연구 > 연구성과 - Page 3 of 49 - KAIST 전기 및 전자공학부

Professor Yang-Kyu Choi’s Research Team Solved Computing Challenges with Neuromorphic Neural Networks

Professor Yang-Kyu Choi’s Research Team Solved Computing Challenges with Neuromorphic Neural Networks

<(from left) Professor Yang-Kyu Choi, ph.d. candidate Seong-Yun Yun, Professor Joon-kyu Han from Sogang University (KAIST alumnus)>

Professor Yang-Kyu Choi’s research team has built a miniature oscillatory neural network using only silicon materials and processes currently used in the semiconductor industry, implementing an edge detection feature and solving the graph coloring problem*.

*Graph coloring problem: A term used in graph theory, requiring different colors to be assigned to each vertex of a graph. This is similar to assigning frequencies to broadcasting stations to prevent overlap and the creation of areas with poor reception, and is widely applied in various fields.

The research team announced on the 3rd that they have developed a neuromorphic oscillatory neural network that mimics the interactions of biological neurons using silicon varistor components.

With the arrival of the big data era, artificial intelligence technology has made significant progress. One of the neuromorphic computing methods, the oscillatory neural network (oscillatory neural network), is an artificial neural network that mimics the interaction of neurons. The oscillatory neural network uses the connection operations of oscillators, which are the basic units, and performs calculations using oscillations rather than the magnitude of signals, thus offering advantages in terms of power consumption.

< Figure 1. The oscillatory neural network using varistors and its applications >

The research team developed the oscillatory neural network using silicon-based oscillators. By connecting two or more silicon oscillators using capacitors, the oscillation signals interact with each other and synchronize over time. The research team implemented edge detection, a feature used in image processing, with the oscillatory neural network and solved one of the challenges, the vertex coloring problem.

Furthermore, this research has the advantage of being immediately applicable to mass production from a manufacturing perspective, as it built the oscillatory neural network using only silicon materials and processes currently used in the semiconductor industry, instead of complex circuits or materials and structures with low compatibility with existing semiconductor processes.

The research, led by Seong-Yun Yun, a doctoral student, and Professor Joon-Kyu Han from Sogang University, stated, “The developed oscillatory neural network can be used as neuromorphic computing hardware capable of calculating complex computing challenges, and is expected to be useful in resource allocation, new drug development, semiconductor circuit design, and scheduling,” highlighting the significance of the research.

The study, co-authored by Seong-Yun Yun and Professor Joon-Kyu Han, was published in ‘Nano Letters’, in its 24th volume, issue 9, on March 2024, and was selected as a supplementary cover article.

Photo Caption: < Figure 2. The image selected as a supplementary cover article for Nano Letters >

(Paper title: A Nanoscale Bistable Resistor for an Oscillatory Neural Network) (https://pubs.acs.org/doi/full/10.1021/acs.nanolett.3c04539).

This research was conducted with the support of the Korea Research Foundation’s Next-Generation Intelligent Semiconductor Technology Development Project and the National Semiconductor Research Laboratory Support Core Technology Development Project.

Seunghyun Lee from Hacking Lab (Advisor: Insu Yun) Wins 190 million Won Prize at International Hacking Contest ‘Pwn2Own’

Seunghyun Lee from Hacking Lab (Advisor: Insu Yun) Wins 190 million Won Prize at International Hacking Contest ‘Pwn2Own’

<(from left) Professor Insu Yun, Seunghyun Lee student>

Seunghyun Lee from Hacking Lab (Advisor: Insu Yun) at KAIST’s EE Department, achieved notable prize at the international hacking contest ‘Pwn2Own,’ held from March 20th to 21st at Toronto, Canada. Seunghyun Lee discovered and successfully exploited two browser vulnerabilities, earning a total prize of $145,000 (approximately 190 million won).

During this competition, Seunghyun Lee also achieved a ‘double tap’ by exploiting a vulnerability in both Google Chrome and Microsoft Edge browsers simultaneously.

‘Pwn2Own’ is a hacking contest in which big global IT companies such as Google, Microsoft, and Apple participate as partners. It targets actual products that constitute the core of modern computer systems, such as browsers, operating systems, and virtual machines.

