<x:xmpmeta tsc:version="2.0.1" xmlns:x="adobe:ns:meta/" xmlns:tsc="http://www.techsmith.com/xmp/tsc/">
   <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:xmp="http://ns.adobe.com/xap/1.0/" xmlns:xmpDM="http://ns.adobe.com/xmp/1.0/DynamicMedia/" xmlns:xmpG="http://ns.adobe.com/xap/1.0/g/" xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/" xmlns:tscDM="http://www.techsmith.com/xmp/tscDM/" xmlns:tscIQ="http://www.techsmith.com/xmp/tscIQ/" xmlns:tscHS="http://www.techsmith.com/xmp/tscHS/" xmlns:stDim="http://ns.adobe.com/xap/1.0/sType/Dimensions#" xmlns:stFnt="http://ns.adobe.com/xap/1.0/sType/Font#" xmlns:exif="http://ns.adobe.com/exif/1.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
      <rdf:Description dc:date="2017-08-09 11:28:33 PM" dc:source="Camtasia,9.0.5,enu" dc:title="icccn17p" tscDM:firstFrame="icccn17p_First_Frame.png" tscDM:originId="2625EA67-814F-4A0C-B4C7-2902396CFF3B" tscDM:project="icccn17p.tscproj">
         <xmpDM:duration xmpDM:scale="1/1000" xmpDM:value="1164366"/>
         <xmpDM:videoFrameSize stDim:unit="pixel" stDim:h="810" stDim:w="1080"/>
         <tsc:langName>
            <rdf:Bag>
               <rdf:li xml:lang="en-US">English</rdf:li></rdf:Bag>
         </tsc:langName>
         <xmpDM:Tracks>
            <rdf:Bag>
               <rdf:li>
                  <rdf:Description xmpDM:trackType="ScreenText" xmpDM:frameRate="f1000" xmpDM:trackName="Screen Text">
                     <xmpDM:markers>
                        <rdf:Seq>
                           <rdf:li><rdf:Description xmpDM:name="Overview Network Function Virtualization (NFV) NFV on multiple clouds Gaps in Fault, Configuration, Accounting, Performance and Security (FCAPS) Fault detection" xmpDM:startTime="29333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="using Shallow Learning Fault location using Deep Learning" xmpDM:startTime="29333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="MME RNC IMS Hardware Hardware Set Top Box CGNAT Residential Gateway Hardware home home home hi-resolution-android.jpg" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="iphone-high-resolution.png" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="hi-resolution-android.jpg" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Cell_Tower.jpg" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="MME RNC IMS Residential Gateway CGNAT Set Top Box MME RNC IMS MME RNC IMS Network Function Virtualization Standard hardware" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is fast and cheap Þ No need for specialized hardware Implement all functions in software Virtualize all functions Þ Create" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="capacity on demand Þ Implement all carrier functions in a cloud" xmpDM:startTime="61233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Advantages of NFV Reduces time to market new services Provides flexibility of scaling Lowers capital and operational costs" xmpDM:startTime="145333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Users Network juanjo_Router.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Micro-Clouds 1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Trend: Computation in the Edge To service mobile users/IoT, the computation needs to come to edge  Mobile Edge Computing" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="174800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Trend: Multi-Cloud Larger and infrequent jobs serviced by local and regional clouds juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Users Network juanjo_Router.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Micro-Clouds 1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Local Clouds Regional Clouds 12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="switch.pdf" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12154415611636377900jcartier_computer.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1195431327409717356database_base_de_donn__01r.svg.hi.png" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="255233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Advantages of NFV on Multi-Cloud Wider footprint for distributed services." xmpDM:startTime="265567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Lower risk of total failure." xmpDM:startTime="265567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="265567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Issues in Multi-Cloud NFV Deployments Cloud downtime higher than five nines requirement of NFV (99.999%" xmpDM:startTime="290267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Þ 3 min 15sec downtime in 1yr)." xmpDM:startTime="290267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Higher complexity of virtual environments FCAPS framework is weak compared to traditional carrier networks." xmpDM:startTime="290267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Not yet carrier grade In this paper we deal primarily with the FCP part of FCAPS." xmpDM:startTime="290267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="From now on: Fault = Faults and Performance Issues" xmpDM:startTime="290267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Cloud 3 Cloud 2 Network Services (NS) Network Service: An ordered set of virtual network functions (VNFs), e.g.," xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="IMS, Mobility Management Entity (MME), … VNFs are chained into service function chains (SFC) or VNF graphs Multiple levels of" xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="management VNFs by NFV-MANO (Management and Orchestration) Virtual Machines (VMs) by Multi-cloud Management and Control Platform (MMCP) Network services by" xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="BSS/OSS (Business and Operation Support Systems) of the carrier." xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Cloud 1 VNF 1 VNF 2 VNF 3 VNF 4 VNF 5 Terminal 1 Terminal 2 Domain 2 Domain 1" xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Domain 3" xmpDM:startTime="430867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="FCP Problem Description Study of markers and metrics Detection: of manifest and impending faults and that could cause performance