• ETRI Journal
• /
• v.45 no.5
• /
• pp.811-821
• /
• 2023

We propose an adaptive unmanned aerial vehicle (UAV)-assisted object recognition algorithm for urban surveillance scenarios. For UAV-assisted surveillance, UAVs are equipped with learning-based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self-adaptive control strategy to maximize the time-averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real-world data demonstrate that the proposed algorithm achieves the desired performance improvements.

• Korean Journal of Applied Biomechanics
• /
• v.34 no.2
• /
• pp.71-80
• /
• 2024

Objective: This study aimed to explore the brain connectivity between brain and biomechanical variables by exploring motion recognition through FFT (fast fourier transform) analysis and AI (artificial intelligence) focusing on quiet standing movement patterns. Method: Participants included 12 young adult males, comprising university students (n=6) and elite gymnasts (n=6). The first experiment involved FFT of biomechanical signals (f_CoP, f_AJtorque and f_EEG), and the second experiment explored the optimization of AI-based GRU (gated recurrent unit) using f_EEG data. Results: Significant differences (p<.05) were observed in frequency bands and maximum power based on group and posture types in the first experiment. The second study improved motion prediction accuracy through GRU performance metrics derived from brain signals. Conclusion: This study delved into the movement pattern of upright standing posture through the analysis of bio-signals linking the cerebral cortex to motor performance, culminating in the attainment of motion recognition prediction performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.160-163
• /
• 1996

This paper deals with MCMBPC(Multivariable Constrained Model Based Predictive Controller) for nonlinear boiler system with noise and disturbance. MCMBPC is designed by linear state space model obtained from some operating point of nonlinear boiler system and Kalman filter is used to estimate the state with noise and disturbance. The solution of optimization of the cost function constrained on input and/or output variables is achieved using quadratic programming, viz. singular value decomposition (SVD). The controller designed is shown to have excellent tracking performance via simulation applied to nonlinear dynamic drum boiler turbine model for 16OMW unit.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.447-454
• /
• 2014

In many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are fairly expensive to obtain. Therefore semi-supervised learning algorithms have attracted much attentions. However, previous research mainly focuses on classication problems. In this paper, a semi-supervised regression method based on support vector regression (SVR) formulation that is proposed. The estimator is easily obtained via the dual formulation of the optimization problem. The experimental results with simulated and real data suggest superior performance of the our proposed method compared with standard SVR.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1709-1712
• /
• 2002

In the microcell- or picocell-based system the frequent movements of the mobile bring about excessive traffics into the networks. A mobile location estimation mechanism can facilitate both efficient resource allocation and better QoS provisioning through handoff optimization. Existing location estimation schemes consider only LOS model and have poor performance in presence of multi- path and shadowing. In this paper we study a novel scheme which can increase estimation accuracy by considering NLOS environment

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.6
• /
• pp.547-556
• /
• 2014

This paper discusses a one-way fluid structural interaction (FSI) analysis and shape optimization of the impeller blades for a 15,000 HP centrifugal compressor using the response surface method (RSM). Because both the aerodynamic performance and the structural safety of the impeller are affected by the shape of its blades, shape optimization is necessary using the FSI analysis, which includes a structural analysis for the induced fluid pressure and centrifugal force. The FSI analysis is performed in ANSYS Workbench: ANSYS CFX is used for the flow field and ANSYS Mechanical is used for the structural field. The response surfaces for the FSI results (efficiency, pressure ratio, maximum stress, etc.) generated based on the design of experiments (DOE) are used to find an optimal shape for the impeller blades, which provides the maximum aerodynamic performance subject to the structural safety constraints.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.26 no.2
• /
• pp.218-225
• /
• 2015

Inverse synthetic aperture radar(ISAR) is coherent imaging system formed by conducting signal processing of received data which consists of radar cross section(RCS) reflected from maneuvering target. A novel algorithm is proposed to compensate inter-pulse motion(IPM) for the purpose of forming an well-focused ISAR image through signals generated by stepped chirp waveform( SCW). The velocity and acceleration of the target related to IPM are estimated based on particle swarm optimization (PSO) which has been widely used in optimization technique. Furthermore, a modified PSO which enables us to improve the performance of PSO is used to compensate IPM in a very short-time. Simulation results using point scatterer model of a Boeing-737 aircraft validate the performance of the proposed algorithm.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.2
• /
• pp.99-104
• /
• 2008

This study performed robust design optimization of fighter wing planform, considering uncertainty based on neural network model. To construct uncertainty model, aerodynamic performance and their sensitivity were evaluated by 3-dimensional Euler equations and adjoint variable method at experimental points selected from central composite design. In addition, because a neural network model has the advantage of capturing non-linear characteristic, it was possible to predict sensitivity of the aerodynamic performance efficiently and accurately . From the results of robust design optimization, it could be confirmed that the robustness of the objective function and constraints were improved if the variation of uncertainty and sigma level were increased.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.131-137
• /
• 2007

Recently, Ant Colony Optimization (ACO) is emerged as a simple yet powerful optimization algorithm for routing and load-balancing of both wired and wireless networks. However, there are few researches trying to adopt ACO to enhance routing performance in WSN owing to difficulties in applying ACO to WSN because of stagnation effect. In this paper, we propose an energy-efficient path selection algorithm based on ACO for WSN. The algorithm is not by simply applying ACO to routing algorithm but by introducing a mechanism to alleviate the influence of stagnation. By the simulation result, the proposed algorithm shows better performance in data propagation delay and energy efficiency over Directed Diffusion which is one of the outstanding schemes in multi-hop flat routing protocols for WSN. Moreover, we checked that the proposed algorithm is able to mitigate stagnation effect than simple ACO adoption to WSN.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.71-84
• /
• 2020

In order to improve the performance of marine centrifugal pump, a centrifugal pump whose specific speed is 66.7 was selected for the research. Outlet diameter D2, outlet width b2, blade outlet angle β2, blade wrap φ and blade number z of the impeller were chosen as the variables. The maximum weighted average efficiency and the minimum vibration intensity at the base were calculated as objectives. Based on the Latin Hypercube method, the impeller was numerically optimized. The numerical results show that after optimization, the amplitudes of pressure fluctuation on the main frequency at different monitoring points decrease in varying degrees. The radial force on impeller decreases obviously under off-design flow rates and is more symmetrical during the operation of the pump. The variation of the axial force is relatively small, which has no obvious relationship with the rotating angle of the impeller. The energy performance and vibration experiment was performed for verifying. The test results show that the weighted average efficiency under 0.8Qd, 1.0Qd and 1.2Qd increases by 4.3% after optimization. The maximal vibration intensity at M1-M4 on the pump base reduced from 0.36 mm/s to 0.25 mm/s, decreasing by 30.5%. In addition, the vibration velocities of bracket in pump side and outlet flange also have significant reductions.