The project aims to develop a reusable face mask filter using nanofiber technique to relieve the social and environmental burden caused by current one-time using face masks. The filter consists of electrospun nanofibers with much smaller diameters (e.g., nm level), which are much smaller than the commercial filter fibers (e.g., µm level). The developed nanofibrous filter has high air filtration efficiency without sacrificing the breathe comfortability, which can be attributed to its high porosity and improved physical structure. The filter design is also highly flexible to incorporated with other physicochemical methods for further improvement of the filter properties. An impressive feature of this invention is the reusability. Simple chemical washing can regenerate the exhausted filter for further reuse with maintained high air filtration performance.
Every day, millions of Hong Kongers use public transport to travel across the city. With the ongoing COVID-19 pandemic, public transport has the potential to spread the novel Coronavirus. This can be avoided if strict preventive measures are in place.
The solution to this is a non-intrusive, real time application that automates fever screening in public transport vehicles. This is made possible thanks to a mobile application that we are developing at HKU. We use a portable thermal camera and a mobile device to detect faces in a stream of thermal images, and then measure forehead temperatures. This can be done in real-time, and requires little to no manual intervention.
This project aimed at building an autonomous chess-playing machine that can play chess with a human player at home. It consisted of making a robotic arm, building arm controller apps, applying openCV on the mobile phone, and building an AI chess engine.
The working logic are described as four steps. First, the phone capture an image of the chessboard. Then, it recognizes the chessboard and location and color of the piece. Next, the chess engine determines the next move and sends the command to the robotic arm. Finally, the robotic arm helps to move the piece.
Since the gaming industry is becoming saturated, players tend to raise their requirements to the quality of gaming experience. Fusion of physical and virtual gaming experience may provide a fresh feeling to the players. In this project, a single-player Augmented Reality (AR) mobile game called Hexplore Fort is developed, where the players can control a spider-like robot – hexapod to adventure with the storyline in the game. Players can explore the fort that is augmented by AR by controlling the movement of hexapod, collecting items, fighting with enemies and buying assistance provided by the spy, in order to capture the princess.
The aim of this project was to detect phishing emails or URLs with a high accuracy. For the same, our deliverable was in the form of an improved email client that scrapes the last unread email from a user’s inbox and checks if it is safe or malicious. A series of Machine Learning algorithms were tried and experiments and research was conducted. From the results obtained, it was determined that a Balanced Random Forest algorithm after optimization in the form of algorithm tuning, training-testing split, feature analysis and other methods, was the most suitable choice for the project as it gave an accuracy of around 98% and after some experiments on optimization, it even reached a 100% accuracy.
Mental health issues, especially depression and loneliness, are becoming more common amongst young people. Fortunately, they are usually treatable without any medical help, and games might be the answer. Since people who suffer with these issues turn to video games, it can be considered as perfect medium to provide them with the remedy. Onslaught Arena is a web-based, online game that was modified to introduce multiplayer support and communication services to combat depression and loneliness. The game is backed by a NodeJS server that analyses user’s preference to provide them with the best possible gaming partner.
Our main objective for this project is to design a deep learning model to perform an efficient and accurate object classification and localization on assembly line so that further human-robot collaboration can be facilitated. We further formulate our task as a weakly supervised object localization problem. More specifically, the model will be training with image-level labeled data and output a predicted category and a bounding box for the object that worker is interacting with given one input image.
The development of Building Information Modelling (BIM) technology has reshaped our construction industry in many aspects throughout different stages in the project life cycle. Our team, BusIMan, has learnt more about the practical usages of BIM through this competition with our collaboration.
The designed complex is dedicated to the Digital Design & Construction Centre (DDCC). Our design comprises two buildings (South Wing and North Wing) linked by an arch bridge (“The Link”) with a podium underneath. This forms a shape of “CIC” when browsing on the plan view. An iconic bridge (“The Wave”) extends from the complex to the adjacent building, transforming the complex into a district icon. With aesthetic considerations and segmented zones for different facilities type, the complex aims at providing a desirable learning space and a professional working environment.
Automation technology has been highly adopted by different manufacturing industries in the past two decades. It shows an increasing investment in research and development throughout these two decades to replace labor in production lines. The leading dyeing and finishing machinery development company Fong’s National Engineering Co. Ltd. offered us a project in device designing to smooth their production line. The head of the raw fabric rolls is usually attached with an adhesive tape to prevent the head from falling out in the transportation process. This project aims to design and build a prototype of an Automatic fabric roll edge extractor with the concept of engineering design thinking. The function of the device is to automate the removal process of adhesive tape without any manpower involved.
Optical microscopy is now seamlessly integrated with many bioassay technologies for disease diagnosis. However, current techniques lack the throughput to image large and heterogeneous cell and tissue samples systematically. In addition, the vast majority of the methods overwhelmingly rely on biochemical markers such as stains and antibodies for enhancing image contrast, which are however not always be cost effective and efficient. To address these challenges, this project is to develop a spinning disk bioassay platform, which enables ultralarge-scale, label-free, high-resolution “on-the-fly” single-cell or whole-tissue-slide imaging at an imaging rate of 100-times faster than current assays. This high-throughput and high-content technology could open a new paradigm in data-driven bioassay applied in disease diagnostics, and biotechnology industries.