degradation" xmpDM:startTime="509833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="or failure." xmpDM:startTime="509833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Localization: of manifest and impending faults and performance issues." xmpDM:startTime="509833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Severity: In case of impending faults severity level should be predicted." xmpDM:startTime="509833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="509833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Markers and Metrics Markers: Alarms, notifications, warning or error messages, measurements and counter values." xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Metrics: Performance Measures CDR (call drop rate) CSSR (call set up success rate) SDCCH congestion TCH Congestion Packet loss ≤" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="2% ≥95% ≤ 1% ≤2% ≤ 1% SDCCH: Standalone Dedicated Control Channel; TCH: Traffic Channel SDCCH: Standalone Dedicated Control Channel;" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TCH: Traffic Channel SDCCH: Standalone Dedicated Control Channel; TCH: Traffic Channel SDCCH: Standalone Dedicated Control Channel; TCH: Traffic Channel SDCCH:" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Standalone Dedicated Control Channel; TCH: Traffic Channel CDR (call drop rate) CSSR (call set up success rate) SDCCH congestion TCH" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Congestion Packet loss ≤ 2% ≥95% ≤ 1% ≤2% ≤ 1% SDCCH: Standalone Dedicated Control Channel; TCH: Traffic Channel Mobile" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Network Fixed Network Broadband Radio Link Time Out No Dial Tone Intermittent Connection Time Slot Shortage Line Cart Port Faulty" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Repeated Training Mobile Network Fixed Network Broadband Radio Link Time Out No Dial Tone Intermittent Connection Time Slot Shortage Line" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Cart Port Faulty Repeated Training" xmpDM:startTime="548233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Description of Training Datasets The Telstra Dataset (2016) [1] The Telstra datasets (2016) are derived from the fault log files" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="containing real customer faults Table 1: Training dataset containing location and severity of faults (0 indicating no fault, 1 indicating" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="a few faults and 2 indicating many faults.)." xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="These are identified by the “id” key." xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Table 2: Test dataset for prediction of fault severity Table 3: Event type gives the type of fault Table 4:" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Resource involved in the fault Table 5: Severity type gives warning given by the system Table 6: Feature dataset contains" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="various markers Ref: Kaggle datasets, https://www.kaggle.com/datasets" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="604700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Telstra Dataset Samples Table 1 Training Dataset (7381 examples) Table 2 Test dataset (11171 examples) Table 3 Event type dataset" xmpDM:startTime="648533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(31170 records) Table 4 Resource type dataset (21076 records) Table 5 Severity type (18552 records) Table 6 Feature dataset (58671" xmpDM:startTime="648533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="records) Table 1 Training Dataset (7381 examples) Table 2 Test dataset (11171 examples) Table 3 Event type dataset (31170 records)" xmpDM:startTime="648533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Table 4 Resource type dataset (21076 records) Table 5 Severity type (18552 records) Table 6 Feature dataset (58671 records)" xmpDM:startTime="648533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Description of Training Datasets The Telstra Dataset (2016) [1] The Telstra datasets (2016) are derived from the fault log files" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="containing real customer faults Table 1: Training dataset containing location and severity of faults (0 indicating no fault, 1 indicating" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="a few faults and 2 indicating many faults.)." xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="These are identified by the “id” key." xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Table 2: Test dataset for prediction of fault severity Table 3: Event type gives the type of fault Table 4:" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Resource involved in the fault Table 5: Severity type gives warning given by the system Table 6: Feature dataset contains" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="various markers Ref: Kaggle datasets, https://www.kaggle.com/datasets" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="657667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Telstra Dataset Samples Table 1 Training Dataset (7381 examples) Table 2 Test dataset (11171 examples) Table 3 Event type dataset" xmpDM:startTime="683967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(31170 records) Table 4 Resource type dataset (21076 records) Table 5 Severity type (18552 records) Table 6 Feature dataset (58671" xmpDM:startTime="683967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="records) Table 1 Training Dataset (7381 examples) Table 2 Test dataset (11171 examples) Table 3 Event type dataset (31170 records)" xmpDM:startTime="683967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Table 4 Resource type dataset (21076 records) Table 5 Severity type (18552 records) Table 6 Feature dataset (58671 records)" xmpDM:startTime="683967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="KDE dataset This is a synthetic dataset generated through multivariate kernel density estimation (KDE) technique [2] Some of the features" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and classes are shown in the table   Features   Classes 1 BTS hardware 1 Call drop 2 