Abstract: This disclosure provides embodiments for context based vehicular traffic prediction. A trained neural network modeling a relationship between historical traffic data and associated historical contextual data for a roadway link is obtained. Expected contextual data for a future time period for the roadway link is acquired. Predicted traffic data for the future time period for the roadway link is generated with the trained neural network based on the expected contextual data.

Abstract: A transportation system for identifying an object using a short range radar at a transportation gate. The transportation system includes one or more short range radars and a cloud server. The radars detect the object within a predetermined distance from the transportation gate and sense the object to generate a point cloud. An identification of the object is determined based on sensed data of the object using a machine learning algorithm from the cloud server. The identification is determined based on matching the point cloud with a plurality of profiles. The plurality of profiles includes matching information for a plurality of predetermined objects. The object is selected from the plurality of predetermined objects using the matching information. An authorization for the object is determined using another machine learning algorithm. Based on the authorization, either the passage through the transportation gate is authorized or the object is flagged as unauthorized.

Abstract: An implementation is for a two-phase shutoff of a device having a sensor coupled to an integral shutoff system. One example includes a metering system with a sensor coupled to an integral shutoff system, wherein the sensor is used to perform a measurement which indicates that a first threshold has been met, a first response system configured to perform at least one action with respect to receiving the indication that the first threshold was met, the at least one action occurring while the integral shutoff system remains inactivated, a second response system configured to receive an indication from the metering system, wherein the sensor is used to perform a second measurement which indicates that a second threshold has been met, and a second response system configured to perform at least one additional action.

Abstract: A motorcycle including a motorcycle body having a front part, a tail part and a central part between the front part and the tail part front and rear wheels constrained to the motorcycle body (2,3,4), a traction engine constrained to the motorcycle body (2,3,4) and operatively connected to at least one of the wheels, at least one optical signalling device fixed to the motorcycle body arranged and oriented so as to be visible by a vehicle that is following the motorcycle, an electronic control unit of the optical signalling device operatively connected to the optical signalling device, an obstacle sensor fixed to the motorcycle body (2,3,4) and operatively connected to the electronic control unit, where the electronic control unit is adapted and configured to receive at least one output signal supplied by the obstacle sensor, verifying whether said output signal meets at least one logical activation condition and, in such case, turning on the optical signalling device to signal a risk of collision with the moto

Abstract: Provided are an output device, a method for generating a machine learning model, and a computer-readable storage medium for properly controlling a human-powered vehicle so as to travel comfortably for a long time by using a machine learning model. The output device includes an acquisition unit that acquires input information related to traveling of a human-powered vehicle, and a processor configured to train a machine learning model in accordance with an index value indicating electric power consumption efficiency in a power supply device for supplying electric power to a component of the human-powered vehicle, and to output output information related to controlling the component when the input information is inputted.

Abstract: A system for determining positions of labels. Each label includes a processor and a transmitting and receiving device, and each label is configured for transmitting an electromagnetic first type beacon signal. The labels are also configured for receiving first type beacon signals from other labels, and for determining first type positioning data. The labels are also configured to transmit information about the positioning data. The system includes a receiver for receiving transmitted information about the positioning data, and a computer configured to calculate, on the basis of the received information, the relative positions of the labels relative to each other. The information about the relative positions of the labels can be exported by means of an electrical information signal.

Abstract: A method and a content receiver configured as an Internet of Things (IoT) gateway are provided. The content receiver receives a first signal transmitted by an IoT device in accordance with an IoT protocol and demodulates and decodes the first signal. The content receiver generates one or more Internet protocol (IP) packets or non-IP packets representative of the first signal and sends the one or more IP packets or non-IP packets to an external server.

Abstract: An autonomous vehicle (e.g., mower) includes two or more wheels supporting a chassis upon a ground surface. A cutting motor powers at least one cutting blade, and a cutting frame supports the cutting motor relative to the chassis. The cutting frame is movable, relative to the chassis, to allow adjustment of a height-of-cut of the cutting blade relative to the ground surface. First and second guide rods are operatively attached to the chassis and are received within corresponding first and second apertures of the cutting frame to guide movement of the cutting frame. Biased bearings associated with the cutting frame may bias associated bearing members against the guide rods.

Abstract: A parking meter detects an object in proximity, based on a change in a proximity measurement at the meter, activates a directional sensor in response to detecting the object, receives sensor data at a meter processor from the directional sensor, wherein the received sensor data indicates a predetermined direction to the detected object relative to the meter. The parking meter determines a presence of the object, or lack thereof, in the predetermined direction based on the sensor data, and upon a positive determination of the presence of the object, stores an indication of the presence of the object along with a time of the positive determination.

Abstract: Optimizing and/or personalizing activities to a user through artificial intelligence and/or virtual reality.

