Stucan-HIVE is an intelligent data analytics engine that sits above the wargaming synthetic environment.
Stucan-HIVE is unique in its adaptive ability to automatically harvest, categorize, store, process and analyze vast amounts of objective and subjective, quantitative and qualitative data and to present it in real-time by means of unique, flexible and innovative visual formats.
Stucan-HIVE has the following capabilities and tools:
Key Performance Indicator (KPI) Management. Through a consultative approach, the Stucan-HIVE implementation teamwork with the customer to capture KPI requirements. This forms the basis of a data schema and capture plan which is designed to effectively extract data from a variety of disparate data repositories.
Data Capture across Wargaming and LVC Environments. Using the data schema and capture plan a technical architecture is generated mapping all the different data sources to Stucan-HIVE. Common open standards such as DIS are already mapped within the tool and where new data sources are provided then these are incorporated through the relevant Application Programming Interfaces (API). Fusing this information in Stucan-HIVE enables the KPIs to be visualized. When conducted in conjunction with training, force development, and doctrine organizations, wargames are informed by or inform capability through a common language (i.e. the KPIs).
Data Storage. Having extracted the appropriate inputs, these are fused within the Stucan-HIVE SQL datastore which can be standalone or integrated as an application on customer-owned cloud-based storage.
Analytics. Having stored the appropriate data in a format based on the data schema, Artificial Intelligence (AI) and Machine Learning (ML) tools are applied. This provides an automated – even intelligent- analytical approach. Self- adapting algorithms, pattern recognition technologies and ML approaches enable the drawing of meaningful insights from mass data sets and is simple, ever-improving, self- teaching and increasingly affordable. Previously, cross-functional wargame data analysis took months, whereas with Stucan-HIVE techniques, now takes minutes.
Reporting and Visualization. Information is most powerful when it is available and visible to the right person, who has the necessary skills and behaviors to manage and exploit it at the right time and right place. Stucan-HIVE users are given appropriate access to insightful visual reports and dashboards with an interactive and tailorable interface using COTS visualization platforms (i.e. Power BI, Tableau Desktop, IBM Watson Analytics. etc.). Reporting occurs in real-time and immediately post wargame to provide objective and subjective evidence to inform wargame adjudication. Additionally, reporting occurs at the end of a wargame series, increasing the size of the data set and validity of any evidence gathered. This allows data to be gathered once and to be reused many times, by many parts of the organization for many purposes: harvest evidence once, uses repeatedly.
Stucan-HIVE Metrics and Data Collection
We developed and employed a suite of performance metrics which were derived from the existing Collective Competency Objectives to provide a logical ‘golden thread’ between training objectives and analytical outputs.
We successfully demonstrated the use of new and emerging performance measures to assess the development of collective knowledge skills and attitudes (KSA). We integrated data from novel collection and analysis systems into the overall KSA collection schema to develop more objective and non-intrusive measures to report on team performance.
We developed and tested the integration of Stucan-HIVE to DVS via a DIS interface. Where there were collection gaps we worked with BiS to develop specific DVS Applied Programming Interfaces (APIs)
Data Storage and Analysis
We loaded all the data into cloud storage (to replicate G-Cloud) and then hosted our analytics engine to automate analysis.
We examined Stucan-HIVE ability to conduct Tactical Communications Information Flow Analysis – experimenting with an automated voice to text transcription and Machine Learning to codify communications activities and exchanges.
We attempted “Ghosting techniques” which are prevalent in sports team analytics. We did this to investigate the use of constructive models to produce simulated outcomes against which training audience performance can be compared, given the same plan and terrain