杰出作品

Actka - Indoor Positioning & Smart Guidance

Actka is a System Integration project, and the project aims to develop a prototype solution of Indoor Positioning with Smart Guidance. In this project, we are going to demonstrate our project's final product with a robotic car, it is to present how our solution is flexible and can be used for different use cases, from using it as a attachable move base to conducting investigations in unknown indoor areas. It allows users to navigate in areas that cannot be seen easily.

The robotics car is expected to analyze the surrounding environment to a certain extent, and it should be able to make rational responses as the follow-up actions...

Youth Services Discord Chatbot

Hidden youth have stayed in their homes for a prolonged period of time, their social and communication skills deteriorate gradually over time. This has resulted in them being less confident, disconnected, and easily nervous in front of people. If the phenomenon is not tackled quickly, it will cause a detrimental impact on their mental health. To help alleviate the phenomenon, we have decided to cooperate with SJS and use Natural Language Processing - NLP to develop a Discord bot that can understand and communicate more humanely and less robotically; and a web application that helps administrators in 6PM to facilitate their events and group conversation record...

Green Star - Multi-object Detection Technology For Waste Classification And Detection

there is a need for us to develop an application that can assist users in sorting a wide mix of recyclable garbage and give users a greater sense of involvement. The application we will develop is called Green Star (it may be developed as an application letter). Four waste categories can be detected in Green Star, which is plastic, paper, metal, and other. Green Star can implement multi-target real-time detection and user-autonomous uploading of waste images and categories. Since the database of the model can be continuously updated based on the images uploaded by users, the accuracy of the model will be continuously improved. In addition, Green Star aims to provide multiple models that users can freely choose to use in different scenarios...

Sign Language Detection and Recognition

This report aims to solve the problem of real-time recognition of sign language for deaf people by developing a Web Application with Deep Learning and Image Processing techniques.

Furthermore, the developed deep learning model and deploy on the website to provide an easier and faster tool for the hearing impaired individuals to communicate with normal people ...

CanChat - Cantonese Empathetic Chatbot for Secondary School Student Counseling

The aim of this project is to create an online chatbot application that can support student counseling services in secondary schools. The chatbot will interact with students prior to direct interaction with school counselors, enabling counselors to save time and focus on more critical issues. The chatbot will provide basic counseling services and valuable information on academic issues and family issues through a person-to-computer personal chat service on social media platforms such as WhatsApp, Telegram, and Discord.

Additionally, it will allow students to express their mood and receive guidance when they are feeling down. In case a student expresses serious psychological issues, an alert will be sent to a social worker for personal  consultation...

Automating First-screening Interview: Conversation with Chatbot and Report Generation

The aim of this project is to achieve interview automation through developing a mobile application coupled with an interview chatbot for HR interviewing first-round interview in a time-efficient and less-resourced approach
To achieve the aim, the project has defined a number of sub-objectives as follow:
Collect text data from the internet that contains a wide variety of question-and-answer patterns and information of related topics for the decision of follow-up questions that is selected by machine learning model.
Research an NLP tool to extract information from the users' speech and resume (PDF) for generating potential questions to be asked in interview...

VR Stroke Rehabilitation Trainer

Based on the present research, existing virtual reality games do not fulfill some of the main core requirements of upper limb training in rehabilitation exercises. For example, the game approach only supports training the motion of pinching or grasping (Sulimanov & Olano, 2019). However, other training activities, such as hand strength training and hand extension training, are not covered in the game. Thus, the game is not able to provide rehabilitation exercises that are covered in training hand motion, extension, and strength.
On the other hand, virtual reality-based stroke rehabilitation games are one of the choices for physiotherapists to attract patients who are feeling bored during rehabilitation treatments...

Yu-Gi-Oh MR assistance system

This project aims to enhance the game experience of 'Yu-Gi-Oh!TCG' with the use of real-time coexistence and interaction in the mixed reality system.
The reason our team wants to do this project is to solve the problem of not being newbie friendly. Yu-Gi-Oh trading card game was launched in 1999, there are over a thousand cards for players, newbie can't know all of the card effect in game, they need to learn a lot from other ways such as internet to learn what are them, therefore newbie can't quickly enjoy the card game. Using our mixed reality system can help new players to enjoy the card game immediately. We decided to create and provide a database with different card information and cooperate with the UI to give some support to players in card battle, also provide important information support in UI such as life point and game phase, let them easily understand the basics and enjoy the game...

Washroom Easy

This project aims at developing an application which can formulate the real-time utilization rate of various washrooms in a shopping mall. After the system analysis which includes considering the potential users' genders and their current floors, the application will suggest the best choice of washroom for them.
The project also helps the management of the shopping malls to relieve the pressure on the usage of some specific washrooms. In a large shopping mall, different levels may have different visitor density. For example, the floor which connects to the MTR station will usually have the highest crowd and the washrooms on that floor will be more crowded than the others. The project can assist to ease the flow of visitors by suggesting them to use the washrooms on the other levels...

Using Event Camera to Detect, Track, and Classify the Human Body

Our project aims to apply the event camera as an all-day stationary surveillance camera to collect continuous event data to train deep learning models to detect accidents and medical emergencies for single-living elderly in low lighting environments.
The objectives of this project are:
Research methods on how to train a model using data outputted by the event camera
Collect event data from the event camera
Use the raw data outputted by the event camera to train a model to detect, track, and classify actions done by humans
Convert the raw data outputted by the event camera, convert this data to frame-based data, and use the resulting data to train a model to detect, track, and classify actions done by humans...

Graph Embeddings for Predicting Traffic Accident Black Spots

The aim of the project is to use observational data to build a deep machine learning model to model the relation between the accident proneness and road network structure design, road installations, and road local properties. In conclusion, this model provides a basis for improving the conditions of traffic facilities and enhancing traffic safety.
1. Collect the accident and road infrastructure data It is of the utmost importance to collect related data as the machine learning model needs to learn the function from data. Our model is to comprehend the connection between traffic accidents and road network design, so obtaining accident data as well as the road structure data is the foundation of the whole model. Therefore, collecting and organizing the data on traffic accidents in the Transport Department and News Feed like RTHK, and the data of road network data in OpenStreetMap are needed. 2. Develop and evaluate the feature set that defines road infrastructure design...

Make HTML learning smarter for Student and Teacher

This project aims to develop a mobile application that makes learning HTML more efficient for secondary school students and more manageable by their teachers. Interaction is an effective way for beginners to pick up new knowledge. Therefore, a comment section is needed for students to have discussions. It will enhance the interactions between students, and they could ask questions through the application and teachers could give a brief response. This will further enhance the teaching effectiveness as online and face-to-face classes are integrated together. The flexibility of mobile learning allows students to decide their learning paths. The school teaching plan does not restrict learning pace, and students can choose the more interesting HTML topics to study first. The application will track student progress, if a student falls behind, it will send a notification to tell them to speed up and to catch the progress. Therefore, the new way of learning increases the motivation and flexibility of students to study HTML. An interface is set up to help teachers to ...

