News

PolyU research unveils hidden microbial threats to ecosystem caused by plastic waste, urging global collaboration to track harmful microbiomes

Plastic pollution is one of the most pressing environmental challenges, requiring in-depth analytical understanding and advanced technology-driven solutions. Prof. JIN Ling Nathanael, Assistant Professor of the Department of Civil and Environmental Engineering and the Department of Health Technology and Informatics at The Hong Kong Polytechnic University (PolyU), and his team have garnered international recognition for the research that sheds light on the often-overlooked microbial threats linked to plastic waste and provides insights for developing more comprehensive global strategies. More than 7 billion tonnes of plastic waste have been generated globally so far, with about 80% accumulating in the environment. As plastic waste continues to be produced and degrades at an extremely slow rate, the plastisphere is expanding rapidly. The plastisphere refers to the communities of microorganisms that colonise plastic debris in both aquatic and terrestrial environments. The plastisphere: an emerging microbial habitat Prof. JIN’s research provides a comprehensive overview of the plastisphere, revealing its unique and diverse microbial communities, which differ markedly from those in natural environments. By analysing samples from freshwater, seawater, and terrestrial environments worldwide, Prof. JIN’s research team found that these communities consist of fragile networks of specialised microorganisms, rarely encountered in nature, with a pronounced ability to decompose organic compounds, potentially accelerating carbon turnover. The study also highlights disturbances in the nitrogen cycle, especially in freshwater systems, where bacteria that release harmful substances such as nitrite and nitrous oxide thrive. Moreover, there has been a rise in harmful microorganisms, including pathogens that pose risks to animals, plants, and humans. These findings have been published in The Innovation, titled “Ecology and risks of the global plastisphere as a newly expanding microbial habitat”, which was recognised as the Most Popular Paper from 2020 to 2024. Prof. JIN said, “Plastic pollution has traditionally been evaluated primarily based on its physical and chemical impacts, such as marine animals becoming entangled in larger debris or fish and seabirds ingesting smaller fragments. However, it is now crucial to consider the microbial threats that plastics harbour. Plastics not only consist of various compounds but also provide nutrients for microbes, which can significantly influence biogeochemical cycling in terrestrial and aquatic environments.” The research team was also invited to publish a commentary in Nature titled “What are the harmful microorganisms in the world's 7 billion tons of plastic waste?”, offering insights into these critical issues. They indicated the fact that because the plastisphere is composed of plastic fragments ranging from micrometres to several metres in size, it can carry inhabiting microbiomes into ecosystems and the food chain through various pathways. Recent findings also showed that one square centimetre of the marine plastisphere can host more than 80,000 diatoms. Remarkably, one gram of marine plastic can contain up to ten times the microbial biomass found in a cubic meter of open ocean water. For instance, harmful algae such as Pseudo-nitzschia, which are known for producing the neurotoxin domoic acid responsible for amnesic shellfish poisoning, have also been observed thriving in the plastisphere. Geographic variation and human activity The severity of the plastisphere varies by geographic location and is closely linked to regional human activities, development, and environmental management. Additionally, ocean currents can concentrate plastics in specific areas, such as the Great Pacific Garbage Patch, leading to intensified plastisphere activity. The research team proposed four priorities for a new risk assessment. These include identifying hotspots with close interactions with humans and food security, such as aquaculture farms; protecting vulnerable sites such as wild coral reefs and wetlands, which are crucial for biodiversity, climate regulation, and are highly sensitive to pollution and microbial invasions; and targeting transportation areas where plastics accumulate, such as estuaries, wastewater treatment plants, and long-distance transport vessels. Lastly, special attention must be given to the food chain, as microplastics accumulate in everything from leafy vegetables to seafood, posing a direct threat to human health. Global cooperation, adapted to local contexts, is essential for effectively mitigating the environmental impacts of plastic pollution. For instance, in Asian cities like Hong Kong, developing a framework to assess plastisphere microbiomes requires tailored strategies that consider unique urban and coastal dynamics. This includes prioritising the monitoring of coastal and urban waterway using advanced technologies such as Geographic Information Systems (GIS), remote sensing, and nano-sensors connected through the Internet of Things (IoT). Mapping the trajectory of plastic debris Mapping the trajectory, transport dynamics, and fate of plastic debris carrying microbiomes across ecosystems, regions, and countries is a complex yet achievable task. Prof. JIN said, “It requires extensive international and interdisciplinary collaboration, along with the integration of advanced technology. A crucial component of this project is the standardisation of methods across different research endeavors and the establishment of a global data-sharing framework, both of which are essential for producing consistent, actionable insights.” Prof. JIN’s team is actively collaborating with global partners to collect plastic samples, create a comprehensive planetary catalogue of hazardous plastisphere microbiomes, and track the flow of associated risks. Additionally, leveraging existing research and models on plastic waste migration, fate, and accumulation, they are developing a model to assess and quantify the microbial impacts of plastic pollution. This model, based on existing plastic presence data and future emission scenarios, and will be validated through simulation experiments. The potential impacts of this mapping initiative on research and efforts to mitigate plastic pollution are profoundly transformative. Enhanced mapping and tracking will deepen our understanding of microbial migrations on plastics, enabling more accurate risk assessments and targeted interventions in critical areas. Consequently, this data could guide more effective environmental policies and public health strategies, particularly in regions most affected by plastic pollution. Recently, Prof. JIN has been awarded the 40 Under 40 Recognition Program by the American Academy of Environmental Engineers and Scientists (AAEES) for his contributions to advancing the fields of environmental science. For more: PolyU scholar's impactful interdisciplinary environmental research honored by the American Academy of Environmental Engineers and Scientists

