Sas Institute Inc.

Varunraj Valsaraj

Kedar Shriram Prabhudesai

Jonathan Lee Walker

Jinxin Yi

Hardi Desai

Jorge Manuel Gomes Da Silva

Mohammadreza Nazari

Afshin Oroojlooyjadid

Pelin Cay

Hamza Mustafa Ghadyali

Davood Hajinezhad

Sanjeev Shyam Heda

Xingqi Du

Xunlei Wu

Julia Moreno

Fang Liang

Bahar Biller

Brett Alexander Vogelsang

Alexander Richard Phelps

Allen Joseph Langlois

Jonathan James McElhinney

Rik Peter De Ruiter

Andrey Matveenko

Nabaruna Karmakar

Roger Lee Baldridge, Jr

Robert Winston Blanchard

Joshua David Griffin

Prathaban Mookiah

Amirhassan Fallah Dizche

Weichen Wang

Ruiwen Zhang

Steven Joseph Gardner

Xuejun Liao

Natalia Summerville

Ye Liu

Hamoon Azizsoltani

Daniele Cazzari

Thomas Tuning

Saurabh Mishra

Frederic Combaneyre

Priti Upadhyay

Kunind Sahu

Bahadir Aral

Rebecca Gallagher

Antony Nicholas Cooper

Necip Baris Kacar

Daniel Keongson Woo

In some examples, a system can access video data collected from one or more image sensors. The system can execute a human detection model to detect a person within a region of interest proximate to the environment based on the video data. The system can also execute an object detection model to detect a presence or absence of personal protection equipment (PPE) based on the video data. The system can associate the PPE with the person to detect an unsafe PPE status. The system can determine that the unsafe PPE status has persisted for a predetermined period of time. In response to determining that the unsafe PPE status has persisted for the predetermined period of time, the system can generate a signal indicating the unsafe PPE status.

Detection of unsafe personal protection equipment status with multi-modal context awareness

A computer-implemented method includes receiving a natural language input including a natural language request for executing an analytical task and processing the natural language input by a language model, where the processing may include translating the natural language input to an analytical function call for calling an analytical function of a set of distinct analytical functions of an analytics computing server. Additionally, the computer-implemented method includes calling the analytical function at the analytics computing server using the analytical function call, receiving a technical output in response to calling the analytical function, and outputting a response to the natural language input that includes the technical analytical output.

Systems, methods, and graphical user interfaces for secure execution of analytical tasks using natural language

In some examples, a system can access video data collected from one or more image sensors, the video data showing a region of interest proximate to a machine. The system can execute an object detection model to detect that a person is within the region of interest proximate to the machine based on the video data. The system can detect a motion status of a component of the machine. The system can execute a pose estimation model on the video data to estimate a pose of the person with respect to the machine. The system can detect a safety rule violation based on the pose of the person with respect to the machine, and the motion status of the machine. The system can transmit a signal to a controller of the machine in response to detecting the safety rule violation.

Detection and mitigation of unsafe behaviors using computer vision

The computing device obtains a training data set related to a plurality of historic user inputs associated with preferences of one or more services or items from an entity. For each of the one or more services or items, the computing device executes operations to train a plurality of models using the training data set to generate a plurality of recommended models, apply a validation data set to generate a plurality of predictions from the plurality of recommended models, obtain a weight of each metric of a plurality of metrics from the entity, obtain user inputs associated with user preferences, and determine a relevancy score for each metric. The computing device selects a recommended model based on the relevancy score of the selected metric or a combination of selected metrics, generates one or more recommendations for the users, and outputs the one or more generated recommendations to the users.

Method and system for obtaining item-based recommendations

A computing system detects a defective object. An image is received of a manufacturing line that includes objects in a process of being manufactured. Each pixel included in the image is classified as a background pixel class, a non-defective object class, or a defective object class using a trained neural network model. The pixels included in the image that were classified as the non-defective object class or the defective object class are grouped into polygons. Each polygon is defined by a contiguous group of pixels classified as the non-defective object class or the defective object class. Each polygon is classified in the non-defective object class or in the defective object class based on a number of pixels included in a respective polygon that are classified in the non-defective object class relative to a number of pixels included in the respective polygon that are classified in the defective object class.

Manufacturing defective object detection system

A flexible computer architecture for performing digital image analysis is described herein. In some examples, the computer architecture can include a distributed messaging platform (DMP) for receiving images from cameras and storing the images in a first queue. The computer architecture can also include a first container for receiving the images from the first queue, applying an image analysis model to the images, and transmitting the image analysis result to the DMP for storage in a second queue. Additionally, the computer architecture can include a second container for receiving the image analysis result from the second queue, performing a post-processing operation on the image analysis result, and transmitting the post-processing result to the DMP for storage in a third queue. The computer architecture can further include an output container for receiving the post-processing result from the third queue and generating an alert notification based on the post-processing result.

