Return-Path: X-Original-To: archive-asf-public-internal@cust-asf2.ponee.io Delivered-To: archive-asf-public-internal@cust-asf2.ponee.io Received: from cust-asf.ponee.io (cust-asf.ponee.io [163.172.22.183]) by cust-asf2.ponee.io (Postfix) with ESMTP id 6D79E200C57 for ; Sat, 15 Apr 2017 20:29:40 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id 6BF60160BA0; Sat, 15 Apr 2017 18:29:40 +0000 (UTC) Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by cust-asf.ponee.io (Postfix) with SMTP id 8CA0A160B8B for ; Sat, 15 Apr 2017 20:29:39 +0200 (CEST) Received: (qmail 71124 invoked by uid 500); 15 Apr 2017 18:29:38 -0000 Mailing-List: contact dev-help@systemml.incubator.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@systemml.incubator.apache.org Delivered-To: mailing list dev@systemml.incubator.apache.org Delivered-To: moderator for dev@systemml.incubator.apache.org Received: (qmail 66124 invoked by uid 99); 15 Apr 2017 18:17:24 -0000 X-Virus-Scanned: Debian amavisd-new at spamd1-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: 4.612 X-Spam-Level: **** X-Spam-Status: No, score=4.612 tagged_above=-999 required=6.31 tests=[DEAR_SOMETHING=1.731, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HTML_IMAGE_RATIO_08=0.001, HTML_MESSAGE=2, KAM_NUMSUBJECT=0.5, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H3=-0.01, RCVD_IN_MSPIKE_WL=-0.01, RCVD_IN_SORBS_SPAM=0.5, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=disabled Authentication-Results: spamd1-us-west.apache.org (amavisd-new); dkim=pass (2048-bit key) header.d=gmail.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:from:date:message-id:subject:to; bh=kJwe5RTiYzWluXu5ktrdqRT9PPLnKXYxPeERVfdqbLk=; b=E+LKpfSgqY9nuWiA8b5OQxUB5vXgqnb+XgPlCYsXNTrDvim1tCol2+vRu1/08FqBi+ M055ZbwQZvLctEVGGqoOGRIw3KiUox4H7ztGahehWf+/T3HeIZPn0J3KXzcDUpFfp4g1 qQfx95mFW/UE2MsjS0ICX0iXtz/X0wJ/NB9EUDsvAcWfTEDam2asQjAS/BY2LO4cJj1M rv+WzoivNw9TUpMfvVcYj+pqKnP0w7DV7ZcxLcQz0wzoz1M0hrG0zKRtX4DVZorBoMhf 32oYPMtnydAjIOZOXjCxfu3rgYEVW/Hm5a8QQvyyDKj/XjD1jmvxV6/MmzSV7OxWax6q Ah8g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=kJwe5RTiYzWluXu5ktrdqRT9PPLnKXYxPeERVfdqbLk=; b=UGq4MIQtybjoBeEoOrOGpBedIJlHYky0yH/q5nCHmu0lLG5UZi5Rg9TGYKpcfhXpTg ABEhmtIRQJtT0GodnL9RA1IjF3nvcYegEuaokm3v3mriNgJX6LJGQ6E9qq/X0VmxZbC6 lbR+7IocbKmX9RZt5wqdP70an7plboxOIzkHYSLz50pdYQqVTm3z/ikSaqhYf+f2bG7u OljW5r41aur2Cx+6JGh91BBw0hMA8HcId23Jy0C83MH2S/O9NwmbRjTH6QDZwuirnTQD tWBdfGhbnFq8Hnz1bTOSOLHT051ChutX/sXDdfpckJfz3XwrcC7pDDl+Uimv5YEDPBRC BKtQ== X-Gm-Message-State: AN3rC/4MCQQd4jvJtDploK1Pn2ZbjYSZFoIFEZisxgNtAHbFP8iKAMXU Hn+WtIW7DdWv6l7ilnZWkLF9rDgGTnKP X-Received: by 10.31.50.9 with SMTP id y9mr871727vky.14.1492280235121; Sat, 15 Apr 2017 11:17:15 -0700 (PDT) MIME-Version: 1.0 From: Janardhan Pulivarthi Date: Sat, 15 Apr 2017 23:46:34 +0530 Message-ID: Subject: Use case for the SYSTEMML-1437 To: dev@systemml.incubator.apache.org Content-Type: multipart/related; boundary=001a11431808521b11054d389156 archived-at: Sat, 15 Apr 2017 18:29:40 -0000 --001a11431808521b11054d389156 Content-Type: multipart/alternative; boundary=001a11431808521b0d054d389155 --001a11431808521b0d054d389155 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Dear sir / ma'am, The potential of Factorization machines has yet to be discovered. The possible uses are traffic prediction, earthquake prediction, movie ratings and much more... Incorporating the Factorization Machines in *SystemML* will be very much necessary, for much of the data that we encountering in many fields is sparse in many respects. *Description for the use case:=F0=9F=9B=AB * The automatic prediction of flight diversion, with no prior knowledge of flight route requirement. This deviation from the expected flight path alerts the ground logistics to find the next best alternative, for the timely delivery of the intended service. The prediction is made by analyzing the flight data anomalies detected by Factorization Machines (FM) classification. Often, the datasets associated with the flight data are sparse, which makes it difficult to analyze the flight path accurately. But, with FM's this will be easier. Already, implemented in SVM by some researchers in this article. The doi: http://doi.org/10.1016/j.dss.2016.05.004 *Diagram: (*Overview of the prediction model for diversion detection. *)[image: Inline image 1]* *Features: (*of the aircraft*)* 1. Distance completed 2. Distance gained 3. Velocity deviation 4. Altitude deviation 5. Phase *What to Optimize:* 1. *Interval length (L):* Interval-length *L* describes the time range in which positional updates are gathered, and consequently the amount of behavior captured in a single feature vector. 2. The parameters capture the expected level of noise and the extent to which the decision hyperplane is fit to the training data. Iterations will be made on these three things & we will be trying to have a sufficient precision as to be needed to safely say that plane will be diverted: *P* =3D Precision, *R* =3D recall,* F*-score =E2=80=8B=E2=80=8B *Dataset inputs:* 1. a unique flight identifier. 2. an aircraft identifier. 3. the flight code. 4. the timestamp of the event. 5. the IATA/FAA codes of departure & arrival airports. 6. the gps coordinates of the aircraft. 7. the altitude of aircraft. 8. the speed of the aircraft. *Datasets:* 1. http://openflights.org/data.html (open database license) 2. https://www.flightradar24.com 3. and there will be more open databases. *Possible extensions:* 1. If it can be applied for air traffic, then it will work for Rail=F0= =9F=9B=A4, Road=F0=9F=9B=A3, Vessel traffic=F0=9F=9B=B3. 2. Earthquake detection is also possible with the Factorization Machines, as the natural event occurrence is subject to variable at any given time & place. --001a11431808521b0d054d389155 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
Dear sir / ma'am,

