Jo Sep 23, 2026
Acoustic sediment classification methods are important for protecting and studying the ecological environment of rivers and seas. Single-beam echosounder, multi-beam echosounder and side-scan sonar are the main measuring means for sediment classification. Recently, neural networks have been applied to sediment classification to improve its accuracy.
Sediment classification using single-beam echosounders has the longest history, and many methods have been proposed for sediment classification using single-beam acoustic sounders.
Jong Kum Chol, a researcher at the Faculty of Naval Architecture and Ocean Engineering, proposed a new MLP-KNN model, a combination of recently widely-used MLP neural network and KNN model to improve sediment classification accuracy in shallow waters.
In shallow waters, the accuracy of sediment classification is reduced because echoes are overlapping. Hence, he first designed an MLP neural network where six feature parameters from the overlapping echo are taken as an input layer and the area of the overlapping part as an output layer, and estimated the area of the overlapping part. Then, based on the estimation results, he calculated E1 and E2 derived from the first and second echoes, respectively, and classified sediment using the KNN model.
The comparison results with the sediment classification method by BP neural network showed that the proposed method classifies sediment with higher accuracy in shallow waters.
For more information, please refer to his paper “Acoustic sediment classification using MLP-KNN model on single-beam echosounder data from shallow water” in “Marine Systems & Ocean Technology” (EI).
...
Jo Sep 22, 2026
Traditionally, process planning and scheduling were executed sequentially. Sequential execution of process planning and scheduling has numerous shortcomings including unbalanced resource utilization and unrealistic process plans.
Recently, researchers have investigated various approaches to overcome the shortcoming of the sequential approach for process planning and scheduling. Although there are various meta-heuristics for IPPS, they still need further improvements using a more efficient algorithm. Moreover, there is a lack of research of effective algorithms for multi-objective IPPS.
Kim Yong Ho, an institute head at the Faculty of Automatics, proposed a new multi-objective differential evolutionary algorithm combined with chaotic map to solve IPPS problems.
The experimental results showed that the proposed algorithm is better than other multi-objective optimization algorithms for IPPS problems.
For further details, you can refer to his paper “A Chaotic-Based Multi-Objective Differential Evolutionary Algorithms for Integrated Process Planning and Scheduling” in “Proceedings of KUTIC-2025”.
...
Jo Sep 22, 2026
Traditional proportional-integral-derivative (PID) controllers may not achieve the control performance desired for large time delay processes. Meanwhile, PI-PD controller is an improved version of PID controller, which can effectively improve the control performance of large time delay plants. However, it still has difficulty in parameter tuning. Even if its parameters can be tuned, the PI-PD may not ensure desired performance because of the large time delay and uncertainties of processes.
Recently, predictive function control (PFC) has been widely applied in practice since it is suitable for effectively coping with large time delays and uncertainties. Therefore, combining PFC with PI-PD control may be a good choice.
Kang Chung Hyok, a researcher at the Faculty of Metallic Engineering, designed a PI-PD controller using predictive functional control (PFC) based on the state space model of processes in order to solve the problem of complex parameter tuning. In order to further improve the performance of the controller, he used an improved grasshopper optimization algorithm (GOA) to optimize the weighting matrix of cost function that has a great impact on the performance of the state space PFC.
The simulation results showed that the proposed design method is far superior to other methods in terms of set-point tracking, disturbance rejection and robustness.
You can find more information in his paper “A Novel PI-PD Controller Design Based on Extended State Space Predictive Functional Control using Improved Grasshopper Optimization Algorithm” in “Proceedings of KUTIC-2025”.
...
Jo Sep 21, 2026
Recently, relay protection devices using digital signal processing techniques have been widely used in power systems to improve the reliability of power supply. In these devices, voltage and current signals are converted into discrete data and appropriate algorithms are used to calculate the results for protection. To detect faults accurately and quickly, voltage and current signals need to be acquired at a high speed and many input data must be processed simultaneously.
Many advanced protection algorithms are implemented in microprocessor-based relay protection devices in the form of software. All conventional microprocessor-based relay protection devices implement protection algorithms by using the continuity of software architecture, which takes up some time for CPU and thus limits the operating speed of protection.
