Submitted by admin on Thu, 08/11/2022 - 08:20

Safety concerns at ATMs

Sequence Number 2 Industry Banking & Finance Banner Safety concerns at ATMs How 5G enabled

Smart ATMs running on 5G equipped with cameras and AI can provide added security with facial recognition and detect suspicious behaviour in the surroundings before taking the necessary actions (e.g., alerts, shutting off, etc.).

Data Flows
Title Devices Icon Devices Description
  • Cameras will gather high-definition images and video data
  • Other sensors collect data about the state of the ATM (e.g., lights, function, equipment, etc.)
Title Connectivity Icon Connectivity Description
  • All data collected available on edge
  • Event data about the status
Title Edge Compute Icon Edge Compute Description
  • With 5G, MV and ML applied to monitor status, environment, and internal components in real-time
  • AI will be required to run autonomously in critical situations 🡪 Call out the police as an example
Title Cloud Compute & Storage Icon Cloud Compute & Storage Description
  • All data is stored in enterprise data storage, where data ownership belongs to the company
Title Applications & Services Icon Applications & Services Description
  • Expectation that activities will take place primarily at the edge
Title Inform Decision Makers Icon Inform Decision Makers Description
  • Operations team will be informed in real-time in the case of abnormal situations
Title Support Decision Making Icon Support Decision Making Description
  • End of process
Application Logic
Description
  • Collect all necessary data to apply AI (ML & MV) to ATM operations to reduce technical issues/damage/ etc:
  • Cameras gather data of ATM surrounding and users
  • Other sensors gather data on ATM internal components
  • Historical data will be stored in Enterprise storage and used to improve AI models.
Description
  • MV will validate ATM surrounding, analysing normal versus abnormal behaviours using historical data.
  • MV can be applied for facial recognition to authenticate users and alert if necessary.
  • Personal data protection of customers will need to be considered and adhered to.
  • SMEs and data scientists will collaborate to develop models.
Description
  • Most of the AI work will be Edge based given the real-time nature.
  • All data is required to be stored in enterprise storage to improve AI model quality.
Expected benefits Key value created