This contest not only provides prize money and prestige but also contributes to enhancing user safety/privacy by patching vulnerabilities discovered after the competition.

Professor Insu Yun evaluated this award as proof that KAIST’s hacking skill has reached a global level and expressed his expectation for the emergence of many talents who will developinto top researchers and hackers at KAIST in the future.

This achievement, recognized at an international competition, serves as an opportunity to showcase KAIST’s technological prowess and students’ excellence to the world.

Professor Lee Kayoung’s research team develops Superior Electron Mobility and Electron Saturation Velocity Characteristics of the New Device Compared to Existing Devices

Professor Lee Kayoung’s research team develops Superior Electron Mobility and Electron Saturation Velocity Characteristics of the New Device Compared to Existing Devices

<(from left) Professor Kayoung Lee, Yongwook Seok ph.d candidate>

Professor Lee Kayoung’s research team has successfully developed a high-performance 2D semiconductor device that can operate at ultra-high speeds and whose performance improves as the temperature decreases, showing potential for use in high-frequency bands and at extremely low temperatures.

The research team led by Professor Lee Kayoung announced on the 20th that they have developed a high-mobility, ultra-high-speed device based on two-dimensional nano-semiconductor indium selenide (InSe), which surpasses the electron mobility and saturation velocity of silicon by more than two-fold.

*Saturation velocity: Refers to the maximum speed at which electrons or holes can move within a semiconductor material. Saturation velocity is a key indicator for evaluating the electrical properties of a semiconductor, as it determines saturation current and cutoff frequency, among other factors.
**Indium Selenide (InSe): An inorganic compound made of indium and selenium that forms two-dimensional layers with van der Waals bonds.

Two-dimensional indium selenide is attracting attention as a next-generation semiconductor material due to its higher electron mobility and current compared to traditional silicon semiconductors and 2D semiconductors. However, indium selenide is vulnerable to oxidation in the air and has lower stability, making the development of high-performance devices challenging.

Professor Lee Kayoung’s research team improved the stability and performance of indium selenide by using high-quality two-dimensional hexagonal boron nitride (hBN) as the lower insulating layer and thin indium metal as the upper protective layer to solve this problem.

*Hexagonal Boron Nitride (hBN): Nitrogen and boron form a hexagonal planar structure and have insulating properties.

Additionally, by forming a two-dimensional heterojunction* structure without contaminating the core channel layer of indium selenide, they significantly improved the electron mobility and electron saturation velocity. This is the first time that the electron saturation velocity of indium selenide has been systematically analyzed, and the research team was able to determine the mechanism for electron saturation velocity.

*Heterojunction: The interface between two layers or regions of different crystalline semiconductors

< Figure 1. Superior Electron Mobility and Electron Saturation Velocity Characteristics of the New Device Compared to Existing Devices >

Leading this research, doctoral candidate Seok Yongwook said, “Through the development of high-performance devices, we were able to confirm the high electron mobility and saturation velocity of the two-dimensional semiconductor indium selenide,” and added, “Research on its application is necessary for actual devices that require ultra-low temperature and high-frequency operation.”

Professor Lee Kayoung said, “The high-performance electronic device developed this time is capable of ultra-fast operation, making it possible to operate in the 6G frequency band beyond the 5G band,” and “As the temperature decreases, the performance of the device improves significantly, making it suitable for ultra-low temperature high-frequency operation environments like those needed for quantum computer quantum control ICs (Integrated Circuits).”

This research, with doctoral student Seok Yongwook from the Department of Electrical and Electronic Engineering as the lead author, was officially published in the international journal of nanoscience, `ACS Nano (Nano),’ on March 19, 2024, and was also featured as the journal cover article. (Paper title: High-Field Electron Transport and High Saturation Velocity in Multilayer Indium Selenide Transistors)

Meanwhile, this research was conducted with the support of the National Research Foundation of Korea’s Young Researchers Program, Basic Research Program, BK21, KAIST’s C2 (Creative & Challenging) Project, LX Semicon-KAIST Future Technology Center, and the Posco Foundation.