The PolyU Industrial Centre initiates the Hybrid Immersive Virtual Environment for cancer children preparing for radiotherapy

The Hong Kong Polytechnic University (PolyU) Industrial Centre (IC) continues to be equipped with various advanced research facilities to meet the evolving needs of society, allowing students to learn in a comfortable environment. The Hybrid Immersive Virtual Environment (HiVE) at the IC stands as the world's first large-scale virtual hybrid classroom, which uses 15 projectors and employs a fully immersive six-sided Cave Automatic Virtual Environment technology to create a lifelike immersive virtual training setting. Students can immerse themselves in different scenarios while comfortably seated in the classroom, enhancing their flexible learning experience. Prof. Vincent Leung, Associate Professor of Practice of the Department of Health Technology and Informatics of PolyU, and his team utilised the HiVE to develop a project named "HEROCARE".  It is specially designed to support children undergoing cancer treatment. Through simulating the radiotherapy process, HEROCARE helped the children initially familiarise themselves with the process and understand the treatment conditions, machine operation and environment, ultimately reducing their anxiety. The HiVE has unlocked new possibilities for medical education, particularly underscored amidst the COVID-19 pandemic. Data shows that fewer than 10% of children aged 5 to 8 complete radiation therapy without anaesthesia. Remarkably, since the introduction of the "HEROCARE" program, over 86% of participating children have successfully completed treatment without anaesthesia. Many children have shared their sense of relaxation, actively interacting with therapists, and demonstrating increased confidence and a positive attitude throughout their treatment journey. Currently, HEROCARE has supported paediatric cancer patients and carcers in Hong Kong for radiotherapy preparation while also expanding its outreach. This holistic, empathy-focused model is scalable and sustainable, aiming to set new standards for ethical, patient-centred healthcare in paediatric cancer treatment.  

