Department+of+mechanical+engineering
-
Hubo Professor Jun-Ho Oh Donates Startup Shares Worth 5 Billion KRW
Rainbow Robotics stock used to endow the development fund
Emeritus Professor Jun-Ho Oh, who developed the 2015 DARPA Challenge winning humanoid robot DRC-Hubo, donated 5 billion KRW on October 25 during a ceremony held at the KAIST campus in Daejeon.
Professor Oh donated his 20% share (400 shares) of his startup Rainbow Robotics, which was established in 2011. Rainbow Robotics was listed on the KOSDAQ this February. The 400 shares were converted to 200,000 shares with a value of approximately 5 billion KRW when listed this year.
KAIST sold the stocks and endowed the Jun-Ho Oh Fund, which will be used for the development of the university. He was the 39th faculty member who launched a startup with technology from his lab and became the biggest faculty entrepreneur donor.
“I have received huge support and funding for my research. Fortunately, the research had a good result and led to the startup. Now I am very delighted to pay back the university. I feel that I have played a part in building the school’s startup ecosystem and creating a virtuous circle,” said Professor Oh during the ceremony.
KAIST President Kwang Hyung Lee declared, “Professor Oh has been a very impressive exemplary model for our aspiring faculty and student tech startups. We will spare no effort to support startups at KAIST.”
Professor Oh, who retired from the Department of Mechanical Engineering last year, now serves as the CTO at Rainbow Robotics. The company is developing humanoid bipedal robots and collaborative robots, and advancing robot technology including parts for astronomical observations.
Professor Hae-Won Park and Professor Je Min Hwangbo, who are now responsible for the Hubo Lab, also joined the ceremony along with employees of Rainbow Robotics.
2021.10.26 View 6374 -
Flexible Sensor-Integrated RFA Needle Leads to Smarter Medical Treatment
Clinical trial of flexible sensor-integrated radiofrequency ablation (RFA) needle tip monitors physical changes and steam pop
Researchers have designed a thin polymeric sensor platform on a radiofrequency ablation needle to monitor temperature and pressure in real time. The sensors integrated onto 1.5 mm diameter needle tip have proven their efficacy during clinical tests and expect to provide a new opportunity for safer and more effective medical practices. The research was reported in Advanced Science as the frontispiece on August 5.
Radiofrequency ablation (RFA) is a minimally invasive surgery technique for removing tumors and treating cardiovascular disease. During a procedure, an unintended audible explosion called ‘steam pop’ can occur due to the increased internal steam pressure in the ablation region. This phenomenon has been cited as a cause of various negative thermal and mechanical effects on neighboring tissue. Even more, the relationship between steam pop and cancer recurrence is still being investigated.
Professor Inkyu Park said that his team’s integrated sensors reliably detected the occurrence of steam pop. The sensors also monitor rapidly spreading hot steam in tissue. It is expected that the diverse properties of tissue undergoing RFA could be checked by utilizing the physical sensors integrated on the needle.
“We believe that the integrated sensors can provide useful information about a variety of medical procedures and accompanying environmental changes in the human body, and help develop more effective and safer surgical procedures,” said Professor Park.
Professor Park’s team built a thin film type pressure and temperature sensor stack with a thickness of less than 10 μm using a microfabrication process. For the pressure sensor, the team used contact resistance changes between metal electrodes and a carbon nanotube coated polymeric membrane. The entire sensor array was thoroughly insulated with medical tubes to minimize any exposure of the sensor materials to external tissue and maximize its biocompatibility.
During the clinical trial, the research team found that the accumulated hot steam is suddenly released during steam pops and this hot air spreads to neighboring tissue, which accelerates the ablation process. Furthermore, using in-situ ultrasound imaging and computational simulations, the research team could confirm the non-uniform temperature distribution around the RFA needle can be one of the primary reasons for the steam popping.
Professor Park explained that various physical and chemical sensors for different targets can be added to create other medical devices and industrial tools.