< Figure 2. Cover Image of the ACS Nano Journal >

Professor Kwon Kyeongha’s Research Team Develops Smart Healthcare Device for Monitoring Chronic Wounds for Monitoring Chronic Wounds in Diabetes Patients

Professor Kwon Kyeongha’s Research Team Develops Smart Healthcare Device for Monitoring Chronic Wounds for Monitoring Chronic Wounds in Diabetes Patients

< (Left to right) KAIST Professor of Electrical and Electronic Engineering Kyeongha Kwon, Ph.D. Candidate Youngmin Sim, and Chung-Ang University Professor of Advanced Materials Engineering Hanjun Ryu >

Professor Kwon Kyeongha’s research team has developed a wireless system capable of accurate and direct monitoring of chronic wound healing process by tracking the spatiotemporal temperature changes and thermal transfer characteristics of injuries caused by diabetes. Professor Kwon Kyeongha’s research team announced on the 5th that they have developed the digital healthcare system in collaboration with Professor Hanjun Ryu of Chung-Ang University.

As the skin serves as a barrier to protect the human body from harmful substances, skin damage in patients under intensive care can lead to serious health risks associated with infection. Chronic wounds are especially common in diabetes patients, who suffer from abnormal blood circulation and deteriorated wound healing processes. Just in the United States alone, billions of dollars in medical expenses are spent annually for the regeneration of such chronic wounds. Although there are various methods to promote wound healing, personalized care specific to each patient is still necessary.

< Diagram of the Real-time Wound Monitoring System >

In response, Kwon’s research team utilized the temperature difference between the wound area and the surrounding healthy skin to track the heat response within the wound. They measured thermal transfer characteristics to observe changes in moisture levels, using this to model the process of scar tissue formation. The team conducted experiments on mice with diabetes, observing the delayed wound healing process in pathological conditions. The collected data proved to be accurate in tracking the wound healing process and the formation of scar tissue.

This system was integrated with a biodegradable sensor module that can naturally decompose within the body to minimize potential tissue damage. Once used, the biodegradable module can decompose on its own through degradation within the body, eliminating the need for manual removal and allowing direct monitoring of the wound site.

Professor Kwon Kyeongha stated, “By continuously monitoring the temperature and thermal transfer characteristics of the wound site, we hope that medical professionals will be able to more accurately assess the condition of wounds in diabetes patients and provide appropriate treatment. Using biodegradable sensors means that the device can safely decompose without the need for removal after wound healing is complete, enabling real-time monitoring not only in hospitals but also at home.”

Kwon’s research team plans to further develop this device by integrating it with materials that have antibacterial properties, expanding its use to observe and prevent inflammatory responses, bacterial infections, and other lesions. By detecting infection levels through changes in temperature and thermal transfer characteristics, their goal is to provide a universal, antibacterial wound monitoring platform that can be used in real-time, both in hospitals and the home.

< Journal Cover – Photo of the Biodegradable Wound Monitoring Sensor >

The results of this research were published in the international academic journal Advanced Healthcare Materials on February 19th and selected as the inside back cover article. (Titled, Materials and Device Designs for Wireless Monitoring of Temperature and Thermal Transport Properties of Wound Beds during Healing)

The research was funded by the Basic Research in Science & Engineering Program of the National Research Foundation of Korea, the Regional Leading Research Center (RLRC), and BK21.

[Professor Rhu Minsoo’s team wins the Best Paper Award’ at the International Symposium on High-Performance Computer Architecture (HPCA)]

[Professor Rhu Minsoo’s team wins the Best Paper Award’ at the International Symposium on High-Performance Computer Architecture (HPCA)]

<(from left) Certificate of Award, Award Ceremony, PhD candidates Bongjoon Hyun (first author), Taehun Kim, and Dongjae Lee>

The research team led by Professor Rhu Minsoo from the school of EE announced that they have won the Best Paper Award at the IEEE International Symposium on High-Performance Computer Architecture (HPCA), one of the premier international conferences on computer architecture. This is the first time a research team from a domestic university has received the Best Paper Award at an international top-tier conference in the field of computer architecture. It is a prestigious honor given to a single top submission out of 410 papers submitted.

The research team led by Professor Rhu Minsoo, consisting of PhD candidates Bongjoon Hyun (first author), Taehun Kim, and Dongjae Lee from the Department of Electrical Engineering, won the Best Paper Award with their proposal of a simulation framework named uPIMulator. This framework is based on the commercialized Processing-In-Memory (PIM) technology of UPMEM.

