Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, generate a time correlated data stream for a data point, and generate a time correlated reliability data stream for the data point. The building device data includes a plurality of data samples of the data point. The time correlated data stream includes values of the plurality of data samples of the data point. The time correlated reliability data stream includes a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.

Abstract: An integration application comprising a plurality of components may be provided. The components may provide connections between systems. The integration application may be configured to allow the systems to exchange data. It may be determined that a new version of a first one of the components is a candidate for release. Prior to release of the new version of the first component, the integration application may be tested using the new version of the first component and an existing version of the first component. An instance of the integration application may be automatically caused to be upgraded to include the new version of the first component.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, the building device data comprising a plurality of data samples of a data point and generate a time correlated data stream for the data point, the time correlated data stream comprising values of the plurality of data samples of the data point. The instructions cause the one or more processors to generate a time correlated reliability data stream for the data point, the time correlated reliability data stream comprising a plurality of reliability values indicating reliability of the values of the plurality of data samples of the data point.

Abstract: A method for using natural language data to analyze tasks via machine learning, includes obtaining task data indicative of at least one task, and including natural language data associated with the at least one task; converting the task data into task feature data; and generating an evaluation of the at least one task by using a trained machine-learning model on the task feature data. The trained machine-learning model has been trained based on historical task feature data and historical evaluations associated with the historical task feature data to learn associations between the historical task feature data and the historical evaluations, so that the trained machine-learning model is configured to use the learned associations to generate the evaluation based on the task feature data.

Abstract: A building system including one or more memory devices configured to store instructions thereon, wherein the instructions, when executed by one or more processors, cause the one or more processors to cause a user interface of a user device to display a plurality of nodes of a semantic building model and a plurality of relationships between the plurality of nodes of the semantic building model. The instructions cause the one or more processors to receive a search input from the user device, generate a search result based on the search input, wherein the search result comprises an indication of a portion of nodes of the plurality of nodes and a portion of relationships of the plurality of relationships, and cause the user interface to display the portion of nodes of the plurality of nodes and the portion of relationships of the plurality of relationships.

Abstract: Described herein are systems and methods for compressing and speeding up dense matrix multiplications as found, for examples, in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, trace norm regularization technique embodiments were introduced and studied for training low rank factored versions of matrix multiplications. Compared to standard low rank training, the methods more consistently lead to good accuracy versus number of parameter trade-offs and can be used to speed-up training of large models. Faster inference may be further enabled on ARM processors through kernels optimized for small batch sizes, resulting in speed ups over the currently used library. Beyond LVCSR, the techniques are also generally applicable to embedded neural networks with large fully connected or recurrent layers.

Abstract: A building system including one or more memory devices configured to store instructions thereon, wherein the instructions, when executed by one or more processors, cause the one or more processors to cause a user interface of a user device to display a plurality of nodes of a semantic building model and a plurality of relationships between the plurality of nodes of the semantic building model. The instructions cause the one or more processors to receive a search input from the user device, generate a search result based on the search input, wherein the search result comprises an indication of a portion of nodes of the plurality of nodes and a portion of relationships of the plurality of relationships, and cause the user interface to display the portion of nodes of the plurality of nodes and the portion of relationships of the plurality of relationships.

Abstract: A building system including one or more memory devices configured to store instructions thereon, wherein the instructions, when executed by one or more processors, cause the one or more processors to cause a user interface of a user device to display a plurality of nodes of a semantic building model and a plurality of relationships between the plurality of nodes of the semantic building model. The instructions cause the one or more processors to receive a search input from the user device, generate a search result based on the search input, wherein the search result comprises an indication of a portion of nodes of the plurality of nodes and a portion of relationships of the plurality of relationships, and cause the user interface to display the portion of nodes of the plurality of nodes and the portion of relationships of the plurality of relationships.

Abstract: A building system for implementing building applications includes one or more memory devices storing instructions, the instructions causing one or more processors to receive a static semantic building application, wherein the static semantic building application comprises one or more operations and a first semantic description of the static semantic building application and determine, based on building information describing a building and the first semantic description of the static semantic building application, one or more implementation details of a particular implementation of the static semantic building application. The instructions cause the one or more processors to generate, based on the one or more implementation details, a dynamic semantic building application comprising the one or more operations and a second semantic description of the dynamic semantic building application and operate the dynamic semantic building application.

Abstract: Revocable biometric-based keys for digital signing are provided by, in part, generating a revocable public key at a secure device and transmitting the public key to a registration system for registration to facilitate linking the public key to the secure device user's identity for use in accessing a protected resource. Generating the revocable public key may include generating a salt, storing the salt on the secure device, and temporarily obtaining, by the secure device, biometric data of the user of the secure device. The biometric data is obtained from user biometrics, and the temporarily obtaining is absent storing the biometric data in persistent storage. A public and private key pair is generated at the secure device based, at least in part, on the stored salt and the user's temporarily obtained biometric data.