EYEDENTIFY(便認): A mobile application for improving the self-esteem of dementia patients in their social life with machine learning

This project aims to develop a mobile application which targets users who are early-stage dementia patients. This application is focusing on their social life. Their self-esteem would be built up through the application. Not only the patients' self-esteem would be benefited, but also the relationship among people around them can be enhanced. Design the user interface of the mobile application Develop the functionalities of the mobile application, it includes
Develop a facial recognition function which can display database results Develop an object recognition function which can display pictures stored in the database Develop a location sharing with GPS that will emit GPS signals to the caretaker Develop a memoir that can display photographs with each person in the database individually...

Caring Low Vision Patients: A Mobile Application to Assisting the Use of Over the Counter Medicines for Low Vision People

The project aim of this project is to develop a mobile application with a medication recognition and information system and reminding system in order to assist people with low vision to take and purchase the over the counter medicine correctly.
A. Medication Recognition and Information System: The medication information system is to classify the medicine package through the Android mobile phone's camera. After the user capture the image through the application, the image will be sent to the server for recognition and retrieve the medication information from the database. The obtained information will be sent back to the user's application. After that, the system will provide the organized medicine information to the user including drug name, dosage, efficacy, caution etc...

Improving Emotional Management of Primary Students using VR Experience

The aim of the project is to help some primary students who may have poor emotional management by using the Virtual Reality System to simulate some emotional occasions and analyze their reaction and response in the test section.
Help poor emotional management students: Approach: provide a VR platform for those students to practice their emotional management and analyze their performance
Simulate Emotional Occasions: Approach: provide different scenarios in school life and home and street. Setting the conflict will get bigger or more complex depending on the game level.
Test section: Approach: provide the multiple choice of different ways to solve the conflict in the simulation...

VR Driving School

The project aim of this project is to develop a software to provide tutorials to users who wish to learn driving and enhance their sense of safety during driving. Also to replace or reduce the pressure of insufficient amount of driving teachers under the influence of COVID-19 and shortage of driving teachers.
Here we have revised objectives for the project. Especially for the third objective, the reasons for changing it as we have a more detailed rules on judging users' behaviors. After a team discussion, we decided to use a rule-based system to verify users' behaviors. Provide Eye-tracking function: To use a VR headset with an eye-tracking function for tracking eyeball movement.
Record the movement of the eyeball: Setting our one of primary objectives will be recording eyeballs activities for data collections...

Visually Impaired Assistant with Neural Network and Image Recognition

The aim of this project is to implement a visually impaired assistant with neural network and image recognition to help visually impaired go outside efficiently and safely. The visually impaired assistant will be similar to a person to accompany the user, using the image recognition technology to describe the nearby environment to the visually impaired in real- time, letting them know what is going on in front of them. The obstacle detector will let them know the obstacles ahead so that they can be prepared early.
To allow visually impaired people to go to their destinations, navigation is also a must, and there are several apps on the Internet providing the navigation function, but the system will make the navigation system more useful to assist the visually impaired to go to the destination...

AI-Powered Question Generator

The aim of this project is to develop a system that can automatically generate questions from text using AI technology. This system can generate wh questions and grammar questions, and it is mainly designed for educational purposes. For example, helping teachers to generate quiz or assignment questions for their students and helping parents to generate practice questions for their children. It can also be used to generate questions for building a reading comprehension dataset, this kind of dataset is widely used in the studies of Natural Language Processing (NLP).
The proposed automated question generation system's objectives are fourfold: Develop a subsystem that can generate wh-questions, Develop a subsystem that can generate grammar questions, Integrate the subsystems into a web backend and Build an easy to use web user interface...

An Investigation of Multi-Objective Particle Swarm Optimization Algorithm for Better Performance and Its Application to Signalized Traffic Problem

There are many different kinds of evolutionary algorithms to solve multi-objective problems, and multi-objective particle swarm optimization is one of the famous heuristic searching techniques. Although some optimization problems can reduce to a single-objective optimization by dimensionality reduction, most optimization problems are difficult to convert into a single-objective, and the demands of MOPs increased.
In this project, we are going to study and improve the state-of-the-art MOPSO algorithms. The proposed algorithm was based on the competitive mechanism MOPSO that guides the particles by the current population. We aim to achieve better performance that balances between exploration and exploitation of the whole swarm, avoid premature convergence, and maintain...

A Chinese Character Training Mobile Application for Dyslexia Children through Machine Learning and Augmented Reality

The aim of this project is to encourage dyslexia children to learn chinese characters in a self-directed way through gamification of training exercise and machine learning.
The main objective of the project is to develop a mobile application that can analyze the dyslexia children's performance when they are using the application and provide a suitable response. The project has also defined a number of sub-objectives as follows: Design the functionalities of the mobile application, Design the user interface of the mobile application, Design the content of the AR game, Train the machine learning model to improve the precision, recall and accuracy of the response...

Dr. Cell : An immersive, Controller-Free VR Game for Promoting Health Awareness from The Perspective of Human Body Defense Mechanism

The aim of this project is to create an immersive VR gaming experience to let players learn more about health awareness from within the human body. Currently, many VR games are played using the VR controllers that come with VR headsets. To move an object in these games, players have to point the two controllers to an object, and then press a button on each controller to be able to grab it. This control method is unrealistic and not immersive, as in real life, we just have to use our hands to pick up an object. To solve this problem, we decided to use gesture sensors and muscle sensors to capture players' input. With gestures and muscle sensors, players can use their hands and muscle to control their character in the game.
The project has defined a number of objectives as follows:
Deliver messages about health awareness to players...

Educate Positive Image for Teenagers about Blood Donation with Virtual Reality

The aim of this project is to develop a blood donating game based on virtual reality technology to solve the problem of lack of positive image about blood donation.
Truly blood donating procedures will be completed by professionals, there involves a lot of expertise, and the process is very complicated. If we hope the teenagers to overcome obstacles in their hearts and become blood donors, we can let them apprehend that the steps to blood donating are not horrible. However, it's hard to make them remember the action of the blood donating process by using only text and pictures. To overcome obstacles psychologically, we believe that personal experience is the easiest way to remember the steps. So that we provide the virtual reality game about blood donation to them, they can exploit to switch the camera function to observe every movement and detail via the first-person view. This game can motivate their interest to be a donator through the challenge mode, easter egg, score system and funny information.

Grab And Cook

The aim of the project has two main parts which provide a safe environment for the user to cook and cumulative experience and promote Hong Kong local recipes. The target of the project is young adults. The players could cook Hong Kong local recipes and acquire the knowledge about the local food from the Grab and Cook. Moreover, the VR game is a training game that familiarizes players with the cooking process and time and the ingredients they need. It provides cooking experience to people who are beginners of cooking or do not know how to cook.
There are several objectives to achieve our aims. First of all, we need To build up the realistic 3D models of ingredients, cooking tools and background of a kitchen; To set up the scene of the kitchen in unreal engine 4 for the player familiar with the surroundings of the kitchen...

Intelligent Traffic Light System for Hong Kong Traffic Network

In Hong Kong, the increasing number of vehicles and population has caused high usage of roads, which has been a major concern. The aim of this project is to implement the Intelligent Traffic Light System (ITLS) with machine learning, which increases the efficiency of the road space usage.
The project has also defined a number of sub-objectives as follows: 1.Collect data of road usage. 2. Design and develop a system to detect the number of vehicles and pedestrians with computer vision. 3. Analyze data to find out the usage pattern. 4. Design and develop an algorithm for the intelligent traffic light control system. 5. Develop a 2D simulation model of intelligent traffic light control system based on the above. 6. Evaluate the new system against current traffic system...

