An information processing apparatus according to an aspect of the present invention includes a situation specifying unit configured to specify a part of a situation of the measurement subject on the basis of the number of measurements of the biological information in each situation of the measurement subject at the time of measuring biological information of the measurement subject by a biological information measuring unit, a current situation detecting unit configured to detect a current situation of the measurement subject, and a support information output unit configured to output support information relating to measurement of the biological information if the current situation corresponds to the measurement promoting situation.

Conventionally, Atrial Fibrillation (AF) has been detected using atrial analyses which is vulnerable to background noise. Again there is a dependency on statistical features which are extracted from R-R intervals of long ECG recordings. The present disclosure addresses AF detection from single lead short ECG recordings of less than one minute wherein automatic detection of P-R and P-Q intervals is difficult, which introduces error in feature computing from the segregated intervals and compromises the performance of the classifier. In the present disclosure, a Recurrent Neural Network (RNN) based architecture comprising two Long Short Term Memory (LSTM) networks is provided for temporal analysis of R-R intervals and P wave regions in an ECG signal respectively. Output sates of the two LSTM networks are merged at a dense layer along with a set of hand-crafted statistical features to create a composite feature set for classification of the AF.

The present invention comprises a novel Virtual Facilities Manager architecture that optimizes home health by combining multiple prediction engines, fed by continuously monitored and processed sensor-based and environmental data (historical as well as current), with an integrated Homecare Network of homeowners and service and other providers. This enables a continuous feedback process in which abnormal conditions (symptoms of an underlying problem, including suboptimal performance) are detected and addressed by issuing contextual alerts with associated actions (related alert-action pairs) in an iterative manner over time. By maintaining a Home Health Record including Scores (e.g., reliability and energy efficiency) representing the systemic state of one or more homes, the present invention detects not only maintenance issues, but also suboptimal performance “problems,” and addresses them with the same iterative troubleshooting approach until such scores return to an acceptable level.

The present invention comprises a novel Virtual Facilities Manager architecture that optimizes home health by combining multiple prediction engines, fed by continuously monitored and processed sensor-based and environmental data (historical as well as current), with an integrated Homecare Network of homeowners and service and other providers. This enables a continuous feedback process in which abnormal conditions (symptoms of an underlying problem, including suboptimal performance) are detected and addressed by issuing contextual alerts with associated actions (related alert-action pairs) in an iterative manner over time. By maintaining a Home Health Record including Scores (e.g., reliability and energy efficiency) representing the systemic state of one or more homes, the present invention detects not only maintenance issues, but also suboptimal performance “problems,” and addresses them with the same iterative troubleshooting approach until such scores return to an acceptable level.

A patient support apparatus, such as a bed, cot, stretcher, etc., for supporting a patient includes an exit detection system with multiple user-selectable modes of operation that each have different sensitivity levels for triggering an exit alert. The exit detection system also includes one or more non-user selectable modes of operation that are automatically implemented in response to a triggering action. For example, a transition mode may be automatically implemented when the user attempts to switch from a first user-selectable mode to a different user selectable mode, or a motion mode may be automatically implemented when movement of one or more components of the patient support apparatus occurs. In the transition mode, the exit detection system may use a least restrictive sensitivity level. In the motion mode, the exit detection system may inhibit exit alerts and/or change the criteria for issuing the exit alert.

A system allows for a user to notify an insurance provider or other third-party with a button press. The button can notify of an emergency situation. An event determiner may analyze information of events surrounding the button click. This information may include the time of day, location, identifying information for the insured, recent locations of the button, information from similar button presses and information from previous insurance claims. Based on this information, the event determiner may provide a high percentage estimate of an abnormal condition: home break-in, car accident, flat tire, etc. The system may automatically take action, depending on the event, such as contacting the police, sending a tow truck, or starting an insurance claim.

A system allows for a user to notify an insurance provider or other third-party with a button press. The button can notify of an emergency situation. An event determiner may analyze information of events surrounding the button click. This information may include the time of day, location, identifying information for the insured, recent locations of the button, information from similar button presses and information from previous insurance claims. Based on this information, the event determiner may provide a high percentage estimate of an abnormal condition: home break-in, car accident, flat tire, etc. The system may automatically take action, depending on the event, such as contacting the police, sending a tow truck, or starting an insurance claim.

A system for alerting a victim of a presence of an offender, the system includes a first bracelet configured to be worn by the victim, the first bracelet including a first GPS receiver, a first wireless network transceiver, a speaker or a vibration motor, and a display element, wherein the first wireless network transceiver comprises a wireless cellular network transceiver or a WiFi transceiver. The system also includes a second bracelet configured to be worn by the offender. A cloud-based monitor system including a computing device and a memory configured to receive data from the first bracelet and the second bracelet and perform appropriate actions as necessary. Each bracelet may include a mechanical lock having at least a first fastener, a second fastener, and/or a third fastener, to provide, respectively, one, two or three levels of security for the device.

A system for alerting a victim of a presence of an offender, the system includes a first bracelet configured to be worn by the victim, the first bracelet including a first GPS receiver, a first wireless network transceiver, a speaker or a vibration motor, and a display element, wherein the first wireless network transceiver comprises a wireless cellular network transceiver or a WiFi transceiver. The system also includes a second bracelet configured to be worn by the offender. A cloud-based monitor system including a computing device and a memory configured to receive data from the first bracelet and the second bracelet and perform appropriate actions as necessary. Each bracelet may include a mechanical lock having at least a first fastener, a second fastener, and/or a third fastener, to provide, respectively, one, two or three levels of security for the device.

A system for notifying occupants of a structure that a pet is proximate to an opening of a structure. The system may include a pet unit wearable on the pet's body and including a transmitter configured to transmit a wireless proximity signal from the pet unit. The system may further include an exit unit positionable at an exit of the structure. The exit unit may include a receiver configured to receive a said wireless proximity signal transmitted by a pet unit, with the receiver being configured to produce an alert signal when a said wireless proximity signal is received. The exit unit may also include an alerting assembly configured to provide a presence alert when the receiver receives a said wireless proximity signal. The alerting assembly may comprise a perceptible alerting mechanism configured to produce a perceptible presence alert which is perceptible to a sense of a human.