Numenta HTM Challenge Submissions, 9 Nov 2015

Previous Meeting

Next Meeting

⏯

youtube image

►

From YouTube: Air Traffic Anomaly Detector - Numenta - Nupic

Description

Submission for Numenta Challenge 2015 http://devpost.com/software/air-traffic-anomaly-detector

Who has never suffer any flight’s delay? Could we use the causes of these issues to avoid bad flights?

ATAD try to answer some of these questions.

We believe that many flights are delayed by meteorological incidents, but there are others reasons of anomalies such as the plane or the airport or the route.

We also are interested in known if a plane changes its typical flight path in order to detect possible security breach.

This first stage was focused on analyzing flights between LA and NY, assessing the flight path and to detect abnormal movements in flight in relation to its geo-position and heading.

We got two different features.

1) The first allows us to view the history of flights and find anomalous points detected by NUPIC

2) But we also, we want to detect if any current flight is having an anomaly, so we can inform the airline about this situation. To do this, we have created a map having real time data, it’ll notify the user if it find any anomaly.

We know that there are thousands of flights above our heads everyday. One problem we noticed is that scalability for this kind of system is crutial. Because of this we built HTM-MOCLU.
By definition HTM-MOCLU is short for Hierarchical Temporal Memory Models Cluster. Htm-Moclu provides a platform similar to HtmEngine for htm.java applications, and has the ability to scale horizontally using multiple servers.

Then we built our app on top of Moclu, that way we can add hardware on demand to deal with tons of data for realtime flights.

On the UI side we are using AngularJS that integrates with Lift 3 and Comet actors, a google maps angular implementation called angular-google-maps and D3 charts.

The backend is built using 2 different web servers.

One of them is used to connect to the models cluster, get 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 the client. Both web servers can be scaled horizontally.

A lot of value can be delivered by ATAD in a short-term future, such as:

* Give the possibility to a person who is about to buy a ticket to select a flight not only based on costs and benefits 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 use by airlines or passagers.

* Report on the number of anomalies by flight to assess their personal onboard.

* Add weather information to understand it impact and to help plan situations where airports are closed to prevent early collapse secondary airport facilities like hotels.

* Analyze routes and airports can enable airlines to enhance their routes management in order to reduce costs generated by anomalies.

We believe this information is useful for all the stakeholders, but primarily for the passenger, who will receive a better travel experience.

https://github.com/antidata/ATAD

https://github.com/antidata/htm-moclu

https://github.com/numenta/htm.java

A

Who has never suffered any flights delay? Can we use the causes of these issues to about bad flight? Eight 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 the plane di poor or the road.

A

We also interested to know if blink changes its typical flat pad in order to detect a possible security breach.

A

This fifth stage 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 view the history of flights and finally, mulus point detect by new pic. Let's see what new pic says about this flight here, I want to select the date of light, and we can pick another one just to compare them.

A

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. To do this, we create a map having real-time data. It will notify the user if it find any anomaly to access real-time feature.

A

We are going to click here to get real-time data, you just need to click here and you will start getting data from the server. So we are using this threshold to take an alert.

A

Any kind of anomaly.

A

So no big detected what I normally point here and this is showing the alert.

A

So we can know that this is something that was never seen before.

A

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 is 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.

A

Then we build our up on top of no clue that way. We can add hardware on demand to deal with tons of data for real-time flights on the UI side. Where is in angularjs that integrate with glittery and comment outdoors, a Google Maps angular implementation called angular google maps and d3 charts?

A

The backend is built using two different web servers. One of them is used to connect to the models cluster get 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.

A

Lot of value can be delivered, but a tag in the short term future such as 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 but find which airports have more anomalies than others.

A

In order to provide this information for later use by early or passengers report on the number of anomalies by flight justice, their personal envoy, ad weather information to understand impact and help and situation where I ports and blows to prevent early collapse of secondary airport facilities like hotels, analyze, roads and iPods can enable errands to enhance the roads management in order to reduce costs generate bite, anomalies.

A

We believe this information is useful for all stakeholders, but apparently for the passenger, who will recite a better travel experience.