The PolyU Industrial Centre facilitates research transformation to benefit society

The Hong Kong Polytechnic University (PolyU) Industrial Centre (IC) not only fosters a focus on cutting-edge technologies among scientific researchers but also actively encourages their involvement in start-up ventures, transforming research outcomes into a driving force for the advancement of our society. Prof. Thomas Lee, Associate Professor of the Department of Biomedical Engineering of PolyU, and his team have been developing portable nucleic acid testing devices since 2014. The initial version of the device was employed in Gold nanoparticle-based loop-mediated isothermal amplification (Gold-LAMP) testing. With the technical support of the IC, the team successfully refined the device and collaborated with the Agriculture, Fisheries and Conservation Department for avian influenza detection. ️During the COVID-19 in 2020, there was a substantial increase in demand for rapid testing. The IC promptly produced 20 portable devices within a brief timeframe, introducing portable detection technology at the Emergency Department of Queen Mary Hospital to provide on-site and real-time support for epidemic prevention and control. This innovative technology enhances safety and stability while making a significant contribution to social health management. Prof. Lee emphasised that the IC provides extensive support, guiding projects from conceptualisation to final product implementation and offering expert guidance at every stage. With the greatest assistance from PolyU and the IC, Prof. Lee established a start-up to commercialise the developed technology. In addition to medical applications, the team has also developed nucleic acid detection technology for non-medical applications including testing for food safety and public environmental hygiene, transforming research into practical societal benefits.  

PolyU signs strategic agreements with China Railway Electrification Group to establish joint research laboratory

Chinese only

PolyU supports seven collaborative projects to advance research in health, energy, and computing with world-class partners

The Hong Kong Polytechnic University (PolyU) has been actively promoting interdisciplinary international research collaborations and developing innovative projects with a global perspective. PolyU recently supported seven academics in advancing projects across various fields, collaborating with renowned partner institutions through the “Collaborative Research with the World's Leading Research Groups 2024/25” scheme, with a total grant of HK$9.5 million. The awarded projects cover a range of research areas, including offshore renewable energy infrastructure, new computational methods and numerical analysis for dispersive and wave problems, and a multilingual speech brain-machine interface. One project focuses on developing a research platform for dual-atom catalysts. These projects are conducted in collaboration with scholars from top institutions, including the University of Edinburgh, the University of Cambridge, University College London, and Peking University. In the field of health and medical care, one project will explore AI-driven biomedical simulation, in collaboration with Johns Hopkins University. Another project, conducted in collaboration with the Icahn School of Medicine at Mount Sinai, aims to develop an AI-driven, single-cell-based spatial transcriptome profiling platform for research on melanoma, lung cancer and depression. In addition, a project will join hands with Zhejiang University to establish a joint research centre on brain-inspired computing. Launched by PolyU, this funding scheme aims to encourage academics to pursue joint research projects or establish research centres in targeted subject areas in collaboration with world-leading research institutions. Each successful applicant will receive a grant of up to HK$2 million.

PolyU unveils large language model-based tourist satisfaction index, providing comprehensive analysis to enhance Hong Kong tourism service quality

