Computer Science

The demand for property is steadily rising with the significant market size of real estates across the world. Looking at the existing property searching applications, they only provide simple filtering functionalities about the properties, such as price, size, etc. However, in reality, users might have some complex requirements about the surroundings of their desired properties. To deal with this unsatisfied demand, we choose to facilitate an advanced query type – Spatial Pattern Matching (SPM), which is a new type of spatial group keyword query raised in recent research. Led by our supervisor, Dr. Reynold C. K. Cheng, its solutions have been well-discussed in theory. In our project, we want to fit these theories in this real-life scenario by resolving practical issues, as well as realizing some additional functionalities related to property searching. In the end, we have developed a standalone web-based application to demonstrate the importance and practicality of this newly proposed functionality.

This project investigates how mutual funds leverage credit derivative by studying their routine filings to the U.S. Securities and Exchange Commission. Credit derivatives are used to transfer credit risk related to an underlying entity from one party to another without transferring the actual underlying entity. Therefore, we developed both rule-based and NLP based methods to extract CDS information from thousands of files and aggregate into a dataset and further developed a one of its kind search engine to provide quick access to historic data

In our project, we implement neuro-evolution using NEAT and reinforcement learning using Sarsa(λ) on micromanagement scenarios in StarCraft II involving the small-scale precise control of combat units. Using our developed training framework for applying NEAT to StarCraft II, we evolved neuroevolutionary agents that learned to demonstrate precise hit-and-run strategies to beat the in-game AI in ranged vs melee matchups. Our reinforcement learning agents using Sarsa(λ) learned to be successful in more complex micromanagement scenarios involving enemy engagement selection and timing. Our results serve as a proof-of-concept of the benefits and potential of the applications of these techniques in video games and represent meaningful contributions to the wider video gaming and artificial intelligence communities.

Create a Massive Multiplayer Online Role-Playing Game (MMORPG) populated with computer mechanism related elements that can help players raise awareness on cyber-secure behaviors in their daily computer and smart device usage. There are two game modes available for demonstration, namely single player career and multiplayer arena. The former displays how the story background is set and links the logic flow between the player and the AR device that allows the player to visualize computer mechanisms and cyber behaviors into magical spells and abilities. The latter allows up to 20 players to practice these abilities in a simulated battle arena where the objective is to take down the enemy “server”, which can then disable enemies to respawn from their server data and obtain victory.

The application makes use of blockchain’s immutability and traceability to create a platform that can better protect copyright and fair use of media by providing secure storage and usage tracking. It aims to preserve the originality of the artwork by validating the proof of work during uploading.

Many students endured a difficult and time-consuming search for an empty chair, particularly during the examination period. Furthermore, hogging seats with personal belongings for a long time are some notorious acts that are very common in the libraries. With a view to tackle these issues, this project “Find A Seat App” aims at building an application that can detect the occupancies of the seats in HKU Main Library in real-time. Two approaches, i.e. using Computer Vision techniques and Internet of Things (IoT) device, are examined and discussed in the project.

Through the BazaAR iOS application, we propose a hybrid shopping experience enabled by Augmented Reality technology and Photogrammetry. A retailer enters the application and adds items for sale with various details including product description and cost. He/she uploads images of this product which are then converted into 3D models(using Photogrammetry) by the application. Once the customer starts the application, he browses through the list of products for sale and selects a product from the list after which the respective 3D models is pulled out from the database for interactive viewing in Augmented Reality.

Dumb ways to fail is a game which simulates a typical student experience, which one’s lack of attention to different aspects of a course (attendance, coursework, exam etc) could lead to failing a course. Within the game, players will go through a series of mini games, in which they will be given short instruction and react quickly to complete that game successfully. After players have played the game for several times, they will become better at the game and could achieve higher grade at the end of the game. Random bonus will be given to players to create extra excitement.

Lost Slime is a Multiplayer-Educational-Rhythm game that runs on your web browser, written in javascript with Node.js, Express.js and Socket.IO. It is designed to be lightweight and responsive to run on any PC.

Find Slimies new houses! Players compete to stack the tallest pillar to gain a high ground — which helps Slimies in spotting new locations for housing. To stack a pillar block, players time their space-bars along with the music beats. There are also phrases or sentences intertwined, that players have to input correctly before pressing space-bar. With these two objectives carried out, Slimies can then jump on the newly stacked pillar block!

What’s more, there are two additional single-player modes, where players strive for stacking the tallest pillar in High-score Mode, as well as surviving as long as possible, in Survival Mode, before the camera catches up!

We set out in making the game casually improve players’ typing proficiency. It could be cheerful-lighthearted, or mechanically intensive. We have designed an additional beat-mapper program to translate music pieces into custom track information used by the game, in json format. Which means players can create authentic mappings with their favorite music!

At Tenki, we hope to delivery accurate local weather data to Hong Kong citizens in minimal manner.

Tenki is a revolutionary weather app. Retrieving its data from Hong Kong Observatory, Tenki provides accurate local weather data to HK citizens. The redesigned minimalistic user interface provides a distinctive and holistic user experience. Users get to access their desired information at their fingertips.

Tenki updates weather information according to users’ location. Users can receive notifications in case of special weather conditions. They can also access to other information such as weather forecast and astronomic data.