ClassS: A Mobile Application for Facilitating Teaching and Learning in Smart Classroom

The project aims at facilitating teaching and learning in a smart learning environment by developing a roll-call system and an educational mobile application, enhancing the reliability of attendance list.
The traditional method of making roll-call by teacher is time-consuming and has an impact on the use of lesson time. Moreover, attendance taken by students may disturb students' learning, and the attendance list may not be credible. Besides, teachers' workloads will be increased for the administrative tasks to be done after class.
With the help of our roll-call system, attendance can be taken once student have arrived at classroom for generating...

Banknote Recognition: Using Machine Learning in Assistive Technology for the Visually Impaired

One of the crucial difficulties that visually impaired people face in daily life is recognizing the value of banknotes. They cannot identify the value of banknotes by eyes but can sometimes identify the value by hands touching the accessibility features on banknotes. However, as time goes by, the accessibility features on banknotes will get damaged and become unreliable. Identifying values on banknotes becomes one of the biggest challenges of them.
The aim of this project is to develop a mobile application to help visually impaired people recognize the value of current Hong Kong banknotes. The application should (1) show the value of banknotes with (2) speech synthesis and (3) cell phone vibration coupled with (4) machine learning...

JavaKey: A Java Programming Keyboard

Recently, many programmers have used mobile devices, such as smartphone and tablet, to code since IDE (Integrated Development Environment) is available in Android devices, and coding on mobile devices is more convenient while programmers working in the outdoors. However, when using mobile IDEs in Android devices to write apps, the speed of typing will be slower than coding on the computer. Moreover, because of the limited screen size in devices, it also easily leads to typos, causing user typing with slow speed.
This project aims to provide a new keyboard interface for programmers who write Android apps and programs in Android devices in order to achieve a coding speed that is similar to using a traditional hardware keyboard. To achieve the aim, the main objective is to provide a new keyboard interface for Java, C, and ...

An Integrated and Realistic Online Classroom

Nowadays, different kinds of online tutoring web applications have been designed. However, these tools are still not widely used by either traditional tutoring schools or private tutoring. We observed that these applications not included integrated function, lacked interaction between participants, lacked small-scale group tutoring, and also lacked classroom management. These applications also cannot simulate a real-life classroom atmosphere.
The aim of the project (RIOC – Realistic Interactive Online Classroom) is to develop a realistic and interactive online classroom by simulating the components and interaction of a traditional classroom. To achieve the aim, the objective is to provide a number of classroom-related functions that simulate realistic classroom atmosphere and improve interaction between participants. They are integrated into an application...

A Mobile App for Learning Computational Thinking

Computational thinking skill is an important skill for everyone, giving us the confidence to solve difficult problems efficiently and creatively. This critical skill can also help children make a better decision and solve a large complex task.
The aim of this project is to create an attractive mobile game, which involves programming virtual robots and collaborative problem solving, for children to improve their computational thinking skill through practicing programming theory. This project not only stimulates interest and motivation for learning by a gamification learning approach, but also improves children's communication skill by allowing children to share their views and to explore their leadership skill.
To achieve the aim, the main objective of the project is to develop a mobile game that can...

Hong Kong Driving Simulator: A Mobile Game for Novice and Learner Drivers to Improve Driving Experience and Performance in Driving Test

According to some research studies, the crash rate of novice drivers is significantly higher than experienced drivers. Drivers who lack experience have less ability to detect hazards, including discovering, recognizing, and reacting against potentially dangerous situations in traffic. Therefore, compared to experienced drivers, novices and learner drivers bring higher risk to road safety. New drivers need to have more practice for developing expertise in driving.
The aim of this project is to use a mobile application to improve novices' and learner drivers' driving experience and let learner drivers get prepared for the driving test anywhere and anytime...

An Investigation of Pre-Trained Sentence Embedding and Compositional Sentence Embedding for Automatic Short Answer Grading

Encoding Emotional Information for Sequence-to-Sequence Response Generation

This paper introduces an alternative approach on embedding emotional information at the encoder stage of a sequence-to-sequence based emotional response generation. It explores different positioning and styles of the embedding, which represent associations of emotion with specific words or the whole sentence. The experiment was set up with standard dataset as well as dataset annotated with emotional classifiers. Preliminary results showed that this new approach should better represent sentence level emotional and work well with standard Recurrent Neural network (RNN) with Long Short Term Memory (LSTM) architecture...

Safety Awareness and Firefighting Skills Training through Virtual Reality on Mobile Phones and Computers

This project intends to enhance general public's safety awareness and firefighting skills by using Virtual Reality (VR) technology. The solution is designed with the use of Virtual Reality (VR) technology. The whole solution is divided into two parts. The first part focuses on improving safety awareness. This part is about a mobile application coupled with a VR helmet to provide risk prevention training such as “Remove tinderbox from stove” and “Replace broken wires”. The other part is called Firefighting Skills. It is a small firefighting skill trainer based on VR with the HTC Vive, which would pay the attention on how users acquire the skills. The main objective of the project is to develop two VR applications that can run on both mobile phones and computers...

Enhancing visitors' experience on revitalized historic buildings with augmented reality

This project aims to enrich the interactive and visiting experience, which mainly focuses on presenting the whole picture in history and structures of the building. For public visitors, they can get more fruitful experience by using the application than using existed solution to learn history. They can gain more historical knowledge and interactive experience than using text boards or pictures that commonly used in most of the revitalized historic building in Hong Kong. Through interactive-experience and showing building history by AR technology, visitors can have more ideas of why the government or organisation would preserve the historic building and learn history in an exciting method. For government or organisation that manages the historic building, by using this application they can...

EASElective - A Chatbot for Elective Course Selection

The Bachelor of Computing with Honours in Internet Technology programme at The Open University of Hong Kong poses final year students with an annual course of selection dilemma. The final year curriculum requires students to take 6 specialization courses from 10 to 12 wide-ranging choices. In making this difficult decision, some students have better access to obtain advice from others. Some basic course information such as course titles and course description can be accessed universally, but the more personalized and sensitive information is often difficult to obtain. In this project, an educational chatbot for resolving the problem of providing elective course advising is proposed. Since chatbots are basically virtual robots they can serve many students at any time of the day. It can offer different aspects of information and recommendations when students are making decision of course selection.

A chatbot for Chinese medical diagnosis and dietary recommendation according to Traditional Chinese Medicine

The aim of this project is to develop a chatbot to strengthen people's health awareness by giving healthcare consulting service base on TCM theory and help people to build healthy eating habits by recommending dietary therapy. A chatbot will act as a traditional Chinese physician to interact with the users and diagnosis by guiding them to speak about all the symptoms they are experiencing. Users can increase understanding of their physical conditions with this healthcare consulting service and thus health awareness can be strengthened. Moreover, dietary recommendation can be made after the consultation. Searching a dietary therapy recipe which meets both personal needs and food preferences can be a time-consuming task as there is too much information online. With the requirements specified by the users...

