Trouble in Your Tank: Implementing Direct Metallization in Advanced Substrate Packaging
It’s Only Common Sense: Storytelling That Sells—Stop Pitching, Start Painting Pictures
The Right Approach: Get Ready for ISO 9001 Version 6
Recognizing Seven Different Face Emotions on a Mobile Platform
March 21, 2018 | KAISTEstimated reading time: 1 minute
A KAIST research team succeeded in achieving face emotion recognition on a mobile platform by developing an AI semiconductor IC that processes two neural networks on a single chip.
Professor Hoi-Jun Yoo and his team (Primary researcher: Jinmook Lee Ph. D. student) from the School of Electrical Engineering developed a unified deep neural network processing unit (UNPU).
Deep learning is a technology for machine learning based on artificial neural networks, which allows a computer to learn by itself, just like a human.
The developed chip adjusts the weight precision (from 1 bit to 16 bit) of a neural network inside of the semiconductor in order to optimize energy efficiency and accuracy. With a single chip, it can process a convolutional neural network (CNN) and recurrent neural network (RNN) simultaneously. CNN is used for categorizing and recognizing images while RNN is for action recognition and speech recognition, such as time-series information.
Moreover, it enables an adjustment in energy efficiency and accuracy dynamically while recognizing objects. To realize mobile AI technology, it needs to process high-speed operations with low energy, otherwise the battery can run out quickly due to processing massive amounts of information at once. According to the team, this chip has better operation performance compared to world-class level mobile AI chips such as Google TPU. The energy efficiency of the new chip is 4 times higher than the TPU.
In order to demonstrate its high performance, the team installed UNPU in a smartphone to facilitate automatic face emotion recognition on the smartphone. This system displays a user’s emotions in real time. The research results for this system were presented at the 2018 International Solid-State Circuits Conference (ISSCC) in San Francisco on February 13.
Professor Yoo said, “We have developed a semiconductor that accelerates with low power requirements in order to realize AI on mobile platforms. We are hoping that this technology will be applied in various areas, such as object recognition, emotion recognition, action recognition, and automatic translation. Within one year, we will commercialize this technology.”
Share on:
Testimonial
"In a year when every marketing dollar mattered, I chose to keep I-Connect007 in our 2025 plan. Their commitment to high-quality, insightful content aligns with Koh Young’s values and helps readers navigate a changing industry. "
Brent Fischthal - Koh YoungSuggested Items
AI-Powered Wearables Transform How Consumers Interact with Everyday Technology
09/15/2025 | PR NewswireThe global demand for AI-driven, touchless wearable technologies is accelerating as consumers seek more natural, seamless and intuitive ways to interact with their devices. Traditional touch screens and voice assistants, while effective, are increasingly viewed as limiting in a world where multitasking, mobility and efficiency are key. As industries from consumer electronics to augmented reality and enterprise computing embrace the possibilities of gesture-based control, the market for neural interfaces is rapidly expanding
Hanwha Aerospace to Collaborate with BAE Systems on Advanced Anti-jamming GPS for Guided Missiles
09/15/2025 | HanwhaHanwha Aerospace has signed a contract with BAE Systems to integrate next-generation, anti-jamming Global Positioning System (GPS) technology into Hanwha Aerospace’s Deep Strike Capability precision-guided weapon system.
United Electronics Corporation Unveils Revolutionary CIMS Galaxy 30 Automated Optical Inspection System
09/11/2025 | United Electronics CorporationUnited Electronics Corporation (UEC) today announced the launch of its new groundbreaking CIMS Galaxy 30 Automated Optical Inspection (AOI) machine, setting a new industry standard for precision electronics manufacturing quality control. The Galaxy 30, developed and manufactured by CIMS, represents a significant leap forward in inspection technology, delivering exceptional speed improvements and introducing cutting-edge artificial intelligence capabilities.
Intel Announces Key Leadership Appointments to Accelerate Innovation and Strengthen Execution
09/09/2025 | Intel CorporationIntel Corporation today announced a series of senior leadership appointments that support the company’s strategy to strengthen its core product business, build a trusted foundry, and foster a culture of engineering across the business.
DARPA, State of New Mexico Establish Framework to Advance Quantum Computing
09/08/2025 | DARPAAs part of the Quantum Benchmarking Initiative (QBI), DARPA signed an agreement with the State of New Mexico’s Economic Development Department to create the Quantum Frontier Project.
Copyright © I-Connect007 | IPC Publishing Group Inc. All rights reserved.
Log in