“This result will expand the usability and applicability of current flexible sensor technologies. We are also trying to integrate this sensor onto a 0.3mm diameter needle for in-vivo diagnosis applications and expect that this approach can be applied to other medical treatments as well as the industrial field,” added Professor Park. This study was supported by the National Research Foundation of Korea.
-PublicationJaeho Park, Jinwoo Lee, Hyo Keun Lim, Inkyu Park et al. “Real-Time Internal Steam Pop Detection during Radiofrequency Ablation with a Radiofrequency Ablation Needle Integrated with a Temperature and Pressure Sensor: Preclinical and clinical pilot tests," Advanced Science (https://doi/org/10.1002/advs.202100725) on August 5, 2021
-ProfileProfessor Inkyu ParkMicro & Nano Tranducers Laboratory http://mintlab1.kaist.ac.kr/
Department of Mechanical EngineeringCollege of EngineeringKAIST
2021.10.20 View 6227 -
Deep Learning Framework to Enable Material Design in Unseen Domain
Researchers propose a deep neural network-based forward design space exploration using active transfer learning and data augmentation
A new study proposed a deep neural network-based forward design approach that enables an efficient search for superior materials far beyond the domain of the initial training set. This approach compensates for the weak predictive power of neural networks on an unseen domain through gradual updates of the neural network with active transfer learning and data augmentation methods.
Professor Seungwha Ryu believes that this study will help address a variety of optimization problems that have an astronomical number of possible design configurations. For the grid composite optimization problem, the proposed framework was able to provide excellent designs close to the global optima, even with the addition of a very small dataset corresponding to less than 0.5% of the initial training data-set size. This study was reported in npj Computational Materials last month.
“We wanted to mitigate the limitation of the neural network, weak predictive power beyond the training set domain for the material or structure design,” said Professor Ryu from the Department of Mechanical Engineering.
Neural network-based generative models have been actively investigated as an inverse design method for finding novel materials in a vast design space. However, the applicability of conventional generative models is limited because they cannot access data outside the range of training sets. Advanced generative models that were devised to overcome this limitation also suffer from weak predictive power for the unseen domain.
Professor Ryu’s team, in collaboration with researchers from Professor Grace Gu’s group at UC Berkeley, devised a design method that simultaneously expands the domain using the strong predictive power of a deep neural network and searches for the optimal design by repetitively performing three key steps.
First, it searches for few candidates with improved properties located close to the training set via genetic algorithms, by mixing superior designs within the training set. Then, it checks to see if the candidates really have improved properties, and expands the training set by duplicating the validated designs via a data augmentation method. Finally, they can expand the reliable prediction domain by updating the neural network with the new superior designs via transfer learning. Because the expansion proceeds along relatively narrow but correct routes toward the optimal design (depicted in the schematic of Fig. 1), the framework enables an efficient search.
As a data-hungry method, a deep neural network model tends to have reliable predictive power only within and near the domain of the training set. When the optimal configuration of materials and structures lies far beyond the initial training set, which frequently is the case, neural network-based design methods suffer from weak predictive power and become inefficient.
Researchers expect that the framework will be applicable for a wide range of optimization problems in other science and engineering disciplines with astronomically large design space, because it provides an efficient way of gradually expanding the reliable prediction domain toward the target design while avoiding the risk of being stuck in local minima. Especially, being a less-data-hungry method, design problems in which data generation is time-consuming and expensive will benefit most from this new framework.
The research team is currently applying the optimization framework for the design task of metamaterial structures, segmented thermoelectric generators, and optimal sensor distributions. “From these sets of on-going studies, we expect to better recognize the pros and cons, and the potential of the suggested algorithm. Ultimately, we want to devise more efficient machine learning-based design approaches,” explained Professor Ryu.This study was funded by the National Research Foundation of Korea and the KAIST Global Singularity Research Project.
