Categories
Undergraduate YPEC 2021

UG07-Fining Website

FIning is a platform that provides high-end dining orders and experiences.

Categories
Undergraduate YPEC 2021

UG17-Elderly E-Party

This project is to develop a suitable for the elderly to interact with friends and family in a VR environment. The project’s primary purpose is to enable the elderly to have a happy life in their later years through the VR environment. At the same time, establish interpersonal relationships for a group of elderly neglected by the community. And encourage the elderly to meet new friends and new things in real life.

Categories
Undergraduate YPEC 2021

UG16-Real time simulation for solar energy system testbed in Hong Kong

Abstract—Climate change is affecting everyone on every continent. Referring to the UN Sustainable Development Goals (SDGs) 2030 agenda, urgent action is needed, and stepped-up efforts in Renewable Energy (RE) applications. How to penetrate high levels of sustainable RE and Distributed Energy Resources(DERs) into power grids become important, and the solution – smart grid with more reliable, efficiency, and flexible features comes out. Back to Hong Kong, the size of solar scale would come-up with small and individual features on the rooftop of buildings with Feed-in-Tariff (FiT) introduced by the post-2018 Scheme of Control Agreements (SCAs). Increasing DERs application reduces the system’s inertia may result in possible frequency stability issues that lead to un-equilibrium active power supply and demand. Understanding low-inertia systems and how to ensure the frequency stability is of crucial importance with load-frequency control. This paper will be introduced with a real-time Microgrid analytical study of solar renewable energy system testbed with Real Time Digital Simulator (RTDS) to evaluate the system dynamic response while an ad-hoc change in load or generation event occurs. With operations in continuous real time, the simulated system can operate close to the real microgrid system with parameters applied with real data of typical solar panels installation in Hong Kong. Featuring RTDS capability, the Hardware in the Loop (HiL) Testing would be investigated in the next stage allowing the microgrid operation, EV chargers, and protection and power devices to be evaluated under realistic operating conditions before they are installed in the actual microgrid system.

Categories
Undergraduate YPEC 2021

UG15-EYEDENTIFY: A mobile application for improving the self-esteem of dementia patients in their social life with machine learning

Due to the rapid growth of Dementia patients, some new mobile applications have been released to the market. However, those applications may not focus on the needs of Dementia patients. Most of them are provided for the Caretaker of the patient to monitor them or some games to slow down the disease progression. Since the social life quality of Dementia patients has been ignored, we decided to implement a mobile application to improve their social life by strengthening their self-dependence and confidence. Our solutions are formed by multiple applications of two recognition functions, facial recognition and object recognition, as well as other functions such as memoir and GPS location sharing. Facial recognition function can reduce the embarrassment when dementia patients forget who is standing in front of them. While the object recognition function helps others find lost belongings to reduce conflicts and arguments among dementia patients with others. The testing of our application shows a good performance in different functions respecting the accuracy of recognition and usability. Feedbacks are also received from respondents, which shows evidence that our solution is useful and truly improves their social life quality.

Categories
Undergraduate YPEC 2021

UG14-The AutoClean

People’s awareness of hygiene has grown rapidly due to the outbreak of COVID-19 pandemic. Dirty and smelly public toilets, well-known for many years in Hong Kong, has been doubted as the potential breeding ground for SARS-COV-2 virus. Evidence of faecal-aerosol transmission of virus, coupled with unacceptable hygiene conditions, has deterred people from using public toilets. Therefore, we should seize the opportunity to renovate the undesirable public toilets to optimise the user experience and reduce the possibility of COVID-19 transmission in these toilets. The AutoClean is a self-cleaning public toilet system that maintains toilets clean and disinfected. With the use of automation, toilet fixtures can be self-cleaned regularly. For instance, toilet seat covers are disinfected by UVC light when closed, and floors are self-cleaned by the feature technique — Movable Floor System (MFS). Besides self-cleaning characteristics, the AutoClean focuses on hands-free experience for toilet users, reducing the frequency of touching public installations such as handrails and doorknobs. All toilet facilities, including toilet doors, toilet seat covers and hand-washer, can be opened automatically without direct touch. In the fast-changing society pursuing better public hygiene, it is hoped that the AutoClean can provide an optimal user experience in public toilets physically and psychologically.