Abstract: A network device is configured to (i) play back a media item indicated by a remote playback queue provided by a cloud-based computing system, (ii) receive an indication that a playback device is available for playback, (iii) display a now playing screen including (a) information identifying the media item, and (b) an icon that indicates that the network device is not in a connected state with any other network device, (iv) receive a first input selecting the icon, (v) in response to the first input, display a list of one or more available network devices including the playback device, (vi) receive a second input selecting the playback device from the list (vii) after receiving the second input, update the list to indicate that the playback device is selected for playback of the remote playback queue, and (viii) transfer playback of the remote playback queue from the network device to the playback device.

Abstract: Systems and methods for detecting determining a volume of urine in an absorbent article such as a diaper. A diaper loading application obtains a first measurement of ambient light received from a photodetector while a light source is off and a second measurement from the photodetector while the light source is transmitting light on an absorbent article. The application determines a normalized measurement of light reflected from an absorbent article by removing an ambient light signal from the second measurement based on the first measurement. The application determines, from the normalized measurement, a presence of urine in the absorbent article. The application further determines an estimated volume of urine in the absorbent article, wherein the determining is based on an elapsed time since the presence of urine and an activity state of an infant wearing the absorbent article.

Abstract: Aspects of the present disclosure include a PIR assembly including a dome comprising a plurality of optical components, a stationary circuit board, and a moveable PIR sensor moveably coupled to the stationary circuit board via a flexible cable, wherein the moveable PIR sensor is configured to move to a first position to monitor a first zone via a first optical component of the plurality of optical components and to a second position to monitor a second zone via a second optical component of the plurality of optical components.

Abstract: Systems and methods are disclosed herein for a pedestrian crossing warning system that may use multi-modal technology to determine attributes of a person and provide a warning to the person in response to a calculated risk level to effect a reduction of the risk level. The system may utilize sensors to receive data indicative of a trajectory of a person external to the vehicle. Specific attributes of the person such as age or walking aids may be determined. Based on the trajectory data and the specific attributes, a risk level may be determined by the system using a machine learning model. The system may cause emission of a warning to the person in response to the risk level.

Abstract: Techniques are described for using sensor data derived from a monitoring system to drive personalized content. Sensor data captured by a monitoring system may be used to determine attributes of users of the monitoring system and/or attributes of a property monitored by the monitoring system. The determined attributes may be used to select content to present to users of the monitoring system. Content presentation may be made through the monitoring system and may be triggered based on events detected by the monitoring system.

Abstract: A controller of a vehicle detects persons that are approaching the vehicle and uses sensors to collect data regarding the persons to determine whether a security risk exists. In one approach, the collected data is used to determine whether each person is associated with the vehicle. In response to determining that at least one of the persons is unknown, a security risk is evaluated based on data from monitoring of the environment of the vehicle. In response to determining that a security risk score exceeds a threshold, one or more actions for the vehicle are performed to make the vehicle more secure.

Abstract: Described is a transformer end-of-life thermal transmitting indicator (thermal transmitting indicator) that is configured and well suited for monitoring the health of a transformer and communicating the health of the transformer to an end user by way of a cellular transceiver. The thermal transmitting indicator can be configured to alert nearby people of an impending transformer explosion if the transformer fails. The thermal transmitting indicator is also arranged to transmit any problems or impending danger from the transformer to the end user who can then respond by preemptively dealing with the failing transformer. The thermal transmitting indicator comprises liquid sensors spaced in its housing to sense if water or high humidity has infiltrated the housing.

Abstract: According to various embodiments, a robotic cleaner may include a battery; a driving device for moving the robotic cleaner; a cleaning device for allowing the robotic cleaner to perform cleaning work; and a processor configured to determine, as a zone that can be cleaned, a first zone in the entire space by considering the residual capacity of the battery and the location of a charging device, operate the driving device and cleaning device to perform cleaning of the first zone, and perform control such that the robotic cleaner moves to the location of the charging device. Other embodiments are possible.

Abstract: The disclosed wearable device systems include several features for alerting and guiding persons who are approaching or near to potentially hazardous or high-risk conditions in their nearby environment. Sensor data from wearable devices (also referred to herein as “wearables”) are used to determine the presence of various unsafe environmental conditions and phenomenon, including dangerous terrain or other unusual conditions. The wearable would be used to warn a person, for example via auditory or haptic-based feedback, if the person is about to encounter an unsafe condition. In particular, the proposed systems can be of great benefit to the visually impaired, those persons with physical disabilities, or persons otherwise vulnerable to particular environmental conditions.

Abstract: A network device is configured to (i) play back a media item indicated by a remote playback queue provided by a cloud-based computing system, (ii) receive an indication that a playback device is available for playback, (iii) display a now playing screen including (a) information identifying the media item, and (b) an icon that indicates that the network device is not in a connected state with any other network device, (iv) receive a first input selecting the icon, (v) in response to the first input, display a list of one or more available network devices including the playback device, (vi) receive a second input selecting the playback device from the list (vii) after receiving the second input, update the list to indicate that the playback device is selected for playback of the remote playback queue, and (viii) transfer playback of the remote playback queue from the network device to the playback device.