Prof. Yousung Jung’s group has developed a new accelerated high throughput screening (HTS) method using uncertainty-quantified machine learning (ML) and density functional theory (DFT) that was applied to explore the Mg-Mn-O chemical space for photoanode application. Notably, the proposed HTS scheme required only 1.5% of the target chemical space for further DFT calculations, accelerating the entire process by > 50 times for the same discovery compared to the brute-force DFT-HTS done previously. This means an improvement of the screening performance (discoverability) by more than a factor of 2 compared to the conventional ML-based HTS approach....read more
KPC4IR (Korea Policy Center for the 4th Industrial Revolution) together with GSI (Global Strategy Institute) hosted the Second GSI International Forum on challenges for educational innovation in the non-contact society in the post-coronavirus era. Live-streamed on Youtube, Naver TV, and KTV on June 24, 2020, the Forum gathered 15 global experts and advisors of educational issues to examine significant challenges for the future of education in an increasingly non-contact society and envision inclusive educational innovations in the post-COVID-19 era....read more
Delayed induction of BAF53b in the amygdala after fear learning has a crucial role for memory persistence via regulating FGF1 expression....read more
At the KAIST Institute for Information Technology Convergence, the Intelligent Technology Research team has conducted research and development of an AI/ML based user anomaly detection solution for enterprise resource planning system (ERP), particularly targeted at SAP ERP, by collaborating with ARMIQ (a company with SAP ERP system expertise). The team is developing core modules for ERP user anomaly detection solutions such as user behavior categorizers, AI/ML inference models, model optimization methods). By utilizing domain expertise related to SAP ERP and cutting-edge AI/ML techniques, it is expected to achieve cost-effective localized ML based user anomaly detection solutions....read more
New algorithms have been developed to generate non-blurry, high-resolution, high-quality, and high-dynamic range intensity images using sparse event streams from an event camera, which is a new imaging sensor able to capture visual information with low latency even under extremely low illumination....read more
Prof. Il-Doo Kim, Prof. Hong Jung-Wuk, and Prof. Seokwoo Jeon jointly developed a novel multi-stimuli-responsive (thermochromic and mechanochromic) membrane based on light scattering at strain-induced nanogaps from oxides and elastomers together with thermochromic dyes. The combination of the polymer writing technique with roll-to-roll production effectively expanded the production area of the smart window membrane to an exceptionally large scale of nearly 300 cm2, far beyond those of previously reported optical modulating membranes to date....read more
Dr. Ji-Ho Park’s group developed a cargo-switching nanoparticle (CSNP) system that can bind to cholesterol and then release an anti-inflammatory drug (statin) in a plaque-containing microenvironment. The as-developed CSNP had a core-shell structure, with a core composed of cyclodextrin and statin and a shell of phospholipids. In vitro, once interacting with cholesterol, which had a higher affinity to cyclodextrin than statin, the CSNP can instantly release statin and scavenge cholesterol by cargo-switching. In vivo, in a mouse model of atherosclerosis, the CSNP administered systemically can effectively target atherosclerotic plaques and reduce their associated cholesterol and macrophages, leading to prevention of atherogenesis and regression of established plaques....read more
ID KAIST Researchers investigated the AI speaker as a family-shared technology and discovered its family-oriented roles for new design opportunities of AI speakers....read more
Professor Sung Yong Kim and his team reported an injection spatial scale and primary driver in the oceanic submesoscale processes as O(10)-km scale baroclinic instability for the first time ever in the world through the ‘big data’ analysis of O(1) km and hourly surface current and chlorophyll concentration maps, observed by remote sensing instruments of high-frequency radars and geostationary ocean color imagery for at least one year up to five years. This work elucidates the pathways of oceanic energy cascades and will enhance studies of bio-physical interactions and improve the performance of regional and global climate models through realistic parameterization at submesoscale. The scientific outcomes have been published as two companion papers in the Journal of Geophysical Research-Oceans, a prestigious, top-shelf journal in earth science and geophysical fluid dynamics....read more
The SWRC (Semantic Web Research Center, led by Prof. Choi) aims to construct and expand its knowledge base through self-machine-learning from unstructured big data (natural language), and to develop a novel technology to further verify the knowledge base....read more