Radio link" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="phase 2 Call setup 3 Antenna tilt 3 No Roaming 4 C/I ratio 4 Weak Signal 5 TCH congestion 5" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="No registration 6 BCC fault 6 No outgoing 7 Time slot short 7 Data not working 8 Rx Noise" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Features   Classes 1 BTS hardware 1 Call drop 2 Radio link phase 2 Call setup 3 Antenna tilt 3" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="No Roaming 4 C/I ratio 4 Weak Signal 5 TCH congestion 5 No registration 6 BCC fault 6 No outgoing" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="7 Time slot short 7 Data not working 8 Rx Noise" xmpDM:startTime="685700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fault Detection Goal: Correlate markers to infer manifest or to predict impending performance and fault conditions." xmpDM:startTime="713767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Two stage machine learning model: Trained Model for Classification Stage 1 Trained Model for Classification Stage 2 Markers Fault No" xmpDM:startTime="713767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fault No Action Manifest Fault Impending Fault Priority Localization Elective Localization Minor faults and warnings are the main contributors to" xmpDM:startTime="713767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="the impending faults and need to be analyzed." xmpDM:startTime="713767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="713767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Detection of Faults and Performance Problems   SVM ADT Random Forests Correctly classified instances 95.42%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="95.00%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="86.67%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Precision (Average) 95.7%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="95.2%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="86.9%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Mean absolute error 0.0458" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0.0859" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0.2509" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="True positive for class 1 97.6%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="96.4%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="69.9%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="False positive for class 0 2.4%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="3.6%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="30.1%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SVM ADT Random Forests Correctly classified instances 95.42%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="95.00%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="86.67%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Precision (Average) 95.7%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="95.2%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="86.9%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Mean absolute error 0.0458" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0.0859" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0.2509" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="True positive for class 1 97.6%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="96.4%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="69.9%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="False positive for class 0 2.4%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="3.6%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="30.1%" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="‘Fault’, “No Fault’ binary classification tested with Support Vector Machine (SVM), Alternating Decision Trees (ADT) and Random Forests (RF) Each" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of the models was trained with 240 examples and 10% cross-validation." xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SVM had highest accuracy and precision, high true positive (TP) rate for class 1 (fault cases)" xmpDM:startTime="761800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Detection (cont.)" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The second model was trained to classify fault as manifest or impending." xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Prediction rate was 100% with SVM in test set for predicting impending faults from warning cases." xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Comparison with other works: In [3] the authors used SVM to classify wind turbine faults using operational data and achieved" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="99.6%" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="accuracy." xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="In [4] wind turbine faults were detected with accuracy 98.26%" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="for linear SVM and 97.35" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="for Gaussian." xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="In [5] authors achieved 99.9%" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="accuracy of classification of faults in rotating machinery with SVM." xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="816267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Localization of Faults Two layered machine learning model for localizing manifest faults: Deep learning (Stacked Autoencoder) for impending faults: Reasons:" xmpDM:startTime="843900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Automatic selection of features from high dimensional data Filtering information through the layers for better accuracy Gives improved results in" xmpDM:startTime="843900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="other areas Layer 1 Broad Categorization Layer 2 Fine Grain Localization Markers Fault Category Manifest fault Maintenance Work order Impending" xmpDM:startTime="843900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fault SAE Localization Severity and Location Markers" xmpDM:startTime="843900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Localization