Recent research:
Across a comprehensive body of work focused on Transportation, Mobility, Vehicles & Emissions and the integration of Urban Digital Transformation, Smart Cities & Digital Twins, the researcher develops and applies data-driven, machine learning–driven approaches to understand and optimize urban mobility and transport systems. The work combines real-world driving data (RDE/PEMS), GPS-based sensing, OBD-II telemetry, and neural ensemble methods to model emissions (CO, CO2, NOx, HC), energy consumption, and driving styles across Cuenca and surrounding routes in Ecuador. Methodologies include fuzzy logic diagnostics, random forests, ANNs, decision trees, and K-means, paired with GIS and sensor instrumentation to estimate emission inventories, classify transport modes, predict state-of-charge and energy use in HEVs and EVs, and develop practical tools (datasets like EngineFaultDB) for diagnostics and planning. The research demonstrates that driving style (acceleration, speed, gear use), route characteristics (slopes, urban/rural mix), altitude, and vehicle type substantially influence emissions and energy efficiency. It also yields actionable insights for policy and planning (ecological driving benefits, electrified corridors, route redesign) and contributes open datasets and benchmark models to advance automotive diagnostics and emission modeling. The impact lies in delivering scalable, data-driven models for real-world emissions estimation, energy management, and urban transport planning, with close ties to Cuenca’s mobility context and high-altitude driving realities.

Key Topics:

• Transportation, Mobility, Vehicles & Emissions
• Artificial Intelligence, Machine Learning & Data Science
• Energy Storage, Batteries & Electric Mobility
• Sensors, Instrumentation & Measurement Systems
• Geospatial Analysis, Remote Sensing & GIS
• Environmental Monitoring, Remote Sensing & Conservation
• Urban Digital Transformation, Smart Cities & Digital Twins