-Publication
Yongtae Kim, Youngsoo, Charles Yang, Kundo Park, Grace X. Gu, and Seunghwa Ryu, “Deep learning framework for material design space exploration using active transfer learning and data augmentation,” npj Computational Materials (https://doi.org/10.1038/s41524-021-00609-2)
-Profile
Professor Seunghwa Ryu
Mechanics & Materials Modeling Lab
Department of Mechanical Engineering
KAIST
2021.09.29 View 8765 -
How Stingrays Became the Most Efficient Swimmers in Nature
Study shows the hydrodynamic benefits of protruding eyes and mouth in a self-propelled flexible stingray
With their compressed bodies and flexible pectoral fins, stingrays have evolved to become one of nature’s most efficient swimmers. Scientists have long wondered about the role played by their protruding eyes and mouths, which one might expect to be hydrodynamic disadvantages.
Professor Hyung Jin Sung and his colleagues have discovered how such features on simulated stingrays affect a range of forces involved in propulsion, such as pressure and vorticity. Despite what one might expect, their research team found these protruding features actually help streamline the stingrays.
‘The influence of the 3D protruding eyes and mouth on a self-propelled flexible stingray and its underlying hydrodynamic mechanism are not yet fully understood,” said Professor Sung. “In the present study, the hydrodynamic benefit of protruding eyes and mouth was explored for the first time, revealing their hydrodynamic role.”
To illustrate the complex interplay between hydrodynamic forces, the researchers set to work creating a computer model of a self-propelled flexible plate. They clamped the front end of the model and then forced it to mimic the up-and-down harmonic oscillations stingrays use to propel themselves.
To re-create the effect of the eyes and mouth on the surrounding water, the team simulated multiple rigid plates on the model. They compared this model to one without eyes and a mouth using a technique called the penalty immersed boundary method.
“Managing random fish swimming and isolating the desired purpose of the measurements from numerous factors was difficult,” Sung said. “To overcome these limitations, the penalty immersed boundary method was adopted to find the hydrodynamic benefits of the protruding eyes and mouth.”
The team discovered that the eyes and mouth generated a vortex of flow in the forward-backward , which increased negative pressure at the simulated animal’s front, and a side-to-side vortex that increased the pressure difference above and below the stingray. The result was increased thrust and accelerated cruising.
Further analysis showed that the eyes and mouth increased overall propulsion efficiency by more than 20.5% and 10.6%, respectively.
Researchers hope their work, driven by curiosity, further stokes interest in exploring fluid phenomena in nature. They are hoping to find ways to adapt this for next-generation water vehicle designs based more closely on marine animals.
This study was supported by the National Research Foundation of Korea and the State Scholar Fund from the China Scholarship Council.
-ProfileProfessor Hyung Jin SungDepartment of Mechanical EngineeringKAIST
-PublicationHyung Jin Sung, Qian Mao, Ziazhen Zhao, Yingzheng Liu, “Hydrodynamic benefits of protruding eyes and mouth in a self-propelled flexible stingray,” Aug.31, 2021, Physics of Fluids
(https://doi.org/10.1063/5.0061287)
-News release from the American Institute of Physics, Aug.31, 2021
2021.09.06 View 5487 -
Electrosprayed Micro Droplets Help Kill Bacteria and Viruses
With COVID-19 raging around the globe, researchers are doubling down on methods for developing diverse antimicrobial technologies that could be effective in killing a virus, but harmless to humans and the environment.
A recent study by a KAIST research team will be one of the responses to such efforts. Professor Seung Seob Lee and Dr. Ji-hun Jeong from the Department of Mechanical Engineering developed a harmless air sterilization prototype featuring electrosprayed water from a polymer micro-nozzle array. This study is one of the projects being supported by the KAIST New Deal R&D Initiative in response to COVID-19. Their study was reported in Polymer.
The electrosprayed microdroplets encapsulate reactive oxygen species such as hydroxyl radicals, superoxides that are known to have an antimicrobial function. The encapsulation prolongs the life of reactive oxygen species, which enable the droplets to perform their antimicrobial function effectively. Prior research has already proven the antimicrobial and encapsulation effects of electrosprayed droplets.
