Trainease

What it does

Trainease was born a smart system that uses sensors and AI technology to monitor the occupancy of subway cars in real time and communicate this information to passengers.

Your inspiration

When I was a student, I used my city's subway every day to get to university. It was a routine that, while theoretically efficient, became a daily challenge. Every morning, I faced the same frustration: the cars I tried to board were always overcrowded, with people pushing their way in. However, over time, I started to notice a pattern. While many of us crammed into the central cars, the ones at the ends often had more space. Additionally, at certain stations, a large number of passengers would get off, leaving some cars less crowded than others.

How it works

Trainease operates through a combination of sensors, AI, and a mobile app or station screens. 1. Real-time data The system uses pressure sensors, AI-powered cameras, and train door system data to determine the number of passengers in each car. 2. AI-powered data processing The collected data is analyzed by an AI algorithm that identifies occupancy patterns in each train. The AI not only detects the number of passengers in each car but also predicts future occupancy based on schedules, stations, and historical trends. 3. User communication The processed information is displayed in real-time to passengers through: Screens on platforms, showing which train cars have lower occupancy. A mobile app, allowing users to see train occupancy distribution and plan where to board. 4. Optimization With this data, users can distribute themselves more efficiently along the platform, reducing overcrowding in specific train cars and improving boarding efficiency.

Design process

a) Identifying the Problem The idea originated from a personal experience: the difficulty of boarding the least crowded subway car. b) Field Research Observations were conducted at various stations and times to analyze passenger distribution in train cars. Data on train frequency, boarding time, and disembarkation patterns at key stations was collected. c) Analysis of Existing Solutions Current systems used in other metro networks, such as weight-based occupancy indicators or AI-powered cameras, were studied. This research highlighted an opportunity to develop a more accessible and adaptable solution for different transportation systems. 2. Ideation and Conceptualization a) System Definition A system based on sensors, artificial intelligence, and a user interface was designed to provide real-time information on train car occupancy. b) Initial Prototyping Sketches and flow diagrams were created to define the system’s functionality. Different data collection and visualization methods were explored to find the most efficient and feasible option. 3. Prototype Development a) Technological Implementation b) User Interface Development A graphical interface was designed to display train occupancy using: • Station screens. • Mobile application. • LED platform signage.

How it is different

Real-Time Occupancy Insights – Trainease provides live updates on passenger distribution within each train, helping commuters make informed boarding decisions instantly. AI-Driven Data Processing – The system leverages pressure sensors and AI-powered cameras to analyze passenger flow dynamically, ensuring accurate and continuous monitoring rather than relying on weight-based estimates or outdated crowd predictions. User-Centric Experience – Trainease integrates into multiple platforms, including station screens, mobile apps, and LED platform indicators, ensuring that all types of passengers—whether daily commuters or tourists—can access and interpret the information effortlessly. Cost-Effective and Easy to Implement – Unlike complex infrastructure overhauls, Trainease is designed for seamless integration into existing metro systems with minimal installation and maintenance costs. This makes it scalable and adaptable for different transit networks.

Future plans

1.-The prototype will be tested in a simulated station to evaluate the accuracy of the sensors and passenger response. Adjustments will be made to data processing and information presentation to improve usability. 2.-After the initial validation: Optimization of data update time. Enhancements in the accuracy of the occupancy recognition system. Adjustments to the user interface for greater clarity. 3 Following successful testing, plans were made for real-world metro system implementation and potential collaborations with transportation authorities. The system’s expansion to other urban transit networks is being explored.

Awards

.----------------------------------