Categories
Undergraduate YPEC 2021

UG13-A Game Generator for Sliding Puzzles

A sliding puzzle, or sliding block game, is a very interesting and challenging game. It requires players to move one block horizontally or vertically without overlapping or crossing the game board in each step. The main target is to use as few steps as possible to reach an end configuration. Over the past few years, it has been proved that finding solutions to some sliding puzzles is an NP-hard problem, and some research work has been done to figure out solutions to all kinds of sliding puzzles. However, little work pays attention to developing an intelligent and compatible system that can automatically generate a series of sliding puzzles. In this project, a novel game generator for sliding puzzles is designed and implemented, producing different types of complex sliding puzzles with optimal solutions. In general, this powerful system is composed of three main components: (1) a pivotal algorithm that can conduct a complete search on configurations of various sliding puzzles and generate the corresponding game codes; (2) a compatible game framework that defines game logic of several sliding puzzles and can render the generated puzzles in real time; (3) an image interpreter that can process the image input, i.e., a hand-painted puzzle, and convert it into a numerical matrix in the pre-defined format of the pivotal algorithm’s input. Overall, plenty of methods and techniques are utilized, including the multi-source Breadth-First Search, fast hash operations, and image processing. As a result, a powerful game generator is achieved for generating three kinds of complex sliding puzzles with optimal solutions, i.e., Kltoski, 15-puzzle, and Sokoban. Besides, a complete search on Klotski is successfully carried out, generating the most complicated Klotski puzzle games. Additionally, it provides users with a platform to design and produce diverse sliding puzzles by processing and reading information from pictorial or text inputs.

Categories
Undergraduate YPEC 2021

UG21-Smart Traffic Control System

As one of the world’s most fast-paced cities, traffic congestion is serious and frequent in Hong Kong. It greatly hinders efficiency when traveling time is greatly increased. Nowadays, traffic signaling times at a junction is determined by the saturation flow of every possible route combination. However, there are many cases where instantaneous traffic flows on different parts of an intersection varies greatly. Inappropriate traffic signaling time leads to congestion on busy sides of an intersection. Smart Traffic Control System (STCS) is a solution to the problem. Two examples of STCS are Adaptive Traffic Signal Control (ATSC) and Emergency Vehicle Signal Preemption (EVSP). ATSC utilizes sensors and video analytics (VA) technologies to adjust the traffic signaling time at intersections. VA systems collect traffic flow data which is transferred to the ATSC system, which yields optimized signaling times. EVSP alerts drivers in the planned route of emergency vehicles so they can give way accordingly. Rescue services could be provided in a more timely manner. Our research aims to further look into the possible applications of STCS that can relieve traffic congestion in Hong Kong and its benefits.

Categories
Undergraduate YPEC 2021

UG20-University RPG

The global pandemic has changed the learning mode for tertiary education from semi-online learning (University’s Portal + Physical lesson) to full online learning on zoom. Universities and firms have adopted studying and working from home to adapt to the pandemic. Despite the fact that online learning is working for many academically under such extreme circumstances, it has side effects especially socially such as that the bonding among students and professors is very weak and there are not many effective opportunities for students to expand their social circle. To solve these issues, we propose an idea to integrate social interaction to online learning to expand the range of virtual university from only being academic to having more social opportunities which is a 2D role-playing game combined with 3D virtual rooms and zoom classes.This game could be simulated with the university background. Both students and professors could first customize their own characters and then walk around the virtual school campus with a keyboard or touchpad on the phone. With this, students can chat in the virtual hallways and have more interaction with other students in 3D activity rooms, enabling students to have opportunities to interact with others while having lessons as well.

Categories
Undergraduate YPEC 2021

UG19-Walking Assistant for the Visually Impaired with Hand-Held LIDAR through Machine Learning

There are around 18000 people in Hong Kong who are visually impaired. Walking around in the streets is an essential part of their daily life. They need help in walking from one location to reach their destinations in a safe manner. An affordable and reliable technological solution will improve their personal safety and their quality of life. In this project, a LIDAR augmented mobile device which aids visually impaired people for day and night navigation has been developed and evaluated. The application includes navigation in the streets, obstacle warning and avoidance, falling detection and rescue. These functions are interacted through suitable user interface including voice-over and voice control. The navigation in the street function exploits the Global Positioning System (GPS) and assists users with voice guidance. The obstacle warning and avoidance function indicates to the user if the obstacles are detected within a close range during the navigation. The falling detection and rescue function keeps tracing the visually impaired people for falling accidents. When a falling action detected, the emergency call will be triggered for rescue immediately. The device can operate day and night under the uncongested area, and it can be attached to a walking stick or hanging on the neck. In general, the mobile application was found to improve the mobility of the visually impaired and their experience of walking in the street.

Categories
Undergraduate YPEC 2021

UG18-Thermal camera temperature measurement system using embedded machine learning

Since 2019, COVID-19 has spread among different countries and seriously affected our daily life. To identify people with fever, there are several body temperature measurement methods on the market. However, these methods have different drawbacks on their efficiency, price, or privacy issue. Our project aims to use low-cost and portable hardware to build a body temperature measurement system. Our system has achieved 89.6% face detection accuracy, error of ±1.0°C in temperature readings, and a valid distance of 2.5 meters. The main difference between our system and the existing solution is that our system only captures low-resolution thermal images, and preventing privacy issues. The system captures thermal images through a thermal camera and passes them to a Raspberry Pi, and implements machine learning with the assistance of a USB accelerator in order to detect the position of the human face in the image. Finally, the target’s body temperature can be calculated.