Despite its potential for antimicrobial applications, electrosprayed water generally operates under an electrical discharge condition, which can generate ozone. The inhalation of ozone is known to cause damage to the respiratory system of humans. Another technical barrier for electrospraying is the low flow rate problem. Since electrospraying exhibits the dependence of droplet size on the flow rate, there is a limit for the amount of water microdroplets a single nozzle can produce.
With this in mind, the research team developed a dielectric polymer micro-nozzle array to perform the multiplexed electrospraying of water without electrical discharge. The polymer micro-nozzle array was fabricated using the MEMS (Micro Electro-Mechanical System) process. According to the research team, the nozzle can carry five to 19 micro-nozzles depending on the required application.
The high aspect ratio of the micro-nozzle and an in-plane extractor were proposed to concentrate the electric field at the tip of the micro-nozzle, which prevents the electrical discharge caused by the high surface tension of water. A micro-pillar array with a hydrophobic coating around the micro-nozzle was also proposed to prevent the wetting of the micro-nozzle array.
The polymer micro-nozzle array performed in steady cone jet mode without electrical discharge as confirmed by high-speed imaging and nanosecond pulsed imaging. The water microdroplets were measured to be in the range of six to 10 μm and displayed an antimicrobial effect on Escherichia coli and Staphylococcus aureus.
Professor Lee said, “We believe that this research can be applied to air conditioning products in areas that require antimicrobial and humidifying functions.”
Publication:
Jeong, J. H., et al. (2020) Polymer micro-atomizer for water electrospray in the cone jet mode. Polymer. Vol. No. 194, 122405. Available online at https://doi.org/10.1016/j.polymer.2020.122405
Profile: Seung Seob Lee, Ph.D.
sslee97@kaist.ac.kr
http://mmst.kaist.ac.kr/
Professor
Department of Mechanical Engineering (ME)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr
Daejeon 34141, Korea
Profile: Ji-hun Jeong, Ph.D.
jiuni6022@kaist.ac.kr
Postdoctoral researcher
Department of Mechanical Engineering (ME)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr
Daejeon 34141, Korea
(END)
2020.12.21 View 10282 -
‘WalkON Suit 4’ Releases Paraplegics from Wheelchairs
- KAIST Athletes in ‘WalkON Suit 4’ Dominated the Cybathlon 2020 Global Edition. -
Paraplegic athletes Byeong-Uk Kim and Joohyun Lee from KAIST’s Team Angel Robotics won a gold and a bronze medal respectively at the Cybathlon 2020 Global Edition last week. ‘WalkON Suit 4,’ a wearable robot developed by the Professor Kyoungchul Kong’s team from the Department of Mechanical Engineering topped the standings at the event with double medal success.
Kim, the former bronze medallist, clinched his gold medal by finishing all six tasks in 3 minutes and 47 seconds, whereas Lee came in third with a time of 5 minutes and 51 seconds. TWIICE, a Swiss team, lagged 53 seconds behind Kim’s winning time to be the runner-up.
Cybathlon is a global championship, organized by ETH Zurich, which brings together people with physical disabilities to compete using state-of-the-art assistive technologies to perform everyday tasks. The first championship was held in 2016 in Zurich, Switzerland.
Due to the COVID-19 pandemic, the second championship was postponed twice and held in a new format in a decentralized setting. A total of 51 teams from 20 countries across the world performed the events in their home bases in different time zones instead of traveling to Zurich. Under the supervision of a referee and timekeeper, all races were filmed and then reviewed by judges.
KAIST’s Team Angel Robotics participated in the Powered Exoskeleton Race category, where nine pilots representing five nations including Korea, Switzerland, the US, Russia, and France competed against each other.
The team installed their own arena and raced at the KAIST Main Campus in Daejeon according to the framework, tasks, and rules defined by the competition committee. The two paraplegic pilots were each equipped with exoskeletal devices, the WalkON Suit 4, and undertook six tasks related to daily activities.
