Daejeon, Korea, Sept 4, 2019 – Electronic and Telecommunications Research Institute researchers will present the latest Artificial Intelligence (AI) technologies at the Internationale Funkausstellung (IFA), the world’s largest trade fair for consumer electronics, taking place in Berlin, Germany from Sep. 6 to Sept. 11.
The researchers will showcase four technologies at the exhibition: a smart factory operation control system; Internet of media technology; a deep learning high-speed processing system; and AI motion analysis technology.
In addition, Dr. Kim Hyun of the Smart Information and Communications Technology (ICT) Convergence Research Department will present a keynote presentation titled “ICT-enabled smart factory” at the IFA NEXT Innovation Engine.
Smart factory operation control system
ETRI’s smart factory operation control system can manage personalized manufacturing that uses 3D printers or robots.
In particular, it can easily reconfigure the manufacturing line using modular design. In addition, it can manage the smart factory in real time or analyze the operational data using Internet of Things (IoT) sensors.
This technology can be applied to sectors requiring customized flexible manufacturing. Furthermore, experimental products can be quickly produced for small and medium-sized businesses.
Internet of media technology
Internet of media technology verifies whether media, such as videos, photos and text, are safe and genuine by using AI technology. AI is applied to collect information from various media contents to analyze the harmfulness and authenticity of the data.
Last July, ETRI researchers developed a webhard illegal contents elimination system using this technology. By comparing the reported illegal videos and web hard posts using AI, the technology automatically detects the same illicit contents for elimination.
In the future, the technology can be used to create reliable media services by blocking harmful information.
Deep learning acceleration system
A huge amount of data is essential to increase the accuracy of deep learning. The Deep Learning Acceleration System is a distributed computing platform technology enabling computer clusters to learn a large, deep learning model at high speed. By applying this technology, deep learning training time can be reduced by up to 4 times without changing the existing models. Companies with data centers can develop a high-speed deep learning system using this technology.
AI motion analysis mechanism
AI motion analysis technology recognizes user’s actions and behavior. Aside from analyzing dynamic and complex movements such as K-POP dances, this technology can also be used for effective posture correction by comparing an expert’s posture and learner’s posture, and providing an evaluation result. Motion-based educational contents, sports posture analysis and correction systems, and medical rehabilitation clinic service can be created using this technology.
“By participating in IFA 2019, we plan to carry out technology commercialization and overseas marketing by releasing AI research achievements implemented by ETRI,” said ETRI President Myung-Joon Kim.