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

 

6583f9170dbd4

 

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).
 
 
 

Inline image 2023 12 19 16.28.15.531

<picture 1. A smartphone displaying an app interface for mental health diagnosis. The app shows visualizations of user’s voice and keyboard input analysis, with federated learning technology>
 
 
Inline image 2023 12 19 16.28.42.148
 
<picture 2. A schematic diagram of the mental health diagnosis technology using federated learning, based on user voice and keyboard input on a smartphone>
 
 
 
 
 

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>
 
 
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.

 

Inline image 2023 12 13 09.26.51.912

<IEEE ComSoc AP Award Ceremony & Plaque>

M.S Course Seoyeon Jang won the Best Paper Award in RiTA 2023

M.S Course Seoyeon Jang won the Best Paper Award in RiTA 2023

 

RiTA2023 수상

Seoyeon Jang, Minho Oh, Byeongho Yu, Seungjae lee, I Made Aswin Nahrendra, and Hyungtae Lim received the Best Paper Award at the Int’l Conf. on RiTA (Robot Intelligence Technology and Applications) 2023 held in Taicang, Dec. 6-8, 2023.

 

-Conference: The 11th International Conference on Robot Intelligence Technology and Applications (RiTA 2023)

-Date: December 6-8, 2023

-Venue: XJTLU Entrepreneur College, Xi’an Jiaotong-Liverpool University, Taicang, China

-Award: Best Paper Award

-Authors: Seoyeon Jang, Minho Oh, Byeongho Yu, Seungjae lee, I Made Aswin Nahrendra, Hyungtae Lim, and Hyun Myung (Advisory Professor)

-Paper Title: TOSS: Real-time Tracking and Moving Object Segmentation for Static Scene Mapping                                          

 

Professor Hoi-Jun Yoo was elected as the 7th Chairman of the Institute of Semiconductor Engineers

Professor Hoi-Jun Yoo was elected as the 7th Chairman of the Institute of Semiconductor Engineers

 

news p.v1.20231211.cc8421ab44594fff910826420cdbb2e1 P1

[Prof. Hoi-Jun Yoo ]

 

Professor Hoi-Jun Yoo was elected as the 7th Chairman of the Institute of Semiconductor Engineers.
Congratulations on the big news, and we sincerely appreciate his effort and contribution to EE all the time.
 
FYI) https://www.etnews.com/20231211000068
 

Professor Cho SeongHwan receives ‘2023 Hae-dong Semiconductor Engineering Award from Institute of Semiconductor Engineers’

Professor Cho SeongHwan receives ‘2023 Hae-dong Semiconductor Engineering Award from Institute of Semiconductor Engineers’

 

Inline image 2023 12 07 16.25.34.306

<Professor Cho SeongHwan>
 
 
Professor Cho SeongHwan received 2023 Hae-dong Semiconductor Engineering Award from Institute of Semiconductor Engineers.
Congratulations on the big news, and we are extremely grateful for his effort and contributions to EE.
 
Professor Cho SeongHwan has been conducting research in analog integrated circuits, making significant contributions to the domestic and international technological advancements in this field.
 
While producing numerous outstanding papers in traditional analog circuits, Professor Cho SeongHwan also conducted unique researches such as time-based circuits to overcome low voltage and employing CMOS processes for sensing components rather than computational components. His relentless efforts in such innovative research have made numerous breakthroughs in the field.
 
The citation count for Professor Cho SeongHwan’s papers on analog circuits exceeds 3,000 citations, and he has received prestigious awards, including the IEEE Circuits & Systems Society Best Paper Award and the ISSCC Outstanding Far-East Paper Award.
 
His outstanding research was acknowledged by people in his field, as he served as an associate editor for IEEE Journal of Solid-State Circuits, IEEE Transactions on Circuits & Systems-I, TPC Chair for the IEEE Asian Solid-State Circuits Conference., and SSCS Distinguished Lecturer.
 
Furthermore, Professor Cho SeongHwan has been contributing to the development of semiconductor education in Korea for 20 years through his voluntary work at IDEC. Especially, he introduced the sub-MPW system, enhancing accessibility to MPW (Multi-Project Wafer) for domestic universities to help students.
 
* Catalog attached.

 

Prof. Hyun Myung Receives Academic Awards from Korea Robotics Society and ICROS

Prof. Hyun Myung Receives Academic Awards from Korea Robotics Society and ICROS

 

<Professor Hyun Myung>
 

Professor Hyun Myung from the School of Electrical Engineering has received academic awards from two major domestic robotics societies, the Korea Robotics Society and the ICROS (Institute for Control, Robotics and Systems).