Flexible computer architecture for performing digital image analysis

Requests for computing resources and other resources can be predicted and managed. For example, a system can determine a baseline prediction indicating a number of requests for an object over a future time-period. The system can then execute a first model to generate a first set of values based on seasonality in the baseline prediction, a second model to generate a second set of values based on short-term trends in the baseline prediction, and a third model to generate a third set of values based on the baseline prediction. The system can select a most accurate model from among the three models and generate an output prediction by applying the set of values output by the most accurate model to the baseline prediction. Based on the output prediction, the system can cause an adjustment to be made to a provisioning process for the object.

Predicting and managing requests for computing resources or other resources

A computing device trains a machine state predictive model. A generative adversarial network with an autoencoder is trained using a first plurality of observation vectors. Each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable. The state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state. The first plurality of observation vectors successively defines sequential machine states to manufacture a product. A second plurality of observation vectors is generated using the trained generative adversarial network with the autoencoder. A machine state machine learning model is trained to predict a subsequent machine state using the first plurality of observation vectors and the generated second plurality of observation vectors. A description of the machine state machine learning model is output.

Automated control of a manufacturing process

A computing system responsive to obtaining original image data, detects a set of data point(s), in the original image data, that indicates an object. The system determines, based on the set of data point(s), a set of pixels associated with the object in the original image data. The system generates an alternative visual identifier for the object that provides a unique identifier for the set of pixels absent in the original image data. The system generates, autonomously from intervention by any user of the computing system, pixel information to conceal feature(s) of the object. The system obtains modified image data comprising the alternative visual identifier. The modified image data further comprises the feature(s) of the object in the original image data visually concealed in the modified image data according to the pixel information. The system outputs an image representation of a trajectory of the object through the modified image data.

Real-time concealed object tracking

A computing system obtains image data representing images. Each of the images is captured at different time points of a physical environment. The physical environment comprises a first object and a second object. The computing system executes a control system to augment the physical environment. The control system detects a group forming in the images. The control system tracks an aspect of a movement, of a given object, in the group. The control system simulates the physical environment and the movement, of the given object, in the group in a simulated environment. The control system evaluates simulated actions in the simulated environment for a predefined objective for the physical environment. The predefined objective is related to an interaction between objects in the group. The control system generates based on evaluated simulated actions and autonomously from involvement by any user of the control system, an indication to augment the physical environment.

Real-time spatial and group monitoring and optimization

A computing system receives historical data. The historical data comprises physical actions taken in an experiment in a physical environment. The experiment comprises user-defined stages. The historical data comprises a recorded outcome, according to user-defined performance indicator(s) related to the user-defined stages, for each physical action taken in the experiment. The system generates, by a discrete event simulator, a computing representation of a simulated environment of the physical environment. The simulated environment comprises processing stages. The system obtains simulation data. The simulation data comprises simulated actions taken by the discrete event simulator. The simulation data comprises a predicted outcome, according to user-defined performance indicator(s) related to the processing stages, for each simulated action taken by the discrete event simulator. The system validates accuracy of the discrete event simulator at predicting the recorded outcome in the experiment. The system trains a computing agent according to a sequential decision-making algorithm.

Discrete event simulation with sequential decision making

Manufacturing processes can be optimized using machine learning models. For example, a system can execute an optimization model to identify a recommended set of values for configurable settings of a manufacturing process associated with an object. The optimization model can determine the recommended set of values by implementing an iterative process using an objective function. Each iteration of the iterative process can include selecting a current set of candidate values for the configurable settings from within a current region of a search space defined by the optimization model; providing the current set of candidate values as input to a trained machine learning model that can predict a value for a target characteristic of the object or the manufacturing process based on the current set of candidate values; and identifying a next region of the search space to use in a next iteration of the iterative process based on the value.

Optimizing manufacturing processes using one or more machine learning models

One exemplary system can receive a selection of a dataset via a graphical user interface (GUI). The dataset can represent a time-series projection. The system can feed the dataset into a first machine-learning model to obtain an output indicating whether the time-series projection has a data value that should be overridden with an override value. If the first machine-learning model indicates that the time-series projection has the data value that should be overridden, the system can feed the data value as input to a second machine-learning model to obtain an output indicating whether the override value should be greater than or less than the data value. The system can then render a visual directionality cue within the GUI based on the output from the second machine-learning model. The visual directionality cue can provide guidance for overriding the data value.

Interactive graphical user interface with override guidance

Growing community of inventors

Cary, NC, United States of America

Varunraj Valsaraj