Abstract: A computing device stores a predictive model generated by a neural network training engine. The computing device receives first and second two-dimensional (2D) thermal images comprising temperature measurements from respective first and second infrared (IR) sensors. The first and second images have the same size. An image capturing visual field of the second IR sensor partially overlaps with an image capturing visual field of the first IR sensor. The computing device executes a neural network using a predictive model for generating outputs based on inputs. The inputs comprise the temperature measurements of the first and second images. The outputs comprise horizontal and vertical shifts defining a translation of the second image with respect to the first image. An overlapping area in the first image, having a rectangular shape and overlapping with the second image, is determined using the horizontal and vertical shifts.

Abstract: Interactions between a training server and a plurality of environment controllers are used for updating the weights of a predictive model used by a neural network executed by the plurality of environment controllers. Each environment controller executes the neural network using a current version of the predictive model to generate outputs based on inputs, modifies the outputs, and generates metrics representative of the effectiveness of the modified outputs for controlling the environment. The training server collects the inputs, the corresponding modified outputs, and the corresponding metrics from the plurality of environment controllers. The collected inputs, modified outputs and metrics are used by the training server for updating the weights of the current predictive model through reinforcement learning. A new predictive model comprising the updated weights is transmitted to the environment controllers to be used in place of the current predictive model.

Abstract: A method and computing device for inferring an airflow of a controlled appliance operating in an area of a building. The computing device stores a predictive model. The computing device determines a measured airflow of the controlled appliance and a plurality of consecutive temperature measurements in the area. The computing device executes a neural network inference engine using the predictive model for inferring an inferred airflow based on inputs. The inputs comprise the measured airflow and the plurality of consecutive temperature measurements. The inputs may further include at least one of a plurality of consecutive humidity level measurements in the area and a plurality of consecutive carbon dioxide (CO2) level measurements in the area. For instance, the controlled appliance is a Variable Air Volume (VAV) appliance and a K factor of the VAV appliance is calculated based on the inferred airflow.

Abstract: Method and computing device using a neural network to determine whether or not to process images of an image flow. A predictive model of the neural network is generated and stored at a computing device. The computing device receives (b) an image of the image flow and executes (c) the neural network, using the predictive model for generating an indication of whether or not to process the image based on input(s) of the neural network, the input(s) comprising the image. The computing device determines (d) whether or not to process the image by an image processing module, based on the indication of whether or not to process the image. The image is processed by the image processing module if the determination is positive and not processed if the determination is negative. Steps (b), (c), (d) are repeated for consecutive images of the image flow.

Abstract: Method and computing device using a neural network to analyze temperature measurements of an infrared sensor. A predictive model of the neural network is stored by the computing device. The computing device receives a two-dimensional (2D) matrix of temperature measurements generated by the IR sensor, and executes the neural network using the predictive model for generating outputs based on inputs. The inputs comprise the 2D matrix of temperature measurements. The outputs comprise a 2D matrix of inferred temperatures. The computing device determines a subset of values of the 2D matrix of temperature measurements, and applies a comparison algorithm to the subset of values of the 2D matrix of temperature measurements and a corresponding subset of values of the 2D matrix of inferred temperatures, to detect an anomaly in the subset of values of the 2D matrix of temperature measurements. A method for training the neural network is also provided.

Abstract: A service is stored in a non-volatile memory of a computing device and comprises instructions executable by a processor of the computing device. The processor generates an operational instance of the service, which comprises a reference to the service. The processor stores the operational instance of the service in the non-volatile memory with a read-write access right. The processor launches an executable instance of the service associated to the operational instance of the service. The launching comprises copying the instructions of the service from the non-volatile memory to a volatile memory of the computing device. The launching further comprises executing the instructions of the service copied into the volatile memory. The processor adds data generated by the execution of the instructions of the service to the operational instance of the service for permanent storage in the non-volatile memory.

