Abstract: An example robot performs a scan to obtain image data of a given region. The robot performs image analysis on the image data to detect a set of undesirable objects, and generates a reference map that excludes the set of undesirable objects, where the reference map is associated with the location of the robot at the time of the scan.

Abstract: Examples of neural networks trained for multiple tasks are described herein. In some examples, a method may include determining a feature vector using a first portion of a neural network. In some examples, the neural network is trained for multiple tasks. Some examples of the method may include transmitting the feature vector to a remote device. In some examples, the remote device is to perform one of the multiple tasks using a second portion of the neural network.

Abstract: An example control system includes a memory and at least one processor to obtain image data from a given region and perform image analysis on the image data to detect a set of objects in the given region. For each object of the set, the example control system may classify each object as being one of multiple predefined classifications of object permanency, including (i) a fixed classification, (ii) a static and fixed classification, and/or (iii) a dynamic classification. The control system may generate at least a first layer of a occupancy map for the given region that depicts each detected object that is of the static and fixed classification and excluding each detected object that is either of the static and unfixed classification or of the dynamic classification.

Abstract: A method includes receiving, with a computing device, a configuration file and a client request to apply a machine learning model to a set of data from a sensor. The method includes performing, with the computing device, preprocessing on the set of data from the sensor based on the configuration file to generate preprocessed data. The method includes sending, with the computing device, a call to a model server to apply the machine learning model to the preprocessed data.

Abstract: The rack mounted weather shield is an awning. The rack mounted weather shield is configured for use with an automobile. The rack mounted weather shield attaches to a cargo rack. The rack mounted weather shield creates a weather protected space along a side of the automobile. The rack mounted weather shield is used for entering and exiting the automobile in inclement weather. The rack mounted weather shield extends and retracts. The rack mounted weather shield comprises a plurality of fans, a plurality of control circuits, and a remote control. Each of the plurality of fans creates the weather protected space on a side of the automobile. Each of the plurality of control circuits extends and retracts an individual fan selected from the plurality of fans. The remote control is a radio frequency device that controls the operation of the plurality of control circuits.

Abstract: Techniques are described herein for evaluating user activities on a website for detecting and alerting anomalies with the website. For example, an alerting system may determine a set of time-windows for each of a set of attribute value(s) and use a set of performance metrics and/or web session events for the time-windows from historical web sessions to detect an anomaly in a current time-window. The alerting system may determine an evaluation range based on weighted performance ranges, and alert a client indicating a performance anomaly if a performance metric at the time of evaluation are out of the evaluation range. Attribute value(s) related to a website issue can be identified based on a correlated to anomalous web session events or to an anomalous time-window.

Abstract: The invention generally relates to methods and systems for adding chemicals to a body of water through a skimmer basket in a strainer well associated with the body of water.

Abstract: A method includes receiving, with a computing device, a first client request from a first client that identifies a machine learning model and a sensor. The method includes sending, with the computing device, a call to a server to apply the identified machine learning model to a set of data from the identified sensor, in response to the first client request. The method includes receiving, with the computing device, a second client request from a second client that identifies a same machine learning model and sensor as the first client request. The method includes sending, with the computing device, response data from the identified machine learning model to both the first client and the second client without sending an additional call to the server in response to the second client request.

Abstract: A hierarchical sensor data storage system includes a data storage to store processed data that includes sensor data generated by a sensor and feature vectors associated with the sensor data that are generated by a processing subsystem processing the sensor data. Another data storage may store a reduced subset of the feature vectors and associated sensor data as salient data, as determined by a saliency subsystem.

Abstract: A method includes receiving, with a computing device, a configuration file and a client request to apply a machine learning model to a set of data from a sensor. The method includes performing, with the computing device, preprocessing on the set of data from the sensor based on the configuration file to generate preprocessed data. The method includes sending, with the computing device, a call to a model server to apply the machine learning model to the preprocessed data.

Abstract: In one example in accordance with the present disclosure, a method is described. According to the method, from assembly instructions for a multi-component device, component-specific assembly instructions are generated for a component. The component-specific assembly instructions include a portion of the assembly instructions that relate to the component. Data identifying the component-specific assembly instructions are encoded into a format to be formed onto the component and the encoded data is formed onto the component.

Abstract: In example implementations, an apparatus is provided. The apparatus includes a communication interface, a memory, a moving mechanism, and a processor. The communication interface is to receive a request to initiate a telepresence session. The memory is to store a location policy. The moving mechanism is to move the apparatus to a selected telepresence location to initiate the telepresence session based on the location policy. The processor is communicatively coupled to the communication interface, the memory and the moving mechanism. The processor is to determine the selected telepresence location to initiate the telepresence session in response to the request before the telepresence session is initiated.

Abstract: Embodiments of an interconnect apparatus advantageously useful in handling Big Data Graph Analytics enable improved signal integrity, even at high clock rates, increased bandwidth, and lower latency. In an interconnect apparatus for core arrays a sending processing core can send data to a receiving core by forming a packet whose header indicates the location of the receiving core and whose pay load is the data to be sent. The packet is sent to a Data Vortex switch described herein and in the patents incorporated herein. The Data Vortex switch is on the same chip as an array of processing cores and routes the packet to the receiving core first by routing the packet to the processing core array containing the receiving processing core. The Data Vortex switch then routes the packet to the receiving processor core in a processor core array.

Abstract: Techniques are disclosed for auditing an IP address prefix that has been assigned to an entity as part of an administrator policy, to determine whether the assignment was implemented on the network. In an embodiment, associations between IP addresses and their assignment are stored in a database. IP addresses are read and semi-authoritative sources (e.g., DNS servers) are queried for information about the IP addresses. Information received in response to the query may be used to validate the IP address (e.g., in a network, all IP addresses used for VM instances will have a corresponding URL in a specific format).

Abstract: Dispenser systems, dispensers, and repositories can add a fragrance to an unscented liquid beauty preparation. The dispenser system includes a dispenser having a cavity for retaining at least a first liquid, and a repository configured for removably attaching to the dispenser, the repository having a reservoir for retaining at least a second liquid. The dispenser is coupled with a pump assembly including at least one pump for drawing the at least a first liquid and the at least a second liquid into a mixing chamber. The mixing chamber is coupled with an actuator in such a manner that when the actuator is pressed down by an external force, the mixing chamber communicates with the pump to suction the first and second liquids into the mixing chamber to form a liquid mixture for dispensing through a nozzle.

Abstract: A conveyor apparatus comprising an elongated endless flexible conveyor belt having a moulded ridged conformation on its inner surface mounted between a drive roller drum and a take up roller drum, two elongated conveyor side plates and a plurality of idle conveyor rollers, wherein the diameter of the drive roller drum and the take up roller drum is uniform throughout their length.

Abstract: One example of a video monitoring system includes a frame acquisition subsystem, a stage gate motion detection subsystem, a person detection subsystem, a face recognition subsystem, and an alert emission subsystem. The frame acquisition subsystem extracts frames from an input video. The stage gate motion detection subsystem separates background motion from foreground motion within frames. The person detection subsystem detects people including faces and bodies within the foreground motion. The face recognition subsystem matches detected faces to previously registered users. The alert emission subsystem provides alerts based on events detected by the stage gate motion subsystem, the person detection subsystem, and the face recognition subsystem.