Due to the characteristics of inherent parallel hardware routing architecture, FPGAs (field programmable gate arrays) have many applications in industrial and mass manufacturing systems. Some researchers proposed a scheme to implement the function of relay protection by utilizing the characteristics of FPGA.
Im Jung Bin, a researcher at the Faculty of Electronics, proposed a novel FPGA-based data acquisition and processing system to realize fast operation of protection.
Using the characteristics of parallel operation of FPGA, the proposed digital relay protection device can simultaneously judge multi-protection logic by controlling ADCs that simultaneously sample and transform the voltage and current signals of multiple channels and by processing discrete data in real time with full cycle discrete Fourier transform (FCDFT) algorithm. The proposed data acquisition and processing module is configured in the Altera Cyclone III EP3C40Q240CN8 to realize high-speed operation, the main requirement of relay protection.
The proposed digital relay protection device can operate within 1.1 cycles of power system frequency.
For more information, please refer to his paper “FPGA-Based Data Acquisition and Processing System for Digital Relay Protection” in “Proceedings of KUTIC-2025”.
...
Jo Sep 20, 2026
Recently, the ecological environment is deteriorating due to various natural disasters caused by global warming and domestic waste. Therefore, it is important to develop a reliable USV control approach to collect river or sea waste under the challenging environment.
Kim Chung Il, a researcher at the Faculty of Naval Architecture and Ocean Engineering, established a mathematical model of USV motion and a wind model in the presence of mass variation, and then designed a fuzzy neural adaptive sliding mode controller to estimate uncertain mass and wind disturbance simultaneously when collecting sea waste.
First, he devised a mathematical model of USV motion and a wind model to consider added mass and wind variation when collecting sea waste. Then, he used a fuzzy neural method to determine varying wind effect during the mass variation and designed a nonlinear disturbance observer to estimate uncertain disturbances involving mass variation. Finally, he designed an adaptive sliding mode controller to consider varying displacement and wind effect.
The simulation results showed that this methodology enables USV to deal with added mass and varying wind disturbance during a transient period of time to collect sea waste.
You can find more information in his paper “Fuzzy Neural Adaptive SMC of an Unmanned Surface Vehicle for Sea Waste Collection with Varying Displacement and Wind Effect” in “Proceedings of KUTIC-2025”.
...
Jo Sep 18, 2026
The most efficient routing approach for data collection in WSNs is the cluster-based approach. The sensor nodes of WSNs are discriminated by several multi-criteria. Hence, a number of energy-efficient cluster-based routing protocols that comprehensively consider these mutually contradictory multi-criteria have been developed.
The typical algorithms which were used to comprehensively consider multi-criteria include fuzzy logic, MCDM, meta-heuristic optimization algorithm, and the combination of these approaches.
MCDM approach is mainly used to evaluate the completed alternatives defined by several criteria or factors. Thus, recently, there has been active research effort to exploit MCDM approaches for cluster-based routing.
The goal of cluster-based routing optimization is to maximize energy consumption balancing among nodes by taking into account various criteria in the whole process of clustering routing while maintaining stability, reliability and connectivity of network, and thus to extend network lifetime as much as possible. However, existing cluster-based routing protocols exploit either individual MCDM approaches or fuzzy logic or meta-heuristic optimization algorithms in the cluster head (CH) node selection of clustering stage.
Ri Man Gun, an institute head at the Faculty of Communication, proposed a novel clustering scheme using adaptive fuzzy C-means (AFCM) and an improved ant-lion optimization (ALO) approach.
This scheme first divides the whole network into k clusters using the AFCM algorithm. After that, an improved ALO is applied to each cluster to select the optimal CH nodes. The improved ALO prescribes a new fitness function by the multi-criteria based on the weights assigned by FCNP-VWA.
The simulation results revealed that the proposed scheme achieves superior energy consumption balance.
For more information, you can refer to his paper “An Energy Efficient Routing Scheme using a Hybrid MCDM and Meta-Heuristic Algorithm in WSNs” in “Proceedings of KUTIC-2025”.
...