Artificial Intelligence

A new study highlights how machine learning can effectively identify key factors influencing rice yield for over five decades, emphasizing the importance of tailored management practices and varietal replacement as a response to climate change.

On 19 August, World Humanitarian Day, Lingnan University announced the signing of an Agreement of Cooperation with the United Nations University (UNU) to establish the UNU Hub on Humanitarian Innovation and Technology at Lingnan University (UNU Hub at Lingnan University), making it the first higher education institution in Asia to set up a UNU Hub. The Hub is scheduled to open officially in October 2025 and will have an annual operating budget of over HK$8 million. Its Humanitarian Innovation and Technology Laboratory (HIT Lab) will spearhead research and design initiatives, education and training programmes, and international collaborations, and improve living conditions in developing countries and regions of the Global South by leveraging innovative and cutting-edge technologies. Scholarships will be awarded to encourage local youth to fulfil their ambitions through knowledge and innovation.

Sensitive region detection for improved non-invasive cattle monitoring

Lingnan University's science and innovation teams have achieved outstanding results at the 11th Silicon Valley International Invention Festival 2025 (SVIIF) in their first-ever participation. All 13 participating projects, covering areas such as artificial intelligence (AI), smart manufacturing, and intelligent transportation, won awards, including 8 gold and 5 silver medals. One of the projects, the AI-based Fencing Training and Assessment System, led by Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), also received a special award ⸺ Prize of the International Federation of Inventors’ Association (IFIA), making Lingnan the Hong Kong higher education institution that won the highest number of total awards and gold medals at this year’s festival.

From a seed-inspired design to a 26-minute flight time on a single rotor, a new monocopter developed by SUTD researchers marks a 10-year journey towards redefining how efficient small flying robots can be.

Scientists found three language-model chatbots — even with advanced prompt‐engineering tricks — often give suboptimal guidance across stroke prevention, diagnosis, treatment and recovery, highlighting the need for human oversight to ensure appropriateness and safety.

The Ateneo de Manila University’s Business Insights Laboratory for Development (BUILD) is looking at ways for artificial intelligence (AI) to enhance human labor in small businesses, which make up the bulk of the Philippine economy.

- DGIST research team led by Yoonhee Lee and Gyogwon Koo enhances lung cancer diagnostic accuracy by combining exosome physical properties with AI. - The research also proposes the potential for rapid and precise liquid biopsy-based lung cancer diagnosis without fluorescent labeling.

Using AI to decode system diagrams and simulate nine policy scenarios for better material reuse and resource efficiency.

Researchers at The University of Osaka developed a deep learning model for rapid building damage assessment after floods using satellite imagery. This research establishes the first systematic benchmark for this task and introduces a novel semi-supervised learning method achieving 74% of fully supervised performance with just 10% of the labeled data. A new, lightweight deep learning model named Simple Prior Attention Disaster Assessment Net or SPADANet significantly reduces missed damaged buildings, improving recall by over 9% compared to existing models. This work provides crucial design principles for future AI disaster response, enabling faster and more efficient life-saving operations.

To promote equality in education and allow aspiring creators to learn about film production without physical equipment, a team from the Department of Digital Arts and Creative Industries at Lingnan University has spent two years developing CineSim, the world’s first cinematography simulation education software. CineSim enables hands-on filmmaking skills to be learnt easily using computer simulation and eliminating the need for professional studios and camera equipment. The project was supported by a subsidy of approximately HKD $800,000 from the University Grants Council (UGC), and is now freely available to all Lingnan staff and students. The team will market the software to secondary schools and the film production industry to encourage Hong Kong’s creative talents. In mid-June, the full version of CineSim was officially launched on Steam, one of the world’s largest digital game distribution platforms for PC gaming, a significant move into the international market.

Researchers at The University of Osaka have developed a novel framework for measuring occupancy in open-plan offices with unprecedented precision. This innovative system uses computer vision and AI to analyze occupancy at a micro-scale level, focusing on specific functional zones within the office. This addresses a significant gap in current occupancy tracking methods, which typically only provide macro-level data and struggle to capture detailed usage patterns within shared spaces.

Lingnan University, in partnership with Times Higher Education (THE), launched Digital Universities Asia 2025 on 8 July at its Tuen Mun campus. Held over two days, 8-9 July, the summit was themed “Powering social innovation with digital transformation”, and brought together more than 300 leading scholars, industry leaders, and policy experts from over 90 universities and 140 organisations worldwide. Participants looked at how emerging technologies, and particularly artificial intelligence (AI), can transform teaching and learning, and promote sustainability and social progress.

Researchers from The University of Osaka have developed a method to visualize and reconstruct individual urban plants in different seasons using AI and street view images. The novel Seasonal Species-Specific Plant View Index allows urban designers to enhance the ecological sustainability and the well-being of city dwellers by incorporating diverse plant configurations, colors, and seasonality into current and future urban green spaces.