The WalkON Suit 4 recorded the fastest walking speed for a complete paraplegic ever reported. For a continuous walk, it achieved a maximum speed of 40 meters per minute. This is comparable to the average walking pace of a non-disabled person, which is around two to four kilometers per hour.
The research team raised the functionality of the robot by adding technology that can observe the user’s level of anxiety and external factors like the state of the walking surface, so it can control itself intelligently. The assistive functions a robot should provide vary greatly with the environment, and the WalkON Suit 4 made it possible to analyze the pace of the user within 30 steps and provide a personally optimized walking pattern, enabling a high walking speed.
The six tasks that Kim and Lee had to complete were:1) sitting and standing back up, 2) navigating around obstacles while avoiding collisions, 3) stepping over obstacles on the ground, 4) going up and down stairs, 5) walking across a tilted path, and 6) climbing a steep slope, opening and closing a door, and descending a steep slope.
Points were given based on the accuracy of each completed task, and the final scores were calculated by adding all of the points that were gained in each attempt, which lasted 10 minutes. Each pilot was given three opportunities and used his/her highest score. Should pilots have the same final score, the pilot who completed the race in the shortest amount of time would win.
Kim said in his victory speech that he was so thrilled to see all his and fellow researchers’ years of hard work paying off. “This will be a good opportunity to show how outstanding Korean wearable robot technologies are,” he added.
Lee, who participated in the competition for the first time, said, “By showing that I can overcome my physical disabilities with robot technology, I’d like to send out a message of hope to everyone who is tired because of COVID-19”.
Professor Kong’s team collaborated in technology development and pilot training with their colleagues from Angel Robotics Co., Ltd., Severance Rehabilitation Hospital, Yeungnam University, Stalks, and the Institute of Rehabilitation Technology.
Footage from the competition is available at the Cybathlon’s official website.
(END)
2020.11.20 View 6929 -
KAIST Showcases Healthcare Technologies at K-Hospital Fair 2020
KAIST Pavilion showcased its innovative medical and healthcare technologies and their advanced applications at the K-Hospital Fair 2020. Five KAIST research groups who teamed up for the Post-COVID-19 New Deal R&D Initiative Project participated in the fair held in Seoul last week.
The K-Hospital Fair is a yearly event organized by the Korean Hospital Association to present the latest research and practical innovations to help the medical industry better serve the patients. This year, 120 healthcare organizations participated in the fair and operated 320 booths.
At the fair, a research group led by Professor Il-Doo Kim from the Department of Materials Science and Engineering demonstrated the manufacturing process of orthogonal nanofibers used to develop their ‘recyclable nano-fiber filtered face mask’ introduced in March of this year. This mask has garnered immense international attention for maintaining its sturdy frame and filtering function even after being washed more than 20 times. Professor Kim is now extending his facilities for the mass production of this mask at his start-up company. While awaiting final approval from the Ministry of Food and Drug Safety to bring his product into the market, Professor Kim is developing other mask variations such as eco-friendly biodegradable masks and transparent masks to aid the hearing-impaired who rely on lip reading to communicate.
The team working under Professor Wonho Choe from the Department of Nuclear and Quantum Engineering presented two low-temperature plasma sterilizers for medical use, co-developed with Plasmapp, a start-up company founded by a KAIST alumnus. Their sterilizers are the first ones that can sterilize medical devices by diffusing hydrogen peroxide vapor into the pouch. They rapidly sterilize medical instruments and materials in just seven minutes without leaving toxic residue, while reducing sterilization time and costs by 90%.
Professor Hyung-Soon Park and his researchers from the Department of Mechanical Engineering introduced a smart protective suit ventilation system that features high cooling capacity and a slimmed-down design. For comfortable use, the suit is equipped with a technique that monitors its inner temperature and humidity and automatically controls its inner circulation accordingly. The group also presented a new system that helps a person in a contaminated suit undress without coming into contact with the contaminated outer part of the suit.