As tourism, one of the major pillars of the Hong Kong economy, gradually recovers from the pandemic, the government has planned a series of measures to promote the all-round development of the tourism industry. The Research Centre for Digital Transformation of Tourism (RCdTT) of The Hong Kong Polytechnic University (PolyU) School of Hotel and Tourism Management (SHTM) has developed an innovative, large language model (LLM)-based assessment framework – the Hong Kong Tourist Satisfaction Index (HKTSI) – to evaluate the satisfaction level of inbound tourists to Hong Kong from 2012 to 2024 across different tourism-related sectors, temporal scales and regions. Findings reveal that, while performance variations across different regions were clearly indicated, the TSI rebounded and reached its highest-ever recorded score after the temporary decline during the pandemic. Under the leadership of Prof. Haiyan SONG, Principal Investigator and SHTM Associate Dean, RCdTT Director and Mr and Mrs Chan Chak Fu Professor in International Tourism, the TSI was initially introduced in 2009, using a questionnaire-based methodology to evaluate tourists’ satisfaction with various tourism services. Seeking to provide a more comprehensive and accurate analysis, the team has transformed the framework by adopting an interdisciplinary approach that integrates theories from management science, economics and computer science, and leveraging the advanced LLM technology. The enhanced TSI framework offers multi-dimensional analysis, enabling TSI measurement across different dimensions (such as service topics, service sectors and trip types), temporal scales (monthly and annually) and regions. This adaptable approach provides stakeholders with timely, data-driven insights to guide service improvement, policy development and strategic decision-making. Prof. Kaye CHON, SHTM Dean, Chair Professor and Walter and Wendy Kwok Family Foundation Professor in International Hospitality Management, said, “Hong Kong’s competitiveness as a global tourism hub hinges on it delivering exceptional service quality that meets travellers’ expectations. The RCdTT-SHTM’s ongoing development of the TSI underscores our commitment to advancing Hong Kong’s reputation as a world-class destination for international visitors.” The team gathered over 1.25 million reviews from TripAdvisor, a global Online Travel Agency (OTA) platform, covering 13,694 Hong Kong service providers across five tourism service sectors, namely attractions, hotels, restaurants, retail shops and transportation. The LLM-based assessment framework then utilises Alibaba’s open-source General Text Embedding model to extract semantic insights from the visitor reviews in different languages and formats. Key findings include: 1. Topic-based analysis reveals that the largest proportion of reviews are about “service reliability and safety”. This reflects that reliability in tourism services emerged as the most crucial factor influencing tourist satisfaction, forming the foundation of trust in the travel industry. 2. Since 2012, the Hong Kong TSI has shown an overall upward trend, while consistently scoring above 75 points on a 0-100 scale for the past decade. Despite a temporary decline during the pandemic, Hong Kong TSI levels had fully recovered to pre-pandemic levels in 2024. 3. Notably, the transportation sector has consistently achieved high TSI scores, largely due to Hong Kong’s well-developed public transport infrastructure, which continues to enhance visitor experiences. Retail shops and restaurants, on the other hand, have lagged behind, primarily owing to price-related factors. The traditional price advantage of retail shops is gradually diminishing, significantly impacted by the rise of e-commerce. Similarly, restaurants in Hong Kong tend to be relatively expensive, prompting some tourists to seek more affordable dining options on the mainland. Figure 1: TSI at destination and sector levels 4. From a spatial perspective, all districts recorded TSI scores above 73 points, yet a north-south divide persists, with higher satisfaction levels in the southern regions and lower levels in the north. The highest TSI values were concentrated along both sides of Victoria Harbour, such as in the Central and Western, and Yau Tsim Mong Districts, while Kowloon City District recorded considerably lower TSI levels, creating a distinct localised satisfaction gap compared to its surrounding districts. Figure 2: TSI Spatial distribution 5. Tourists with different trip types exhibit significant variations in their satisfaction levels towards Hong Kong. Business tourists generally report the highest satisfaction across most sectors, whereas solo travellers exhibit lower satisfaction overall. This may be due to their different needs: business tourists typically prioritise standardised functional requirements, while the solo travellers place greater emphasis on unique and personalised experiences.  6. Language-based analysis further highlights differences in the TSI, with reviews in English and European languages yielding higher satisfaction levels than the Japanese- and Korean- language reviews. This highlights the impact of cultural differences on tourist satisfaction. Objectives of the TSI The LLM-based TSI framework is crafted to deliver regular, data-driven insights that benefit tourism service providers, policymakers and destination management organisations. Through topic-level TSI analysis, for instance, businesses can pinpoint specific areas for service enhancement, while destination- and sector-level assessments provide a broader perspective for strategic planning and policy formulation. Additionally, monthly TSI updates ensure that assessment results remain timely and relevant, enabling swift and informed decision-making. Although the Hong Kong economy has largely recovered from disruptions caused by the pandemic, challenges such as labour shortages, supply constraints, changing economic conditions, evolving consumer behaviour and competition persist. Highlighting the significance of the TSI in tackling these challenges and facilitating relevant decision-making and planning, Prof. Song remarked, “To sustain ongoing recovery, accurate and timely assessment of the satisfaction level of inbound tourists is essential for policymakers and industry practitioners to develop sustainable tourism strategies that will further fortify Hong Kong’s tourism advantages, propel its tourism industry and ultimately promote long-term economic growth in the City.” As technology advances, both destinations and visitors increasingly rely on information and communication technologies to make their decisions. In support of the long-term sustainability of the tourism sector, by harnessing artificial intelligence, LLM and big data analytics, the enhanced TSI assessment framework aims to offer more precise and targeted advice for strengthening tourism service quality and bolstering Hong Kong’s global competitiveness.

