Technology
We offer a fully autonomous mobile application (agentic AI) that can predict and prevent road traffic accidents caused by tiredness and inattention (achieving research-proven 94% effectiveness within just 3 months of contact with a given individual). Our technology is also used for presymptomatic medical diagnostics (e.g., Parkinson’s disease, diabetes, arthritis) on the basis of subtle driving anomalies.
SUMMARY
Fundamental Neuroscience
Two-year scientific research (including the foundational model training workflow) with novel findings about human cognition — combining theoretical analysis, VR simulations, real-world testing and neuroscience-related experiments
Mathematical Ground Truth
One of the largest proprietary datasets of digital biomarkers (focused on attention stability and high-dimensional health phenotypes)
Technological Engine
Proprietary ML models (custom LSTMs with a tailored attention mechanism that operate within a reinforcement learning framework) and a diagnostic-grade training workflow — combining non-invasive functional neuroimaging (e.g., EEG, fNIRS) with subconscious behavioural patterns observed while driving a vehicle (derived from direction micro-corrections, acceleration changes, response delays, chosen driving trajectories) and the user's initial cognitive state (related to health, sleep traits, lifestyle and environment in previous months)
Proprietary Signal Processing
Feature engineering and noise isolation designed to successfully separate relevant signals (related to the user's health phenotypes and digital biomarkers of cognitive states) from artefacts of different phenomena (e.g., unevenness of the road, weather, tire pressure difference, driver's movement, breathing, blood flow in human arteries) — optimized for older mobile devices
Edge Personalization
On-device individual cognitive decoder implemented as a static behavioural adapter (a compact set of algorithms tailored to the user's brain, requiring no local ML computing) and regularly actualized after data processing in the cloud
Custom Data Flywheel
Continuous evolution of the model thanks to raw, anonymized data from multiple users of the mobile application — aggregated in the cloud and utilized either to update the foundational architecture or to create its specialized variant adjusted to a given demographic group
Seamless Customer Journey
No action is required from the user beyond installing the fully autonomous mobile application that operates in the background (regardless of whether the phone is mounted on the dashboard or kept in a pocket) and, whenever necessary, [1] emits sound alerts designed to avert attention lapses at least three minutes before any discernible cognitive impairment, or [2] provides medical insights/diagnoses of chronic disorders up to 5 years before the onset of clinical symptoms
INTRODUCTION
TCR App Mobility offers a fully autonomous mobile application (agentic AI) that can predict and prevent road traffic accidents caused by tiredness and inattention (achieving research-proven 94% effectiveness within just 3 months of contact with a given individual). This process is made possible thanks to the non-invasive analysis of nearly a hundred biometric data streams, monitored exclusively by embedded sensors of a smartphone.
Our solution constantly examines the driver’s subconscious behavioural patterns observed both outside of the vehicle (related to health, sleep traits, lifestyle, environment) and during a journey (derived from direction fluctuations, accelerations changes, response delays, chosen driving trajectories). It emits sound alerts whenever a dangerous data pattern is detected — averting the natural lapse in attention at least three minutes before any discernible cognitive impairment. It ensures sustained awareness throughout the entire journey.
Our ML models are rooted in two-year scientific research with novel findings about human cognition. Leveraging this expertise, we have built one of the largest datasets of digital biomarkers (focused on attention stability and high-dimensional health phenotypes) — combining non-invasive functional neuroimaging (e.g., EEG, fNIRS) with subtle driving micro-corrections. Our VR-based training workflow with diagnostic-grade feature engineering allowed us to correlate actual brain activity with physiological signals and behavioural anomalies manifested while driving a vehicle. We utilize our proprietary deep neural networks (custom LSTMs with a tailored attention mechanism that operate within a reinforcement learning framework) to translate collected data into personalized mathematical representations of the user’s cognitive states. These models are subsequently employed to determine how the user’s driving patterns are impacted by approaching attention lapses.
Moreover, our algorithms are able to identify subtle changes in driving habits that are characteristic of prevalent medical disorders (e.g., Parkinson’s disease, dementia, diabetes, arthritis) years before the onset of clinical symptoms (allowing the early start of disease-modifying therapies).
COMPETITION AND USP
The vast majority of the population is not protected in any systematic way against tiredness and inattention while driving. Our indirect competitors primarily include the vehicle-embedded safety systems (developed by car manufacturers), which utilize eye and lane-tracking cameras to detect excessive tiredness once it has already begun (without any real predictive abilities). These systems can also be acquired independently as either a device or a mobile application. In terms of medical diagnostics, similar methodologies are limited to theoretical literature — and were explored solely regarding neurocognitive diseases.
In contrast, our technology:
[1] is based on science-backed custom deep learning models that are kept as trade secrets (allowing 94% effectiveness in prediction of road traffic accidents caused by inattention and guaranteeing the data moat needed to deter future market entrants);
[2] can automatically describe the user’s individual brain activity while driving a vehicle (correlating non-invasive functional neuroimaging and standard smartphone sensors);
[3] translates complex neurophysiological impairments (e.g., early Parkinson’s) into measurable driving micro-corrections, embedding a clinical-grade tool in a consumer-grade device;
[4] is implemented as a fully autonomous mobile application (agentic AI) with a proprietary data flywheel and a unique multi-modal dataset of digital biomarkers.