►
Description
2015 HTM Challenge Application Submission - 2nd place
A
B
Who
has
never
suffered
any
flights
delay?
Can
we
use
the
causes
of
these
issues
to
about
bad
flight
hate
that
try
to
answer
some
of
these
questions?
We
believe
that
many
flights
are
delayed
but
meteorological
incidents,
but
we
believe
there
are
other
reasons
of
anomalies
such
as
a
plane,
the
airport
or
the
road.
B
This
field
stretch
was
focused
on
analyzing
flights
between
LA
and
New
York,
assessing
the
flight
path
until
that
abnormal
movements
in
flight
in
relation
to
it
geo
position
and
healing,
we
had
two
different
feature
in
our
up:
the
first
one
allow
us
to
with
the
history
of
flights
and
final
emulous
point
detect
by
new
pic.
Let's
see
what
new
pics
says
about
this
flight
here,
I
want
to
select
the
date
of
light,
and
we
can
pick
another
one
just
to
compare
them.
B
Using
this,
you
can
show
the
anomaly
points
on
the
flight
path
and
below.
There
are
two
different
charts.
This
is
for
the
last
flight
path
selected
and
this
one
will
compare
both
flights,
but
we
also
want
to
detect
if
any
current
flight
is
having
an
anomaly.
So
we
can
inform
the
airline
about
this
situation.
B
B
B
We
know
that
there
are
thousands
flights
above
our
heads
every
day.
One
problem
we
noticed
is
that
scalability
for
this
kind
of
system
is
crucial
because
of
this
we
built
HTM,
no
clue
by
definition.
In
short,
for
hierarchical
temporal
memory
models.
Cluster
more
glue
provides
a
platform
similar
to
HTM
engine
for
java
application
has
the
ability
to
scale
horizontally
using
multiple
servers.
B
B
The
backend
is
built
using
two
different
web
server.
One
of
them
is
used
to
connect
to
the
models
cluster
yet
and
push
new
flights
data
coming
from
external
sources.
Also,
it
saves
results
into
MongoDB.
The
second
web
server
is
used
to
serve
this
data
to
decline.
Both
web
servers
can
build
scale
horizontally,
a.
B
Lot
of
value
can
be
delivered,
but
a
tad
in
the
short
end
future,
so
just
keep
the
possibility
to
a
person
who
is
about
to
buy
a
ticket
to
select
a
flight
not
only
based
on
cost
and
benefit,
but
also
for
the
possibility
of
having
a
fault
making
the
travel
experience
better,
find
which
airports
have
more
anomalies
than
others.
In
order
to
provide
this
information
for
later
used
by
early
or
passengers
report
on
the
number
of
anomalies,
but
fly
justice.
A
Well,
you
guys
want
to
come
up
to
the
mic.
I
just
want
to
point
out
that
this
is
a
java
application
built
on
top
of
HTM
java
implementation
and
that
Mike
built
his
own
scaling
structure
in
order
to
facilitate
this
application,
which
is
an
impressive
feat
in
itself
and
I
suggested
he
could
even
submit
that
as
an
innovation
demo
on
its
own,
so
that
even
just
stands
alone,
I
think
so,
thanks
for
doing
that
and
I'll
turn
it
over
for
questions
comments.
A
C
B
Well,
first
of
all,
we
try
with
different
flights
like
this.
One
was
la
la
and
New
York
City,
but
we
rate
right
with
San
Francisco
to
as
a
new
york
city
and
do
the
parameters
we
were
using.
A
new
peak
were
similar
and
we
got
similar
results.
So,
for
example,
we
found
many
anomalies
on
the
ipod
because,
for
example,
we
just
got
one
month
of
data
for
each
fly,
so
we
know
that
each
flight
departs
from
a
different
gate
every
every
day.
C
B
Fitting
new
pic
with
more
data,
we
can
reduce
this
kind
of
anomalies
and
starting
new
anomalies
on
the
fly
pot.
So
another
thing
we
think
that
can
improve
this
is
to
add
weather
data
into
new
pic
as
well
to
detect
and
differentiate
these
dis
anomalies
on
the
flight
path.
So,
for
example,
if
the
plane
want
to
avoid
a
storm-
or
we
knew
big-
can
learn
a
very
interesting.
D
E
Did
your
users,
the
the
standard,
geospatial
encoder,
that
that
yes,
yes,
so
that
encoder,
it's
really
about
deviation
and
path
and
deviation
and
velocity
I,
imagine
most
of
the
real
anomalies
you'd
see,
is
when
a
plane
goes
out
of
its
way
for
something,
as
opposed
to
going
slower
or
faster
make.
You
know
once
they're
up
in
the
air
they're
going
to
keep
moving.
I
think,
but
I'm,
just
thinking
kind
of
you
kind
of
limit
yourself
really
till
I
hey
is
it?
Is
it
deviating
from
path,
yeah,
I,
just
normal
speed?
B
E
B
E
And
apparently
you
know
it
moved
away
and
no
one
noticed
that
it
was
going
in
the
wrong
direction
so
that
we
released
with
that
bother.
You
focus
in
the
end,
maybe
on
improving
the
quality
of
the
the
customer
experience.
I,
wasn't
convinced
by
that,
but
I
thought
there'd
be
a
lot
of
value
in
just
sort
of
you
know.
F
I
could
see
this
being
really
useful
and
I
think
something
that
Donna
has
always
mentioned
that
something
like
this
could
have
caught
the
Germanwings
think,
because
there
was
definitely
a
deviation
in
path
and
actually
I
think
in
that
case
it
was
even
like
the
day
before
the
pilots
had
practiced
a
something
that
was
very
unusual
was
all
right
yeah.
So
this
could
have
easily
you
know
caught.
Something
like
that
is
really
impressive.
Is.