classifier with the feature set so that, based on the training data in kernel space, the classifier is able to classify unseen data.
7. The bed system of claim 6 , wherein training a classifier comprises unsupervised training.
8. The bed system of claim 7 , wherein the unsupervised training comprises at least one of the group comprising k-means clustering, mixture modeling, hierarchical clustering, self-organizing mapping, and hidden Markov modelling.
9. The bed system of claim 6 , wherein training a classifier comprises supervised training.
10. The bed system of claim 9 , wherein the supervised training comprises providing the remote server with a set of annotations for the training data.
11. The bed system of claim 10 , wherein the annotations for the training data are provided by a human.
12. The bed system of claim 10 , wherein the annotations for the training data are provided programmatically.
13. The bed system of claim 5 , wherein generating the one or more sleep-state classifiers comprises training a deep learning model on the training data.
14. The bed system of claim 13 , wherein training the deep learning model on the training data comprises generating an initial neural network configured to receive pressure data and generate sleep-state votes.
15. The bed system of claim 14 , wherein the sleep-state vote comprises a sleep-state classification and a confidence value.
16. The bed system of claim 14 , wherein generating the one or more sleep-state classifiers comprises:
determining a loss value for the initial neural network; and
iteratively refining, beginning with the initial neural network, to a final neural network having a lower loss value than the initial neural network.
17. The bed system of claim 16 , wherein the iterative refining is performed with a gradient descent process until a lower loss value cannot be found with the gradient descent process.
18. The bed system of claim 1 , wherein a particular sleep-state classifier is used for multiple users in multiple beds.
19. The bed system of claim 1 , wherein the sleep-state classifiers are personalized for a single user such that the sleep-state classifiers are generated from training data of the single user's use of the bed system and the sleep-state classifiers are used to detect sleep-state of the single user on the second bed.
20. A bed system comprising:
a first bed comprising:
a first mattress;
means for supporting the first mattress;
a first pressure sensor in communication with the first mattress to sense pressure applied to the first mattress; and
a first controller in data communication with the first pressure sensor, the first controller configured to:
receive, from the first pressure sensor, first pressure readings indicative of the sensed pressure of the first mattress; and
transmit the first pressure readings to a remote server such that the remote server is able to generate one or more sleep-state classifiers that, when run by a controller on incoming pressure readings, provide a sleep-state vote;
a second bed comprising:
a second mattress;
a second pressure sensor in communication with the second mattress to sense pressure applied to the second mattress; and
a second controller in data communication with the second pressure sensor, the controller configured to:
receive the one or more sleep-state classifiers;
run the received sleep-state classifiers on second pressure readings in order to collect one or more sleep-state votes from the running sleep-state classifiers;
determine, from the one or more sleep-state votes, a sleep-state of a user on the second bed;
responsive to the determined sleep-state, operate the bed system according to the determined sleep-state.