A Mobile Application for Assisting the Visually Impaired in Shopping Products Based on Machine Learning

The aim of this project is to develop an application to assist visually impaired in shopping products in supermarket. As there are numerous products in a supermarket, we will focus on the canned food in this project. The reason is that canned foods have the similar shape which makes visually impaired cannot distinguish among them by touching. If they have an allergy to some food such as pork or beef, the consequence of misidentification may be fatal. For this application, object recognition based on machine learning will be used to classify different canned foods. Object recognition is recognizing the canned foods from an image. Machine learning approach allows the application to learn from numerous data and perform recognition after training. To achieve the aim, the main objective of the project is to...

Enhancing the Knowledge of Chinese Orthography in Junior Education

This project aims to enhance the cognition of Chinese orthography in daily life of junior education, which can finally improve the problem of using typos and raise their awareness of writing orthography.
A gamification of education in Android platform is designed to ease the problem found above. User needs to control a character to escape from the maze through studying different types of orthographies. As a result, their knowledge on orthography will be enhanced. In achieving the aim, seven objectives are included as following. Data Collection Collect the common typos in daily life according to observation, academic paper and books.
Question Bank Create a question bank with different types of questions which contains appropriate amounts of typos based on the result of data analysis from data collection.

Improving the Efficiency of MOPSO with Adaptive Inertia Weight and Dynamic Search Space

In this paper, a new Multi-Objective Particle Swarm optimization algorithm (MOPSO) with adaptive inertia weight and dynamic search space is introduced for multi-objective optimization. The objective of the study is to investigate an efficient MOPSO to deal with large-scale optimization and multi-modal problems. The new adaptive inertia weight strategy allows the inertia weight to keep varying throughout the algorithm process, which helps the algorithm to escape from local optima. The dynamic search space design can avoid decision variables from continuously taking their extreme values, and therefore enhances the searching efficiency. The performance of the proposed algorithm was compared with three popular multi-objective algorithms in solving seven benchmark test functions. Results show that the new algorithm can produce...

An investigation of performance on Two Phase Local Search and Multi-Objective Ant Colony Optimization

Three objectives were carried out to come up with the project. First, introduce hybrid paradigms of Two Phase local search (TPLS) and multi-objective ant colony optimization (MOACO). Second, implement the Iterated Local Search – Variable Neighborhood Search (ILS-VNS) as the first phase in TPLS; and then, to investigate the performance of proposed algorithm with different settings of local search choice and population size. To specify, comparison of choice of TPLS using with WLS and PLS is also considered. A statistical testing will be carried out to evaluate the significance of the result. More importantly, further analyze on population size effect on solution archive size and performance...

Classification of Short Answers for Semi-Automated Grading and Feedback in online Assessment

The aim of the project is to develop a semi-automated grading short answer algorithm to reduce and make better use of instructors grading effort. In traditional way, short answer grading process need a lot of effort and time. We think that this process can be done in a more efficient way. Semi-automated grading is the combination of traditional grading and automated grouping of answer. We will design a framework for clustering the short answer in different group. The answers which are similar and share common feature are grouped in a cluster. We want to explore the ideal feature set so that the answers will successfully cluster the answers according to the similarity. Hence, instructors only grade representative answer of each group, the grading apply to all the answer in the cluster...

Nimble body: A Mobile Application with Wireless Sensor for A Reliable and Fast Measurement of Range of Motion

The aim of this project is to develop a mobile application combining with sensor technology to measure the range of motion of physical joints that can be done the user himself without the help of any professionals. The mobile application is designed to achieve a faster way of physical assessment but with reliability comparable to the orthodox procedure done by professionals like doctors. The application should arouse rehabilitant/patient to be concerned more about their physical health, have a faster convalescence and better prevention. This project has several objectives to achieve, the major part is the collection of a series of ROM measurements, in order to let users assess their joints' status objectively by analyze the data and compare to the normal standard. Rigorous built-in guidance would ensure...

A Virtual Reality Application for Visual Art Education

The aim of the project is to develop a VR application to enhance Hong Kong secondary school students' interest of western artwork appreciation. The application focuses on helping users to deepen their impressions and memories of western artworks.
The application will be divided into three parts: Artwork Tutorial, Art Gallery and Gameplay. The artwork tutorial is an interactive experience between artworks and users. The visual elements of the artwork will become dynamic and response with user actions to attract users' attention. The virtual gallery is a free space for users to explore around and discover the artworks. It provides a well-designed environment for artwork appreciation and the details of each artwork will also be provided. For selected artworks, there will be some related games for users to play in order to discover more...

Treatment of Cockroach Phobia with Graded Exposure in Augmented Reality

To achieve the goal, the project has defined a number of sub-objectives as follows: Design a treatment in graded exposure for users to handle their fear of cockroaches and investigate the effectiveness of the treatment.
Design different levels of augmented reality game. To define the levels, 4 aspects of cockroach are concerned: number, movement, distance and interaction. With higher level, number of cockroach increases, distance between cockroach and players shortens, movement of cockroach becomes vigorous, interactions between cockroach and player is also enhances.
Develop a cockroach movement model: Cockroach movements are restricted by a model...

VR Rehearsal Simulator

The aim of our project is to reduce the cost of doing a real practice for practice teachers with the use of VR classroom rehearsal simulator. The practice teachers can use our VR rehearsal simulator. It can enhance practice efficiency. Practice teachers and the experienced teacher can use application to know the report and the result of the user. The report will record the grades for the teacher. And give them some suggestion to improve themselves. Also, the application has the interactive system. It has some basic interactive to the user who using this VR application. Such as voice command input, eyes contact. Application has some different burst situation; it need the teachers to handle and make some decide. Therefore, the VR rehearsal simulator have the Situation editor, user can modify the rehearsal situation. User can modify the Difficulty level...

VR Serious Game for Treatment of Trypophobia

The aim of this project is to develop a serious game with VR technology on Android platform to help people with Trypophobia to reduce fear. The idea of serious game is applied in this project as we are aiming to use gaming as a treatment of Trypophobia. One of the treatments for phobias is exposure therapy. To achieve the aim, the main objective of the project is to develop a VR game on Android platform that can be played as a treatment of Trypophobia. The project has also defined a number of sub-objectives as follows: Design a treatment procedure based on exposure therapy. This treatment procedure will be the core of our application.

Improved Adaptive Global Replacement Scheme for MOEA/D-AGR

“Multi-Objective Particle Swarm Optimization” (MOPSO) is one of the long-term developed algorithm technique in the area of multi-objective optimization. However, the solution set comes from original MOPSO algorithm is usually not the best in solving the complex multi-objective problems (MOP). Multi-Objective Evolutionary Algorithm based on decomposition (MOEA/D) has been proposed for a decade in solving complex MOP by decomposing it into several single-objective problems. MOEA/D is widely considered as an ideal substitution of MOPSO algorithm.
MOEA/D-AGR is one of the improved algorithm introduced recently to substitute the original replacement scheme in MOEA/D with a new adaptive global replacement (GR) scheme so that the neighborhood replacement size Tr is increased among the generation to achieve the shifting of focus from solution diversity to convergence...