Abstract: Method and computing device using a neural network to bypass calibration data of an infrared sensor. A predictive model generated by a neural network training engine is stored by the computing device. The computing device determines a two-dimensional (2D) matrix of raw sensor data. Each raw sensor datum is representative of heat energy collected by the infrared sensor. The computing device executes a neural network inference engine. The neural network inference engine implements the neural network using the predictive model for generating outputs based on inputs. The inputs comprise the 2D matrix of raw sensor data. The outputs comprise a 2D matrix of inferred temperatures. A method for training a neural network to bypass calibration data of an infrared sensor is also provided.

Abstract: Method providing resilient execution of a service on a computing device. The service is stored in a non-volatile memory of the computing device and comprises instructions executable by a processor of the computing device. The processor generates an operational instance of the service, which comprises a reference to the service. The processor stores the operational instance of the service in the non-volatile memory with a read-write access right. The processor launches an executable instance of the service associated to the operational instance of the service. The launching comprises copying the instructions of the service from the non-volatile memory to a volatile memory of the computing device. The launching further comprises executing the instructions of the service copied into the volatile memory. The processor adds data generated by the execution of the instructions of the service to the operational instance of the service for permanent storage in the non-volatile memory.

Abstract: Inference server and computing device for inferring an optimal wireless data transfer rate. The computing device determines parameters of a data transfer through a wireless communication interface of the computing device, and transmits the parameters of the data transfer to the inference server. The inference server receives the parameters of the data transfer, executes a neural network inference engine using a predictive model (generated by a neural network training engine) for inferring an optimal data transfer rate based on the parameters of the data transfer, and transmits the optimal data transfer rate to the computing device. The computing device receives the optimal data transfer rate, and configures its wireless communication interface to operate at the optimal data transfer rate. For example, the computing device consists of an environment control device (e.g. an environment controller, a sensor, a controlled appliance, and a relay).

Abstract: Method and environment controller for validating a predictive model of a neural network. The environment controller receives at least one environmental characteristic value and determines a plurality of input variables. At least one of the plurality of input variables is based on one among the environmental characteristic value(s). The environment controller executes an environment control software module for calculating at least one output variable based on the plurality of input variables. The environment controller transmits the plurality of input variables to a training server executing a neural network training engine using the predictive model; and receives at least one inferred output variable from the training server. Each inferred output variable corresponds to one of the at least one output variable calculated by the environment control software module.

Abstract: Method and computing device for inferring a predicted state of a communication channel. The computing device stores a predictive model generated by a neural network training engine. The computing device collects a plurality of data samples representative of operating conditions of the communication channel. The communication channel is associated to a communication interface of the computing device. The communication interface allows an exchange of data between the computing device and at least one remote computing device over the communication channel. Each data sample comprises a measure of the amount of data respectively transmitted and received by the communication interface over the communication channel and a connection status of the communication channel, during a period of time. The computing device further executes a neural network inference engine using the predictive model for inferring the predicted state of the communication channel based on the plurality of data samples.

Abstract: Method and environment controller for validating a predictive model of a neural network. The environment controller receives at least one environmental characteristic value and determines a plurality of input variables. At least one of the plurality of input variables is based on one among the environmental characteristic value(s). The environment controller executes an environment control software module for calculating at least one output variable based on the plurality of input variables. The environment controller transmits the plurality of input variables to a training server executing a neural network training engine using the predictive model; and receives at least one inferred output variable from the training server. Each inferred output variable corresponds to one of the at least one output variable calculated by the environment control software module.

Abstract: Computing device and method for inferring a predicted number of data chunks writable on a flash memory before the flash memory wears out. The computing device stores a predictive model generated by a neural network training engine. A processing unit of the computing device executes a neural network inference engine, using the predictive model for inferring the predicted number of data chunks writable on the flash memory before the flash memory wears out based on inputs. The inputs comprise a total number of physical blocks previously erased from the flash memory, a size of the data chunk, and optionally an operating temperature of the flash memory. In a particular aspect, the flash memory is comprised in the computing device, and an action may be taken for preserving a lifespan of the flash memory based at least on the predicted number of data chunks writable on the flash memory.