The potential of Fa= ctorization machines has yet to be discovered. The possible uses are traffi= c prediction, earthquake prediction, movie ratings and much more... Incorpo= rating the Factorization Machines in SystemML will be very much nece= ssary, for much of the data that we encountering in many fields is sparse i= n many respects.

Description for the use case:=F0=9F=9B=AB
<= /b>
The automatic prediction of flight diversion, with no prior knowledge of=20 flight route requirement. This deviation from the expected flight path=20 alerts the ground logistics to find the next best alternative, for the=20 timely delivery of the intended service. The prediction is made by=20 analyzing the flight data anomalies detected by Factorization Machines (FM)= classification. Often, the datasets associated with the flight data are sp= arse, which makes it difficult to analyze the flight path accurately. But, = with FM's this will be easier.

Already, implemented in SVM= by some researchers in this article. The doi: http://doi.org/10.1016/j.dss.201= 6.05.004

Diagram: (Overview of the prediction model= for diversion detection.)
=3D"Inline

Features: (of the aircraft)
  1. Di= stance completed
  2. Distance gained
  3. Velocity deviation
  4. Altitude deviation
  5. Phase
What to Optimize:
  1. Interval length (L): Interval-length L=C2=A0describes the time range in which positional updates are gathered, and=20 consequently the amount of behavior captured in a single feature vector.
  2. The parameters capture the expected level of noise and the ext= ent to=20 which the decision hyperplane is fit to the training data.
It= erations will be made on these three things & we will be trying to have= a sufficient precision as to be needed to safely say that plane will be di= verted: P =3D Precision, R =3D recall, F-score
=E2= =80=8B=E2=80=8B
Dataset inputs:
  1. a unique f= light identifier.
  2. an aircraft identifier.
  3. the flight code.<= /li>
  4. the timestamp of the event.
  5. the IATA/FAA codes of departure= & arrival airports.
  6. the gps coordinates of the aircraft.
    7. <= li>the altitude of aircraft.
  7. the speed of the aircraft.
Datasets:

  1. http= ://openflights.org/data.html (open database license)
    2. https://www.flightradar24.= com
  2. and there will be more open databases.
<= p>Possible extensions:

  1. If it can be applied for air traff= ic, then it will work for Rail=F0=9F=9B=A4, Road=F0=9F=9B=A3, Vessel traffi= c=F0=9F=9B=B3.
  2. Earthquake detection is also possible with the Facto= rization Machines, as the natural event occurrence is subject to variable a= t any given time & place.
--001a11431808521b0d054d389155-- --001a11431808521b11054d389156--