 

Professor Hyun Myung was awarded the academic award at the regular meeting of the Korea Robotics Society, held at the SC Convention in Seoul on December 1st.

The Korea Robotics Society’s academic award is the most prestigious award given by the society at the end of each year.

It is awarded to a researcher who has made outstanding contributions to the development of domestic and international robotics technology and related fields through innovative research achievements and publication activities.

 

Professor Hyun Myung’s research team has published over 100 SCI papers and presented more than 300 international conference papers in the field of autonomous robot navigation.

Additionally, they received recognition for their excellent achievements, including winning the Autonomous Quadruped Robot Competition at the 2023 IEEE ICRA (International Conference on Robotics and Automation) held in London, UK, and being double-crowned champion of the HILTI SLAM Challenge.

 

Furthermore, Professor Hyun Myung was honored with the IEEE Academic Activity Award at the regular meeting of the ICROS (Institute for Control, Robotics and Systems) held at the Venezia Hotel in Yeosu on October 19th.

The IEEE Academic Activity Award is one of six academic awards presented annually by ICROS and is awarded to researchers who have demonstrated outstanding IEEE-related academic activities.

Professor Hyun Myung received this award in recognition of his achievements this year, including winning the IEEE ICRA Autonomous Quadruped Robot Competition and achieving double championships in the HILTI SLAM Challenge.

 

 

Inline image 2023 12 06 16.10.37.473

<Academic Award & IEEE Academic Acitivity Award>

 

 

Inline image 2023 12 06 16.12.19.303

<Award Ceremony, Korean Robotics Society>

 

/Reference/ Robot News (December 5, 2023): “Completion of the 2023 Annual Meeting of the Korean Robotics Society”

https://www.irobotnews.com/news/articleView.html?idxno=33416 

Professor Lee Si-Hyeon Selected as Distinguished Lecturer for the IEEE Information Theory Society

Professor Lee Si-Hyeon Selected as Distinguished Lecturer for the IEEE Information Theory Society

<Professor Lee Si-Hyeon>
 
 
Professor Lee Si-Hyeon from the Department of Electrical and Electronic Engineering has been selected as a Distinguished Lecturer for the IEEE Information Theory Society (ITSoc). She will serve the role for two years starting from 2024.
 
Every year, the IEEE ITSoc selects a few world-renowned scholars in the field of information theory as Distinguished Lecturers.
They support invited lectures in chapters around the world, providing society members and the general public with the latest research trends and an opportunity to directly communicate with the Distinguished Lecturers.
 
Professor Lee Si-Hyeon was selected as a Distinguished Lecturer in recognition of her excellence in research on network information theory and statistical inference.
Recently, she was also appointed as the TPC Co-Chair for the IEEE Information Theory Workshop 2024, one of the most prestigious conferences in the field of information theory.
 
The list of IEEE ITSoc Distinguished Lecturers can be found at the link below.
Link: https://www.itsoc.org/resources/dlp

 

Kim Minje, PhD Candidate in Professor Choi Junil’s Research Lab at the Department of EE, Awarded the 15th ICT Paper Competition Grand Exhibition

Kim Minje, PhD Candidate in Professor Choi Junil’s Research Lab at the Department of EE, Awarded the 15th ICT Paper Competition Grand Exhibition

 

<Professor Choi Junil and Ph.D. candidate Kim Minje>

 

Professor Choi Junil’s research lab at the Department of EE congratulates doctoral candidate Kim Minje for receiving an excellence award at the 15th ICT Paper Competition Grand Exhibition, hosted by the Electronic Newspaper, Web Keshi Group, and the Software Credit Union.

 

Over the past five years, professor Choi Junil’s research team has been recognized with outstanding awards, including the highest honors and excellence awards, in the ICT Paper Competition Grand Exhibition.

 

The research by PhD candidate Kim Minje, titled “Meta-Heuristic Fronthaul Bit Allocation for Cell-free Massive MIMO Systems,” proposes an algorithm to efficiently solve the problem of distributing front-haul link capacity in Cell-free multi-antenna systems.

 

This research suggests a technology that can effectively reduce the computational workload of central processing units (CPUs), which rapidly increases with the growing number of terminals and access points (APs).

