VeDISCom Research
Vehicular, Distributed, Intelligent Systems and Computing
Vehicular, Distributed, Intelligent Systems and Computing
VeDISCom Research is a multidisciplinary research group dedicated to advancing intelligent, distributed, and data-driven computing and communication systems. Our research spans distributed computing, communication networks, intelligent systems, and machine learning, with a strong emphasis on scalable data analysis, privacy-preserving learning, and efficient data management across heterogeneous computing environments. A central focus of our work is data partitioning and data distribution in heterogeneous distributed systems. We investigate how data, computation, and learning tasks can be efficiently partitioned, allocated, and coordinated across diverse nodes including vehicles, edge, and fog platforms, cloud infrastructures, and general distributed systems while accounting for heterogeneity in compute capability, communication bandwidth, latency, energy constraints, and trust.
Machine learning forms a core pillar of our research, particularly federated learning, distributed learning, and large-scale data analytics. We study how learning models can be trained and deployed collaboratively through data- and model-partitioning strategies that enable scalable, adaptive, and privacy-aware intelligence without centralized data aggregation. Our work emphasizes the tight coupling between learning performance, data distribution policies, and system-level constraints.
While vehicular communication systems, including V2X, VANETs and smart mobility platforms represent an important application domain, our proposed frameworks are inherently transferable across diverse distributed computing environments. We develop algorithms and system architectures that jointly optimize data partitioning, learning accuracy, communication efficiency, and computational resource utilization, addressing challenges such as scalability, latency, reliability, and robustness in dynamic and large-scale systems.
Data analysis is fundamental to our methodology. We leverage real-world datasets, network traces, and sensor data to inform the design, training, and evaluation of intelligent models and distributed algorithms. Our research combines theoretical foundations, analytical modeling, simulation-based evaluation, and experimental implementation, bridging the gap between abstract theory and deployable real-world systems. Security, privacy, and trust are embedded throughout our research agenda. We explore secure data partitioning, robust and privacy-preserving federated learning, and trustworthy distributed architectures capable of operating under adversarial conditions and resource constraints. These efforts support the development of safe, dependable, and intelligent systems for next-generation applications.
VeDISCom Research provides a collaborative platform for students, researchers, and industry partners to pursue forward-looking research that advances connected systems, intelligent infrastructure, and data-centric distributed computing. Through interdisciplinary collaboration and innovation, we aim to deliver impactful solutions that shape the future of smart mobility, edge intelligence, and large-scale heterogeneous distributed systems.
Vehicular Ad Hoc Networks (VANETs) enable vehicles to communicate with each other and with roadside infrastructure to improve road safety, traffic efficiency, and intelligent transportation services. Our research focuses on building reliable, scalable, and secure communication systems for highly dynamic vehicular environments.
Vehicular mobility modeling studies vehicle movement patterns and traffic behavior under real-world road conditions. Accurate mobility models are essential for evaluating vehicular communication protocols, traffic control mechanisms, and intelligent transportation applications.
Vehicle-to-Everything (V2X) communication introduces challenges related to security, privacy, and trust due to open wireless channels and high mobility. Our research addresses secure communication, authentication, privacy preservation, and trust management for safe and reliable vehicular systems.
Distributed computing systems consist of multiple interconnected computing nodes that collaboratively process data and execute tasks. Our research investigates scalable, efficient, and reliable distributed architectures, particularly in mobility-aware and data-intensive environments.
Vehicular cloud computing extends traditional cloud services to vehicles by utilizing onboard computing resources, roadside infrastructure, and edge servers. This research focuses on task offloading, resource sharing, and service optimization for intelligent transportation applications.
Efficient data partitioning and distribution are critical for improving performance and scalability in distributed systems. Our work explores load balancing, data placement strategies, and communication-efficient techniques for large-scale distributed environments.
Artificial Intelligence (AI) and Machine Learning (ML) enable systems to learn from data and make intelligent decisions. Our research applies AI and ML techniques to vehicular networks, distributed systems, and edge computing environments.
This research focuses on improving the efficiency, accuracy, and scalability of machine learning and data analysis algorithms. Emphasis is placed on optimization techniques for training, inference, and resource-constrained systems.
Federated Learning enables collaborative model training across distributed devices without sharing raw data. Our work investigates privacy-preserving, secure, and communication-efficient federated learning frameworks for vehicular and distributed systems.
Multi-agent AI systems involve multiple intelligent agents that interact and collaborate to achieve common or individual goals. Our research focuses on agent coordination, learning strategies, and decision-making in dynamic environments such as vehicular networks and smart cities.
📅 Aug 1, 2024 - March 31, 2026
📅 June 1, 2025 - June 30, 2026
📅 November 1, 2025 - January. 31, 2027
Founder and Principal Investigator
Researcher
Researcher
Researcher
VeDISCom Research is pleased to announce an open call for interested students and researchers to join and collaborate in the areas of Vehicular Networks, Distributed Computing, and Machine Learning.
We are actively working on research topics related to intelligent transportation systems, vehicular and edge/cloud computing, distributed and federated learning, and scalable parallel processing techniques. This initiative aims to bring together individuals who are passionate about research, innovation, and collaborative problem-solving.
This opportunity is open to undergraduate and postgraduate students, as well as researchers, who are eager to contribute to ongoing and future research projects, participate in technical discussions, and co-author high-quality research publications.
Interested individuals are encouraged to express their interest by sending contacting us:
Include a brief introduction and your area(s) of interest. We look forward to collaborating with motivated individuals.
Page under construction:
We’re working on this page and it’ll be available soon. Thanks for your patience.
Department of Computer Science
Carolina University
420
South Broad Street
Winston-Salem, NC
27101
Email: danquahm@carolinau.edu
