Jo Aug 28, 2026
UN and many countries are calling for urgent measures because air pollution caused by air pollutants seriously threatens human health and causes premature death. Many investigations and studies have revealed that PM2.5 is a main pollutant that destroys the environment of ecosystems and harms human health, and that air pollutants containing PM 2.5 cause various diseases such as respiratory, lung and heart diseases.
In the air pollution concentration prediction task, it was reported that the artificial neural network (ANN) model improves prediction performance while avoiding the complexity and annoyance of modeling, compared to the deterministic method which has lack in representing the heterogeneity and nonlinearity of many factors related to pollutant formation.
Therefore, many researchers have begun to apply artificial neural networks extensively to air pollution prediction, and since then they have ensured the accurate prediction performance by combining deep neural networks with several other optimization techniques that have shown dramatic effectiveness in the prediction of large time series data. In a word, their research results show that deep learning models significantly improve their performance when combined with several other effective analytical methods on time series data rather than being used as a single model.
Based on this analysis, Pak Un Jin, a researcher at the Faculty of Automatics, proposed a hybrid model consisting of convolutional neural network (CNN)-long short-term (LSTM) with multifractal detrended fluctuation analysis (MF-DFA) for air pollution and meteorological time series data, and used it to predict the next day’s 24-h average PM2.5 concentration in Beijing City.
The comparison of the performance indexes of the proposed model with MLP and LSTM models showed that the proposed model provides higher prediction accuracy.
For further details, please refer to his paper “A deep learning approach via multifractal detrended fluctuation analysis for PM2.5 prediction” in “Journal of Atmospheric and Solar-Terrestrial Physics” (SCI).
...
Jo Aug 27, 2026
The evacuated tube solar collector (ETSC) shows superior performance over the flat-plate collector (FPC) as it can reduce convective and radiation heat loss, and the thermal efficiency of ETSC has a linear relationship with the difference between the fluid inlet temperature and the ambient temperature divided by the solar radiation incident on the collector.
Under steady-state operating conditions, the useful output power of FPC is a function of many parameters, and one of them is the overall heat loss coefficient of FPC.
WGETSC (water-in-glass evacuated tube solar collector), unlike FPC, typically consists of 16-28 flooded solar tubes in direct connection to a horizontal water tank, so it is difficult to use the single overall heat loss coefficient as in FPC.
Having considered the solar tube and the water tank respectively in WGETSC, Jong Hyon Il, a section head at the Faculty of Thermal Engineering, derived a formula to determine the thermal performance of WGETSC and compared the calculated value with measured one.
The mean relative error between the measured and calculated values was 9.8%.
For more information, you can refer to his paper “On evaluating thermal performance of water-in-glass evacuated tube solar collector” in “International Journal of Research in Engineering”.
...
Jo Aug 26, 2026
As face is rather invariable among human biometric features, face recognition is considered as the most important biometric identification task. Face recognition has been widely used for user authentication in security systems such as electronic payment systems as a technology to search faces from facial images from photographs or videos and therefore, it has been studied for years.
Over the past decade, the mainstream of face recognition has been based on deep learning and it has been developed to a much higher level than average human ability. Nevertheless, face recognition is still far from “perfect”.
Recently, face recognition systems using convolutional neural networks are considered as the best methods among existing face recognition systems. Face recognition network models that have been developed and proved to be superior in performance cannot perform real-time face recognition in devices with constrained computational resources such as low base computers or mobile phones because their structure is very complex and they need a large amount of computation. What is more, reducing the number of layers continuously to reduce computational burden affects recognition performance.
In GhostFaceNets, they improved the trade-off between speed and accuracy by performing the attention operation using a DFC (decoupled fully-connected) attention. However, the DFC attention has limitations in capturing wide spatial information, which may lead to the degradation of recognition performance.
Jo Kwang Chol, a researcher at the Institute of Information Technology, has designed a network structure with low computational cost and improved performance by combining the self-attention module with the extended Ghost module based on the backbone of GhostFaceNets, and verified its accuracy using international standard databases.
The results showed that the proposed network model brings significant improvement in face recognition performance with 99.74% in LFW and 97.7% in AgeDB-30 and that with 42 MFLOP, it can support stable real-time face recognition in embedded devices.