 

Link:  https://www.etnews.com/20231117000193

 

 

Ph.D. candidate Sunjae Yoon (Prof. Chang D. Yoo) wins Best Paper Award

Ph.D. candidate Sunjae Yoon (Prof. Chang D. Yoo) wins Best Paper Award

 

Inline image 2023 12 01 17.35.13.048

<Professor Chang D. Yoo and Ph.D. candidate Sunjae Yoon>
 
 
Ph.D. candidate Sunjae Yoon from Professor Chang D. Yoo’s lab at our department won the Best Paper Award at the 2023 Korean Artificial Intelligence Association.
The Korean Artificial Intelligence Association holds conferences every spring and fall, and this academic conference was held by Naver from November 23 to 25, 2023.
Ph.D. candidate Sunjae Yoon presented a paper titled ‘Pivotal Prompt Tuning for Video Dynamic Editing’ and was selected as the award recipient in recognition of its excellence.
 
 
The detailed information is as follows:
 * Conference Name: 2023 Fall Conference of the Korean Artificial Intelligence Association
 * Period: November 23 to 25, 2023
 * Award Name: Best Paper Award
 * Authors: Sunjae Yoon, Gwanhyeong Koo, Ji Woo Hong, Hee Suk Yoon, Chang D. Yoo (Supervising Professor)
 * Paper Title: Pivotal Prompt Tuning for Video Dynamic Editing
 
 
Inline image 2023 12 01 17.36.34.177

 

Prof. Myoungsoo Jung’s research team develops DockerSSD, a smart SSD that can be utilized as independent server without computer

Inline image 2023 11 29 10.14.46.051

 <ph.D Miryeong Kwon, Prof. Myoungsoo Jung, ph.D. candidate Donghyun Gouk and Hanyeoreum Bae>

 

Our department’s Professor Myoungsoo Jung’s research team has developed ‘DockerSSD,’ which allows storage devices to be utilized as independent server that processes data without computer.
 
 
The DockerSSD employs Docker, a widely used operating system-level virtualization software, to provide a complete environment for executing user-level applications.
Such a complete environment empowers the users to easily leverage Smart SSD technology.
The evaluation result showed that DockerSSD accelerates the execution by 2x and reduces the power consumption by 2x.
 
Smart SSD technology has been discussed for decades as a solution to accelerate data processing by minimizing data movement. To leverage Smart SSD’s advantage, there were numerous approaches from memory/storage vendors.
 
However, these approaches have not been widely deployed due to their poor usability. This is because the vendors did not want their internal hardware and software disclosed.
Instead, they have provided their internal environments through different interfaces, forcing applications to be modified to fit these interfaces.
 
To enhance the usability of Smart SSD technology, Prof. Jung’s research team developed DockerSSD, a new way of Smart SSD that employs Docker inside the storage device.
Docker is an operating system-level virtualization software that provides all the necessary environments for user applications running on the operating system. By leveraging Docker, DockerSSD can implement an environment used in a host within the storage device.
 
This allows users to run their application in storage, without being bounded by vendor-specific interfaces. Since this work relieves a significant burden on the users while providing high performance and high energy efficiency, the research team expects this work to be widely adopted in growing data centers.
 
 
Inline image 2023 11 29 10.19.14.910
(picture 1 Docker SSD’s hardware prototype)
 
 
Inline image 2023 11 29 10.20.30.720

(picture 2   Docker SSD’s logotype)

 
The KAIST Ph.D. Candidates (Donghyun Gouk, Miryeong Kwon, and Hanyeoreum Bae) participated in this research, and the paper (DockerSSD: Containerized In-Storage Processing and Hardware Acceleration for Computational SSDs) will be presented in March at ‘IEEE International Symposium on High Performance Computer Architecture, (HPCA) 2024’ held in Edinburgh, Scotland.
 

The research was supported by Panmnesia(http://panmnesia.com) and Institute for Information and Communication Technology Promotion Planning and Evaluation(IITP).

 
More information on this paper can be found at CAMELab website (http://camelab.org)

This result has been reported by domestic media as followed.

 

[Link]

ChosunBiz: https://n.news.naver.com/mnews/article/366/0000950506?sid=105
Donga Science: https://n.news.naver.com/mnews/article/584/0000025070?sid=105
Electronic Times: https://n.news.naver.com/mnews/article/030/0003160306?sid=102
AI Times: https://www.aitimes.kr/news/articleView.html?idxno=29501
The Herald Business: https://n.news.naver.com/mnews/article/016/0002230110?sid=105
ZDNet Korea: https://n.news.naver.com/mnews/article/092/0002312851?sid=105
Naver: https://search.naver.com/search.naver?where=news&sm=tab_tnw&query=%EB%8F%84%EC%BB%A4ssd&nso=so:r,p:all,a:all&related=1&docid=4210007199396
Daum: https://search.daum.net/search?nil_suggest=btn&w=news&DA=SBC&cluster=y&q=%EB%8F%84%EC%BB%A4SSD+KAIST