Artificial Intelligence

Lithium-ion batteries are widely used daily in electronic appliances, and with the growing popularity of electric vehicles globally, battery safety has become a mounting concern. The development of battery monitoring and fault diagnosis technologies is therefore crucial. Prof Tang Xiaopeng, Assistant Professor of the Science Unit at Lingnan University, in collaboration with researchers from the University of Shanghai for Science and Technology, Shanghai University of Engineering Science, and Tongji University, has proposed a small-sample-learning-based, deep learning model to accurately predict the battery electrochemical impedance spectroscopy (EIS), making it a low-cost, very efficient and highly accurate battery assessment method. The co-authored paper "Online multi-scenario impedance spectra generation for batteries based on small-sample learning" was recently published in the prestigious international academic journal "Cell Reports Physical Science".

The competition in managing short video content on social media platforms and executing online marketing has intensified in recent years. Crafting eye-catching video titles and thumbnails to increase viewer engagement has become a crucial marketing strategy. A recent study by the Department of Marketing and International Business at Lingnan University titled “Clicks for money: Predicting video views through a sentiment analysis of titles and thumbnails” used artificial intelligence (AI) to show that thumbnails expressing strong sentiments tend to attract more views, while strong sentiments conveyed in video titles may have the opposite effect. Additionally, videos with punctuation, capital letters, and emojis in their titles tend to receive more clicks. The Lingnan research team suggests these findings indicate that specific strategies in producing video content can fully leverage their videos’ potential to boost viewership and enhance online marketing efforts.

In a multi-institutional collaboration, one SUTD researcher finds a way to optimise the design of perovskite tandem solar cells using machine learning.

An experimental approach based on universal multi-branch general-purpose convolutional neural network

Growing use of AI reveals the need for global sustainability initiatives

Inexperienced users of voice-controlled smart speakers face challenges due to lack of system feedback

Potential benefits of method include subjecting patients to fewer exams and reducing health care costs

Asia Research News monitors the latest research news in Asia. Some highlights that caught our attention this week are small robots with human brain organoids, new findings about the ancient Denisovan culture, and how to create the perfect environment for bad bacteria.

Lingnan University in Hong Kong participated in the Times Higher Education’s Digital Universities Asia 2024 conference, held from 1 to 3 July in Bali, Indonesia, where Prof S. Joe Qin, President and Wai Kee Kau Chair Professor of Data Science of Lingnan University, delivered a keynote talk and took part in a roundtable discussion, contributing valuable insights to this prestigious annual event. This year, the conference focused on transforming academic institutions into more accessible and inclusive environments, and pointed out the current groundbreaking innovations at the intersection of academic progress and technological advancement. The conference is an important platform where leaders in higher education, industry, and policy exchange ideas on leveraging cutting-edge digital tools and technologies.

The first-ever Lingnan-Yuanpei STEM Summer Academy, organised jointly by Lingnan University in Hong Kong and Yuanpei College of Peking University (PKU), held a seven-day Innovation and Entrepreneurship Training Camp-cum-STEM Competition from 22 to 28 June. Thirty of the best students from both universities formed five teams to compete on various innovative and entrepreneurial smart green technological projects. After a tight race, the project “Sustainable Green Building” team won the championship prize, and the chance to be nominated for the Lingnan University Entrepreneurship Fund, and will be put up for an application for seed or incubation funds.

Lingnan University recently held an agreement signing ceremony on campus to mark the donation of HK$100 million by the Hopson Education Charitable Funds Limited towards establishing a university development fund and supporting Lingnan University to cultivate research-oriented talents.

Machine learning helps find advantageous combination of salts and organic solvents

Blue energy future, Off switch for brain cells, New Japanese lily species, Generative AI in motion, Economies take off with new airports and Braille-shaped electrodes for retinal implants. Read all in the latest Editor's Choice. Plus SciCom Coffee with Catriona Child.

On the occasion of World Environment Day today (5 June), the Science Unit of Lingnan University and Friends of the Earth (HK) (FoE (HK)) have signed a partnership agreement to launch the first Executive Certificate in Sustainable Finance & ESG Analytics for executives of higher education institutions in the Greater Bay Area (GBA), and aligned with the CESGA global certification. Acting in response to our era of digital transformation, this executive certificate training programme not only explores the concepts of Sustainable Finance, but also incorporates Lingnan’s expertise in Artificial Intelligence (AI) analytics, reflecting the global shift towards Sustainable Finance and the increasing integration of Environmental, Social, and Governance (ESG) factors in financial decision-making.

A research group at Osaka University developed a mixed reality (MR) system to intuitively share flooding forecasts, which can be visualized on mobile devices via server rendering. This system addresses the challenge of displaying detailed flood risks, enhancing understanding among both experts and the public. By offloading computational tasks to servers, the system allows for real-time MR visualization over large city areas, potentially integrating advanced features like deep learning to improve disaster resilience and public safety.