For more details, you can refer to his paper “GhostFormerNet: A Lightweight Face Recognition Method based on Extended Ghost Module and Self-Attention” in “2025 International Conference on Graphics and Signal Processing”.
...
Jo Aug 25, 2026
Hydrodynamics of a floating body near a vertical wall is of interest in the field of coastal and offshore engineering. One reason for the need to understand this class of hydrodynamics is that lot of efforts have been devoted to developing the floating types of wave energy converters (WECs) that operate in nearshore or coastal zones from the purpose of reducing the emission of greenhouse gas. The other reason is that marine structures such as liquefied natural gas (LNG) shuttle carriers and very large floating structures (VLFS) are deployed near wharves or quay piers.
Rim Un Ryong, a researcher at the Faculty of Naval Architecture and Ocean Engineering, has studied the oscillating motion of an arbitrarily-shaped floating structure near a vertical wall under a linear wave by using a numerical method (i.e. BEM) with an exact NtD boundary condition.
His study results can be adopted to predict the motion responses and wave forces of an arbitrarily-shaped floating body in front of a vertical breakwater under a linear incident wave.
You can find details in his paper “Hydrodynamic Interaction Between a Linear Water Wave and a Floating Structure Near a Vertical Wall by Using an Exact Neumann-to-Dirichlet (NtD) Boundary Condition” in “Journal of The Institution of Engineers” (EI).
...
Jo Aug 24, 2026
As environmental protection is becoming more and more serious, it is a pressing task to reduce industrial waste as well as to develop eco-friendly material that can be used for people’s living.
Ri Chol Jin, a section head at the Faculty of Earth Science and Technology, has investigated a synthesis method of 13X zeolite using fine granite dust (FGD) resulting from granite processing. Zeolite has good physio-chemical properties as an adsorbent, a cation exchanger, a molecular sieve and a catalyst and it is widely used as a selective scavenger of heavy metals from liquid effluents.
He selected and applied both the alkaline fusion method (770-830℃, 80min) and the hydrothermal process (95-100℃, 8-12h) to the synthesis of 13X zeolite.
What is important in the synthesis of zeolite by using alkaline fusion method is high sintering temperature. He lowered the sintering temperature from 1 300℃ to 800℃ by putting FGD into water and maintaining it for 5 minutes to remove crystalline quartz which has low reactivity.
In addition, it is important to find appropriate sintering temperature at which albite is decomposed more easily than kalifeldspar in FGD because 13X zeolite is chemically concerned with sodium (Na). For this, he calculated the reaction heats of kalifeldspar and albite at the temperature range of 770~830℃.
As a result, he proved that albite has the possibility to be dissolved thermodynamically more easily than kalifeldspar, but the difference between the heat effects of albite and kalifeldspar is not so significant according to the increase in temperature.
Eventually, he successfully synthesized 13X zeolite from FGD with low energy consumption and all other stone processing waste can be recycled by this method.
For more information, you can refer to his paper “Characteristics of flourite{111} surface with various terminations: A first-principles investigation” in “Results in Surfaces and Interfaces” (SCOPUS).
...
Jo Aug 23, 2026
It is difficult to find out a suitable type for desired purpose among a large number of mechanisms that can be made by the spatial combination of links and joints. Here, quick calculation of correct mobility is the basic requirement for structural synthesis of parallel robot mechanisms.
Various methods reported in the literature for mobility calculation of closed loop mechanisms fall into two basic categories: an approach for mobility calculation based on setting up kinematic constraint equations and calculating their rank and an approach for finding formulae for quick calculation of mobility without constraint equations. Among them, the former is very useful.
Kim Yong Ho, a researcher at the Faculty of Mechanical Science and Technology, proposed a new method of calculating the mobility of parallel mechanisms by automatically generating velocity constraint equations and calculating the rank.
For automatic generation of kinematic constraint equations, he used formulae which enable automatic generation of the homogeneous transformation matrix and the Jacobian matrix of serial robot mechanisms.
He applied this method to CPM mechanism, Bennett mechanism and Bricard mechanism to validate its correctness, availability and prospectiveness.
For more information, please refer to his paper “Calculation of Correct Mobility of Special Mechanisms Based on Automatic Generation of Jacobian Matrix and Velocity Constraint Equation” in “Proceedings of KUTIC-2025”.
...