abstract data

Harnessing Sensor Data

Accelerating Relevant Answers through Simulation 

More and more sensors are adding to exabytes of data collection each day. However, capturing this data is only part of making it useful. With an integrated end-to-end process for sensor technology, data is transformed from information to answers. Leaders need infrastructure that uses open-source technology to draw insights from streaming data and integrates context from stored data in real time. When combined with pre-operations planning tools that consume sensor data and run simulators, such technology can inform leaders where to place sensors, how sensors will interact with the environment, and what to expect when the data starts rolling in.  

Our technology agnostic operating model allows decision makers to ask, “What if…”  

  • streaming data could interact with stored data in real time? 
  • the amount of data streamed didn’t impact the speed at which it’s received? 
  • modeling and simulation were quickly and easily accessible for testing? 

and learn how 

  • to understand ways sensor data will interact with systems in advance 
  • the environment will impact sensor hardware 
  • to supplement gaps with synthetic data. 

To address these questions and proactively mitigate risks, decision makers and users need a rapid, flexible, and highly customizable solution to model their operational environment, integrated technologies, and operations tracking from data collection and analytics to decision support. 

LMI’s approach incorporates modeling and simulations based on artificial intelligence/machine learning (AI/ML) to test Internet of Things (IoT) networks deployed alongside teams in the field. 

Use Cases: 

  • SENSORS

    Leveraging IoT technologies such as automated and radiofrequency identification and wireless sensor mesh, LMI built an enterprise level digital tracking tool that increases accountability, auditability, and mission readiness. Designed to provide continuous asset visibility, this business intelligence system is hardware and data agnostic. It aggregates data from various collection technologies, creating a reliable, high-fidelity logistics common operation picture.  

  • LMI supports DoD in developing decision-support capabilities by ingesting chemical exposure data from hand-held sensors into a health risk assessment tool and displaying the data on a Decision Support Screen. Initial prototypes include using a hand-held MultiRAE sensor as well as emulators to provide chemical exposure data to create initial field accounts and health risk assessments during health hazard exposure events that can be displayed in a map-based decision support system.

  •  

    LMI data scientists developed sensor-based algorithms to predict the failure of mechanical components across DoD where weapon-system availability is critical to mission success. Being able to predict impending failures, alert maintenance crews, and provision inventory by detecting anomalies in streaming sensor data enables DoD to transition from a corrective to a preventive maintenance paradigm and represents a powerful enabler of battlefield superiority. 

Case Study: NIST CommanDINGTech Challenge  

In 2023, the National Institute of Standards and Technology's (NIST) Public Safety Communications Research (PSCR) Division hosted a challenge to identify next-generation incident command capabilities. The four phases of the challenge included concept papers, video demos, and two live scenario competitions. More than 30 teams competed for the opportunity to win prizes totaling $1 million.  

Download our Case Study to learn how LMI’s Wearables Integrated Sensor Platform supported NIST by livestreaming sensor data for competitors to leverage during the challenge.