SparkT – System for Analyzing Users’ Driving Behavior

  • project: SparkT
  • client: Sparkbit internal project
  • year: 2018
  • website: www.sparkt.ai

challenge:

Our goal was to create a telematics platform that evaluates users’ driving behavior. The system had to be modular and customizable so that it can be offered in different configurations to clients in various sectors. We wanted our system to provide the driver with feedback and tips on what can be improved.

tools used:

Backend platform:
Kotlin,
Kafka,
Cassandra,
Spring 5,
Redis,
Docker,
AWS EC2, ECS, RDS, S3


iOS: Swift


Android: Kotlin


Web dashboard:
TypeScript,
React
We wanted to create a modular and customizable system for individual driver's behavior analysis

solution:

Our system works based on different data sources such as smartphone sensors, BLE (Bluetooth low energy devices), OBD2.

This data, in turn, is enriched with the information from the 3rd party data sources such as weather conditions, traffic regulations, road infrastructure or type of settlement.

Based on collected data hazardous events are detected – our system identifies driver’s actions, such as speeding, harsh accelerations or following another car too closely that are a sign of bad driving habits.

This information allows us to build the driver’s profile and evaluate each driver in terms of safe and economical driving.

The collected data and results of the analysis are presented in the form of clear dashboards and reports.

impact:

We created a fully-featured, modular white-label platform that uses real-time sensor data from various devices to track and analyze driver behavior and measure vehicle performance.