Lingnan University in Hong Kong welcomes the Audit Report by the Quality Assurance Council (QAC) of the University Grants Committee (UGC) today, 27 June. The Audit Panel praises Lingnan’s robust governance and quality management systems for managing academic standards and academic quality, and commends their proactive approach to digital innovation as reflected in the Strategic Plan since the appointment of the President, Prof S. Joe Qin. A typical example of this is the School of Data Science (SDS), which opened in May 2024 to develop teaching and research in related areas.

Lifesaving deep learning model developed using standard radiographs

Cyborg jellyfish, 3D collagen, Light, light go away, AI electronic nose, FLASHing cancer, Hydrogen storage in nanoscales & Can I drink this? Read all in the latest Editor's Choice

Bringing top Korean and foreign scholars and companies together to present a roadmap for next-generation AI technology

University of the Philippines – Diliman researchers tested various artificial intelligence prediction models to determine the antimicrobial resistance of E. coli using genetic data and laboratory test results from the National Center for Biotechnology Information (NCBI) database.

To further expand collaboration with top-tier Mainland universities, a delegation led by the members of the Council and senior management of Lingnan University visited Beijing from 27 to 29 May for meetings with the Ministry of Education and the National Natural Science Foundation of China (NSFC), and also visited Tsinghua University and Peking University to foster new partnerships in higher education.

Duke-NUS Medical School’s Class of 2025 graduates 121 medical and doctoral students, including MDs, MD-PhDs, PhDs, and masters’ degrees; Landmark first batch of Masters in Patient Safety and Healthcare Quality graduates, unique to Southeast Asia; Inaugural graduates from conditional admissions pathways with National University of Singapore and Singapore University of Technology and Design; 41% of MD and MD-PhD graduates made bold mid-career shifts from fields such as law, PR, accounting and mental health support

- DGIST research team led by Professor Kyungjoon Park achieves 96% glass wall detection accuracy without using additional sensors, reducing hardware costs by 90% - Smart algorithm negates the need for expensive sensors: PINMAP software replaces hardware!

Cosmic hide-and-seek, Controlling quantum light, Thinking face robot, Live DNA folding & Menopause-dementia link. Plus latest SciCom Coffee talk. Read all in the latest Editor's Choice.

Researchers from The University of Osaka have revealed that vision transformers can develop gaze patterns similar to humans, learning to prioritize faces without ever being taught what a face is. The findings suggest that self-supervised ViTs may serve as a practical tool in computer vision and a theoretical model for studying human visual processing. The research underscores the potential of biologically inspired AI systems to uncover the mechanisms of human cognition.

Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), Acting Dean of the School of Data Science, Dean of the School of Graduate Studies and J.K. Lee Chair Professor of Computational Intelligence at Lingnan University, has been elected as a Fellow of the Canadian Academy of Engineering (CAE)—one of the highest honours in the engineering field. This is formal recognition of his significant contribution to global engineering and his commitment to scientific knowledge and innovative techniques to develop effective solutions for the betterment of society, the environment, and the economy. This year, 57 new Fellows were elected into the CAE, including 50 new Fellows and seven new International Fellows. Prof Kwong is the only scholar from Hong Kong SAR who was elected as a CAE Fellow this year.

Researchers develop energy-efficient spintronic devices with 11 memory states for next-generation neuromorphic computing.

With the rapid development of Artificial Intelligence (AI) and increasing environmental challenges, global catastrophic risks have gone beyond traditional natural disasters to raise controversial ethical issues. In view of this, the Hong Kong Catastrophic Risk Centre (HKCRC) of Lingnan University has introduced a new, free, online bilingual self-learning course on Ethics and Global Catastrophic Risks, taught by international authorities in philosophy and ethics. Designed to help people understand and cope with the complex landscape of global disaster risks through eight modules, the new programme, launched in late February this year, incorporates in-depth, real-life examples in AI, the environment, and the sciences, and has already attracted more than 8,000 participants from Mainland China, Hong Kong SAR, South Asia, the US, and Europe. It is now open to the public at no charge.

- Professor Hyuk-jun Kwon’s team at DGIST has developed a high-performance artificial olfactory platform that mimics the human nose to identify a wide range of scents - A simple laser-based process enables scent-sensitive sensors ... AI-powered scent analysis is expected to impact healthcare, cosmetics, and environmental monitoring

Researchers at Tohoku University have developed a data-driven AI framework that gives scientists a head start by suggesting ideal candidate materials.

The world is paying attention to the impact of the trade war on various industries, and Lingnan University recently published a report titled "Data-Driven Job Search: Big Data Series Report on Hong Kong's Employment Market", analysing the employment risks and potential challenges in Hong Kong's labour market. This study used Artificial Intelligence (AI) models to examine more than 140,000 job advertisements in Hong Kong, suggesting that over 40 per cent of job vacancies are in traditional service sectors such as import-export, wholesale and retail, which are vulnerable to external environmental factors. While the strong trend of gig work in the retail industry accounts for approximately 20 per cent of positions, there is little demand for advanced technologies like AI, with less than two per cent of vacancies requiring such skills. The research team proposes that the government should assist workers in traditional service industries with their transitions, and provide targeted cross-industry skills training to improve employment competitiveness in the context of the present trade war economy.