February 5, 2020 – Seeq Corporation, a manufacturer of Industrial Internet of Things (IIoT) analytics software, announced availability of their latest release, R22, and beta availability of Seeq Data Lab, at the ARC Industry Forum 2020. Seeq applications include Workbench for analytics, Organizer for publishing insights in reports and dashboards, and now Seeq Data Lab for accessing Python libraries. These applications work to empower engineers and scientists in process manufacturing organizations to analyze, predict, collaborate, and share insights.
R22 features support enterprise data governance initiatives and priorities to support Seeq expansion in large organizations. For example, Seeq Integrated Security honors OSIsoft PI security restrictions for PI data access and enables administrators to set signal-level permissions on data in historians and other time series data stores. Each user therefore only has access to the data they need, facilitating data access compliance.
Additional R22 features requested by Seeq users include:
-
Improved Scatterplot in Workbench: Conditional filtering and more display options help users find relationships among signals -
NOAA Weather Service Connector: Data from the National Weather Service API can be integrated into Seeq analytics -
Multi-user Awareness:Know when other users are viewing, editing, or presenting the same Worksheet or Topic
Seeq Data Lab, now in beta, was driven by Mark Derbecker, Seeq’s Vice President of Engineering, in response to requests by Seeq users to gain access to Python machine learning algorithms, and data scientist requests to leverage Seeq functionality.
Seeq Data Lab is built on Jupyter Notebooks and a Seeq Python library, called Spy, to access Seeq functionality, and it is managed by the same administration features as other Seeq applications. The result is a set of experiences for process engineers analyzing time series data including viewing and reporting of data in Seeq Organizer, analytics with Seeq Workbench, and expanding analytics capabilities with Python libraries in Seeq Data Lab. Seeq Data Lab also enables data scientists to find insights using machine learning algorithms and libraries, system integrators to create custom analytics for their clients, and asset vendors to enrich their remote monitoring and predictive analytics services for customers.
All of the browser-based Seeq applications – Organizer, Workbench, and Data Lab – connect to a shared Seeq server to enable collaboration, access connected data sources, and enable administrative control. For example, graphics created in Data Lab may be viewed in Organizer Topics, data modeled in Workbench may be accessed by Data Lab users, and Data Lab algorithm results are available for use in the other Seeq applications. Example use cases for process engineers and data scientists using Seeq Data Lab include;
-
Advanced models: Python libraries for inclusion of Neural Network, Random Forest, K-means, and other algorithms -
Custom visualizations: Python libraries for the display of specific data types and calculations can be incorporated in Data Lab analytics -
Non time-series data: Python libraries enable analytics which include population statistics, data look-ups, and multi-dimensional data
February 5, 2020 – Seeq Corporation, a manufacturer of Industrial Internet of Things (IIoT) analytics software, announced availability of their latest release, R22, and beta availability of Seeq Data Lab, at the ARC Industry Forum 2020. Seeq applications include Workbench for analytics, Organizer for publishing insights in reports and dashboards, and now Seeq Data Lab for accessing Python libraries. These applications work to empower engineers and scientists in process manufacturing organizations to analyze, predict, collaborate, and share insights.
R22 features support enterprise data governance initiatives and priorities to support Seeq expansion in large organizations. For example, Seeq Integrated Security honors OSIsoft PI security restrictions for PI data access and enables administrators to set signal-level permissions on data in historians and other time series data stores. Each user therefore only has access to the data they need, facilitating data access compliance.
Additional R22 features requested by Seeq users include:
-
Improved Scatterplot in Workbench: Conditional filtering and more display options help users find relationships among signals -
NOAA Weather Service Connector: Data from the National Weather Service API can be integrated into Seeq analytics -
Multi-user Awareness:Know when other users are viewing, editing, or presenting the same Worksheet or Topic
Seeq Data Lab, now in beta, was driven by Mark Derbecker, Seeq’s Vice President of Engineering, in response to requests by Seeq users to gain access to Python machine learning algorithms, and data scientist requests to leverage Seeq functionality.
Seeq Data Lab is built on Jupyter Notebooks and a Seeq Python library, called Spy, to access Seeq functionality, and it is managed by the same administration features as other Seeq applications. The result is a set of experiences for process engineers analyzing time series data including viewing and reporting of data in Seeq Organizer, analytics with Seeq Workbench, and expanding analytics capabilities with Python libraries in Seeq Data Lab. Seeq Data Lab also enables data scientists to find insights using machine learning algorithms and libraries, system integrators to create custom analytics for their clients, and asset vendors to enrich their remote monitoring and predictive analytics services for customers.
All of the browser-based Seeq applications – Organizer, Workbench, and Data Lab – connect to a shared Seeq server to enable collaboration, access connected data sources, and enable administrative control. For example, graphics created in Data Lab may be viewed in Organizer Topics, data modeled in Workbench may be accessed by Data Lab users, and Data Lab algorithm results are available for use in the other Seeq applications. Example use cases for process engineers and data scientists using Seeq Data Lab include;
-
Advanced models: Python libraries for inclusion of Neural Network, Random Forest, K-means, and other algorithms -
Custom visualizations: Python libraries for the display of specific data types and calculations can be incorporated in Data Lab analytics -
Non time-series data: Python libraries enable analytics which include population statistics, data look-ups, and multi-dimensional data
© 2019, Best Brothers Group. All rights reserved.