of Faults and Performance Problems Telstra dataset was adapted for evaluation Fault severity level classes: No fault (0), a" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="few faults (1) and many faults (2) and are based on actual faults reported by users Severity Type: Intensity of" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="the warning – predicts impending faults 1 Id 5 Resource type 1 to 10 2 Location 6 Severity type 1" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="to 5 3 Features 1 to 386 7 Event type 4 Volumes for features 8 Fault severity level 1 Id" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="5 Resource type 1 to 10 2 Location 6 Severity type 1 to 5 3 Features 1 to 386 7" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Event type 4 Volumes for features 8 Fault severity level" xmpDM:startTime="885600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stacked Autoencoder 100 Hidden layers in the first encoder 50 Hidden layers in the 2nd encoder Softmax layer provides supervised" xmpDM:startTime="909533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="back-propagation improvement of the weights learned during unsupervised training." xmpDM:startTime="909533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="909533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix Confusion matrix shows how many are correctly and incorrectly classified." xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="A well tuned model give 100% accuracy." xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This is good compared to deep learning model for HVAC where accuracy is reported as ≥ 95% [6]." xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 12 44.4%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 3.7%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 87.5%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12.5%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 7 25.9%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 92.3%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="7.7%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 96.3%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="3.7%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 2 1 3 0 0% 13 48.1%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 100% 0% 0 0% 0 0% 7 25.9%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 100% 0% 100% 0% 100% 0% 1 2 3 2 1 3 Output Class Output Class" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Target Class Target Class W/O Sparsity Regularization W Sparsity Regularization ρ=0.05," xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=1, Accuracy=96.3%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="ρ=0.1," xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=4, Accuracy=100%" xmpDM:startTime="945667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Effect of Relative Sizes of Hidden Layers H1=Size of hidden layer 1, H2=Size of hidden layer 2 Accuracy and MSE" xmpDM:startTime="945867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are good for certain ranges of H1 and H2 H2=10 H2=5 H2=10 H2=5 H1 H1" xmpDM:startTime="945867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix Confusion matrix shows how many are correctly and incorrectly classified." xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="A well tuned model give 100% accuracy." xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This is good compared to deep learning model for HVAC where accuracy is reported as ≥ 95% [6]." xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 12 44.4%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 3.7%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 87.5%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12.5%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 7 25.9%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 92.3%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="7.7%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 96.3%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="3.7%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 2 1 3 0 0% 13 48.1%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 100% 0% 0 0% 0 0% 7 25.9%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 100% 0% 100% 0% 100% 0% 1 2 3 2 1 3 Output Class Output Class" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Target Class Target Class W/O Sparsity Regularization W Sparsity Regularization ρ=0.05," xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=1, Accuracy=96.3%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="ρ=0.1," xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=4, Accuracy=100%" xmpDM:startTime="947000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stacked Autoencoder 100 Hidden layers in the first encoder 50 Hidden layers in the 2nd encoder Softmax layer provides supervised" xmpDM:startTime="948400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="back-propagation improvement of the weights learned during unsupervised training." xmpDM:startTime="948400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="948400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix Confusion matrix shows how many are correctly and incorrectly classified." xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="A well tuned model give 100% accuracy." xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This is good compared to deep learning model for HVAC where accuracy is reported as ≥ 95% [6]." xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 12 44.4%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 3.7%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 87.5%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="12.5%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 7 25.9%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 92.3%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="7.7%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 96.3%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="3.7%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 2 1 3 0 0% 13 48.1%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 100% 0% 7 25.9%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="0 