Imagine you are in a heated debate with a friend, and tension seems to escalate until you two share common ground. A relationship you have been building with a friend, partner, or someone you are close to, and everything diminish at just a flick of a switch, and you are left with tears and repent. In relationships, minute details matter, hence the choice of words and your attitude are paramount. We would like to introduce Gentlelens, smart AR glasses powered by AI technology that capture body gestures and facial expressions to analyse people’s sentiments. Besides, they are capable of capturing audio to analyse prosody to determine sentiment; after further analysis, our AI will provide guidance to excel in every conversation and to retire social barriers. All in all, the data we will receive or share can be used to train a more humane AI to develop social skills with users on a more appropriate occasion. There is not always a second chance in relationships. So we are here to save the first. Join us as we give everyone a chance to thrive in every conversation so they can turn challenges into opportunities.
Category: Subdegree
The project introduces a novel Auditory Orientation Training System (AOTS) named SoundScene, designed to enhance spatial awareness and independent navigation for visually impaired individuals. This system, leveraging AI technologies and mobile platforms, consists of two interconnected applications—one for trainees and one for trainers—operating over a local WiFi network using peer-to-peer connectivity. The trainee application uses spatial audio and augmented reality (AR) to create a 3D virtual environment, enabling users to orient themselves using auditory cues. This is achieved through the device’s camera and motion sensors, which adjust the spatial audio output to simulate real-world auditory scenarios. The trainer application facilitates real-time monitoring and dynamic scenario adjustment, enhancing the training experience. SoundScene can function in both connected and disconnected modes, ensuring versatile use in various settings. Evaluated through qualitative and quantitative measures, the system demonstrated significant improvements in the orientation and mobility skills of visually impaired users. It offers a scalable, cost-effective solution that harnesses widely available mobile technology, opening new avenues for training and assistance for the visually impaired, while also benefiting professions requiring enhanced auditory orientation.
The integration of generative artificial intelligence (Gen AI) holds significant promise for future engineers, particularly in mastering and applying complex technologies. This paper presents nanoCraft, a 3D modelling application developed by students to aid their peers in Information and Communication Technology (ICT). nanoCraft serves as an example to address the challenges beginners face in 3D modelling, such as navigating technical intricacies and steep learning curves. The development team, initially without 3D modelling knowledge, undertook an extensive learning process covering essential concepts like defining vertex data structures and UV mapping. This app encapsulates the team’s educational journey, offering a user-friendly platform for creating low-poly models and custom textures. nanoCraft is tailored for ICT students who prefer hands-on learning. It supports the full creative workflow, from initial model creation to augmented reality (AR) visualisation. By using nanoCraft, students not only learn theoretical aspects of 3D design but also gain practical experience through active creation and experimentation. This experiential learning approach, facilitated by nanoCraft, demonstrates the powerful combination of learning and implementation enabled by Gen AI, paving the way for innovative advancements in engineering education.
Amidst Hong Kong’s intense summer heat, 2023 witnessed fatal heatstroke cases, highlighting the urgent need for effective occupational heat protection. The government’s “Heat Stress at Work Warning” system, derived from the Summer Heat Index, has been critiqued for its inadequate reflection of actual working conditions, constrained by a limited weather station network. This paper examines these limitations and underscores the necessity for a robust system to enhance city resilience against escalating temperatures from global warming and urban heat island effects. We developed an innovative heatstroke prevention strategy that leverages AI and IoT for precise, localised summer heat index forecasts. A proof-of-concept prototype has been developed, illustrating the feasibility of a sophisticated warning system. This approach aims to deliver accurate, real-time alerts, thereby offering a tailored protection for the workforce against the growing threat of heat-related illnesses in the face of ongoing climate changes.
According to the World Health Organization Road Traffic Injuries Fact Sheet, approximately 1.3 million people die yearly from road traffic crashes. In addition, the fact sheet shows that drivers using mobile phones are about four times more likely to be involved in a crash than drivers not using a mobile phone. Apart from this, dangerous driving behaviours and driver emotions are growing concerns for road safety. This project aims to develop a model for detecting unsafe driving behaviours and analysing driver emotions to avoid and minimise traffic accidents. We focus on detecting distractive behaviours, lousy driving practices, and abnormal feelings. An alert feedback will notify the driver when unsafe driving behaviours are seen. Furthermore, To mitigate the hardware requirement and disturb the driver, the detection framework will host to a cloud platform and connect with all cameras pre-installed in the car. We foresee that an innovative micro-service will monitor all driving behaviours in rented vehicles.
The project is a web application developed using Azure Open AI Service and Azure Static Web Apps Serverless infrastructure. The application’s goal is to improve student academic performance by leveraging the power of machine learning and artificial intelligence. The application features a chatbot powered by OpenAI’s GPT-3 language model, which can assist students in generating high-quality written assignments, understanding complex concepts, and providing personalized feedback. Furthermore, the model is bundled with awesome chatbot prompts, allowing the ChatGPT model to talk to provide different features with just a click. It also utilizes Azure Cognitive Services for tasks such as image recognition, speech recognition, and natural language processing. Additionally is deployed using Azure Static Web Apps Serverless infrastructure, which provides a fast and secure way to deploy and manage web applications. It also allows for easy scaling as the number of users and interactions with the application increases