PolyU nine projects awarded the Environment and Conservation Fund

The Hong Kong Polytechnic University (PolyU) has been dedicated to conducting research in the field of environmental protection and nature conservation, contributing to the sustainable development of Hong Kong. PolyU nine projects have been supported by the Environment and Conservation Fund, with a total grant of approximately HK$6.99 million. Led by scholars from the Faculty of Construction and Environment, the Faculty of Engineering, and the Faculty of Science, the awarded projects aim to advance environmental protection and conservation efforts through cutting-edge technologies and innovative research. These projects include developing a real-time platform for carbon monitoring, creating novel noise reduction barriers, investigating atmospheric oxidation capacity, and designing structures for carbon-neutral construction. Additionally, they focus on the formation of secondary organic aerosols, sound absorption, noise prediction, the conversion of CO₂ into sustainable methanol, and simultaneous solar desalination with hydrogen production. The Environment and Conservation Fund provides funding support for educational initiatives, community waste reduction and recovery, research, technology demonstration, and other projects related to environmental and conservation matters. The awarded project must help enhance the overall environmental quality of Hong Kong, raise environmental awareness of the local community, and promote public participation in green and low-carbon living.

PolyU’s AI and medicine-engineering integration empowers a new era of medical excellence

The Hong Kong Polytechnic University (PolyU) is committed to harnessingmedicine-engineering integration and adoption of artificial intelligence (AI) in healthcare to drive innovations and translation of research outcomes into real-world solutions. These efforts support the development of precision medicine, preventive medicine, and primary healthcare, thereby enhancing the quality and efficiency of healthcare services in Hong Kong and the Greater Bay Area (GBA), while also contributing to Hong Kong’s development into an international health and medical innovation hub. PolyU has established a strong foundation in medical and health research, supported by key infrastructure, including seven relevant research institutes and centres under the PolyU Academy for Interdisciplinary Research, 19 university-level research institutes and centres, and four University Research Facilities. By integrating expertise from engineering, medicine, and public health, these facilities drive the development of innovative solutions to advance healthcare in Hong Kong and beyond. PolyU encourages interdisciplinary research that combines healthcare with AI, engineering, and data science. The newly-established PolyU Academy for AI empowers researchers to conduct research that integrates medicine and engineering. This initiative accelerates the deep integration of AI across key fields, including drug discovery, mental health, medical imaging, radiotherapy, Chinese medicine, biomedical engineering and cell immunotherapy. PolyU continues to attract world-class scholars to spearhead interdisciplinary research at the convergence of medicine, AI, engineering, and data science, pioneering a new era of healthcare innovation. The University has achieved notable success in securing funding for health and medical research, ranking first in Hong Kong for both the number of projects and the amount of funding received from the Collaborative Research Fund under the Hong Kong Research Grants Council (RGC), with 14 projects in the 2024/25 exercise. PolyU also ranked second among local tertiary institutions in terms of total RGC funding in 2023/24. Over the past five years, several of PolyU’s health and medical research projects have received RGC funding. Between 2018 and 2022, the University also ranks third among local tertiary institutions in terms of average funding secured from the HKSAR Government’s Health and Medical Research Fund. Prof. Christopher CHAO, PolyU Vice President (Research and Innovation) said, “PolyU adheres to a patient-centred approach, leveraging our strengths in medicine-engineering integration and AI-driven healthcare to advance medical innovation and knowledge transfer. With our world-renowned researchers, state-of-the-art research facilities, and extensive experience in medical