News

R&D

Intuidex awarded AFRL STTR Phase II – PAI Information Extraction

May 6, 2022 – By Intuidex

Intuidex, Inc. is proud to announce the award of a Small Business Technology Transfer (STTR) Phase II contract from the Air Force Reach Lab. The project will focus on further research and development of Intuidex’s Higher-Order Low-Resource Learning™ (HO-LRL™) technology, focusing on information extraction from Publicly Available Information (PAI) in partnership with Carnegie Mellon University.

During the STTR Phase I effort Intuidex, Inc., in partnership with Carnegie Mellon University, focused on research and development (R&D) of deep-learning-based information extraction techniques that leveraged Intuidex’s Deep Learning-based Named Entity Recognition (DL-NER™) framework for Named Entity Extraction (NER) based on Intuidex’s proprietary HO-LRL™ technology. Phase II will continue this effort with the objective to research, design, and develop information extraction theory, algorithms and techniques for extraction from noisy, user-generated text and related PAI based on R&D of low-resource learning approaches to entity resolution across multiple sources coupled with research into linguistically-informed decoders for deep networks, unsupervised decipherment of noisy text, and non­destructive text normalization.

Anticipated benefits include:

  1. significant enhancements to deep learning predictive performance of information extraction and entity resolution in multi-source data in low-resource settings;
  2. significant improvements in the accurate extraction of meaningful information from PAI;
  3. reduced effort and improved throughput in the exploitation of noisy PAI data; and
  4. successful transition into the hands of warfighters realistically within one calendar year of completion of the Phase II effort.

Expected commercial applications include the Watchman for Defense™ (W4D™) platform (for Department of Defense, Intelligence Community and Homeland Security applications), the Watchman for Emergency Management™ (W4EM™) platform (for both public- and private-sector emergency management in near-real-time situational awareness applications), and the Watchman for Law Enforcement™ (W4LE™) platform (for law enforcement and private security concerns).

R&D

Intuidex's Higher-Order Low-Resource Learning™ (HO-LRL™) in Use Case Developed with Serco NA Greatly Improves Predictive Analytics

March 9, 2022 – By Intuidex

Intuidex, Inc. partnered with Serco North America (Serco NA) to develop a use case for predictive analytics in low resource environments leveraging Intuidex’s Higher-Order Low-Resource Learning™ (HO-LRL™) to improve performance over traditional predictive models. 

 

This use case will be presented at the Sixth Annual Workshop on Naval Applications of Machine Learning (NAML), March 22-24, 2022.


Poster Schedule Session 1A, Wednesday March 23, 2022: Rapid Exploitation of Human Language in a Low-Resource Environment by Alex Rojas, Serco North America Inc. See the full schedule here.

Presentation Intro Video – courtesy Serco North America

Problem Statement

Data quality, consistency, and integrity remain a common challenge across artificial intelligence (AI) use cases, including in natural language processing (NLP). Most AI algorithms and machine learning methods rely on a large number of training data examples in order to provide higher accuracy predictions.

 

To better address predictive analytics in low resource environments, Intuidex and Serco NA tested the use of Intuidex’s proprietary HO-LRL™ technology to predict schedule overruns in the delivery of military assets utilizing condition and maintenance planning data. Currently, teams of personnel within the military are required to produce Availability Duration Scorecard (ADS) predictions. 

Testing

Previous modeling of predictive analytics performed by Serco NA using a traditional machine learning algorithm produced a baseline solution which provided better results than the human expert-driven ADS approach (14% versus 12.45% mean absolute percent error) but there was room for improvement.

In this test, NLP features were incorporated into a Support Vector Machine (SVM) model enhanced to use HO-LRL™. The HO-LRL™ technique transforms the data to focus on important discriminators for target conditions.  

 

Findings

Metric

HO-LRL™

Original Implementation

Fβ=0.25 / Accuracy

>99%

86%

Error / MAPE (Mean Absolute
Percentage Error)

<1%

14%

Training Time

<20 seconds (avg. depends on
data set size and resources)

1:300 hrs. ratio

Training Data

6,500 records (0.2% of original
data) Least Minimum: 180 samples, 30 samples overrun and 150 non overrun
samples

3,158,219 records

Time to Implement

2 weeks

Few months when data available

Conclusions

Using HO-LRL™ yielded > 99% Fβ=0.25, a 13% increase from the original implementation!