Technologies that have been gaining significant attention recently such as Large Language Models like ChatGPT and recommendation systems require a high amount of memory bandwidth (the amount of data that can be moved in and out of memory at one time). Traditional CPU and GPU-based systems face limitations in meeting the increasing demand for memory bandwidth due to physical constraints.

To address the issue of limited memory bandwidth, Processing-In-Memory (PIM) technology, which integrates computing units within the memory itself, has started to gain attention. PIM technology is receiving recognition not only in academia but also in the industry, with the unveiling of PIM prototype products such as Samsung Electronics’ HBM-PIM and SK Hynix’s AiMX, as well as commercialization examples through UPMEM’s UPMEM-PIM product, demonstrating its potential.

However, the current state of Processing-In-Memory (PIM) technology is relatively in its early stages compared to the level of development in hardware architectures like CPUs or GPUs, and there is a need for extensive research on a wide range of hardware structures. Simulators that mimic hardware are frequently used in both academia and industry to explore various hardware design spaces, but research on simulators for PIM is comparatively lacking.

Professor Rhu Minsoo’s research team explored various hardware structures that could improve the performance, robustness, and security of PIM through the development of a simulator based on the commercial PIM technology, UPMEM-PIM, undergoing design and verification processes. The significance of this research lies in the detailed analysis of PIM hardware structures and the exploration of various design directions through a simulator grounded in actual PIM products. The developed simulator is currently available as open-source (https://github.com/VIA-Research/uPIMulator), contributing to the research and development community.

This research was conducted with the support of the Korean government (Ministry of Science and ICT), the National Research Foundation of Korea, the Institute for Information & communications Technology Planning & Evaluation, and Samsung Electronics.

https://arxiv.org/abs/2308.00846

uPIMulator: https://github.com/VIA-Research/uPIMulator

Professor Hyunchul Shim’s joint research team won second place at the 3rd MBZIRE International Robotics Challenge

Professor Hyunchul Shim’s joint research team won second place at the 3rd MBZIRE International Robotics Challenge

At the recent 3^rd MBZIRC hosted at Abu Dhabi, UAE, the joint team by Prof. Hyunchul Shim(EE) and Jinwhan Kim (KAIST ME) won 2^nd place in Feb 8, 2024, winning $650K USD.

This competition requires USV and UAV perform a joint mission to retrieve designated objects from “illegal” boat on actual sea absolutely without GPS.

For this, Prof. Shim developed vision-based navigation technology and autonomous robot based retrieval system while Prof. Kim’s team developed radar-based autonomous USV.

During the competition, there were numerous difficulties including the ship’s mechanical problems and many unforeseen problems from operating actual high sea, but 20 graduate students in our team were able to overcome these problems, winning 2^nd place.

Prof Shim said, “there were so many problems not only in technical side but also in operational side, we were able to win a real competition, not some small scale competition, and I’d like to thank Prof. Kim and all the students did their best and more”

Professor Youjip Won has been elected as the 39th president of the Korean Institute of Information Scienctists and Engineers

Professor Youjip Won has been elected as the 39th president of the Korean Institute of Information Scienctists and Engineers

The Korean Institute of Information Scientists and Engineers has announced that Professor Won Youjip from our department has been elected as the 39th president. He took office on January 1, 2024, and will lead the society for the next year.

Professor Won Youjip graduated with a Bachelor’s and Master’s degree in Computational Statistics from Seoul National University and a Ph.D. in Computer Science from the University of Minnesota in the United States.

He has been a professor in the School of Electrical Engineering at KAIST since 2019, after serving as a professor in the Department of Computer Engineering at Hanyang University.

He is currently a member of the Korean Academy of Engineering and the director of the KAIST Storage Research Center.

Professor Won Youjip stated, “During my term, I will reestablish the identity of the society and seek qualitative leaps that match its quantitative expansion.

First, in the field of education, I will create a forum for discussion and sharing education content, teaching methods, assignments and projects, and the simplification of technical terms into Korean, to achieve world-class information science education.

In the research field, I will do my utmost to improve personnel systems, evaluation systems, and reward standards so that the research results of our members are properly evaluated. Furthermore, I will create a space in which members can share and discuss various difficulties they encounter in educational, research, and development settings.”

