Safe Drive Africa: PhD Research and Continuing Impact

Safe Drive Africa is a completed PhD research programme and continuing impact initiative focused on reducing unsafe driving in Nigeria through culturally grounded, AI-enabled mobile feedback. The work combines smartphone telematics, machine learning, natural language generation, and behaviour-change theory to create practical, low-cost interventions for road safety in low-resource environments.

The programme originated as doctoral research at the University of Aberdeen addressing a major gap in road safety technology: most telematics-based behaviour-change systems were designed for Western, high-income settings and did not transfer well to countries like Nigeria. The programme responded by designing an intervention grounded in Nigerian realities — including weak insurance-based telematics infrastructure, inconsistent internet connectivity, limited speed-limit data, local driving culture, and the importance of legal authority in persuasive communication.

The result was an AI-enabled, culturally attuned mobile system that detects unsafe driving behaviours, generates persuasive feedback grounded in Nigerian traffic law, and supports safer driving through legally grounded, supportive communication rather than financial incentives. A within-subjects evaluation with 54 drivers demonstrated statistically significant behavioural improvement: Unsafe Behaviours Per Kilometre (UBPK) decreased 19.4% (1.44 to 1.16 events/km, p < 0.001), with 79.6% of drivers improving.

What began as a doctoral project now forms the foundation for continuing work on institutional adoption, fleet deployment, and scalable road safety solutions for West Africa.

Road traffic crashes remain a severe public health challenge in low- and middle-income countries, and Nigeria faces particularly difficult conditions shaped by poor road infrastructure, inconsistent enforcement, risky driving habits, and digital limitations such as unreliable speed-limit mapping and intermittent connectivity. These realities make direct transfer of Western telematics solutions ineffective or incomplete.

Safe Drive Africa was built on the premise that road-safety interventions for Nigeria must be culturally and infrastructurally adapted. Instead of assuming mature insurance markets, continuous internet access, or Western persuasive norms, the project focused on offline-capable sensing, legal grounding in Nigerian traffic law, and persuasive feedback aligned with local conditions and behavioural realities.

The programme was guided by two central research questions:

RQ1: Does culturally attuned AI-enabled feedback without financial incentives reduce Unsafe Behaviours Per Kilometre (UBPK)?

RQ2: Do drivers who use the app more frequently show larger reductions in unsafe behaviour?

The programme combined survey research, mobile data collection, behavioural analytics, AI modelling, and mixed-methods evaluation.

Survey and Stakeholder Engagement: An early mixed-methods survey with 80 participants (51 drivers, 29 FRSC officials) established the local understanding of unsafe driving, highlighted major behavioural risks such as alcohol use, speeding, and aggressive manoeuvres, and informed the intervention design. Data were collected via paper and online forms under University of Aberdeen ethics approval.

Mobile Data Collection: A custom Android application captured accelerometer, gyroscope, and GPS data from smartphone sensors during real-world driving sessions in Nigeria. The app implemented configurable thresholds for detecting harsh braking (≤ −0.4 g), rapid acceleration (≥ 0.35 g), and swerving (lateral ≥ 0.35 g or yaw rate ≥ 25°/s).

Machine Learning — Alcohol Detection: A supervised ML model was trained on 152 labelled trips (24 alcohol-positive) using sensor-derived temporal and variability features, achieving an AUC of 0.855 for distinguishing alcohol-influenced from sober driving — without requiring breathalysers.

AI Feedback Generation: A dual-LLM architecture (GPT-4 and Gemini) produces two feedback types: event-triggered Tips with legal citations from the Nigerian Highway Code and National Road Traffic Regulations, and comprehensive weekly Reports with supportive, encouraging tone aligned with the Theory of Planned Behaviour.

Evaluation: A within-subjects design over six months compared pre-intervention (data collection only) versus intervention phases (Tips and Reports) with 54 drivers (27 commercial, 14 private, 13 company). Quantitative analysis used paired t-tests and Wilcoxon signed-rank tests; qualitative analysis of interviews followed Braun and Clarke's inductive thematic analysis.

Safe Drive Africa evolved into an end-to-end mobile intervention system combining smartphone-based data capture, unsafe behaviour detection, machine-learning-based alcohol impairment modelling, and AI-generated feedback. The system comprises eight components: application interface, core utilities and offline database, GPS and inertial sensor capture, user profile management, AI-based text generation, on-device alcohol detection model, driving behaviour analytics, and in-app questionnaires for self-reported alcohol use.

A key innovation was the dual-feedback structure: event-triggered Tips and weekly Reports. Tips provide concise, legally grounded reflections on specific unsafe manoeuvres, each explicitly citing Nigerian traffic laws with specific fines and penalties (e.g., 'Dangerous driving: ₦50,000 fine or 2 years imprisonment, Regulation 167(1)'). Reports deliver 150–180 word performance summaries generated through a two-step reflection process using GPT-4-turbo (draft) and GPT-4o-mini (refinement).

