• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• Korean Chemical Engineering Research
• /
• v.59 no.3
• /
• pp.393-398
• /
• 2021

In order to optimize the performance of a lithium-ion battery, a performance prediction modeling technique that considers various degradation factors is required. In this work, mathematical modeling was carried-out to predict the change in discharging behavior and cycle life, taking into account the cycle aging of lithium-ion batteries. In order to validate the modeling, a cycling test was performed at the charge/discharge rate of 0.25C, and discharging behavior was measured through RPT (Reference Performance Test) performed at 30 cycle intervals. The accuracy of cycle life prediction was improved by considering the break-in mechanism, one of the phenomena occurring in the BOL (beginning of life), in the model for predicting the cycle life of lithium-ion batteries. The predicted change in cycle life based on the model was in good agreement with the experimental results.

• Bulletin of the Korean Space Science Society
• /
• 2008.10a
• /
• pp.33.3-34
• /
• 2008

As an activity of building Korean Space Weather Prediction Center (KSWPC), we has studied of radiation effect on the spacecraft components. High energy charged particles trapped by geomagnetic field in the region named Van Allen Belt can move to low altitude along magnetic field and threaten even low altitude spacecraft. Space Radiation can cause equipment failures and on occasions can even destroy operations of satellites in orbit. Sun sensors aboard Science and Technology Satellite (STSAT-1) was designed to detect sun light with silicon solar cells which performance was degraded during satellite operation. In this study, we try to identify which particle contribute to the solar cell degradation with ground based radiation facilities. We measured the short circuit current after bombarding electrons and protons on the solar cells same as STSAT-1 sun sensors. Also we estimated particle flux on the STSAT-1 orbit with analyzing NOAA POES particle data. Our result clearly shows STSAT-1 solar cell degradation was caused by energetic protons which energy is about 700 keV to 1.5 MeV. Our result can be applied to estimate solar cell conditions of other satellites.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.245-249
• /
• 2013

In this paper, we propose two rate control algorithms for multi-view extension of HEVC with two rate control algorithms adopted in HEVC and analyze the multi-view rate control performance. The proposed multi-view rate controls are designed on HEVC-based multi-view video coding (MV-HEVC) platform with consideration of high-level syntax, inter-view prediction, etc. not only for the base view but also for the extended views using the rate control algorithms based on URQ (Unified Rate-Quantization) and R-lambda model adopted in HEVC. The proposed multi-view rate controls also contain view-wise target bit allocation for providing the compatibility to the base view. By allocating the target bitrates for each view, the proposed multi-view rate control based on URQ model achieved about 1.83% of average bitrate accuracy and 1.73dB of average PSNR degradation. In addition, about 2.97% of average bitrate accuracy and 0.31dB of average PSNR degradation are achieved with the proposed multi-view rate control based on R-lambda model.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.11
• /
• pp.94-101
• /
• 2020

In the age of industry 4.0, artificial intelligence is being widely used to realize machinery condition monitoring. Due to their excellent performance and the ability to handle large volumes of data, machine learning techniques have been applied to realize the fault diagnosis of different equipment. In this study, we performed the failure mode effect analysis (FMEA) of an aluminum electrolytic capacitor by using deep learning and big data. Several tests were performed to identify the main failure mode of the aluminum electrolytic capacitor, and it was noted that the capacitance reduced significantly over time due to overheating. To reflect the capacitance degradation behavior over time, we employed the Vanilla long short-term memory (LSTM) neural network architecture. The LSTM neural network has been demonstrated to achieve excellent long-term predictions. The prediction results and metrics of the LSTM and Vanilla LSTM models were examined and compared. The Vanilla LSTM outperformed the conventional LSTM in terms of the computational resources and time required to predict the capacitance degradation.

• Steel and Composite Structures
• /
• v.23 no.1
• /
• pp.17-29
• /
• 2017

The seismic performance of steel beam to concrete-encased composite column with unsymmetrical steel section joints is investigated and reported within this paper. Experimental and analytical evaluation were conducted on a total of 8 specimens with T-shaped and L-shaped steel section under lateral cyclic loading and axial compression. The test parameters included concrete strength, stirrup ratio and axial compression ratio. The response of the specimens was presented in terms of their hysterisis loop behavior, stress distribution, joint shear strength, and performance degradation. The experiment indicated good structural behavior and good seismic performance. In addition, a three-dimensional nonlinear finite-element analysis simulating was conducted to simulate their seismic behaviors. The finite-element analysis incorporated both bond-slip relationship and crack interface interaction between steel and concrete. The results were also compared with the test data, and the analytical prediction of joint shear strength was satisfactory for both joints with T-shaped and L-shaped steel section columns. The steel beam to concrete-encased composite column with unsymmetrical steel section joints can develop stable hysteretic response and large energy absorption capacity by providing enough stirrups and decreased spacing of transverse ties in column.

