Dr. Mingyue Cui is a pioneering computer scientist whose multidisciplinary work bridges intelligent vehicles, biomedical computing, and real-time embedded systems. He earned his Ph.D. in Computer Science and Engineering from Sun Yat-sen University, with research affiliations at the Technical University of Munich. His scholarly journey reflects deep engagement in applied AI, autonomous driving, edge computing, and sensor data processing. Dr. Cui has authored over 20 high-impact papers in IEEE and AAAI venues and holds several national patents in autonomous systems and LiDAR compression. His innovation has been recognized through prestigious awards, including top honors in robotics and AI design competitions in China. Dr. Cui continues to advance research in scalable, low-cost AI for smart healthcare and mobility, driving collaborations across academia and industry.
Profiles
Google Scholar
Scopus
🎓 Education
Mingyue Cui holds a Ph.D. in Computer Science and Engineering from Sun Yat-sen University (2018–2022), with research conducted in partnership with the Technical University of Munich. His doctoral work, supervised by Prof. Kai Huang, focused on intelligent connected vehicles, emphasizing autonomous driving systems and biomedical signal processing. Prior to this, he completed a Master’s degree in Software Engineering (2015–2017) from the same university, authoring a thesis on real-time scene flow for embedded systems. His Bachelor’s degree in Software Engineering (2010–2014) was obtained from Chongqing Normal University, where he specialized in embedded software engineering. His academic training spans advanced topics like optimization theory, computational complexity, machine learning, and embedded systems.
🧪 Experience
Dr. Mingyue Cui has built a robust research profile with a focus on real-world applications of AI and embedded systems. His Ph.D. thesis explored intelligent connected vehicles, targeting the challenges of real-time computation and network reliability in autonomous driving. He led pioneering efforts in algorithm parallelization, edge computing for autonomous services, and quality of service assurance using low-cost embedded platforms. His current research has expanded to biomedical domains, particularly ECG signal processing and cardiovascular disease diagnostics. With over 20 academic publications and patents, Cui collaborates extensively with Prof. Kai Huang and research groups at both Sun Yat-sen University and the Technical University of Munich. In addition to his academic output, he actively contributes to competitive research through international robotics and AI competitions, where he has earned multiple first and second-place awards.
🏆 Awards and Honors
Dr. Mingyue Cui’s research excellence is widely recognized through multiple awards. In 2023, he received a Bronze Award at the China College Students’ ‘Internet+’ Innovation Competition. He also secured the First Prize at the CCF Mobile Robot Challenge with a $10,000 grant, and a Second Prize in the International Running Intelligent Robot Competition. Earlier, he won the First Prize in the same international robotics event in 2019. In 2021, he earned the Second Prize in the World 5G Conference Application Design Competition. These accolades highlight his ability to translate complex theoretical work into high-impact innovations, especially in robotics, autonomous systems, and AI-powered design.
🔍 Research Focus
Dr. Mingyue Cui’s research integrates real-time embedded systems, AI-driven autonomous vehicles, biomedical signal processing, and point cloud compression. His Ph.D. centered on Intelligent Connected Vehicles (ICV), where he developed methods for optimizing service offloading and computing efficiency while maintaining Quality of Service under network fluctuations. His recent research includes developing hybrid CNN-Transformer models for ECG denoising, distributed AI processors for seizure detection, and octree-based transformers for LiDAR compression. With applications spanning autonomous mobility to wearable health diagnostics, Cui’s work emphasizes scalable, cost-effective, and intelligent system architectures. He is also deeply involved in collaborative SLAM for multi-vehicle networks and cross-modal sensor fusion, pushing the boundaries of edge computing in real-time robotics and healthcare contexts.
📄 Publication Top Notes
1. Dense Depth-Map Estimation Based on Fusion of Event Camera and Sparse LiDAR
Cui et al., IEEE Transactions on Instrumentation and Measurement, 2022
This paper presents a novel method combining sparse LiDAR data with asynchronous event camera signals to estimate dense depth maps efficiently. The fusion approach leverages temporal resolution from event cameras and spatial accuracy from LiDAR to improve performance in dynamic environments.
2. Offloading Autonomous Driving Services via Edge Computing
Cui et al., IEEE Internet of Things Journal, 2020
A seminal work on optimizing the offloading of AI services in autonomous driving. It explores real-time system performance under various load conditions and proposes an adaptive framework to ensure service continuity with minimal latency.
3. OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression
Cui et al., AAAI Conference on Artificial Intelligence, 2023
Proposes OctFormer, an efficient transformer architecture for compressing point cloud data using octree structures. It achieves local detail preservation with high compression ratios, enabling faster data transmission in autonomous systems.
4. OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression
Cui et al., AAAI 2023
This paper introduces OctFormer, a novel transformer-based framework that leverages the octree structure for efficient point cloud compression. It enhances local feature extraction while achieving significant compression gains, facilitating faster 3D data transfer in autonomous systems.
5. ECG Signal Denoising Based on Hybrid CNN-Transformer Network
Cui et al., Journal of Healthcare Engineering, 2023
This study proposes a deep hybrid model combining Convolutional Neural Networks (CNNs) and Transformers to denoise ECG signals. The model effectively suppresses motion artifacts and improves diagnostic signal quality, contributing to wearable and mobile health solutions.
6. Distributed Lightweight AI Processor for Real-Time Epileptic Seizure Detection
Cui et al., Biomedical Signal Processing and Control, 2022
Presents a low-latency, power-efficient edge processor design for seizure detection using EEG signals. The AI model is optimized for resource-constrained devices, enabling early and accurate detection in remote or wearable healthcare settings.
7. Cooperative SLAM for Multi-Vehicle Systems Based on Dynamic Bayesian Optimization
Cui et al., IEEE Access, 2021
This paper addresses collaborative simultaneous localization and mapping (SLAM) for autonomous vehicles. It proposes a Bayesian optimization strategy to dynamically adjust SLAM parameters across a vehicle fleet, enhancing map accuracy and robustness in changing environments.
8. Quality of Service-Oriented Computation Offloading for Autonomous Driving Applications
Cui et al., Sensors, 2020
Focuses on computation offloading strategies that prioritize QoS in vehicle-to-edge communication. It balances task latency and network reliability to ensure real-time performance for self-driving applications, even under fluctuating network conditions.
9. Real-Time Scene Flow Estimation for Stereo Vision Using Embedded GPU Platforms
Cui et al., International Conference on Embedded Systems and Applications, 2019
Develops a lightweight algorithm for estimating scene flow from stereo images, optimized for embedded GPU platforms. The approach supports real-time performance, enabling practical deployment in mobile robots and AR/VR applications.
10. LiDAR-Assisted Pedestrian Detection Based on Multi-Sensor Fusion with Deep Learning
Cui et al., Proceedings of the Chinese Conference on Intelligent Transportation, 2021
Integrates LiDAR data with camera input using a deep fusion network to enhance pedestrian detection accuracy in autonomous vehicles. The fusion technique improves robustness in low-light or occluded conditions.
Conclusion
Dr. M. Cui is a highly accomplished and forward-thinking researcher with:
-
A clear impact in autonomous systems and intelligent robotics,
-
Strong innovation credentials (patents and real-world applications),
-
Recognized technical contributions through competitive awards, and
-
A trajectory that continues to expand into biomedical applications.
He is highly suitable for a Best Researcher Award, especially in fields related to smart mobility, embedded systems, and AI-powered healthcare technologies.