A building management system of a building includes one or more memory devices configured to store instructions thereon, that, when executed by one or more processors, cause the one or more processors to generate agents, each agent of the agents paired with one entity of a plurality of entities of an entity database, wherein the entity database includes relationships between the entities, wherein the entities represent physical building entities of the building comprising building equipment or building spaces. The instructions cause the one or more processors to communicate, by the plurality of agents, data of the physical building entities via a plurality of agent communication channels and perform, by the plurality of agents, one or more operations for the plurality of entities based on the data.

Techniques are provided for detecting copy number variations. Each sequence read of a set of sequence reads is aligned with a portion of a reference sequence. A coverage vector is generated that includes a plurality of elements, each element in the plurality of elements indicating a number of the set of sequence reads that were aligned to a particular position within the reference sequence. A normalization vector is accessed that was generated based on performance of a component analysis on a set of other coverage vectors corresponding to a set of other subjects. An adjusted coverage vector is generated using the coverage vector and normalization vector. One or more subject-specific normalization values are generated based on the coverage vector. One or more copy number variations are identified that corresponding to the sample using the adjusted coverage vector and the subject-specific normalization values.

Systems and methods that yield highly-accurate classification of acoustic and other non-image events, involving pre-processing data from one or more transducers and generating a visual representation of the source as well as associated features and processing, are disclosed. According to certain exemplary implementations herein, such pre-processing steps may be utilized in situations where 1) all impulsive acoustic events have many features in common due to their point source origin and impulsive nature, and/or 2) the error rates that are considered acceptable in general purpose image classification are much higher than the acceptable levels in automatic impulsive incident classification. Further, according to some aspects, the data may be pre-processed in various ways, such as to remove extraneous or irrelevant details and/or perform any required rotation, alignment, scaling, etc. tasks, such that these tasks do not need to be “learned” in a less direct and more expensive manner in the neural network.

An outlier detection device includes a reservoir computer having an input layer, a reservoir main unit including neurons connected by synapses, and a read-out configured to calculate and output an inner product of a weight vector and an activity value vector, each element of which is an activity value output from each of neurons based on an input to the input layer, a learning unit configured to acquire an observed signal, calculate an error between the inner product and the observed signal, and update the weight vector using a value obtained by applying an adaptive filter to the error, a norm calculation unit configured to sequentially calculate a norm of the weight vector updated by the learning unit, and a determination unit configured to determine whether an outlier is included in the observed signal based on at least one of the norms calculated by the norm calculation unit.

An electronic device is provided. The electronic device includes a display including a sensing area, a sensing layer below the display, the sensing layer including a plurality of openings, and a biometric sensor for receiving light emitted from the sensing area and reflected from an external object. The sensing layer includes first signal line sets, each including a plurality of first signal lines extending in a first direction, repeatedly arranged and spaced from each other by a specified spacing, and second signal line sets, each including a plurality of second signal lines extending in a second direction intersecting the first direction, repeatedly arranged and spaced from each other by a specified spacing. At least one of the first or second signal lines extends in and along a portion of the sensing layer between adjacent ones of the openings, which are positioned in a path along which light is reflected from the object and is then incident on the biometric sensor.

Disclosed herein is a method and system a system that enables users to simply tap their smartphone or other electronic device to an object to discover and rapidly utilize contextual functionality. As described herein, the system and method provide for recognition of physical contact with uninstrumented objects, and summons object-specific interfaces.

Methods, system, and computer readable medium are presented for predicting defects using a machine learning component based on a generated signature. A trained machine learning component that has been trained with historic data that represents a series of events that occurred within a plurality of heterogeneous systems over a plurality of periods of change for the heterogeneous systems can be received. A base signature for a first heterogeneous system that includes a first mix of modules can be compared to a current signature for the first heterogeneous system to identify one or more irregularities. The trained machine learning component can predict one or more defects for the first heterogeneous system based on the identified irregularity.

Head-mounted augmented reality (AR) devices can track pose of a wearer's head or pose of a hand-held user input device to enable wearer interaction in a three-dimensional AR environment. A pose sensor (e.g., an inertial measurement unit) in the user input device can provide data on pose (e.g., position or orientation) of the user input device. An electromagnetic (EM) tracking system can also provide pose data. For example, the handheld user input device can include an EM emitter that generates an EM field, and the head-mounted AR device can include an EM sensor that senses the EM field. The AR device can combine the output of the pose sensor and the EM tracking system to reduce drift in the estimated pose of the user input device or to transform the pose into a world coordinate system used by the AR device. The AR device can utilize a Kalman filter to combine the output of the pose sensor and the EM tracking system.

Systems and methods for detecting patterns in data from a time-series are provided. According to some implementations, the systems and methods may use network topology information combined with object recognition techniques to detect patterns. One embodiment of a method includes the steps of obtaining information defining a topology of a multi-layer network having a plurality of Network Elements (NEs) and a plurality of links interconnecting the NEs and receiving Performance Monitoring (PM) metrics and one or more alarms from the multi-layer network. Based on the information defining the topology, the PM metrics, and the one or more alarms, the method also includes the step of utilizing a Machine Learning (ML) process to identify a problematic component from the plurality of NEs and links and to identify a root cause associated with the problematic component.

A method comprising performing object detection within a set of representations of a hierarchically-structured signal, the set of representations comprising at least a first representation of the signal at a first level of quality and a second representation of the signal at a second, higher level of quality.