education – particularly in training allied healthcare professionals – PolyU is confident in its ability to establish Hong Kong’s third medical school. We look forward to cultivating the next generation of clinician-scientists who will pioneer medical breakthroughs, ultimately contributing to the global vision of ‘Health for All’.” PolyU today showcased four outstanding research projects. AI-assisted radiotherapy support system to enhance treatment outcomes through precision medicine Lung cancer is the leading cancer killer in Hong Kong and worldwide, and radiotherapy is one of the most common forms of cancer treatment. A team led by Prof. CAI Jing, Head and Professor of the PolyU Department of Health Technology and Informatics has developed an AI-assisted lung radiotherapy support system that can automatically analyse patients’ CT scan images and create lung ventilation and perfusion maps without the need for contrast agents. It distinguishes the functions of different lung regions for designing optimal personalised radiotherapy plans through an innovative “function-guided” approach. This method avoids high-functioning lung areas and reduces radiation damage to the patient’s lungs, thereby improving post-operative quality of life. The team collected CT scan images from over a hundred lung cancer patients to train the AI model and employed cutting-edge image processing algorithms to ensure high accuracy and consistency. The system featured a user-friendly interface and a powerful backend and is compatible with major hospital operating systems. The team is currently collaborating with several local and mainland hospitals for clinical trials. They also plan to develop AI models for “function-guided” radiotherapy for liver and brain cancers. This innovation won a Silver Medal at the 50th International Exhibition of Inventions Geneva. Prof. Cai Jing and his team have developed an AI-assisted lung radiotherapy support system that can automatically analyse patients’ CT scan images and create lung ventilation and perfusion maps without the need for contrast agents. It helps design personalised optimal radiotherapy plans that avoid high-functioning lung areas and reduce radiation damage to the patient’s lungs. AI-assisted non-invasive angiography to help overcome the bottleneck of traditional diagnostic approach Diabetic retinopathy is a leading cause of blindness globally. The traditional diagnostic approach relies on fluorescein angiography, which is invasive, expensive and causes patient discomfort, putting constraints on primary healthcare screening capacity. A team led by Prof. HE Mingguang, Director of the PolyU-Wuhan Technology and Innovation Research Institute, Henry G. Leong Professor in Elderly Vision Health, Chair Professor of Experimental Ophthalmology of the PolyU School of Optometry, Director of the Research Centre for SHARP Vision and Global STEM Scholar, has leveraged Generative AI technology to facilitate the diagnosis of eye diseases. Their innovation marks three significant breakthroughs. Firstly, it converts fundus photographs to high-precision angiographic images and dynamic videos within a couple seconds, eliminating the risks associated with traditional dye injections. Secondly, its smart diagnostic system enables early detection of pathological changes on the retina such as microaneurysms and retinal hemorrhages, with a sensitivity of 96.2% and specificity of 91.8%. Thirdly, by incorporating ultra-widefield imaging technology, it expands the detection area by 300%. The innovation has already secured five different international patents and is now undergoing multi-centre clinical trials in top medical institutions in GBA. Its teleconsultation system also enables patients in remote areas to receive ophthalmic diagnostic services. This breakthrough research won the Special Merit Award from French Inventors Federation and Europe-France Inventors and a Gold Medal with Congratulations of the Jury at the 50th International Exhibition of Inventions Geneva. Prof. He and his team have leveraged Generative AI technology to facilitate the diagnosis of eye diseases. It converts fundus photographs to high-precision angiographic images and dynamic videos within couple seconds, enables early detection of pathological changes on the retina such as microaneurysms and retinal hemorrhages, and expands the detection area by incorporating the ultra-widefield imaging technology. Embodied