Θ New Jersey's UAS Sensing by yourDragonXi Δ 9th of January 2018 Ω 6:11 AM

ΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞ
~ UAS Test Site from FAA (UASIPP) ~ RaptorMaps -UASIPP ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ
~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ ~ sense for Ξ ~ sense for Ξ	~ sense for Ξ
«UAS Sensing in U.S.	Θ	Θ
ΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞ

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~ UAS Test Site from FAA

Virginia, Maryland, New Jeresey's UAS Test Site
ξ portal offline

~[Σ] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~ RaptorMaps

»RaptorMaps <-- Boston
Raptor Maps is a software company specializing in data processing and machine learning.
The company provides tools to organize data, perform virtual inspections, and
generate reports that seamlessly integrate into the workflows of asset owners.
Raptor Maps also develops algorithms for automated assessments and predictive analytics.
It was founded by MIT engineers and has investment from Y Combinator and the Commercial Drone Fund.

Eddie Obropta
Co-founder, CTO
Eddie earned his B.S. and M.S. in Aeronautics and Astronautics from MIT.
Eddie has a wide range of interests and experiences including iPhone game development,
solid mechanics, simulations, and working on thermal dynamics and
life support systems at SpaceX.
He has built computer vision systems to measure material deformation for the Navy (ONR).

Nikhil Vadhavkar
Co-founder, CEO
Nikhil earned his B.S. in Biomedical Engineering and an M.S. in Engineering Management from Johns Hopkins University.
He worked at Accenture in the Federal Services division, and
spent five years at MIT researching thermal control for space suits.
Nikhil previously led a Bill and Melinda Gates Foundation project
to use of drones for emergency medical supply delivery in developing countries.

Full-Stack Engineer
We�re looking for developers with swiss-army knife coding skills.
You should be experienced with Python and/or Javascript (specifically React).
Willingness to learn new things fast and
move throughout the architecture as needed are essential.
Data science skills or interests in geo-location, image processing, and
machine learning are big pluses as these concepts are heavily used.
Previous experience with cloud-computing infrastructure and dev-ops are bonuses, but not required.

Skills: Python, Javascript, Unix-style terminal.

Excited to be apart of the NJ Team and help contribute to the application!
Raptor Maps is proud to be a member of the NJ Team on the FAA/DOT/White House UAS Integration Pilot Program,
led by UAS Hub Cape May County, N.J.
We submitted our application �.
Wait �til you hear about our missions!

Excited to announce our public launch and
$3.5M fundraise from Lightspeed
(working with Aaron Batalion :D),
researchers from »OpenAI
ξ Elon Musk is the co-founder and chairman of OpenAI <-- California!
and others!
We're hiring!

Machine Learning Definition
Machine learning is the science of getting computers to act
without being explicitly programmed.
In the past decade, machine learning has given us self-driving cars,
practical speech recognition, effective web search,
and a vastly improved understanding of the human genome.
Andrew Ng, Professor, Stanford University <-- California!

Machine Learning for Drones
Drones are generating more data than we know what to do with.
Every mission can generate thousands of images (or hours of video) that need analysis.
With machine learning,
we can teach algorithms to detect something we care about
(e.g., leaf, soil, and pumpkin), classify it, and localize it in space.

From there, we can do further processing,
such as measuring the diameter and mapping the density.
By incorporating additional data streams and decision-making capabilities,
your machine learning becomes artificial intelligence (AI).

Supervised Learning for Pumpkins
Fortunately, there is still a role for humans.
Raptor Maps fed the machine learning algorithm labeled examples of pumpkins (�positives�),
as well as examples of vines and soil (�negatives�).
The negative examples are important, since reflections on large,
broad leaves would otherwise be flagged by the algorithm as �pumpkins� and
result in an artificially higher count.
As you can see in the map below,
the pumpkins may occasionally be touching,
so Raptor Maps had to ensure that the software could smartly identify this area
as two separate pumpkins, instead of one large one.

Diagram of a 1-layer neural network.
The �weight� of each arrow is updated with every iteration as the network is trained.
This approach is known as supervised learning.
The examples fed to the algorithm are the training data.
And the category associated with each example is a label.
Once this labeled training data has been generated,
it�s time to train our neural network.

Neural Networks
There are many types of machine learning algorithms.
In this case, Raptor Maps used a neural network.
Neural networks are modeled after the human brain.
Each arrow has a �weight� associated with it
(how much input it takes from the previous layer).
With every training example,
the weights are updated and the model improves.
After millions of iterations, the neural network is trained.
Popular libraries for neural networks include
UC Berkeley�s Caffe and
Google�s TensorFlow.

Post-Processing
As seen in the photo, each individual crop is given a unique identifier.
This makes it easier to monitor and track
individual crops during repeat inspections,
even if they slightly shift over time.
This type of approach brings the industry closer to analytics and
management at the single-crop level.

Each pumpkin is given a unique ID
Once each pumpkin is identified,
the yield map is created by dividing the field into pixels (in this case 1/32 acres).
The resulting yield maps are shapefiles
that are compatible with farm management software,
such as the John Deere Operations Center,
Case IH AFS,
Climate FieldView, and
FarmLogs.

Machine Learning for Your Data
Raptor Maps leverages its expertise in machine learning
to help companies like Deveron UAS provide farmers with accurate, variety-specific analytics.
This approach works for other industries as well,
including electrical utilities, oil and gas, insurance, and telecommunications.
Whether you�re counting pumpkins or detecting corrosion,
Raptor Maps builds intelligent software to put your drone data to work.

»Case study: identifying pumpkins with drones and machine learning

~[Σ] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~

ξ

~[Σ] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~

ξ

~[Ω] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~

ξ

~[Σ] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

ξ

~[Σ] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~

ξ

~[Σ] ~[Ω] ~[Δ]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

~

ξ

~[Σ] ~[Ω]!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Small & Smart Inc reserves rights to change this document without any notice
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~