An improved home automation system is provided to facilitate senior care, as well as to facilitate care for individuals suffering from Alzheimer's disease or other dementias. A home control unit is provided that is connected to, and interfaces with, a combination of health equipment, smart home appliances, a smart medicine cabinet, a smart pantry, wearable sensors, motion detectors, video cameras, microphones, video monitors, speakers, smart thermostat, lighting, floor sensors, bed sensors, smoke detectors, glass breakage detectors, door sensors, and other perimeter sensors. A distributed computational architecture is provided having a CPU associated with each video camera and an associated proximate microphone and speaker, wherein speech detection and processing, and video processing, is performed by each such CPU in conjunction with its associated video camera, microphone, and speaker. Remote backup for such distributed speech processing is selectively provided by a remote server based upon confidence scopes generated by each such CPU. The distributed computational architecture is also utilized for video processing to facilitate peer-to-peer video conferencing communication using industry standard formats and to reduce latency and response times that would otherwise be encountered using remote servers.

An improved home automation system is provided to facilitate senior care, as well as to facilitate care for individuals suffering from Alzheimer's disease or other dementias. A home control unit is provided that is connected to, and interfaces with, a combination of health equipment, smart home appliances, a smart medicine cabinet, a smart pantry, wearable sensors, motion detectors, video cameras, microphones, video monitors, speakers, smart thermostat, lighting, floor sensors, bed sensors, smoke detectors, glass breakage detectors, door sensors, and other perimeter sensors. A distributed computational architecture is provided having a CPU associated with each video camera and an associated proximate microphone and speaker, wherein speech detection and processing, and video processing, is performed by each such CPU in conjunction with its associated video camera, microphone, and speaker. Remote backup for such distributed speech processing is selectively provided by a remote server based upon confidence scopes generated by each such CPU. The distributed computational architecture is also utilized for video processing to facilitate peer-to-peer video conferencing communication using industry standard formats and to reduce latency and response times that would otherwise be encountered using remote servers.

An online system, such as a social networking system, generates shared models for one or more clusters of categories. A shared model for a cluster is common to the categories assigned to the cluster. In this manner, the shared models are specific to the group of categories (e.g., selected content providers) in each cluster while requiring a reasonable computational complexity for the online system. The categories are clustered based on the performance of a model specific to a category on data for other categories.

An online system, such as a social networking system, generates shared models for one or more clusters of categories. A shared model for a cluster is common to the categories assigned to the cluster. In this manner, the shared models are specific to the group of categories (e.g., selected content providers) in each cluster while requiring a reasonable computational complexity for the online system. The categories are clustered based on the performance of a model specific to a category on data for other categories.

The technology disclosed herein enables removal of extraneous voices from audio in a communication session. In a particular embodiment, a method includes receiving audio captured from an endpoint operated by a user on a communication session. The method further includes identifying an extraneous voice in the audio, wherein the voice is from a person other than the user, and removing the extraneous voice from the audio. After removing the extraneous voice, the method includes transmitting the audio to another endpoint on the communication session.

The technology disclosed herein enables removal of extraneous voices from audio in a communication session. In a particular embodiment, a method includes receiving audio captured from an endpoint operated by a user on a communication session. The method further includes identifying an extraneous voice in the audio, wherein the voice is from a person other than the user, and removing the extraneous voice from the audio. After removing the extraneous voice, the method includes transmitting the audio to another endpoint on the communication session.

Machine learning models used in medical diagnosis should be validated after being deployed in order to reduce the number of misdiagnoses. Validation processes presented here assess a performance of the machine learning model post-deployment. In post-deployment validation, the validation process monitoring can include: (1) monitoring to ensure a model performs as well as a reference member such as another machine learning model, and (2) monitoring to detect anomalies in data. This post-deployment validation helps identify low-performing models that are already deployed, so that relevant parties can quickly take action to improve either the machine learning model or the input data.

Machine learning models used in medical diagnosis should be validated after being deployed in order to reduce the number of misdiagnoses. Validation processes presented here assess a performance of the machine learning model post-deployment. In post-deployment validation, the validation process monitoring can include: (1) monitoring to ensure a model performs as well as a reference member such as another machine learning model, and (2) monitoring to detect anomalies in data. This post-deployment validation helps identify low-performing models that are already deployed, so that relevant parties can quickly take action to improve either the machine learning model or the input data.

A system and method for detecting anomalies in very large datasets is disclosed. The method includes calculating statistics for data elements in a data set over a range of time periods. These statistics are arranged into a 2D array and analyzed using a machine learning algorithm to detect anomalous regions. The method also includes steps of analyzing time series of the data based on detected anomalous regions, correcting any errors in the datasets, and storing the corrected values in a separate database to maintain data integrity.

A system and method for detecting anomalies in very large datasets is disclosed. The method includes calculating statistics for data elements in a data set over a range of time periods. These statistics are arranged into a 2D array and analyzed using a machine learning algorithm to detect anomalous regions. The method also includes steps of analyzing time series of the data based on detected anomalous regions, correcting any errors in the datasets, and storing the corrected values in a separate database to maintain data integrity.