Abstract: A building system including one or more memory devices configured to store instructions thereon, wherein the instructions, when executed by one or more processors, cause the one or more processors to cause a user interface of a user device to display a plurality of nodes of a semantic building model and a plurality of relationships between the plurality of nodes of the semantic building model. The instructions cause the one or more processors to receive a search input from the user device, generate a search result based on the search input, wherein the search result comprises an indication of a portion of nodes of the plurality of nodes and a portion of relationships of the plurality of relationships, and cause the user interface to display the portion of nodes of the plurality of nodes and the portion of relationships of the plurality of relationships.

Abstract: A building interface system for generating a custom user interface, the building interface system includes one or more memory devices configured to store instructions thereon, the instructions causing one or more processors to receive user input defining one or more graphical requirements from a user device, retrieve a semantic building system model based on the one or more graphical requirements, wherein the semantic building system model comprises semantic information describing a building system, retrieve one or more graphic templates based on the semantic building system model and the one or more graphical requirements, the one or more graphic templates providing a generic description of one or more user interface elements, generate the custom user interface based on the one or more graphic templates and the semantic building system model, and cause the user device to display the custom user interface.

Abstract: A building system for implementing user defined logic 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 receive user input from a user device, the user input providing a natural language description of a building logic application for a piece of building equipment. The instructions cause the one or more processors to retrieve a semantic logic application comprising a semantic description of the building logic application based on the natural language description and a semantic building model comprising a semantic building description of the piece of building equipment, generate a custom logic application based on the semantic logic application, the natural language description, and the semantic building model, and operate the custom logic application.

Abstract: A building system of a building including one or more memory devices configured to store one or more instructions that, when executed on one or more processors, cause the one or more processors to exercise a building entity causing building entity data to be generated associated with the building entity, the building entity data indicating a result of exercising the building entity and collect the building entity data. The instructions cause the one or more processors to identify, based on a relational model, one or more relationships between one or more building entities and the building entity, wherein the one or more relationships indicate that exercising the building entity affects operation of the one or more building entities and identify that the building is experiencing a performance issue by analyzing the building entity data and the one or more relationships.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, the building device data comprising a plurality of data samples of a data point and generate a time correlated data stream for the data point, the time correlated data stream comprising values of the plurality of data samples of the data point. The instructions cause the one or more processors to generate a time correlated reliability data stream for the data point, the time correlated reliability data stream comprising a plurality of reliability values indicating reliability of the values of the plurality of data samples of the data point.

Abstract: A building system for implementing building applications includes one or more memory devices storing instructions, the instructions causing one or more processors to receive a static semantic building application, wherein the static semantic building application comprises one or more operations and a first semantic description of the static semantic building application and determine, based on building information describing a building and the first semantic description of the static semantic building application, one or more implementation details of a particular implementation of the static semantic building application. The instructions cause the one or more processors to generate, based on the one or more implementation details, a dynamic semantic building application comprising the one or more operations and a second semantic description of the dynamic semantic building application and operate the dynamic semantic building application.

Abstract: Revocable biometric-based keys for digital signing are provided by, in part, generating a revocable public key at a secure device and transmitting the public key to a registration system for registration to facilitate linking the public key to the secure device user's identity for use in accessing a protected resource. Generating the revocable public key may include generating a salt, storing the salt on the secure device, and temporarily obtaining, by the secure device, biometric data of the user of the secure device. The biometric data is obtained from user biometrics, and the temporarily obtaining is absent storing the biometric data in persistent storage. A public and private key pair is generated at the secure device based, at least in part, on the stored salt and the user's temporarily obtained biometric data.

Abstract: Described herein are systems and methods for compressing and speeding up dense matrix multiplications as found, for examples, in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, trace norm regularization technique embodiments were introduced and studied for training low rank factored versions of matrix multiplications. Compared to standard low rank training, the methods more consistently lead to good accuracy versus number of parameter trade-offs and can be used to speed-up training of large models. Faster inference may be further enabled on ARM processors through kernels optimized for small batch sizes, resulting in speed ups over the currently used library. Beyond LVCSR, the techniques are also generally applicable to embedded neural networks with large fully connected or recurrent layers.

Abstract: A system for controlling at least one heating, ventilation, and/or air conditioning unit to increase efficiency while maintaining comfort. The system comprises at least one computer. The at least one computer is configured to receive an indication of measured occupant load. The at least one computer is further configured to send a control signal to the at least one heating, ventilation, and/or air conditioning unit. The at least one computer may receive the indication of the measured occupant load by receiving from at least one sensor node at least a zone occupant quantity and a zone temperature. The at least one computer may send the control signal to the at least one heating, ventilation, and/or air conditioning unit by sending a signal that controls at least one variable air volume box to set a supply air flow rate and a supply air temperature based on the measured occupant load.

Abstract: A system for controlling at least one heating, ventilation, and/or air conditioning unit to increase efficiency while maintaining comfort. The system comprises at least one computer. The at least one computer is configured to receive an indication of measured occupant load. The at least one computer is further configured to send a control signal to the at least one heating, ventilation, and/or air conditioning unit. The at least one computer may receive the indication of the measured occupant load by receiving from at least one sensor node at least a zone occupant quantity and a zone temperature. The at least one computer may send the control signal to the at least one heating, ventilation, and/or air conditioning unit by sending a signal that controls at least one variable air volume box to set a supply air flow rate and a supply air temperature based on the measured occupant load.