A prediction device 100 of the present invention includes a detection means 121 for, on the basis of a river image that is an image obtained by capturing a river and associated with capturing position information representing a position where the river is captured, detecting river condition information representing a condition of the river at the position where the river image is captured; and a prediction means 122 for, on the basis of the capturing position information, the river condition information, and topography information representing the topography of the river, predicting a river condition representing a condition of the river at a given point of the river. The given point is different from the position represented by the capturing position information.

Systems and methods are described for identifying, using a sensor, a location of an object in an environment, and determining a classification of the object. A human may be identified in proximity with the object, an identity of the human may be determined, and a determination may be made that a hazardous condition may occur, based on a combination of the location of the object, the classification of the object, and the identity of the human in proximity with the object. In response to determining that the hazardous condition may occur, an augmented reality scene associated with the potentially hazardous condition associated with the object may be generated for presentation, at a user device.

A physical condition detection method executed by a computer includes: obtaining body motion data of a subject over a given current time period including a current time; generating a current state model representing a current state of physical condition of the subject from the body motion data of the subject over the current time period, by using a mathematical model constructed using body motion data of the subject over a past period during which the physical condition of the subject was in a normal state; and outputting the current state model for detecting a change in the physical condition of the subject based on one or more differences obtained by comparing the current state model and a normal state model representing the normal state of the physical condition of the subject and generated from the body motion data of the subject over the past period using the mathematical model.

A system for determining whether shoppers are eligible for frictionless checkout is disclosed. The system has a processor that obtains image data captured using image sensors positioned in a retail store. The processor analyzes the image data to identify at least one shopper at one or more locations of the retail store. The processor detects, based on the analysis of the image data, at least one product interaction event associated with an action of the at least one shopper at the one or more locations of the retail store. Further, based on the detected at least one product interaction event, the processor determines whether the at least one shopper is eligible for frictionless checkout. In response to a determination that the at least one shopper is ineligible for frictionless checkout, the processor causes delivery of an indicator that the at least one shopper is ineligible for frictionless checkout.

A method may include receiving an event message from a home security edge device, including image data. The method may include determining whether the image data represents a false trigger event based on inputting the image data into an artificial intelligence model and/or receiving a user input. The user input may be responsive to a presentation of the image data. If the image data represents the false trigger event, the method may include generating training data for retraining the artificial model. The training data may include a portion of the image data. The method may include updating a local dataset to include the training data and training the artificial intelligence model. The method may include transmitting the training data to a central database. If the image data does not represent a false trigger event, the method may include providing a security alert for display on one or more user devices.

A method may include receiving an event message from a home security edge device, including image data. The method may include determining whether the image data represents a false trigger event based on inputting the image data into an artificial intelligence model and/or receiving a user input. The user input may be responsive to a presentation of the image data. If the image data represents the false trigger event, the method may include generating training data for retraining the artificial model. The training data may include a portion of the image data. The method may include updating a local dataset to include the training data and training the artificial intelligence model. The method may include transmitting the training data to a central database. If the image data does not represent a false trigger event, the method may include providing a security alert for display on one or more user devices.

A security system of a building includes a processing circuit. The processing circuit is configured to detect, based on data of security equipment of the building, that a security alarm of the building is a false alarm and search, responsive to the detection of the false alarm, a database to identify a past corrective action accepted for implementation and at least one false alarm occurring after the past corrective action was accepted and before detection of the false alarm. The processing circuits is configured to generate a corrective action to reduce an occurrence of the false alarm based on a result of the search and implement the corrective action to update operation of the security equipment to reduce the occurrence of the false alarm.

A security system of a building includes a processing circuit. The processing circuit is configured to detect, based on data of security equipment of the building, that a security alarm of the building is a false alarm and search, responsive to the detection of the false alarm, a database to identify a past corrective action accepted for implementation and at least one false alarm occurring after the past corrective action was accepted and before detection of the false alarm. The processing circuits is configured to generate a corrective action to reduce an occurrence of the false alarm based on a result of the search and implement the corrective action to update operation of the security equipment to reduce the occurrence of the false alarm.

Systems, methods and apparatuses to detect an item left in a vehicle and to generate an alert about the item. For example, a camera configured in a vehicle can be used to monitor an item associated with a user of the vehicle. The item as in an image from the camera can be identified and recognized using an artificial neural network. In response to a determination that the item recognized in the image is left in the vehicle after the user has exited the vehicle, an alert is generated to indicate that an item is in the vehicle but the user is leaving the vehicle.

A system and method for detecting in real-time high risk lightning (HRL) strikes and sending out alerts to responsible personnel to allow for earlier responses to lightning caused fire ignitions to help maintain and/or reduce the chance of spread by the wildfire. The system and method allow for HRL events and fire ignitions to be detected preferably within seconds. The system and method can use a network of detectors, data from environmental satellites and/or other environmental data sources, and novel AI/algorithms for signal processing to relatively quickly locate fire ignition spots. Thus, the system and method provide for actionable wildfire intelligence in real-time and to relatively quickly and accurately send out alerts when an HRL event has been determined. Cameras and drones can be used to provide real-time visualization at the location of the HRL event to verify or monitor any fire ignition or smoldering at the area of the HRL event.