Research

Publication

Poster: Digital Twin for Optimizing the Electric Bus Fleet Operations Under Network-Induced Uncertainty

A communication-aware digital twin for reliable electric-bus fleet scheduling and charging under incomplete telemetry.

Publication

Poster: Cloud-Based Passenger Safety Monitoring for Agentic Autonomous Public Transport

Cloud-based vision-language monitoring for detecting safety-critical incidents inside autonomous public transport.

Publication

MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

An agentic mediator that aligns driver needs, vehicle perception, safety rules, and explainable driving strategies.

Publication

An Agentic LLM Framework for Adverse Media Screening in AML Compliance

An agentic RAG framework that automates adverse-media screening for AML and KYC compliance.

Publication

Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance

An evaluation of LLM agents for cleaning noisy maintenance logs used in predictive-maintenance pipelines.

Publication

Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy

A framework distinguishing vehicle agency from autonomy and describing how both can co-develop for human-centered mobility.

Publication

A Risk-Based AML Framework: Finding Associates Through Ultimate Beneficial Owners

Aug 2024

Towards a Conversational LLM-Based Voice Assistant for Transportation Applications

KITT is an in-car assistant capable of verbally communicating with the driver, and by utilizing external APIs, it can answer questions related to routing, finding points of interest, and is …

Publication

Towards a Conversational LLM-Based Voice Assistant for Transportation Applications

Sep 2019

What is driver identification?

The prevalence of smartphones have changed our lives, perhaps mostly for better but in a few cases they have caused harm. Gig-economies only made possible thanks to smartphones, and …

Publication

Triplet Loss and its Applications to Driver Identification and Verification [WIP]

A major issue in driver identification is lack of enough data from the target group of drivers. In this work I use Triplet loss to train neural nets that learn to discriminate between small …

Publication

Driver Identification only using GPS trajectories: A Deep Learning Approach

This is one of my latest works in which I apply deep learning to problem of driver identification using GPS data collected from smartphone.