Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

WSO2Con USA 2017: IoT in Airline Operations

1,136 views

Published on

WSO2Con USA 2017: IoT in Airline Operations

Published in: Technology
  • Be the first to comment

WSO2Con USA 2017: IoT in Airline Operations

  1. 1. February 22, 2017 IoT in Airline Operations
  2. 2. About United § 339 Destinations in 54 Countries § 212 Domestic / 127 International § 9 Hubs (Chicago, Denver, Guam, Houston, Los Angeles, Newark, San Francisco, Tokyo, Washington, D.C.) § 4,523 Daily Departures § 143 Million passengers in 2016 § Fleet Size: 738 Mainline / 566 United Express
  3. 3. IoT Layers – From sensors to apps Things – Sensors, Devices etc. Connectivity – Communications, protocols, networks etc. Infrastructure – Public cloud, private DC, hybrid etc. Data Ingestion – Event processing, storage etc. Data Analysis – Data mining, machine learning etc. Applications – Reporting, Sensing applications People & Processes – Improving Customer Experience Business Value Big Data FogCloud
  4. 4. Things Bluetooth Low Energy (BLE) Beacons § Low-energy “smart” Bluetooth beacons broadcast information that can be received by nearby smartphones § Current beacons identify that a handset is adjacent to a specific beacon Upcoming Bluetooth standards improve on precision § Range: 1M-30M, 2-Dimensional ***Sub 1 meter precision locations broadcast in the works
  5. 5. Things Geocoded High Resolution Indoor Maps
  6. 6. Application Indoor Navigation with blue-dot experience
  7. 7. Data Ingestion Event Processing and Storage AWS cloud Amazon API Gateway Airports CEP Processor Amazon Kinesis AWS S3 Storage Amazon API Gateway DB Dashboards iBeacon
  8. 8. Infrastructure Elastic infrastructure running in cloud 8
  9. 9. Infrastructure Elastic infrastructure running in cloud 9
  10. 10. Infrastructure Elastic infrastructure running in cloud
  11. 11. Data Analysis TSA Wait Times
  12. 12. Data Analysis TSA Wait Times Cont.
  13. 13. Data Analysis Predicting TSA Wait Times Event Processing with Machine Learning Models using Long short-term memory (LSTM) Recurrent Neural Network (RNN)
  14. 14. Application Airplane Turn Management / Task tracking
  15. 15. Application Wheelchair App
  16. 16. Application Future Potential Use cases § Context aware guidance/help § Ground Fleet Management § Aircraft activity tracking § Deicing equipment planning and resource management
  17. 17. Thank You suresh.subasinghe@united.com

×