A Virtual Reality Game for Exercise with Motion Capture and Body Sensors

We aim at developing a sports game that helps people to release stress by doing more exercise. With the combination of the new technology(Virtual Reality, abbreviated as VR), we focus on how to create a new way for people to do sports, without consideration of the weather, budget, the size of venue and others‛ company. In reference to the success of a very hot society “Superhuman Sports”, extending human abilities or sensation would make people be more motivated and excited to do sports.
To achieve our aim, the main objective of the project is to develop a monster combat sports game which can calculate and analyse for the calories burned after users have played the game. The project is defined by a number of objectives...

Running Treasure Hunt Game with Smartphone and Indoor Positioning Technologies

Every year, treasure hunt inside the university is a common game in an orientation day. This game lets participants explore different locations on the campus as a team. Teams usually made up with a number of new students and one higher-year student who can lead the team. A Treasure hunt game can have different types of missions for different stations. Different missions: Each team explores some key location on campus to be familiar with each location. Stations will be set up at some key locations, each team need to finish the participate mission provided with teamwork. The aim of is to assist a treasure hunting game organizer to design, prepare and execute this popular campus game with an IT solution.
In order to achieve the aims, the project has defined as the following objectives...

Man-ager: a device for the Well-Being of the elderly

The aim of this project is to investigate IT solutions to relief the consequence caused by geriatrics by using new technologies. Although there are some existing tools that support the elderly's daily life, it still cannot provide all-rounded caring services. They are inconvenient to the patients and their family members, even causing serious consequences such as Overmedication. Therefore, this project will focus on how to apply different terms of expression to help the elderly suffered from the geriatrics diseases to adapt their daily lives.
To achieve the aim, the main objective of the project is to develop a tool for elderly that can schedule a timetable to remind them what time to take medicine and provide healthcare information to the user. The project has defined a number of sub-objectives as follows...

Reuse Your Old Smartphone: Automatic Surveillance Camera Application iEye

The aim of this project is to utilize the camera and microphone of an old smartphone to keep our home under automatic surveillance in order to increase the utilization rate of old smartphone and keep home safe. This application focuses on real time streaming. It turns your old smartphone to home security cameras which captures the audio and video and send them to the server by Wi-Fi. This allows user to keep monitor the current home situation on another smartphone wherever you are. Besides, automatic surveillance is another important issue. This application will automatically detect abnormal activity at home such as stranger comings or goings from the door, brightness variations, objects motion, baby crying and falling of someone (elderly or children). The application will notify the user by email immediately...

Augmented Reality Gift-box DIY System SOSGift

This project aims to provide a convenient, efficient and well-described utility for users to create gift-box in order to enhance the making process experience with augmented reality technology (AR). Because the lack of utility for the whole process, this utility aims to provide service from gift-box selection to final product creation which is convenient. When people DIY the gift-box, they need to draw the paper pattern. If the size is not perfect, they go back and draw the pattern one more time which is totally wasting time. This utility aims to reduce the overall time of DIY gift-box especially in the size-measurement part in order to achieve efficiency. Some existing tutorials of DIY gift-box are complicated and unclear. This utility also aims to provide well-described tutorials for user with assist with AR...

Not Just A Wall: Mobile Augmented Reality and for Sharing Multimedia Campus Moments and Enhancing Campus Climates

The aim of this project is to develop a mobile application to connect OUHK students through the things on campus in order to improve students' sense of belonging. The mobile phone allows students to interact with the server in a specific place with the support of camera and Augmented Reality technology.
This application focuses on providing a virtual platform for OUHK students to share their campus life with each other and facilitate their discussion on common experiences that they can relate to. Internet-of-Things is the idea that carries out this project. By utilizing this application, OUHK students can improve their sense of belonging and enjoy being a part of it. Students can build up stronger relationship and connection with others. The project objectives are...

A Food Ingredient Consultation App

The aim of this project is to give suggestion to the user when they are using smartphone to scan the packaged food label. We are going to develop a food ingredient consultation system to analysis the relationship between user personal data (age, food allergy, weight) with the packaged food ingredient. The warning message will occur when the user matches the risk factors, by doing that the accident rate will decrease.
To achieve the aim, the main objective is to develop a food ingredient consultation app that can read 1D barcode and food ingredient facts labels. Then provide health instructions suitable for normal users and warn the user when there are potential food allergens. The project has defined a number of subobjectives as follows...

Furnish-It-Yourself: A Mobile Furnishing Simulator with Augmented Reality

The aim of this project is developing a home solution to help furniture buyers evaluate which furniture fits their home style at home and provide a real-like furnishing experience. This project will develop an AR furnishing mobile application. This application focuses on helping furniture buyers to foresee the furnishing effect. Users can get a concrete view of the effect before buying furniture. The details as follows:
Develop a model positioning handler;
Design and develop an user-friendly user interface;
Implement social feature...

A Book Finding App for the Library

The aims of this project are to improve the availability and efficiency on book finding. This can be done by adding additional function onto the original system and developing multi-platform version of the searching system. In addition, the system can generate a map with the shortest path for user to reach the books they are searching for. The main objective to achieve the aim is developing a path generating function. This function should provide a path for user to reach all the books they are looking for on a 2D library map. There are also some sub-objectives improving the availability and efficiency of the searching process. The expected result after applied the new Path finding method is we can find a shortest path that passes every books we want, then we can pick all the books up along this path, without wasting time on the shelves...

FluteKit: A Mobile Learning Application for Beginners to train Rhythm Skills and learn Flute Fundamentals

It is difficult for flute beginners to learn and practice flutes by themselves without any guidance from the instructors. Flute beginners often suffer from rhythmic errors as they may play a note longer or shorter than its correct duration. Sometimes, the rhythms written in the music sheets are too complicated for them to comprehend. Most flute beginners also do not know how to build a solid foundation in playing flutes. They may lose their interests when they keep performing unsatisfactorily. This project is to develop a mobile e-learning application for flute learners to train their rhythmic skills and help them learn flute fundamentals so that they can play a new song in a better way with fewer mistakes. This application focuses on helping users to learn rhythmic skills and sight reading. The rhythms that the learners have played...

A Piano Assistant for Beginner

The aim of the project is to develop a mobile E-learning application for beginners to learn basic knowledge and assist them to do piano practicing. The focus of this application is on helping beginners who are weak on the basic music theory of piano. Beginners are hard to handle music theory which looks like easy, such as music notes, beats and so on. So, there are some learning materials for the beginners of music, let them be easy to start learning music. The project has defined following objective: Designing learning materials for beginners to learn basic music theory. Develop basic music theory exercises for learners to review; Develop a piano keyboard for learners to practice piano; Develop a piano game for learners to practice and for fun...

iWedding: A Web-based Application for Wedding Planning

The project aims to develop a web-based wedding planning application, iWedding, accessible through browsers or smartphones. The purpose of iWedding is to guide wedding couples through the decision-making process and provide them advices on budget and planning. Important information such as dates suitable for wedding is also provided. Other built-in tools like the guest list and seating planner are given to assist couples in inviting guests and assign appropriate banquet seating. In case the couples encounter difficulties during planning, they can seek help from consultants who advertise their services on iWedding. In order to achieve the aims, the project has defined a number of objectives as follows: Design and create schedule template for couples to know what they need to do...