intelligent ankle rehabilitation robot to assist stroke patients with home-based rehabilitation Strokes pose a significant health challenge in an aging society, particularly for patients with mobility difficulties and those bedridden for extended periods. These patients require ongoing and repetitive rehabilitation training to prevent joint contractures and excessive muscle atrophy. A team led by Prof. ZHANG Dan, Director of the PolyU-Nanjing Technology and Innovation Research Institute, and the Consortium for Intelligent Robotics Research, and Chair Professor of Intelligent Robotics and Automation of the PolyU Department of Mechanical Engineering, has developed a first-of-its-kind robot product with three degrees of freedom (3-DoF) to provide comprehensive ankle rehabilitation. The robot assists patients with restricted ankle joints in home-based rehabilitation and aids in post-operative ankle joint functional rehabilitation for patients with cerebral hemiplegia and stroke. By integrating embodied intelligence technology and 3-DoF design, the robot can meet the rehabilitation exercise needs of different patients at different stages of rehabilitation. It uses sensors to track and adjust the ankle position for rehabilitation training and simulates natural movements such as dorsiflexion/plantarflexion, inversion/eversion, and internal/external rotation according to different scenarios. In addition, the robot can collect muscle activity data through electromyography signals, enabling real-time monitoring and adjustment of speed and force to tailor the training intensity and mode. The team is currently conducting clinical trials in collaboration with Huashan Hospital in Shanghai and plans to apply AI to offer personalised training for patients. This innovation holds significant potential for rehabilitation of the shoulder joint or hand. Prof. Zhang Dan and his team have developed the first-of-its-kind robot product with 3-DoF to provide comprehensive ankle rehabilitation. The robot assists patients with restricted ankle joints in home-based rehabilitation, and aids in post-operative ankle joint functional rehabilitation for patients with cerebral hemiplegia and stroke. Ultrafine high-sensitivity optical fibre sensor to enhance precision of cochlear implantation surgery The World Report on Hearing from the World Health Organisation indicates that hearing impairment affects over 1.5 billion people globally. However, due to the complexity of cochlear implantation surgery, only 1.5 million such procedures have been performed during the past 45 years. A team led by Prof. TAM Haw Yaw, Chair Professor of Photonics of the PolyU Department of Electrical and Electronic Engineering and Associate Director of the Photonics Research Institute has overcome the technical bottleneck of excessive rigidity in traditional glass optical fibres. The team developed an ultrafine, biocompatible plastic optical fibre sensor and integrated it into the cochlear implant electrode arrays to enhance surgical navigation and reduce trauma during cochlear implantation procedures. As the electrode arraymust be precisely inserted into the scala tympaniof the human ear, the integrated optical fibre sensors help guide the electrode array and monitor contact force during the implantation process. By integrating the novel fibre sensor into commercial electrode arrays, real-time adjustments to the electrode array’s bending angle can be made to further minimise tissue damage. With the technology patents filed, the team is collaborating with the renowned implantable hearing solutions company Cochlear Limited, the University of Melbourne, and the Royal Victorian Eye and Ear Hospital to advance its clinical trials and commercialisation. The team also plans to develop an AI model to enable robots to perform hearing restoration procedures, further enhancing their efficiency, safety, and precision. This invention won the Thailand Award for the Best International Invention and Innovation and a Gold Medal with Congratulations of Juryat the 50th International Exhibition of Inventions Geneva. Prof. Tam Haw Yaw and his team have developed an ultrafine, biocompatible plastic optical fibre sensor and integrated it into the cochlear implant electrode arrays to enhance surgical navigation and reduce trauma during cochlear implantation procedures. Dr Cui Jingxian (pictured) who participated in the research introduced the project details.