• Computers and Concrete
• /
• v.16 no.5
• /
• pp.669-682
• /
• 2015

Degradation of reinforced concrete (RC) structures due to chloride penetration followed by reinforcement corrosion has been a serious problem in civil engineering for many years. The numerical simulation methods at present are mainly finite element method (FEM) and finite difference method (FDM), which are based on mesh. Mesh generation in engineering takes a long time. In the present article, the numerical solution of chloride transport in concrete is analyzed using radial point interpolation method (RPIM) and element-free Galerkin (EFG). They are all meshless methods. RPIM utilizes radial polynomial basis, whereas EFG uses the moving least-square approximation. A Galerkin weak form on global is used to attain the discrete equation, and four different numerical examples are presented. MQ function and appropriate parameters have been proposed in RPIM. Numerical simulation results are compared with those obtained from the finite element method (FEM) and analytical solutions. Two case of chloride transport in full saturated and unsaturated concrete are analyzed to test the practical applicability and performance of the RPIM and EFG. A good agreement is obtained among RPIM, EFG, and the experimental data. It indicates that RPIM and EFG are reliable meshless methods for prediction of chloride concentration in concrete structures.

• ETRI Journal
• /
• v.32 no.4
• /
• pp.577-587
• /
• 2010

The layered coding structure of scalable video coding (SVC) with adaptive inter-layer prediction causes noticeable computational complexity increments when compared to existing video coding standards. To lighten the computational complexity of SVC, we present a fast algorithm to speed up the inter-mode decision process. The proposed algorithm terminates inter-mode decision early in the enhancement layers by estimating the rate-distortion (RD) cost from the macroblocks of the base layer and the enhancement layer in temporal, spatial, and inter-layer directions. Moreover, a search range decision algorithm is also proposed in this paper to further increase the motion estimation speed by using the motion vector information from temporal, spatial, or inter-layer domains. Simulation results show that the proposed algorithm can determine the best mode and provide more efficient total coding time saving with very slight RD performance degradation for spatial and quality scalabilities.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.8
• /
• pp.1199-1203
• /
• 2012

H.264 adopted many compression tools to increase image data compression efficiency such as B frame bi-directional predictions, the direct mode coding and so on. Despite its high compression efficiency, H.264 can suffer from its long coding time due to the complicated tools of H.264. To realize a high performance H.264, several fast algorithms were proposed. One of them is adaptive fast direct mode decision algorithm using mode and Lagrangian cost prediction for B frame in H.264/AVC (MLP) algorithm which can determine the direct coding mode for macroblocks without a complex mode decision process. However, in this algorithm, macroblocks not satisfying the conditions of the MLP algorithm are required to process the complex mode decision calculation, yet suffering a long coding time. To overcome the problem, this paper proposes a fast direct mode prediction algorithm. Simulation results show that the proposed algorithm can determine the direct mode coding without a complex mode decision process for 42% more macroblocks and, this algorithm can reduce coding time by up to 23%, compared with Jin's algorithm. This enables to encode B frames fast with a less quality degradation.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.5
• /
• pp.29-39
• /
• 2012

The main objective is to predict the future degradation and maintenance budget for a suspension bridge system. Bayesian inference is applied to find the posterior probability density function of the source parameters (damage indices and serviceability), given ten years of maintenance data. The posterior distribution of the parameters is sampled using a Markov chain Monte Carlo method. The simulated risk prediction for decreased serviceability conditions are posterior distributions based on prior distribution and likelihood of data updated from annual maintenance tasks. Compared with conventional linear prediction model, the proposed quadratic model provides highly improved convergence and closeness to measured data in terms of serviceability, risky factors, and maintenance budget for bridge components, which allows forecasting a future performance and financial management of complex infrastructures based on the proposed quadratic stochastic regression model.