AIoT-based Remote Monitoring System

Background:

Client is one of the largest Cash Logistics company in India, they are one of the top 5 in APAC. They enable commerce – connecting business, banks and people with money. They automate ATM and currency management in India. Their networks and support services ensure money is readily available across all states. They provide Cashiering services for top retail chains to picking up cash from thousands of merchants and banking it, they provide a range of services across each stage of the cash cycle in India from currency chests to ATMs to vaults to stores to wallets, to installing and managing Intelligent ATMs, Cash Deposit Machines and Recyclers; they are pioneer in helping change banking in India.

Challenges Faced:

Client wanted to build an end-to-end system to monitor the key activities in their managed ATMs across different location. Currently, client is leveraging 3rd party product and would like to build this as a home-grown product from the scratch. As part of this prototype, we are helping client to build a monitoring system based on Computer Vision for Helmet, Face cover, Loitering, Crowd Count, Camera Tempering They already have a hardware system (pi 4b based) identified for this purpose and this new application need to be integrated leveraging the same hardware.

There is need to create a training pipeline at the Cloud and optimize models to run at the EDGE device ( RPi 4b based)

Objectives:

• Build an IoT-based system for real-time equipment monitoring.
• Enable predictive maintenance through advanced analytics and alert mechanisms.
• Design a solution that is easily scalable and integrates seamlessly with the existing infrastructure.
• Leverage AWS cloud services to achieve cost efficiency, robust performance, and high scalability.

Solution Summary:

There are three major components a) Inference pipeline involving the edge device and the cloud, b) Training pipeline at the cloud and c) Device provisioning and management.

We developed an IoT-based remote monitoring system prototype that utilizes cloud and edge technologies for seamless integration and data processing. The key highlights of the solution include:

IoT Device Integration:

• Sensors were connected to machines to capture real-time operational data, such as temperature, pressure, and vibration.
• The system supported a diverse range of devices and communication protocols.

• Data streams from IoT devices were processed in real-time using AWS IoT Core, ensuring low latency.
• Collected data was stored and managed on AWS S3, enabling secure and scalable data storage.

• Predictive analytics models were deployed using AWS SageMaker, identifying potential failures before they occurred.
• Dashboards on Amazon QuickSight provided actionable insights and visualizations for key metrics.

• The system utilized AWS Lambda to trigger alerts and notifications based on predefined thresholds or anomalies detected in the equipment’s performance.

• The use of serverless services (e.g., Lambda, AWS IoT Core) ensured the solution could scale automatically based on demand without incurring unnecessary costs.

Tech Stack:

• Development : Python, Django, Angular

• AWS Services : Amazon API Gateway, AWS IoT Core, AWS SageMaker, AWS EC2, AWS Lambda, Deep Learning Models