Prologic Robotics is a local brand based in Hong Kong, established in 2010. The Prologic Robotics brand team focuses on developing cutting-edge intelligent automatic robots and launched the intelligent automatic vacuuming robot in the same year, committed to simplifying people’s lives through technology. In order to expand its influence in the market, we have conducted market analysis of Prologic using IBM data analysis technology. Firstly, we collected and organized a large amount of market data, including market share, consumer demand, and competitors’ information, based on its target market (Hong Kong). Secondly, we conducted descriptive statistical analysis to help Prologic understand the basic features of the data, such as mean, median, standard deviation, and the distribution of the data, in order to better understand market trends and consumer demand. Then, we used time series analysis, regression analysis, and machine learning algorithms to conduct predictive analysis, which helps the Prologic brand predict future market trends. Finally, we conducted market data mining for Prologic, helping the company discover patterns and relationships hidden in the data. In the future, in order to expand Prologic’s market competitiveness, we will continue to collect and organize market data from foreign markets (such as Seoul, Tokyo, Taipei, and Singapore) that Prologic benchmarks against, and continue to track and analyze Prologic’s market performance using IBM data analysis technology, providing more specific and accurate market analysis reports for the company. We believe that through these market analysis efforts, Prologic will be able to better meet consumer demand, improve market competitive-ness, and achieve sustainable development.
Based on the literature review, researchers reported that at most, 24.6% of young children in the world were estimated to have speech delay or speech sound disorder (SSD). Once children with SSD are identified, speech-language pathologists (SLPs) select initial therapy programs for children with regular review and adjustments on therapy. The success of therapy highly re-lies on the effectiveness of long-term home training. In this project, we carry out human voice analysis and design and implement a virtual teacher for home training in speech therapy. For the first part of this project, we conduct a sound analysis research to see if children’s Cantonese pronunciation is correct. Once the children’s voices are captured, human voices can be automatically transferred for waveform analysis, allowing a large number of tasks to be completed quickly. The created waveform is compared to the standard waveform. If the majority of the waveform is inconsistent, it suggests that the pronunciation of children is not standard. As a result, it points out children’s pronunciation problems and generates feedback quickly. Through the waveform diagram, our system can accurately process and analyze the sound, as well as eliminate the inaccuracy caused by varied timbres of children, making the analysis more accurate and effective. For the second part of this project, we implement a virtual teacher to carry out training for speech therapy. It can achieve low-cost popularization, timely correction of children’s pronunciation problems.
Nowadays, mobile games are commonly used for children training and therapy. Literature show that multisensory activities help raise the children’s interest in their learning, raise their concentration and reinforce their memories. Portable multi-sensory games can provide an immersive training environment for children anywhere. In this paper, we design and develop a portable multisensory educational game, Fun2Write, to help children to learn and recognize Traditional Chinese words. It could also help to evaluate how effective it is on encouraging children to learn and effectiveness of game-based inter-active teaching method. The game mechanism is based on whack-a-mole game, each mole holds a card with a Chinese character, players have to whack the correct mole in order to gain points, which is the metric to assess how well does the player recognize Chinese characters. Unlike conventional control such as mouse, keyboard or screen tapping, Fun2Write utilize con-troller that has in-built gyro system (Such as Nintentdo’s Joycon) to simulate real life mole-whacking experience. The controller’s mechanism is similar to laser-pointer, which allows pointer movement in 3D space, and accurately tracks the movement of the players hand and adjust the pointer’s position accordingly. When the pointer hovers above the mole. Upon locking onto the target, the player can then perform swinging gesture to simulate swinging a hammer, this design is intuitive and help reducing cognitive load on re-learning controls. The game can be accessed on most of the hardware such as smart phone and computer. To extend the portability, we design and develop a low-cost portable cave by using projectors. The output results demonstrate the effectiveness of a portable immersive environment application.
Safe-3 aims to revolutionize the construction industry in Hong Kong by leveraging blockchain technology to create a secure and efficient system for managing worker safety training and certifications. By using non-fungible tokens (NFTs) and smart contracts, Safe-3 will automate the verification and enforcement of safety requirements, reducing human errors and ensuring compliance with industry standards. This will result in reduced workplace accidents, increased trust in worker qualifications, and streamlined safety management processes.
