Second Exhibition – Digitization

This is a large-scale simulation platform for managing and controlling Hong Kong taxis. The simulator platform can be used to simulate the movements and trajectories of taxis for idle cruising, picking up passengers, and delivering passengers on a large-scale transportation network. The simulation platform is calibrated by a real dataset of Hong Kong taxis to ensure that the simulation well approximates the reality. This simulator is jointly developed by the teams of Dr. Jintao Ke at HKU and Prof. Hai Yang at HKUST. The simulation platform will be open for public use in the near future.

Garment industry needs to embrace flexible automation and robotics to lower cost and to enhance human productivity. As it is too complex to achieve full automation in garment production, collaborative works between robots and humans will be foreseen. The project demonstrates the feasibility of deploying multi-robots by combining computer vision and robotic technologies.

Undergraduate medical education has been severely affected by the COVID-19 outbreak. While lectures can be easily conducted online via Zoom, clinical bedside teachings, including training of history taking skills from patients, cannot be easily replaced. A novel chatbot mobile app for training of undergraduate medical students’ clinical history taking skills was developed.

Hong Kong is a mega city and is developed on the mountains and hillside slopes and nearby the sea. Hence, slope engineering is very important to Hong Kong sustainability and development against landslide hazards in Hong Kong. The University of Hong Kong has developed a system called Drilling Process Monitoring (DPM) technique.

Optical Coherence Tomography is a spectrum-encoded, cross-sectional, and non-invasive imaging device. The future OCT would be able to image thicker samples more efficiently. Our novel and compact fiber laser has the potential to be used as a dual-comb source for more advanced imaging device.

Compared to current wearable devices that can only measure vital signals, PERfECT is able to detect molecular indicators in the body fluid for disease screening and monitoring. “HKU PERfECT” is the first wearable platform that can simultaneously address three challenges: 1. highly sensitive, 2. smallest and lightest and 3. energy efficient.

Digital twins virtually represent an object and accurately replicate its performance in reality with low cost. Digital design framework generally consists of three parts, i.e., modelling, optimization and manufacturing. By adjustment of microstructures, the performance of products can be maneuvered to achieve various optimization targets.

The Law and Technology Centre, co-directed by Professor Kao, aims to advance research and provide public service in the interdisciplinary area of information technology and law. The current research focuses on the integration of artificial intelligence (AI) into legal research and practice.

MindPipe, the first 4D parallel training system for large DNN models, has the following objectives:
1. Greatly reducing load imbalance in GPU pipeline parallel stages; 2. Effectively resolving contention of the 3D parallel communication tasks; 3. Deterministically scheduling multiple subnets to be trained in supernet parallelism, a novel parallel dimension proposed by MindPipe; and 4. Automatic near-optimal 4D configuration of GPUs considering both DNN converging efficiency and GPU utilization.

The LiDAR Camera fusion captures 3D space in real-time, opening up the portal into the virtual world. The built model can be used in real scene games, virtual campus tour, metaverse, and more! However, existing products in the market are costly, and the working process is not only slow but also complicated.

The project is an integral part of a flagship research initiative being carried out under the auspices of the HKU Center for Water Technology and Policy. The Water Centre was jointly established by the Faculty of Engineering and the Faculty of Social Sciences to conduct cutting-edge research on water science, technology and policy issues that pertain to the broader urban sustainability agenda. We would like to acknowledge the contributions of the members of our inter-disciplinary project team. They come from the Department of Civil Engineering, Department of Electrical and Electronic Engineering, Department of Mechanical Engineering, Department of Politics and Public Administration and the Faculty of Social Sciences.

Computer vision enables machines to “see”. The capability of machine vision based on cameras, however, is fundamentally limited to a certain field-of-view with good lighting conditions – they cannot see through any occlusions or in the dark.
Wireless sensing opens a new sense for machine perception to decipher the physical world, even in absolute darkness and through walls and obstacles.
It can capture human activities invisibly in a contactless and sensorless way.