Asia Research News monitors the latest research news in Asia. Some highlights that caught our attention this week are how to analyze sweat without getting sweaty, man’s best (robot) friends, and a satellite made from an innovative material: wood.

Lingnan University signed multiple significant strategic cooperation framework agreements yesterday (28 May) with Rizhao City, Shandong Province, Shandong Hi-Speed Group Co, Ltd. (Shandong Hi-Speed Group), Shandong Huge Dental Material Co., Ltd., and Hong Kong Applied Science and Technology Research Institute Company Limited (ASTRI). These collaborations aim to leverage each party’s unique strengths in talent, research, and industry. Lingnan will conduct research projects with partner institutions, promote collaborative innovation, develop new quality productive forces, establish new research and development (R&D) institutions, accelerate the commercialisation of technological achievements, and cultivate a new generation of exceptional talent.

Bicycle sharing has become a green travel option for city dwellers in recent years. However, the initial launch of the service in Hong Kong was met with controversies, such as road obstruction and random parking. Locobike is currently the only bike-sharing brand in Hong Kong, and its success is attributed to the team’s focus on proper fleet management. Through the use of technologies such as artificial intelligence (AI) and the Internet of Things (IoT), Locobike can accurately locate its bikes and provide the team with real-time instructions on how to deploy and maintain them. This strikes a balance between social responsibility and the public’s need for mobility and helps society reduce carbon emissions in the long term.

To improve innovation and technology education, Lingnan University and Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, have announced a partnership and recently held a Memorandum of Understanding (MoU) signing ceremony at Lingnan University. The MoU, a milestone in their collaboration, was signed by Prof Leng Mingming, Dean of the Faculty of Business and Chair Professor of Operations and Risk Management of Lingnan University, and Mr Leo Liu, Vice-President of International Business and General Manager of North APAC Region at Alibaba Cloud.

- Professor Sanghyun Park’s research team in the Department of Robotics and Mechatronics Engineering successfully developed a novel AI model that can effectively utilize medical images from multiple healthcare institutions with the knowledge distillation technique based on federated learning - Findings were published in Medical Image Analysis (MedIA), one of the top journals in medical AI

Researchers have developed a groundbreaking data-driven model to predict the dehydrogenation barriers of magnesium hydride, a promising material for solid-state hydrogen storage. This advancement holds significant potential for enhancing hydrogen storage technologies, a crucial component in the transition to sustainable energy solutions.

Lingnan University in Hong Kong has participated in the two-day QS China Summit 2024 from 17 to 18 April in Shanghai to explore how universities can contribute to China’s global leadership in higher education. The main theme of the summit is “Remaining Distinct in Global Higher Ed: China’s Place in the New World of Education”. As part of efforts to strengthen Lingnan’s international visibility, the University hosted a President Panel Discussion titled "Fostering Distinction in Chinese Higher Education Through Digital Innovation". The Panel provided an exceptional platform for discussions on Chinese higher education within the rapidly evolving field of digital innovation.

Researchers at Tohoku University and the University of California, Santa Barbara have unveiled a probabilistic computer prototype. Manufacturable with a near-future technology, the prototype combines a complementary metal-oxide semiconductor (CMOS) circuit with a limited number of stochastic nanomagnets, creating a heterogeneous probabilistic computer.

Lingnan University’s Teaching and Learning Centre held its annual “Inno-GBA: Empowering education with Generative Artificial Intelligence tools” from 16 to 19 April. The four-day event examined the latest Generative AI (GAI) tools for teaching and learning in higher education, and sophisticated state-of-the-art GAI tools to facilitate academic research and student learning, and assist jobseekers. The first day of the event, which was conducted in hybrid mode, over 200 people came to hear leading professors from the main universities in the Greater Bay Area (GBA) and industry experts from high-tech companies speak.

- Professor Jaeyoun Hwang’s team at DGIST, in collaboration with Dabeeo Inc., has developed a deep learning technology for object detection using aerial and satellite images. - The technology is anticipated to find applications in various fields, including defense, autonomous driving vehicles, and medical imaging.

A comprehensive analysis of the integration of artificial intelligence in science and research across various countries. It addresses both the advancements made and the challenges faced in this field.

AI is revolutionizing the way researchers seek to identify new materials, but it still has some shortcomings. Now, a team of researchers has navigated AI’s pitfalls to identify a thermoelectric material that boasts remarkable properties.

- Prof. Sang Hyun Park of the Department of Robotics and Mechatronics Engineering has developed a logical anomaly detection technology that utilizes segmentation results through artificial intelligence (AI). - The research results were published by the Association for the Advancement of Artificial Intelligence (AAAI), the premier AI conference, in February 2024.

Recreating the action of opening doors in the virtual world requires engineering ways in which to provide the equivalent haptic feedback and steer users away from walls in the real world. A research group has done just this; developing RedirectedDoors+, which employs door robots and rotation to create a more realistic experience.

In celebration of International Women's Day, we are putting the spotlight on women experts from various fields who are open to speaking with international media about their research and advocacies.