Abstract: Computing device and method using a neural network to predict values of an input variable of a software. Computing device determines an initial series of n consecutive values of the input variable and then performs an iterative process, which includes using the neural network for inferring a next value of the input variable based at least on the series of n consecutive values of the input variable. Iterative process includes executing the software, using the next value of the input variable to calculate a corresponding next value of an output variable. Iterative process includes updating the series of n consecutive values by removing the first value among the series of n consecutive values and adding the next value as the last value of the series of n consecutive values. Iterative process may include determining that a condition is met based at least on the next value of the output variable.

Abstract: Computing device and method for inferring via a neural network a two-dimensional temperature mapping of an area. A predictive model is stored by the computing device. The computing device receives a plurality of temperature measurements transmitted by a corresponding plurality of temperature sensors located at a corresponding plurality of locations on a periphery of the area. The computing device executes a neural network inference engine, using the predictive model for inferring outputs based on inputs. The inputs comprise the plurality of temperature measurements. The outputs consist of a plurality of temperature values at a corresponding plurality of zones, the plurality of zones being comprised in a two-dimensional grid mapped on a plane within the area. For instance, the area is a room of a building, the periphery is an interface of a ceiling and walls of the room, and the plane is a horizontal plane within the room.

Abstract: Method and environment controller using a neural network for bypassing a legacy environment control software module. The environment controller receives at least one environmental characteristic value and determines a plurality of input variables. At least one of the plurality of input variables is based on one among the at least one environmental characteristic value. The environment controller transmits the plurality of input variables to an inference server executing a neural network inference engine. The environment controller receives at least one inferred output variable from the inference server. The environment controller uses the at least one inferred output variable received from the inference server in place of at least one output variable calculated by the legacy environment control software module based on the plurality of input variables.

Abstract: Computing device and method for inferring a predicted number of data chunks writable on a flash memory before the flash memory wears out. The computing device stores a predictive model generated by a neural network training engine. A processing unit of the computing device executes a neural network inference engine, using the predictive model for inferring the predicted number of data chunks writable on the flash memory before the flash memory wears out based on inputs. The inputs comprise a total number of physical blocks previously erased from the flash memory, a size of the data chunk, and optionally an operating temperature of the flash memory. In a particular aspect, the flash memory is comprised in the computing device, and an action may be taken for preserving a lifespan of the flash memory based at least on the predicted number of data chunks writable on the flash memory.

Abstract: Computing device and method for inferring a predicted number of physical blocks erased from a flash memory. The computing device stores a predictive model generated by a neural network training engine. A processing unit of the computing device executes a neural network inference engine, using the predictive model for inferring the predicted number of physical blocks erased from the flash memory based on inputs. The inputs comprise a total number of physical blocks previously erased from the flash memory, an amount of data to be written on the flash memory, and optionally an operating temperature of the flash memory. In a particular aspect, the flash memory is comprised in the computing device, and an action may be taken for preserving a lifespan of the flash memory based at least on the predicted number of physical blocks erased from the flash memory.

Abstract: Computing device and method using a neural network to adjust temperature measurements. The computing device comprises a temperature sensing module, one or more processor and a display. The neural network receives as inputs a plurality of consecutive temperature measurements performed by the temperature sensing module, a plurality of consecutive utilization metrics of the one or more processor, and a plurality of consecutive utilization metrics of the display. The neural network outputs an inferred temperature, which is an adjustment of the temperature measured by the temperature sensing module to take into consideration heat dissipated by the one or more processor and the display when using the temperature sensing module for measuring the temperature in an area where the computing device is deployed. An example of computing device is a smart thermostat. A corresponding method for training a neural network to adjust temperature measurements is also disclosed.

Abstract: Method and environment controller for inferring via a neural network one or more commands for controlling an appliance. A predictive model generated by a neural network training engine is stored by the environment controller. The environment controller determines at least one room characteristic. The environment controller receives at least one environmental characteristic value and at least one set point. The environment controller executes a neural network inference engine, which uses the predictive model for inferring the one or more commands for controlling the appliance. The inference is based on the at least one environmental characteristic value, the at least one set point and the at least one room characteristic. The environment controller transmits the one or more commands to the controlled appliance.