Media interview: PolyU develops AI platform to preserve and promote Cantonese Porcelain art

As the number of people learning the art of Cantonese porcelain diminishes, a research team led by Prof. Henry DUH, Associate Dean (Global & Industry Engagement) and Professor of the School of Design at The Hong Kong Polytechnic University, has developed a creative painting platform named “Beauty of Cantonese Porcelain.” It seamlessly blends the essence of traditional Cantonese porcelain art with cutting-edge generative artificial intelligence (AI), forging new pathways for preserving and promoting this precious intangible cultural heritage. “Beauty of Cantonese Porcelain” leverages generative AI to precisely control creative details, significantly reducing the time and effort traditionally required for creating Cantonese porcelain. In a recent media interview, Prof. Duh shared that the platform provides real-time evaluation and targeted guidance through a large AI model. This interactive and personalised feedback enhances users’ skills, makes the art form more accessible, and encourages creative expression, all while supporting the preservation of this intangible cultural heritage. Generative AI has not only revolutionised traditional art teaching methodologies but has also dramatically improved the efficiency of cultural transmission, unlocking unprecedented possibilities for artistic creation. Prof. Duh highlighted that collaborations with museums and cultural preservation organisations will further refine and validate the platform’s innovative approach, extending its benefits to a wider range of intangible cultural heritage.   

PolyU develops innovative Language Model Linguistic Personality Assessment system, advancing AI for diverse applications in manufacturing, business and education

Large language models (LLMs) are at the forefront of artificial intelligence (AI) and have been widely used for conversational interactions. However, assessing the personality of a given LLM remains a significant challenge. A research team at The Hong Kong Polytechnic University (PolyU) has developed an AI-driven assessment system, the Language Model Linguistic Personality Assessment (LMLPA), with capabilities to quantitatively measure the personality traits of LLMs through linguistic analysis. This innovative interdisciplinary research in AI and computational linguistics has led to the development of robust, data-driven AI tools for evaluating nuanced LLM personality traits and behaviours. The LMLPA system represents a critical step forward in understanding LLMs and developing them to be more aligned with human values and needs. Led by Prof. Lik-Hang LEE, Assistant Professor of the PolyU Department of Industrial and Systems Engineering, the research has been published in Computational Linguistics. LMLPA is designed to evaluate and characterise the personalities of LLMs by examining the linguistic patterns, style and other language-related features in their outputs. The system comprises two main components: the Adapted Big Five Inventory (Adapted BFI) and the AI rater. LMLPA first administers the Adapted-BFI, which is derived from previous language-based personality assessment theories, to LLMs. The AI rater then evaluates the responses, converting the textual answers into quantifiable numerical values representing personality traits. This innovative technology not only advances human-centred AI and computational linguistics by providing a robust framework for refining AI personality assessments, but also applications in various fields, including education and manufacturing, as well as in business such as by helping companies with compliance requirements and Environmental, Social and Governance reporting. It also supports sustainable development goals and the enhancement of legal services. Prof. Lee said, “In addressing the limitation of LLMs in capturing the cognitive and affective dimensions of human personality, our team has successfully developed novel assessment tools to evaluate LLM personalities in linguistic terms, aligning with their functional capabilities and operational paradigms.” The research opens up new possibilities of understanding and interacting with AI. By quantifying LLM personalities, their communication styles for specific applications can be tailored, paving the way for more personalised interactions between humans and machines. Prof. Lee has translated the technological foundations of his research to create an AI-driven business compliance platform. Leveraging natural language processing, the platform can analyse and interpret large volumes of textual data and reports, including those generated by LLMs. AI technology is used to perform automated data collection, analysis and insight generation, significantly streamlining the business compliance and reporting process. The integration of LMLPA highlights AI’s nuanced capabilities in assessing language-based personality traits, suggesting potential applications in the analysis of qualitative business and human data.