The Government plans to renew the Kowloon City district (The KC-017 scheme). In order to preserve the history of the Old Kowloon City and promote Sustainable development goals for sustainable cities and communities, “VR Metaverse in Kowloon City” is created. The 3D model of the four key historical buildings namely Lok Sin Tong Primary school, Kowloon Walled City Park, Wong Chun Chun Thai Restaurant and Kowloon City Hospital were built and virtually presented. Mini-games and interactive education activities are incorporated in the project to make it more interesting and to allow player to get familiar with the unique characteristics of Kowloon City. For example, in the chat room, users may share their experiences inside the Kowloon City as if they were meeting face-to-face. Users may “walk” inside the Lok Sin Tong Primary School to visit the school using the first-person view. They may also “walk” the Kowloon Walled City Park, and collect the play cards which show the lifestyle of the locals in 90s. In the famous Thai Restaurant, user may even “order” the dishes and experience the Thais living in Kowloon City. It is hoped that this project can help promote the importance of history conservation among the public.
MedMate is a user-friendly medication management solution designed for seniors. It ensures medical compliance by providing timely reminders and clear instructions. The system includes an Electronic Health Record (EHR) platform that connects patients, doctors, and pharmacists, facilitating data sharing and adherence tracking. The dispenser, refilled by pharmacists, has clearly labeled compartments for safe storage and accurate medication. It dispenses pills automatically at the correct time, with reminders provided through a red light, verbal announcements, and SMS for compatibility with older mobile devices. MedMate includes sensors to ensure pill count accuracy and to check if medication has been taken. Unused pills are automatically disposed of after 30 minutes to prevent confusion. The system is set up by placing labeled drug bottles into corresponding racks. As doctors update medication details in the EHR system, pharmacists refill the bottles accordingly. The app generates reports of patients’ medication patterns, shared with doctors through the EHR system. Ideal for seniors dealing with polypharmacy, MedMate can be set up remotely by pharmacists, and the dispenser’s racks are detachable for easy refill. The service operates on a monthly subscription model, providing flexibility for users..
To gain a better understanding of cancer development and the efficacy of therapies, it is crucial to analyze the tumor microenvironment. The abundance of immune cells is a key indicator that heavily influences clinical decision-making. However, direct measurement of immune cell abundance is challenging, thus specific algorithms are usually used to give some insights to the situations. Unfortunately, existing methods are limited in the number of cell types they can infer and the ability to generalize. To address these limitations, here we present a novel algorithm to infer fractions for various cell types from bulk data and try to lower the barriers to fit the models in a wider range of conditions to enhance the convenience of the tool for potential users. The methods will mainly be based on multiple advanced machine learning techniques. Models trained on datasets across multiple cancer types will be provided for rapid inference. Our tool also offers greater flexibility than others, as users can train their own models using our baseline logics. With our algorithm, users can obtain relatively reliable cell type fraction results conveniently and cost-effectively.
WasteWise provides a broad solution to the issue of household waste management. The app covers different aspects of waste management, including waste monitoring and sorting, reporting and analytics, and optimization. With WasteWise, users can monitor the waste sorting process in real-time, making sure that waste is sorted in the correct place efficiently. The app also provides feedback to users, generating reports based on their waste sorting performance and offering suggestions for improvement. In addition to waste sorting monitoring and user feedback, WasteWise also includes optimization features. These features allow users to optimise their waste management processes by providing data-driven insights into how to reduce waste, increase recycling rates, and improve overall efficiency. It also provides a monthly report that analyses users waste habits, enabling users to make informed decisions about waste management. This app is designed to be user-friendly and can be further made accessible to a wide range of users. The app provides information on waste management systems, including waste collection trucks, recycling centres and waste-to-energy facilities in Hong Kong. With the smart waste management app, users can take control of their waste management processes, reduce waste, and contribute to a cleaner, more sustainable environment.
A fundamental problem of the aquaponics system in CUHK Smart Garden is the lack of automation strategies. Significant risks will be posed to the fish when the system is subject to uncertainty. This project aims to construct an online management platform for the aquatic environment using data analytics and the Internet of Things (IoT). The acquired water quality parameters from multiple sensors were collected by an Arduino board and transmitted to an ESP micro-controller. The controller would then be connected to a mobile application and a cloud server through wi-fi. Whereas the former unit allowed user to remotely track the health of the system, the latter one was used for data storage. If the received data did not match with the optimal value, signals would be sent to both the application and the actuators to balance the conditions through automatic fish feeding and temperature compensation. The proposed monitoring and control strategies could reduce manual operation and the loss of fishes, increasing the overall efficiency and sustainability of the system. The efficacy of the design has been validated by the experimental results.