Training time was greatly reduced to <20 seconds (avg. depends on data set size and resources)!

The amount of data used was only 0.2 % (6500 records) of the original data (3,158,219 records). The smallest amount of data modeled was only 180 samples, 30 with the overrun condition and 150 with non-overrun. HO-LRL™-enhanced SVM beat standard SVM by several points with >99% confidence!

Take away: What is remarkable is that this represents a >99.99999% reduction in training data and subsequent training time but resulted in significantly increased accuracy!

Benefits of HO-LRL™

HO-LRL™ is part of Intuidex’s Watchman Analytics Suite from which several products, including Watchman for Defense™ (W4D) are derived. W4D provides multi-INT fusion and alerting, including pattern of life and anomaly detection. HO-LRL™ is a data transformation for machine learning in low-resource settings and supports both generative and discriminative learning, including natural language processing (NLP) with deep learning networks and latent embeddings. 

 

HO-LRL™ can be used in a wide array of use cases and applications and provides numerous benefits, such as a much lower threshold of training data, significantly less training time, and greatly improved predictive performance in low-resource settings including real-time streaming data scenarios. 

Read the full presentation here.

See the slick sheet here.

Contact Us to Learn More!

Picosat Launch Updates

Intuidex + Quub Challenger Picosat Launches on SpaceX Transporter-3!

March 6, 2022 – By Intuidex

Updates: 

3/6/2022 – Joe Latrell, CEO of Quub, discusses the picosat launch, his thoughts on the space industry, their partnership with Intuidex, and much more – including an update on the current status of the Challenger Picosat – with Lancaster Online. Read the full article here!  

1/13/2022 – Watch the WFMZ News interview with our CSO, Justin Frank, here!

1/13/2022 – SpaceX Transporter-3 launches. Deployment of the Challenger Picosat at T+01:05:44 as part of FOSSA Pod 2!

Learn More: 

courtesy SpaceX Youtube channel

Press Release

Intuidex Teams With Quub to Launch Next-Gen PicoSatellite on SpaceX Rocket

January 11, 2022 By Intuidex

Intuidex Inc, a provider of cutting-edge defense software and technology, has teamed with Quub (Mini-Cubes, LLC), a satellite manufacturer, to produce and launch a first-of-its-kind, high functionality, low-cost satellite (picosat) to provide enhanced situational awareness and early warning anomaly detection using sensor data.

Satellites with this type of sensor functionality have traditionally taken months, if not years, to build and cost hundreds of millions of dollars. In contrast, these next-gen picosats take a matter of days to build with commercially available, off-the-shelf parts with a parts cost of less than $50 thousand. However, it’s their technology that makes them just as functional as their larger and much more expensive cousins. We’ve married two best-of-breed technologies to create something marvelous. Quub produces best-in-class low-SWaP2 picosats: low-size, low-weight, low-power and low-price. We are able to deploy flocks of picosats with various sensor types including electro-optical, LiDAR and SAR (Synthetic Aperture Radar) that can stay in orbit for up to five years with little or no debris upon re-entry. But the real game-changer is the on-board technology in processing this sensor data. At Intuidex, we provide the proprietary HO-LRL™ (Higher-Order Low-Resource Learning) technology. Our technology processes and fuses multiple-source sensor data and quickly identifies objects and events with high accuracy, even in situations where limited data is available for making decisions. This is all edge-based processing on-board the picosats, meaning the object and event detection, fusion and alerting is performed entirely on-board the picosat in milliseconds, resulting in actionable alerts in down-linked systems in near-real-time. This is the very same machine learning technology that’s in Intuidex’s Watchman Analytics™ Suite, a successful analytics platform that has been proven in both the defense and public safety vertical markets.

The upcoming launch is the first-ever picosat of its type to be launched in the United States.  According to Dr. Bill Pottenger, CEO for Intuidex, “The first of many, this launch is opening up a new market for space data as a service.”

Launch Information:  https://www.spacex.com or https://spacecoastlaunches.com/launch-schedule 

Date: January 13, 2022. Vehicle: SpaceX Falcon 9. 

Mission: A SpaceX Falcon 9 rocket will launch the Transporter 3 mission, a rideshare flight to a sun-synchronous orbit with numerous small microsatellites and nanosatellites for commercial and government customers. 

Launch Site: Cape Canaveral Air Force Station

Launch Broadcast: www.spacex.com 

For more information please visit www.intuidex.com or email info@intuidex.com