Professor Jong Chul Ye's group from the Department of Bio and Brain Engineering demonstrated AI software that can quickly diagnose an infectious disease based on chest X-ray imaging. The technique compares the differences in the severity of pneumonia in individual patients to distinguish whether their conditions fall under viral pneumonia including COVID-19, bacterial pneumonia, tuberculosis, other diseases, or normal conditions. The AI software visualizes the basis of its reasoning for each of the suspected diseases and provides them as information that can be utilized by medical personnel.
Finally, researchers of Professor Ki-Hun Jeong’s team from the Department of Bio and Brain Engineering demonstrated their ultra-high-speed sub-miniature molecular diagnostic system for the on-site diagnosis of diseases. The existing Polymerase Chain Reaction (PCR) diagnostic usually takes from 30 minutes to an hour to provide results, but their new technique using an LED light source can present results within just three minutes and it is expected to be used actively for on-site diagnosis.
Professor Choongsik Bae, the Director of the Post-COVID-19 New Deal R&D Initiative Project, said, “KAIST will build a healthy relationship amongst researchers, enterprises, and hospitals to contribute to the end of COVID-19 and build a new paradigm of Korean disease prevention and control.”
KAIST launched the Post-COVID-19 New Deal R&D Initiative in July with the support of the Ministry of Science and ICT of Korea. This unit was created to overcome the pandemic crisis by using science and technology, and to contribute to economic development by creating a new antiviral drug industry. The unit is comprised of 464 KAIST members including professors, researchers, and students as well as 503 professionals from enterprises, hospitals, and research centers.
(END)
2020.10.26 View 11223 -
Scientist of October: Professor Jungwon Kim
Professor Jungwon Kim from the Department of Mechanical Engineering was selected as the ‘Scientist of the Month’ for October 2020 by the Ministry of Science and ICT and the National Research Foundation of Korea. Professor Kim was recognized for his contributions to expanding the horizons of the basics of precision engineering through his research on multifunctional ultrahigh-speed, high-resolution sensors. He received 10 million KRW in prize money.
Professor Kim was selected as the recipient of this award in celebration of “Measurement Day”, which commemorates October 26 as the day in which King Sejong the Great established a volume measurement system.
Professor Kim discovered that the time difference between the pulse of light created by a laser and the pulse of the current produced by a light-emitting diode was as small as 100 attoseconds (10-16 seconds). He then developed a unique multifunctional ultrahigh-speed, high-resolution Time-of-Flight (TOF) sensor that could take measurements of multiple points at the same time by sampling electric light. The sensor, with a measurement speed of 100 megahertz (100 million vibrations per second), a resolution of 180 picometers (1/5.5 billion meters), and a dynamic range of 150 decibels, overcame the limitations of both existing TOF techniques and laser interferometric techniques at the same time. The results of this research were published in Nature Photonics on February 10, 2020.
Professor Kim said, “I’d like to thank the graduate students who worked passionately with me, and KAIST for providing an environment in which I could fully focus on research. I am looking forward to the new and diverse applications in the field of machine manufacturing, such as studying the dynamic phenomena in microdevices, or taking ultraprecision measurement of shapes for advanced manufacturing.”
(END)
2020.10.15 View 8853 -
Slippery When Wet: Fish and Seaweed Inspire Ships to Reduce Fluid Friction
Faster ships could be on the horizon after KAIST scientists develop a slippery surface inspired by fish and seaweed to reduce the hull's drag through the water.
Long-distance cargo ships lose a significant amount of energy due to fluid friction. Looking to the drag reduction mechanisms employed by aquatic life can provide inspiration on how to improve efficiency.
Fish and seaweed secrete a layer of mucus to create a slippery surface, reducing their friction as they travel through water. A potential way to mimic this is by creating lubricant-infused surfaces covered with cavities. As the cavities are continuously filled with the lubricant, a layer is formed over the surface.