'Watch' Out! Elderly Safety Alert System

This project is aiming to provide an integrated, smart platform that can able to study the behavior of elderly residents. We decided to develop an Android application with Elderly safety alert system. The final product we expected the system could determine whether the elderly fell down or not and notify the guardian when the elderly need assistance.
The concept of our system is to provide a promising and cost-effective way of improving safety alert for the elderly residents and the disabled in a non-obtrusive way. Therefore we will implement a personal safety system that keeps an eye on elderly residents, monitoring their behaviors and serves as an alert system to notify users if they are injured or incapacitated. A brief line of message will be send to the guardian's station or smart device which indicates the activity or abnormal incident about the resident...

The Intelligent Work Desk System

The aim of the intelligent work desk system (IWDS) is to enhance the efficiency and safety of human who working on a work desk. We are developing an intelligent system with the use of real-time monitoring 3D sensor. The system is expected to allow user to find their missed things and to preventing the things stolen from the work desk. We have concluded the concepts of the project into three core parts: Monitoring and logging the stuff of work desk in real time Helping users to memorize the location of missing stuff Creating the user-friendly and modern interface of the application In order to decrease and enhance the safety of the working process, The IWDS can logs the date, times, coordinates, movements and other related information of different objects so users can locate the lost object easily. Also, IWDS is easy to use so users can interact with the system efficiently.

A Mobile Application Development for Recognition of Common Flowers in Hong Kong

The main objective is to develop a mobile application to recognize the outdoor flowers, and return flower information to the users automatically. The sub-objectives are:
Collect the data of common outdoor flower found in Hong Kong;
Analysis the collected data and classify the flower in different type;
Develop a camera function to capture image for the flower;
Design and Develop a recognition system to identify flower;
Design a result displayer to show flower details;
Evaluate the application.

A Mobile Application for Preparing the Driving Tests in Hong Kong

The project aims to develop an educational mobile application on the Android platform for preparing both the driving theory test and road test in Hong Kong. This application will give car learners some basic concepts of driving and let them to practice and revise with their mobile devices. It provides guidebooks, mock tests, animations and virtual driving games to help users, especially young private automatic car learners who are going to take the driving tests, to do revision and pass the driving tests in Hong Kong easily. The project has defined a number of sub-objectives as follows:
Design and develop a driving theory handbook sorted by topics. Design and develop practices and mock tests for the driving theory test. Design and develop driving guidebook and driving step test. Design and develop animations and virtual driving tests for the road driving test Evaluate the effectiveness of the new application

Identification of 3D Facial Features for Prediction of Respirator's Fitness

This project aims to develop the computer respirator prediction system by finding out the key human facial features that affect the fitness of respirator. The current respirator fitting-test methodology is not efficient and it wastes a lot of resources. To select the best fitting respirator, wearers have to test respirators one by one. Those respirators fail the fitting test are wasted. A computer respirator prediction system will improve the efficiency and effectiveness of the current fitting test. The main goal of this project is to identify the key features on a human face that most likely to affect the fitness of a respirator. This project has defined a number of sub-objectives as follows: 1.Normalize the 3D facial model. 2. Locate facial landmarks. 3. Calculate facial features base on facial landmarks. 4. Evaluate the reliability of the algorithm. 5. Collect respirator fit-testing data. 6. Experiment to use the facial features to predict fitness of respirator to find out the key facial features. 7. Evaluate the reliability of predicting respirator fitness by key facial features

Hello Japanese: An Adaptive Mobile Learning Application for Beginners to Learn Fundamental Japanese Language

The aim of this project is to develop an adaptive mobile e-learning application for beginners to acquire basic knowledge of Japanese language in order to gain the self-learning proficiency in Japanese. This application focuses on helping users to learn fundamental Japanese language topics, such as Japanese alphabet (Hiragana and Katakana), phonology or words (adjective, verb and noun). Besides, adaptability of the application is another important issue. Adaptability allows the application to adjust the learning process depending on the learning performance of individual learners. For example, supplementary exercises are provided to learners adaptively based on individual situations. Here are some objectives to achieve the aim of the project: 1.Design and create learning materials for beginners to learn basic Japanese knowledge, like alphabets, phonology or simple vocabulary...

3D Show Flat Demonstration System of Residential Properties with Leap Motion

This project aims to provide visual aids for people who are potential buyers of residential properties. With Leap Motion, the flat can be presented in 3D that buyers can simply use their bare hands to control which side of the show flat they would like to see and interact with the 3D show flat system on a computer. Buyers can better visualize the details of the flats or apartments and conceive ideas of interior design. As the same time, the hygiene problem in the public first-sale site can be avoided. To achieve the aims, the project objectives are described in detail below: 1. Develop a Tutorial System. 2. Design a simple and clear Graphic User Interface Integrate Leap Motion and the 3D Show Flat System Design gestures for command that are easy to pick up. 3. Develop interior designs of show flat Decoration with different styles...

An Augmented Reality 3D Model Creator

There are few of the 3D model creator application in Android OS.The aim of the project is let more people can make their own 3D model anywhere, enjoy the 3D creation ,enhance the interaction between human and the model as well as the real environment and virtual environment. Moreover, user can modify the 3D model easily, save the time and money while developing the 3D mode. To achieve the aim, the main objective of the project is to develop an android application that user can create and modify the simple 3D model easily. The sub- objectives are: 1. Support different resolution on different android device, such as smart phone or tablet. 2. The makers which used to represent the 3D model in AR environment are easy for user carry. 3. Adopt the Augmented Reality technology that the application can mix up the real world and virtual world. 4. Users can control the 3D model in the Augmented Reality environment through the maker and display this in the monitor. Also, some functional button will allow user touching on the screen...

Investigation of PSO for Multi-objective optimization

The aim of this project is to enhance the searching ability of particle swarm optimization (PSO) in multi-objective problems and hence produce a better result. Besides maximizing the number of found solutions, selecting elitists among the found solutions is important. The elitists should both have a good distribution and high accuracy. The elitists must be store properly. Moreover, other algorithms are needed for comparison. Suitable metrics are necessary to indicate the performance of all the algorithms. Visualization is another important issue to show the performance of all the compared algorithms.
To achieve the aim, the main objective of the project is to make a new proposal for PSO in multi-objective optimization and verify it. The project has defined a number of sub-objectives as follows: 1. Maximize the number of found solutions using our proposed algorithm. 2. Maintain good solutions (nondominated solutions) and discard all bad solutions (dominated solutions). 3. Avoid the swarm in PSO converge too fast (premature), so that larger area can be visited by the swarm...

Treating Cockroach Phobia Using Augmented Reality and Graded Exposure with Microsoft Kinect

This project aims at investigating the help of AR and graded exposure in cockroach phobia therapy with Microsoft Kinect.
In order to let patients handle their fears gradually and to correct their inappropriate cognitions on cockroaches, graded exposure is a good and effective approach. Cockroach phobia sufferers can face their fears step by step. During therapy, patients are guided to reach the levels one by one to relieve their phobia symptoms gently. Once the highest level is met, the treatment is complete and supposed to be successful. AR can be integrated with graded exposure for better achievement. AR allows a virtual cockroach to...