0% 0 0% 100% 0% 0 0% 0 0% 7 25.9%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="100% 0% 100% 0% 100% 0% 100% 0% 100% 0% 1 2 3 2 1 3 Output Class Output Class" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Target Class Target Class W/O Sparsity Regularization W Sparsity Regularization ρ=0.05," xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=1, Accuracy=96.3%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="ρ=0.1," xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="β=4, Accuracy=100%" xmpDM:startTime="949400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Effect of Relative Sizes of Hidden Layers H1=Size of hidden layer 1, H2=Size of hidden layer 2 Accuracy and MSE" xmpDM:startTime="1040367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are good for certain ranges of H1 and H2 H2=10 H2=5 H2=10 H2=5 H1 H1" xmpDM:startTime="1040367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Summary Handling fault and performance anomalies is crucial for the success of NFV deployments over clouds." xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="A combination of shallow and deep learning structures works well for detection and localization of manifest and impending fault and" xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="performance issues." xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Evaluation has been done using real and synthetic datasets and results are comparable to or better than fault detection and" xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="localization in other areas." xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1085500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="References Kaggle datasets, https://www.kaggle.com/datasets" xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Z." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Botev, “Fast multivariate kernel density estimation for high dimensions,” 2016 K." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Leahy, R." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="L." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Hu, I." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="C." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Konstantakopoulos, C." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="J." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Spanos, A." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="M." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Agogino,”Diagnosing wind turbine faults using machine learning techniques applied to operational data,” International Conference on Prognostics and Health Management (ICPHM)," xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="2016 P." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Santos, L." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="F." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Villa, A." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Reñones, A." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Bustillo, J." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Maudes, “An SVM-Based Solution for Fault Detection in Wind Turbines,” Sensors, 2015 G." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Nicchiotti, L." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fromaigeat, L." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Etienne, “Machine Learning Strategy for Fault Classification Using Only Nominal Data,” European Conference Of The Prognostics And Health Management Society," xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="2016 D." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Lee, B." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Lee, J." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="W." xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Shin, “Fault Detection and Diagnosis with Modelica Language using Deep Belief Network,” Proceedings of the 11th International Modelica Conference, 2015" xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1157967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Scan This to Download These Slides thankyou Raj Jain http://rajjain.com" xmpDM:startTime="1159100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1159100" xmpDM:duration="1000"/></rdf:li></rdf:Seq>
                     </xmpDM:markers>
                  </rdf:Description>
               </rdf:li>
               <rdf:li>
                  <rdf:Description xmpDM:trackType="TableOfContents" xmpDM:frameRate="f1000" xmpDM:trackName="Table of Contents">
                     <xmpDM:markers>
                        <rdf:Seq>
                           <rdf:li><rdf:Description xmpDM:name="Overview" xmpDM:startTime="29333" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="0" tscDM:imageoffset="0" tscDM:imagerect="0, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Network Function Virtualization" xmpDM:startTime="61233" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="1" tscDM:imageoffset="0" tscDM:imagerect="75, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Advantages of NFV" xmpDM:startTime="145333" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="2" tscDM:imageoffset="0" tscDM:imagerect="150, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Trend: Computation in the Edge" xmpDM:startTime="174800" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="3" tscDM:imageoffset="0" tscDM:imagerect="225, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Trend: Multi-Cloud" xmpDM:startTime="255233" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="4" tscDM:imageoffset="0" tscDM:imagerect="300, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Advantages of NFV on Multi-Cloud" xmpDM:startTime="265567" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="5" tscDM:imageoffset="0" tscDM:imagerect="375, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Issues in Multi-Cloud NFV Deployments" xmpDM:startTime="290267" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="6" tscDM:imageoffset="0" tscDM:imagerect="450, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Network Services (NS)" xmpDM:startTime="430867" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="7" tscDM:imageoffset="0" tscDM:imagerect="525, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="FCP Problem Description" xmpDM:startTime="509833" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="8" tscDM:imageoffset="0" tscDM:imagerect="600, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Markers and Metrics" xmpDM:startTime="548233" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="9" tscDM:imageoffset="0" tscDM:imagerect="675, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Description of Training Datasets" xmpDM:startTime="604700" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="10" tscDM:imageoffset="0" tscDM:imagerect="750, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Telstra Dataset Samples" xmpDM:startTime="648533" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="11" tscDM:imageoffset="0" tscDM:imagerect="825, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Description of Training Datasets" xmpDM:startTime="657667" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="12" tscDM:imageoffset="0" tscDM:imagerect="900, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Telstra Dataset Samples" xmpDM:startTime="683967" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="13" tscDM:imageoffset="0" tscDM:imagerect="975, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="KDE dataset" xmpDM:startTime="685700" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="14" tscDM:imageoffset="0" tscDM:imagerect="1050, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fault Detection " xmpDM:startTime="713767" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="15" tscDM:imageoffset="0" tscDM:imagerect="1125, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Detection of Faults and Performance Problems" xmpDM:startTime="761800" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="16" tscDM:imageoffset="0" tscDM:imagerect="1200, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Detection (cont.)" xmpDM:startTime="816267" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="17" tscDM:imageoffset="0" tscDM:imagerect="1275, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Localization of Faults" xmpDM:startTime="843900" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="18" tscDM:imageoffset="0" tscDM:imagerect="1350, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Localization of Faults and Performance Problems" xmpDM:startTime="885600" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="19" tscDM:imageoffset="0" tscDM:imagerect="1425, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stacked Autoencoder" xmpDM:startTime="909533" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="20" tscDM:imageoffset="0" tscDM:imagerect="1500, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix" xmpDM:startTime="945667" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="21" tscDM:imageoffset="0" tscDM:imagerect="1575, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Effect of Relative Sizes of Hidden Layers" xmpDM:startTime="945867" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="22" tscDM:imageoffset="0" tscDM:imagerect="1650, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix" xmpDM:startTime="947000" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="23" tscDM:imageoffset="0" tscDM:imagerect="1725, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stacked Autoencoder" xmpDM:startTime="948400" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="24" tscDM:imageoffset="0" tscDM:imagerect="1800, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Confusion Matrix" xmpDM:startTime="949400" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="25" tscDM:imageoffset="0" tscDM:imagerect="1875, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Effect of Relative Sizes of Hidden Layers" xmpDM:startTime="1040367" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="26" tscDM:imageoffset="0" tscDM:imagerect="1950, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Summary" xmpDM:startTime="1085500" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="27" tscDM:imageoffset="0" tscDM:imagerect="2025, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="References" xmpDM:startTime="1157967" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="28" tscDM:imageoffset="0" tscDM:imagerect="2100, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Scan This to Download These Slides" xmpDM:startTime="1159100" tscDM:image="icccn17p_Thumbnails.png" tscDM:imageindex="29" tscDM:imageoffset="0" tscDM:imagerect="2175, 0, 75, 56"/></rdf:li></rdf:Seq>
                     </xmpDM:markers>
                  </rdf:Description>
               </rdf:li>
            </rdf:Bag>
         </xmpDM:Tracks>
         <tscDM:controller>
            <rdf:Description xmpDM:name="tscplayer">
               <tscDM:parameters>
                  <rdf:Bag>
                     <rdf:li xmpDM:name="autohide" xmpDM:value="true"/><rdf:li xmpDM:name="autoplay" xmpDM:value="false"/><rdf:li xmpDM:name="loop" xmpDM:value="false"/><rdf:li xmpDM:name="searchable" xmpDM:value="true"/><rdf:li xmpDM:name="captionsenabled" xmpDM:value="false"/><rdf:li xmpDM:name="sidebarenabled" xmpDM:value="false"/><rdf:li xmpDM:name="unicodeenabled" xmpDM:value="false"/><rdf:li xmpDM:name="backgroundcolor" xmpDM:value="000000"/><rdf:li xmpDM:name="sidebarlocation" xmpDM:value="left"/><rdf:li xmpDM:name="endaction" xmpDM:value="stop"/><rdf:li xmpDM:name="endactionparam" xmpDM:value="true"/><rdf:li xmpDM:name="locale" xmpDM:value="en-US"/></rdf:Bag>
               </tscDM:parameters>
               <tscDM:controllerText>
                  <rdf:Bag>
                  </rdf:Bag>
               </tscDM:controllerText>
            </rdf:Description>
         </tscDM:controller>
         <tscDM:contentList>
            <rdf:Description>
               <tscDM:files>
                  <rdf:Seq>
                     <rdf:li xmpDM:name="0" xmpDM:value="icccn17p.mp4"/><rdf:li xmpDM:name="1" xmpDM:value="icccn17p_First_Frame.png"/><rdf:li xmpDM:name="2" xmpDM:value="icccn17p_Thumbnails.png"/></rdf:Seq>
               </tscDM:files>
            </rdf:Description>
         </tscDM:contentList>
      </rdf:Description>
   </rdf:RDF>
</x:xmpmeta>