Though this method has previously been shown to work, reducing drag by up to 18%, the underlying physics is not fully understood. KAIST researchers in collaboration with a team of researchers from POSTECH conducted simulations of this process to help explain the effects, and their findings were published in the journal Physics of Fluids on September 15.
The group looked at the average speed of a cargo ship with realistic material properties and simulated how it behaves under various lubrication setups. Specifically, they monitored the effects of the open area of the lubricant-filled cavities, as well as the thickness of the cavity lids.
They found that for larger open areas, the lubricant spreads more than it does with smaller open areas, leading to a slipperier surface. On the other hand, the lid thickness does not have much of an effect on the slip, though a thicker lid does create a thicker lubricant buildup layer.
Professor Emeritus Hyung Jin Sung from the KAIST Department of Mechanical Engineering who led this study said, “Our investigation of the hydrodynamics of a lubricant layer and how it results in drag reduction with a slippery surface in a basic configuration has provided significant insight into the benefits of a lubricant-infused surface.”
Now that they have worked on optimizing the lubricant secretion design, the authors hope it can be implemented in real-life marine vehicles.
“If the present design parameters are adopted, the drag reduction rate will increase significantly,” Professor Sung added.
This work was supported by the National Research Foundation (NRF) of Korea.
Source:
Materials provided by American Institute of Physics.
Publication:
Kim, Seung Joong, et al. (2020). A lubricant-infused slip surface for drag reduction. Physics of Fluids. Available online at https://doi.org/10.1063/5.0018460
Profile:
Hyung Jin Sung
Professor Emeritus
hyungjin@kaist.ac.kr
http://flow.kaist.ac.kr/index.php
Flow Control Lab. (FCL)
Department of Mechanical Engineering
http://kaist.ac.kr
Korea Advanced Institute of Science and Technology (KAIST)
Daejeon, Republic of Korea
(END)
2020.10.12 View 5868 -
Deep Learning-Based Cough Recognition Model Helps Detect the Location of Coughing Sounds in Real Time
The Center for Noise and Vibration Control at KAIST announced that their coughing detection camera recognizes where coughing happens, visualizing the locations. The resulting cough recognition camera can track and record information about the person who coughed, their location, and the number of coughs on a real-time basis.
Professor Yong-Hwa Park from the Department of Mechanical Engineering developed a deep learning-based cough recognition model to classify a coughing sound in real time. The coughing event classification model is combined with a sound camera that visualizes their locations in public places. The research team said they achieved a best test accuracy of 87.4 %.
Professor Park said that it will be useful medical equipment during epidemics in public places such as schools, offices, and restaurants, and to constantly monitor patients’ conditions in a hospital room.
Fever and coughing are the most relevant respiratory disease symptoms, among which fever can be recognized remotely using thermal cameras. This new technology is expected to be very helpful for detecting epidemic transmissions in a non-contact way. The cough event classification model is combined with a sound camera that visualizes the cough event and indicates the location in the video image.
To develop a cough recognition model, a supervised learning was conducted with a convolutional neural network (CNN). The model performs binary classification with an input of a one-second sound profile feature, generating output to be either a cough event or something else.
In the training and evaluation, various datasets were collected from Audioset, DEMAND, ETSI, and TIMIT. Coughing and others sounds were extracted from Audioset, and the rest of the datasets were used as background noises for data augmentation so that this model could be generalized for various background noises in public places.
The dataset was augmented by mixing coughing sounds and other sounds from Audioset and background noises with the ratio of 0.15 to 0.75, then the overall volume was adjusted to 0.25 to 1.0 times to generalize the model for various distances.
The training and evaluation datasets were constructed by dividing the augmented dataset by 9:1, and the test dataset was recorded separately in a real office environment.
In the optimization procedure of the network model, training was conducted with various combinations of five acoustic features including spectrogram, Mel-scaled spectrogram and Mel-frequency cepstrum coefficients with seven optimizers. The performance of each combination was compared with the test dataset. The best test accuracy of 87.4% was achieved with Mel-scaled Spectrogram as the acoustic feature and ASGD as the optimizer.