A Consumer Level 3D Object Scanning Device using Kinect for Web-based C2C Business

The aim of the project is to develop a Kinect-based 3D scanner system to scan object for e-commerce website and analyze the possibility of such a system in e-commerce marketing. Currently, online shopping is popular all in the world. So many companies want to join in the online auction market. But usually most of online shop website only displays the image, for example, a shoes, figure, electronic device and accessories etc. That makes the customer without confident to buy the product because they can't view the details of product. The 3D scanner will help the sellers to present the visual 3D product to the customers. Then it can increase the attraction of products to the customers. Also, the 3D system will provide simple steps to produce 3D object and output file and then collaborate with the e-commerce website. The website will be built in 3D component system for user to upload the 3D product easily and display the good quality of product...

The Development of an Open Access Textbook Platform

The project aims to develop an Open Access Textbook Platform. The outcome platform supports both English and Chinese interface. This project is to reduce the cost of textbooks. The students don't need to use a large budget to buy textbooks. Furthermore, increases the attractive of study. Students feel interested in the process of study.
To achieve the aim, the main objective of the project is to develop an Open Access Textbook Platform that user can share or receive the education resources and customized as a textbook.
The project has defined a number of sub-objectives as follows:
1. User (authors) can create or manage their textbook contents. 2. User (teachers) can select the textbook contents and customized as textbooks User (teachers) can design or manage their textbook. 3. User (students) can access the textbooks online, or download the textbooks for offline usage, and make a print on demand requests..

The Development of a Mobile Application adopts News of Legislative Council Motion

The main objective of the project is to develop the software system for automatically handle the scheduling, collecting and analyzing works. The purpose of these works is to get the useful information from the motion result PDF which places at the Legislative Council website. These tasks help us to avoid the manual work and delay update.
Also, develop a mobile application to provide portability and diversify platform for the user to receive and publish the information. User can have a right to vote on each motion and evaluate on each councilor. They can share their opinion freely and comfortably. The project has defined a number of sub-objectives as follows: 1. Develop a method for Legislative Council source information collection. 2. Set up a meeting schedule. 3. Set up a program for the system to collect the data automatically...

A Bird Recognizer based on Particle Swarm Optimization

The aim of this project is to develop a bird recognizer based on particle swarm optimization. Our target is to recognize the 21 kinds of common wild birds seen in Hong Kong urban parks which are listed by Leisure and Cultural Services Department of the Hong Kong Government. It is developed based on the particle swarm optimization and is a kind of application of it. Some kinds of recognition methods have been designed to increase the hit rate in recognition based on particle swarm optimization. To achieve the aim, a bird recognizer with different kinds of recognition methods have built and some is based on particle swarm optimization. Advantage of particle swarm optimization was researched. On entering a bird image into the program, a bird result should be returned. The project has also defined following sub-objectives: 1. Investigate on machine learning algorithms. 2. Create GUI for showing the structure of the algorithm. 3. Design of bird recognizer. 4. Train and test the bird recognizer.

An Augmented Reality Automatic Furniture Fitting System

The aim of this project is to simulate a real room environment in a better way, which allows the users to experience the outcome of possible furniture arrangement and evaluate whether the outcome is acceptable. To achieve the aim, the Augmented Reality technique is applied. The main objective of the project is to measure the dimensions of a real room by a depth camera, which is provided by the Microsoft KINECT sensor. It converts the depth data for our system, and uses those data to estimate the available space in the real room. Afterwards, the users can select the 3D virtual furniture from the system database and put them into the room. Finally, our system enables the user to customize their favorite size or color of furniture and give some suggestion for the user such as whether the space is enough for placing furniture. The project has defined a number of sub-objectives as follows: 1. Get the required data using Computer Vision techniques. 2. Convert the required data into parameters that used for generating a room with virtual furniture. 3. Create and adopt 3D furniture models. 4. Enable the user to...

A hybrid algorithm based on Backpropagation with Magnified Gradient Function guided by Adaptive Particle Swarm Optimization in Neural Network Training

Neural Network is a useful machine-learning model. Training up a Neural Network is however a complicated task. Two of the existing Neural Network training algorithms are Backpropagation with Magnified Gradient Function (MGFProp) and Adaptive Particle Swarm Optimization (APSO). MGFProp is good at searching for optima but usually requires a long start up time before it can make any progress. While APSO requires almost no start up time but bad at searching for optima, i.e. usually there are better positions unexplored next to the global best-explored position. Based on these observations, this project aims to design a hybrid algorithm of MGFProp and APSO and investigate its performance, in terms of learning speed and global optimality. In this project, we use APSO to perform global searches for good starting positions for MGFProp to perform local searches.

A Robotic Chinese Chess(Xiangqi) Master

The aim of this project is to let elderly people playing Chinese Chess with autonomous robot, so that they can still enjoy the fun of the game when they find no people as their opponent.
The project mainly focuses on building an autonomous robot. To achieve this aim, I have defined a number of objectives as follows:
The design and implementation of mechanical arm. The mechanical arm receives a signal from processor and moves chess token from one grid to another on chessboard. The design and implementation of a chessboard sensor. The sensor has the ability to recognize the status of chessboard. After the player finishing his turn, it detects the movement of the chess and sends data to processor for manipulation. The design and implementation of an intelligent chess-playing system. The system is responsible for finding out the most beneficial choice base on the current chesses positions on a chessboard.

An All-in-one Mobile Learning Application Assisting Nursing Students in Problems Solving

The aim of this project is to design a mobile learning application called Nursing Assistant in Android platform for nursing students and nurses to solve problems. This application mainly focuses on common difficulties that most of the nursing students and nurses may often face problems such as remembering nursing terminologies and knowledge, distinguishing the symptoms and situations and performing calculations in a fast and accurate way. There are several objectives of this project: 1. Facilitate students and nurses on learning and problem solving. 2. Enhance students' and nurses' ability of distinguishing the common diseases. 3. Increase the accuracy of the calculation in clinical works. 4. Facilitate interaction between students in learning and nurses in their works.

A Programming Assignment Plagiarism Detection and Automatic Marking System based on Tree-based Comparison

The aim of this project is to design and implement a program comparator. This comparator can be used to detect plagiarism and mark programs for assignments. A system is developed in this project for the evaluation of the comparator. To achieve the aim, the project has defined a number of objectives as follows:
1. To design a program-comparing algorithm and develop a program comparator. 2. To implement the comparator as a plagiarism detection tool. 3. To implement the comparator as an automatic marking tool.

On Solving the Local Minimum Problem in Feed Forward Neural Networks

The aim of this project is to investigate the local minimum problem in neural network and to design an algorithm to solve the problem. Neural network is widely used in pattern recognition and data classification accomplished by training. The training mainly involves comparing the output of neural network with the desire output and the difference is used to adjust the parameters to minimize the error. However, the performance of the training is always affected by the local minimum problem, or even fails in the training. The nature of the local minimum problem is illustrated in the following...

A Study of Executable Specification Frameworks FitNesse versus Concordion

The aim of this final year project is to investigate how FIT table enforce readability of requirement specifications and to investigate how programmer choose a specification framework concerning maintainability. This project includes two experiments in which readability experiment compares FIT tables and word document. Secondly, the maintainability experiment compares requirement specification in FitNesse and Concordion.
This project is initiated due to an observation that many software projects fail to meet the customer requirements. Pure word document and oval meeting may not share a common domain language between customers and programmers. Therefore, one aspect of this project is to investigate whether FIT tables, which are in tabular format, can express the business logic in a more readable way by it executable specification. The objectives of this project have been defined as follows...