The architecture emphasised real-world deployment under low-resource conditions with offline-first data persistence and in-app feedback delivery to avoid SMS costs.

System differentiators from Western apps: 1. Legal grounding in Nigerian law rather than generic safety tips 2. ML-based alcohol detection without invasive testing (AUC 0.855) 3. Pure persuasive feedback without financial incentives, grounded in Theory of Planned Behaviour 4. Dual LLM architecture (GPT-4 + Gemini) for cultural resonance

The intervention produced a statistically significant reduction in unsafe driving behaviour.

Overall Reduction: Driver-level mean UBPK decreased from 1.44 to 1.16 events per kilometre — a 19.4% reduction (p < 0.001, Cohen's d = 0.660, medium effect size). 43 out of 54 drivers (79.6%) improved.

By Behaviour Type: Rapid acceleration showed the largest reduction (32.5%, p < 0.001). Swerving decreased significantly (19.8%, p = 0.002). Harsh braking showed a smaller, non-significant change (10.2%, p = 0.166) — likely because braking often represents unavoidable emergency responses to external hazards rather than conscious driving aggression.

Engagement Pattern: Higher app usage did not systematically predict larger gains (Pearson r = −0.071), though least-engaged drivers rarely improved substantially. Moderate engagement (6–8 trips) showed the highest proportion of improvers (91.7%).

Why It Worked: Qualitative interviews revealed three key mechanisms: 1. Legal grounding enhanced credibility — drivers found law citations authoritative and consequential 2. Supportive tone increased acceptability — non-judgemental feedback motivated rather than alienated 3. Tips and Reports served complementary roles — immediate correction plus weekly reflection

The programme's effectiveness came from combining behavioural theory with local adaptation. The system used legal references from Nigerian road traffic regulations to strengthen credibility and deterrence, while maintaining a supportive, non-judgemental tone that kept drivers engaged rather than alienated.

Legal grounding enhanced credibility: Explicit references to Nigerian laws, fines, and penalties made feedback authoritative and consequential. As one driver emphasized: 'The fines that are attached to it! It makes you sit up. You know that this is not a joke.'

Supportive tone increased acceptability: The non-judgemental, encouraging tone made feedback motivating rather than alienating. Drivers praised: 'The tone of the report is very encouraging. It's not judging... it's not trying to condemn you, rather it's telling you how you can improve.'

Complementary roles of Tips and Reports: Drivers valued both feedback types for different purposes. Tips provided immediate, actionable corrections; Reports enabled weekly reflection.

The project demonstrated that effective digital road-safety support in Nigeria does not need to depend on insurance incentives or always-on connectivity. Instead, context-aware, offline-first, culturally grounded design can produce meaningful change.

The programme produced several software tools and datasets:

The programme has produced peer-reviewed publications, preprints, conference papers, presentations, working software, and datasets contributing to road safety, smartphone telematics, machine learning, and natural language generation.

Welcome to the Safe Drive Africa research team! Our dedicated team is composed of accomplished researchers, academics, and professionals who are passionate about leveraging technology to promote safe driving behaviours and enhance road safety in Nigeria and beyond. Get to know our team members and their invaluable contributions to this innovative research project.

Ethics and Privacy: Ethics and participant privacy were central to the programme from the beginning. Ethical approval was granted by the University of Aberdeen Physical Sciences and Engineering Ethics Board. All participants provided informed consent, data were anonymised for analysis, and drivers received £30 compensation. The system was designed with privacy-aware handling of behavioural data throughout.

Funding: The programme was supported by the Tertiary Education Trust Fund (TETFund) — a distinguished organisation established by the Nigerian government to drive the advancement of higher education, research, and development. TETFund's generous funding empowered the programme to pioneer innovative approaches for tackling road safety in Nigeria.

Additional support came through the University of Aberdeen's research infrastructure and, post-PhD, through IEAF (Impact, Engagement and Agile Funding) for commercialisation exploration activities.

Safe Drive Africa is no longer just a doctoral project. It now stands as the research foundation for a continuing programme of work on AI-enabled, low-cost road-safety interventions for Nigeria and comparable contexts.

The completed PhD established the conceptual, technical, and evaluative foundation. It demonstrated that culturally adapted persuasive technology can achieve meaningful behaviour change in developing countries without reliance on financial incentives or insurance infrastructure. It showed that ML-based alcohol detection from smartphone sensors can operate effectively in real-world LMIC contexts where breathalyser testing is impractical. And it provided a template for adapting Western telematics interventions to non-Western LMIC contexts through explicit local legal grounding and cultural alignment.

The next stage is about extending reach, adoption, partnerships, and real-world implementation. Future directions include ethical RCTs, broader deployment across African regions, adaptive/personalised feedback, integration of speed-limit data as it matures, partnerships with fleets and insurers, and cost-effectiveness analyses for policymakers.

This makes the programme section an important bridge within the personal website: it connects completed doctoral scholarship to ongoing work in applied AI, telematics, persuasive feedback, institutional engagement, and safer mobility in West Africa.