The trained cough recognition model was combined with a sound camera. The sound camera is composed of a microphone array and a camera module. A beamforming process is applied to a collected set of acoustic data to find out the direction of incoming sound source. The integrated cough recognition model determines whether the sound is cough or not. If it is, the location of cough is visualized as a contour image with a ‘cough’ label at the location of the coughing sound source in a video image.
A pilot test of the cough recognition camera in an office environment shows that it successfully distinguishes cough events and other events even in a noisy environment. In addition, it can track the location of the person who coughed and count the number of coughs in real time. The performance will be improved further with additional training data obtained from other real environments such as hospitals and classrooms.
Professor Park said, “In a pandemic situation like we are experiencing with COVID-19, a cough detection camera can contribute to the prevention and early detection of epidemics in public places. Especially when applied to a hospital room, the patient's condition can be tracked 24 hours a day and support more accurate diagnoses while reducing the effort of the medical staff."
This study was conducted in collaboration with SM Instruments Inc.
Profile: Yong-Hwa Park, Ph.D.
Associate Professor
yhpark@kaist.ac.kr
http://human.kaist.ac.kr/
Human-Machine Interaction Laboratory (HuMaN Lab.)
Department of Mechanical Engineering (ME)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr/en/
Daejeon 34141, Korea
Profile: Gyeong Tae Lee
PhD Candidate
hansaram@kaist.ac.kr
HuMaN Lab., ME, KAIST
Profile: Seong Hu Kim
PhD Candidate
tjdgnkim@kaist.ac.kr
HuMaN Lab., ME, KAIST
Profile: Hyeonuk Nam
PhD Candidate
frednam@kaist.ac.kr
HuMaN Lab., ME, KAIST
Profile: Young-Key Kim
CEO
sales@smins.co.kr
http://en.smins.co.kr/
SM Instruments Inc.
Daejeon 34109, Korea
(END)
2020.08.13 View 13089 -
Hubo Debuts as a News Anchor
HUBO, a humanoid robot developed by Professor Jun-Ho Oh’s team, made its debut as a co-anchor during the TJB prime time news 8 on May 14.
“Un-contact" became the new normal after Covid-19 and many business solutions are being transformed using robotics. HUBO made two news reports on contactless services using robots in medical, manufacturing, and logistics industries. HUBO 2, the second generation of HUBO, appeared as a special anchor on the local broadcasting network’s special program in celebration of its 25th anniversary.
HUBO is the champion of the 2015 DARPA Robotics Challenge held in the USA. Its FX-2 riding robot also participated in the Olympic torch relay during the 2018 PyeongChang Winter Olympics.
Click here to watch a full video of HUBO anchoring the news.
(END)
2020.05.14 View 9322 -
Professor Sukyung Park Named Presidential Science and Technology Adviser
Professor Sukyung Park from the Department of Mechanical Engineering was appointed as the science and technology adviser to the President Jae-in Moon on May 4. Professor Park, at the age of 47, became the youngest member of the president’s senior aide team at Chong Wa Dae.
A Chong Wa Dae spokesman said on May 4 while announcing the appointment, “Professor Park, a talent with a great deal of policymaking participation in science and technology, will contribute to accelerating the government’s push for science and technology innovation, especially in the information and communications technology (ICT) sector.”
Professor Park joined KAIST in 2004 as the first female professor of mechanical engineering. She is a biomechanics expert who has conducted extensive research on biometric mechanical behaviors. Professor Park is also a member of the KAIST Board of Trustees. Before that, she served as a senior researcher at the Korea Institute of Machinery and Materials (KIMM) as well as a member of the Presidential Advisory Council on Science and Technology.
After graduating from Seoul Science High School as the first ever two-year graduate, Professor Park earned a bachelor and master’s degrees in mechanical engineering at KAIST. She then finished her Ph.D. from the University of Michigan.
(END)
2020.05.06 View 10589