Hyperpersonal Effect and Spam Mail Detection

The aim of the project is to investigate the detection of spam mail with the consideration of the hyper-personal effect. The hyper-personal effect enables the spammers to selectively project their images and personalities when using only written words to convey their personalities. My idea is that if the spammers can selectively present their images in the form of text then we are able to extract the information of the spammers' images from the text. The images and personalities of the mail author affect the detection of the spam mail in some ways. The hyper-personal effect is hence investigated in this project to find out personalities and images projected by spammers. The result is then used to assist the spam mail detection. The project objectives are described in detail below...

A Novel Visualization System for Analyzing the Performance of Legislative Council Members

The aim of the project is to design a visualization program helping public to analysis the performance of Legislative Councilors from official minutes. We define assessing criteria based on the behavior of members during meetings for example, suggesting idea, interrogating to government, voting and debating of the motion and reporting the voice of public. For instance, a good member should represent general public in meetings and monitoring government. They also suggest idea or ask some questions to improve government's motion to suit the public needs. In other words, they should attend all meeting and speak in each meeting.
Each minute record the action of member in the Legislative Council meeting but the content is too complex and long, public feel difficult and boring when reading these minutes. We use minutes as our data source and...

3D Facial Scanning based on Structured Light with Novel Approach of Automatic Facial Anthropometry Extraction

The aim of the project is to develop a low cost, portable 3D facial scanner based on structured light. Facial anthropometries will be obtained from the reconstructed 3D model for the further investigation of mask fitness test. A 3D facial scanner is a setup which allows human face to be scanned and delivered in the form of 3 dimensional models. Structured light (SL) are specific patterns that acts as the coding parameters for 3D model reconstruction. Anthropometries are measurements of facial features and mask fitness test (MFT) is a standard for selecting suitable mask for users. Typically, anthropometric data are measured to assist the process of MFT. In this project, a portable 3D facial scanner will be developed to obtained anthropometries required for MFT. Another project of MFT will make use of the anthropometries to select suitable mask for target users...

Go-Putonghua: An Online Learning Platform for Self-Learners to Learn Putonghua

This project is aimed to develop a new online learning platform called GoPutonghua for self-learners to learn Putonghua. This platform includes online lectures and e-books. The platform allows learners to conduct online exercises that are related to the lecture contents. An online assessment system is developed for learners to know their performance to seek for improvement. A character dictionary (zidian) and a phrase dictionary (cidian) are built to support mapping from Chinese characters to Pinyin. Learning tools like Pinyin Converter and Text-To-Pinyin Speech have been developed to search for the Pinyin (with tone marks) of Chinese characters and produce the correct pronunciations in Putonghua. The two types of communication tools (asynchronous and synchronous) are also included in the platform. GoPutonghua is developed to provide more free resources and services for self-learners to learn Putonghua in a hassle-free manner.
The project objectives are described in detail in the following...

An Online Platform for Primary Students Learning Phonics

This project aims at developing an interactive learning system, which is named as “PHONICS FUN”, for phonics self-learners in an interesting way. The Platform will provide a certain pack of animations, voices and games to increase the attractiveness of the learning environment. Phonics is a method to help learners to read and write in English. Most of Hong Kong students do not pronounce English correctly according to phonetic rules. They either rely on memory gained from previous learning experiences or simply by guessing. This e-learning platform is designed to be an effective approach and usable for learners. It focuses on four main areas including listening, speaking, reading and writing. The platform will provide a set of colorful and practical materials, exercises and games to help learning Phonics. Students can study by themselves whenever, wherever and whatever they like. The architecture of the platform is shown in the following...

Automatic Digest Generation for Mobile Phone Online Reviews

The aim of the project is to design a system that using opinion mining technique to help buyers reorganize the chaotic information into neat information. Our system is focused on phone reviews and the main objective of the project is to generate a phone summary from available online phone review site. As our framework mentioned, the feature and its corresponding opinion are the most important information people interested in. Hence, the summary will categorize the positive and negative opinions into different feature. Reorganizing the chaotic information, the system allows reader interested exclusively in positive or negative opinions of specific feature to save opinion searching time and clear reader mind on conflicting opinion.

An Improved Resilient Propagation Algorithm by Introducing Deterministic Weight Modification and Magnified Gradient Function

The aim of project is to improve an existing training algorithm on feed-forward neural network. This algorithm will base on Resilient Propagation (RPROP) and try to improve the global convergence capability and speed up the convergence rate. The main approach is modifying RPROP based on the theories of Deterministic Weight Modification (DWM) and Backpropagation with Magnified Gradient Function (MGFPROP).
The following describes the objectives concerning the development of a novel training algorithm based on RPROP and augmented with DWM and MGF: 1. Design and Implement the algorithm using Java: DWM for improve the global convergence capability and MGF for speed up the convergence rate and capability. 2. Evaluate and compare the performance of the new algorithm with existing ones based on standard data sets. 3. Develop graphical tools for visualization and analysis of convergence rate and global convergence capability...

An Self-Assessment System for Facilitating Learners' Engagement

The aim of the project is to integrate both teaching assessments and learning into a single real-time system architecture. Feedback is provided immediately to act as a reflective tool for students. As aforementioned, student-driven concept will be a key part of this project. Therefore, the main objective of this project is to design and implement a web based assessment system to engage students self-learning through the dynamic questions generated by the system.
In this paper, an online assessment system is proposed to engage students to have self-learning through the use of dynamic questions. The system will automatically design and generate questions for individual students according to their learning ability. Students can take the assessment at anytime and anywhere. Questions are not only prepared by the teachers in advance (which are stored in a database), but are also generated by the system automatically known as 'parameterized questions'...

Applying Distributed Computing using Aglets on Delaunay Triangulation

here are currently billions of computers in the world but most of them are in an idle state. This wastes a large amount of computation resources that could be exploited for solving complicated computational problems. Java mobile agent (Aglets) is a distributed computing technology that allows the distribution of a process to any number of computers in the Internet.
This project demonstrates this concept through the implementation of a very complicated computation problem. The Incremental Insertion algorithm of Delaunay Triangulation is chosen to be the very complicated computational problem. First, a computational and visualized program for Delaunay Triangulation in a single computer is designed and implemented. Next another program for Delaunay Triangulation in a distribution system is designed. The algorithm is then analyzed into a parallelized version. Distributed computing program is implemented based on a Master-Slave design pattern with Aglet. The result from the program in a single computer and the result from the distributed computing program were compared in terms of execution time...

Chinese News Mashup: Cloud Computing and Web Service Integration

The aim of the project is to integrate both teaching assessments and learning into a single real-time system architecture. Feedback is provided immediately to act as a reflective tool for students. As aforementioned, student-driven concept will be a key part of this project. Therefore, the main objective of this project is to design and implement a web based assessment system to engage students self-learning...

Handheld Interactive Teaching and Learning System in Classrooms

Financial Data Mining on Web 2.0 Text Sources

EASYLib Library System