The Korean Institute of Information Scientists and Engineers, founded in 1973, is a leading academic organization in the field of computers and software in Korea. It has more than 3,500 university professors as members, with a total membership exceeding 37,000.

EE Prof. Myoungsoo Jung and Panmnesia joint research team showcases Innovation Award-winning CXL-Enabled AI Accelerator at CES 2024

[EE Prof. Myoungsoo Jung and Panmnesia joint research team showcases Innovation Award-winning CXL-Enabled AI Accelerator at CES 2024]

<(from left) CXL-Enabled AI Accelerator Image & System>

Professor Myoungsoo Jung and Panmnesia’s joint research team showcased the Innovation Award-winning ‘CXL-Enabled AI Accelerator’ in world’s premier IT industry event CES 2024.

The award-winning accelerator features virtually limitless memory capacity that brings significant performance boost for large-scale AI-driven services. This innovative feature empowers AI-driven services to handle increasing amount of data, leading to substantial enhancements in accuracy and quality of the services.

In the evaluation using a representative large-scale AI service, AI-powered image search, the system with their accelerator exhibited 101 times faster performance than conventional SSD-based AI acceleration system.

In order to provide better service to users, AI services from global tech giants such as Google and Microsoft are rapidly increasing the amount of data their AI services are handling. However, conventional accelerators have limited memory capacity which makes it hard to load the dataset into their memory. Thus, to manage the large dataset, the conventional systems falls back to employ SSD, whose long latency significantly degrades the overall performance.

To this end, the joint development team showcased the CXL-enabled AI Accelerator that addresses the above problem. The accelerator adopts Compute eXpress Link (CXL), a cache-coherent high-speed interconnect, to connect itself with the system, Such interconnect allows the system access the accelerator’s internal memory.

This feature allows the system to expand its memory space by connecting multiple accelerators to the CPU through CXL switch. In addition, the joint development team further improved the overall system performance by employing specialized hardware acceleration module for parallel processing of AI-based image search inside the accelerator.

The joint development team showcased their outcomes at CES 2024, held in early Jan ‘24 at Las Vegas, US. The accelerator bestowed the CES 2024 innovation award for their technical superiority. The news of the CXL-Enabled AI Accelerator winning the innovation award and exhibiting at CES was reported by international media, including IEEE Spectrum, TechRadar, Storage Newsletter, and Design and Reuse.

The news was also widely covered by multiple domestic media, including Chosun-Ilbo, The Korea Economic Daily, Seoul Economic Daily, ChosunBiz, and ZDNet Korea.

“We had an exclusive meeting with ARM, the world’s largest IP company, and confirmed their interest in our technology,” said Panmnesia’s exhibitor. “HPE (Hewlett Packard Enterprise), a global cloud and data center company, is also very interested in our CXL technology, and we’ve been invited to HPE headquarters for an exclusive meeting later this month,” he added.

Panmnesia is a fabless startup with technological leadership in CXL Intellectual Property (IP). Panmnesia was born out of the collaborative efforts of a talented group of Ph.D. graduates from KAIST EE. They gained exposure from their recent $12.5 million seed funding.

More information on Panmnesia can be found in its website(http://panmnesia.com). More information on Innovation Award-winning accelerator can be found in Panmnesia’s Youtube video (https://youtu.be/ZujXVEr3nO0)

*Link to press coverage on this news: https://www.etoday.co.kr/news/view/2321263

Professor Sung-Ju Lee’s research team develops a smarthphone AI system that diagnoses mental health based on user’s voice and text input

Professor Sung-Ju Lee’s research team develops a smarthphone AI system that diagnoses mental health based on user’s voice and text input

A research team led by Professor Sung-Ju Lee of the Department of Electrical and Electronic Engineering has developed an artificial intelligence (AI) technology that automatically analyzes users’ language usage patterns on smartphones without personal information leakage, thereby monitoring users’ mental health status.

This technology allows smartphones to analyze and diagnose a user’s mental health state simply by carrying and using the phone in everyday life.

The research team focused on the fact that clinical diagnosis of mental disorders is often done through language use analysis during patient consultations.

