FREE WORLDWIDE Shipping On £10+ Orders, Rated 4.6/5 stars (1,900+ reviews).

Menu
0

FREE WORLDWIDE Shipping On £10+ Orders, Rated 4.6/5 stars (1,900+ reviews).

0

Your Cart is Empty

Making Cycling Better

making cycling better

  • making cycling better
  • Main menu
    • Home  / See.Sense Case Studies
    Previous  / Next

    3 min read

    Overview

    The SPINOVATE project in Dublin shows how cities can use sensor-based AI insight data from connected bikes to identify safety risks, evaluate infrastructure, and prioritise investment.

    Funded by EIT Urban Mobility, SPINOVATE explores new business model opportunities for the cycling industry through connected e-bikes, AI-powered dashboards, and real-world mobility data. By bringing together partners including See.Sense, Dún Laoghaire–Rathdown County Council, Moby Bikes, and the University of Exeter, the project demonstrates how collaboration can unlock safer, smarter, and more sustainable mobility solutions.

    🏆 Winner – AI Impact Award (Digital Leaders)
    🏆 Winner – People’s Choice Award (Digital Leaders)

    The Challenge

    Cycling infrastructure decisions are typically based on:

    • collision data (delayed and incomplete)

    • fixed counters (limited coverage)

    • surveys (low frequency and subjective)

    This makes it difficult to identify risks early or measure whether changes are working.

    The Approach

    See.Sense deployed connected SUMMIT2 sensors fitted to shared Moby Bikes across Dublin, turning them into a network of mobile sensors.

    These capture real-world cycling behaviour, including:

    • braking and swerving events

    • route usage and demand

    • speed and dwell time

    • road surface conditions

    • rider-reported issues

    AI analysis converts this into clear, actionable insights — highlighting where cyclists are experiencing risk and how the network is performing.

    Co-Design with City Stakeholders

    A key part of the project was working closely with stakeholders through a structured innovation process led by the University of Exeter’s DIGIT Lab.

    • Workshops brought together local authorities, mobility providers and transport stakeholders

    • Sessions focused on identifying the most useful data outputs for decision-making

    • Multiple datasets were explored and combined (sensor data, perception data, GIS, etc.)

    • Outputs delivered via an operational dashboard used by city stakeholders

    This ensured the solution was aligned with real planning needs and ready for practical use.

    Prototype AI Dashboard (Now Being Rolled Out)

    As part of SPINOVATE, See.Sense developed a prototype dashboard that translates complex cycling data into clear, prioritised insights for transport planners.

    At its core is an AI-driven prioritisation engine that ranks locations based on urgency, using behavioural signals such as:

    • how many cyclists are affected

    • how severe the disruption is

    • how complex the hazard is

    • when and how frequently it occurs

    These insights are validated against real-world context, combining:

    • rider-reported issues from the See.Sense app

    • sentiment and theme analysis of user feedback

    • external datasets such as collision reports and roadworks

    This produces a confidence-weighted priority ranking, helping cities focus on the locations that matter most.

    The dashboard also segments journeys (e.g. commuter vs leisure), providing additional context on who is affected and when.

    The platform is now being prepared for rollout to additional city and mobility partners.

    Scale of Deployment

    • 59 connected bikes fitted to Moby Bikes (SPINOVATE deployment)

    • 36,000+ km of cycling activity

    • 300,000+ minutes of riding data

    Additional data was integrated from a parallel Dublin cycling dataset (Sandyford Pedal Pulse programme):

    • 110 connected bikes

    • 46,000+ km of cycling activity

    This combined dataset provided a richer, network-level view of cycling behaviour across Dublin.

    Key Results

    Safer junctions, proven with data
    A 40% reduction in braking and swerving events was measured following junction improvements in central Dublin.

    Early identification of risk
    25+ high-risk locations were identified using behavioural data — before collisions occurred.

    Clear prioritisation of investment
    Route analysis highlighted key commuter corridors (e.g. Malahide Road), helping target improvements where they matter most.

     

    Image:  AI-identified cycling risk hotspot in Dublin, based on patterns of braking and swerving behaviour from See.Sense connected bike data, validated against additional datasets

    What This Enables for Cities

    • Identify safety risks earlier using real cyclist behaviour

    • Prioritise interventions based on evidence, not assumptions

    • Evaluate infrastructure changes with before/after data

    • Understand real demand across the network

    Why It Matters

    Traditional transport data tells you where cyclists are.
    This approach shows how they experience the network.

    That shift enables cities to move from reactive planning to proactive safety management — improving outcomes while making better use of limited budgets.

    Outcome

    SPINOVATE demonstrates that connected cycling data can deliver:

    • measurable safety improvements

    • network-wide visibility

    • faster, evidence-based decision-making

    All through a scalable, cost-effective approach that can be deployed in any city.