The new technology uses (1) keyboard input content such as text messages written by the user and (2) voice data collected in real-time from the smartphone’s microphone for mental health diagnosis.

This language data, which may contain sensitive user information, has previously been challenging to utilize.

The solution to this issue in this technology involves the application of federated learning AI, which trains the AI model without data leakage outside the user’s device, thus eliminating privacy invasion concerns.

The AI model is trained on datasets based on everyday conversation content and the speaker’s mental health. It analyzes the conversations into the smartphone in real-time and predicts the user’s mental health scale based on the learned content.

Furthermore, the research team developed a methodology to effectively diagnose mental health from the large amount of user language data provided on smartphones.

Recognizing that users’ language usage patterns vary in different real-life situations, they designed the AI model to focus on relatively important language data based on the current situation indicated by the smartphone.

For example, the AI model may prioritize analyzing conversations with family or friends in the evening over work-related discussions, as they may provide more clues for monitoring mental health.

This research was conducted in collaboration with Jaemin Shin(CS), HyungJun Yoon (EE Ph.d course) , Seungjoo Lee (EE master’s course), Sung-Joon Park, CEO of Softly AI (KAIST alumnus), Professor Yunxin Liu of Tsinghua University in China, and Professor Jin-Ho Choi of Emory University in the USA.

The paper, titled “FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning,” was presented at the EMNLP (Conference on Empirical Methods in Natural Language Processing), the most prestigious conference in the field of natural language processing, held in Singapore from December 6th to 10th.

Professor Sung-Ju Lee commented, “This research is significant as it is a collaboration of experts in mobile sensing, natural language processing, artificial intelligence, and psychology. It enables early diagnosis of mental health conditions through smartphone use without worries of personal information leakage or privacy invasion. We hope this research can be commercialized and benefit society.”

This research was funded by the government (Ministry of Science and ICT) and supported by the Institute for Information & Communications Technology Planning & Evaluation (No. 2022-0-00495, Development of Voice Phishing Detection and Prevention Technology in Mobile Terminals, No. 2022-0-00064, Development of Human Digital Twin Technology for Predicting and Managing Mental Health Risks of Emotional Laborers).

Professor Jinseok Choi Receives IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award

Professor Jinseok Choi Receives IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award

Professor Jinseok Choi has been awarded the IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award in recognition of his significant contributions to the advancement of technology in the field of wireless communications, particularly through his research in developing low-power communication systems.

This award is presented annually to outstanding young researchers in the telecommunications field in the Asia-Pacific region.

Prof. Choi has received high acclaim for his creative and challenging research in the field of wireless communications.

His primary focus has been the development of low-power communication systems, leading the field’s advancement through the exploration of new technologies and solutions.

The systems he has developed are characterized by their innovative features, enabling stable and efficient wireless communications while maximizing energy efficiency.

Archives: 연구 > 연구성과

Professor Yang-Kyu Choi’s Research Team Solved Computing Challenges with Neuromorphic Neural Networks

Seunghyun Lee from Hacking Lab (Advisor: Insu Yun) Wins 190 million Won Prize at International Hacking Contest ‘Pwn2Own’

Professor Lee Kayoung’s research team develops Superior Electron Mobility and Electron Saturation Velocity Characteristics of the New Device Compared to Existing Devices

Professor Kwon Kyeongha’s Research Team Develops Smart Healthcare Device for Monitoring Chronic Wounds for Monitoring Chronic Wounds in Diabetes Patients

[Professor Rhu Minsoo’s team wins the Best Paper Award’ at the International Symposium on High-Performance Computer Architecture (HPCA)]

Professor Hyunchul Shim’s joint research team won second place at the 3rd MBZIRE International Robotics Challenge

Professor Youjip Won has been elected as the 39th president of the Korean Institute of Information Scienctists and Engineers

EE Prof. Myoungsoo Jung and Panmnesia joint research team showcases Innovation Award-winning CXL-Enabled AI Accelerator at CES 2024

Professor Sung-Ju Lee’s research team develops a smarthphone AI system that diagnoses mental health based on user’s voice and text input

Professor Jinseok Choi Receives IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award

About Us

Research

EE-X

AI in EE

People & Life

Academics

External Relations

Admissions

News & Event