• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.714-720
• /
• 2021

The ITL (information theoretic learning) based on the kernel density estimation method that has successfully been applied to machine learning and signal processing applications has a drawback of severe sensitiveness in choosing proper kernel sizes. For the maximization of correntropy criterion (MCC) as one of the ITL-type criteria, several methods of adapting the remaining kernel size ( ) after removing the term have been studied. In this paper, it is shown that the main cause of sensitivity in choosing the kernel size derives from the term and that the adaptive adjustment of in the remaining terms leads to approach the absolute value of error, which prevents the weight adjustment from continuing. Thus, it is proposed that choosing an appropriate constant as the kernel size for the remaining terms is more effective. In addition, the experiment results when compared to the conventional algorithm show that the proposed method enhances learning performance by about 2dB of steady state MSE with the same convergence rate. In an experiment for channel models, the proposed method enhances performance by 4 dB so that the proposed method is more suitable for more complex or inferior conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.213-218
• /
• 2021

It is known that total least-squares method shows better estimation performance than least-squares method when noise is present at the input and output at the same time. When total least squares method is applied to data with time series characteristics, Recursive Total Least Squares (RTS) algorithm has been proposed to improve the real-time performance. However, RTLS has numerical instability in calculating the inverse matrix. In this paper, we propose an algorithm for reducing numerical instability as well as having similar convergence to RTLS. For this algorithm, we propose a new RTLS using Iterative Wiener Filter (IWF). Through the simulation, it is shown that the convergence of the proposed algorithm is similar to that of the RTLS, and the numerical robustness is superior to the RTLS.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.4
• /
• pp.221-230
• /
• 2021

This paper proposes full waveform inversion (FWI) for estimating the physical properties of a layered half-space. An FWI solution is obtained using a genetic algorithm (GA), which is a well-known global optimization approach. The dynamic responses of a layered half-space subjected to a harmonic vertical disk load are measured and compared with those calculated using the estimated physical properties. The responses are calculated using the thin-layer method, which is accurate and efficient for layered media. Subsequently, a numerical model is constructed for a layered half-space using mid-point integrated finite elements and perfectly matched discrete layers. An objective function of the global optimization problem is defined as the L2-norm of the difference between the observed and estimated responses. A GA is used to minimize the objective function and obtain a solution for the FWI. The accuracy of the proposed approach is applied to various problems involving layered half-spaces. The results verify that the proposed FWI based on a GA is suitable for estimating the material properties of a layered half-space, even when the measured responses include measurement noise.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Journal of The Korean Astronomical Society
• /
• v.55 no.2
• /
• pp.23-36
• /
• 2022

We present a method to determine nitrogen abundance ratios with respect to iron ([N/Fe]) from molecular CN-band features observed in low-resolution (R ~ 2000) stellar spectra obtained by the Sloan Digital Sky Survey (SDSS) and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST). Various tests are carried out to check the systematic and random errors of our technique, and the impact of signal-to-noise (S/N) ratios of stellar spectra on the determined [N/Fe]. We find that the uncertainty of our derived [N/Fe] is less than 0.3 dex for S/N ratios larger than 10 in the ranges T_eff = [4000, 6000] K, log g = [0.0, 3.5], [Fe/H] = [-3.0, 0.0], [C/Fe] = [-1.0, +4.5], and [N/Fe] = [-1.0, +4.5], the parameter space that we are interested in to identify N-enhanced stars in the Galactic halo. A star-by-star comparison with a sample of stars with [N/Fe] estimates available from the Apache Point Observatory Galactic Evolution Experiment (APOGEE) also suggests a similar level of uncertainty in our measured [N/Fe], after removing its systematic error. Based on these results, we conclude that our method is able to reproduce [N/Fe] from low-resolution spectroscopic data, with an uncertainty sufficiently small to discover N-rich stars that presumably originated from disrupted Galactic globular clusters.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.525-534
• /
• 2022

This investigation used two different geophysical logging techniques to confirm the depth to which a sheet pile was driven. Depth was estimated through analysis of the movement speed and three-component movement directions of a P-wave transmitted through the ground. It was also estimated by pole-pole and pole-dipole methods using electrical data logging to measure apparent resistivity. The two methods' respective results were 9.0 m (±1.5 m) and 7.5 m. As field ground conditions will include mixtures of various materials, electrical data logging is judged to be suitable for assessing depth due to its low signal-to-noise ratio.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.172-178
• /
• 2023

In this paper, performance of autoencoder based OFDM communication systems is compared with IEEE 802.11a Wireless Lan System (Wi-Fi). The proposed autoencoder based OFDM system is composed of the following steps. First, one sub-carrier's transmitter - channel - receiver system is created by autoencoder. Then learning process of the one sub-carrier autoencoder generates constellation map. Secondly, using the plural sub-carrier autoencoder systems, parallel bundle is configured with inserting IFFT and FFT before and after the channel to configure OFDM system. Finally, the receiver part of the OFDM communication system was updated by re-learning process for adapting channel condition such as multipath channel. For performance comparison, IEEE802.11a and the proposed autoencoder based OFDM system are compared. For channel estimation, Wi-Fi uses initial long preamble to measure channel condition. but Autoencoder needs re-learning process to create an equalizer which compensate a distortion caused by the transmission channel. Therefore, this autoencoder based system has basic advantage to the Wi-Fi system. For the comparison of the system, additive random noise and 2-wave and 4-wave multipaths are assumed in the transmission path with no inter-symbol interference. A simulation was performed to compare the conventional type and the autoencoder. As a result of the simulation, the autoencoder properly generated automatic constellations with QPSK, 16QAM, and 64QAM. In the previous simulation, the received data was relearned, thus the performance was poor, but the performance improved by making the initial value of reception a random number. A function equivalent to an equalizer for multipath channels has been realized in OFDM systems. As a future task, there is not include error correction at this time, we plan to make further improvements by incorporating error correction in the future.

• Structural Engineering and Mechanics
• /
• v.86 no.6
• /
• pp.715-730
• /
• 2023

Broad studies have addressed the issue of structural element damage identification, however, rubber bearing, as a key component of load transmission between the superstructure and substructure, is essential to the operational safety of a bridge, which should be paid more attention to its health condition. However, regarding the limitations of the traditional bearing damage detection methods as well as few studies have been conducted on this topic, in this paper, inspired by the model updating-based structural damage identification, a two-stage bearing damage identification method has been proposed. In the first stage, we deduce a novel bearing damage localization indicator, called element relative MSE, to accurately determine the bearing damage location. In the second one, the prior knowledge of bearing damage localization is combined with sailfish optimization (SFO) to perform the bearing damage estimation. In order to validate the feasibility, a numerical example of a 5-span continuous beam is introduced, also the noise robustness has been investigated. Meanwhile, the effectiveness and engineering applicability are further verified based on an experimental simply supported beam and actual engineering of the I-40 Bridge. The obtained results are good, which indicate that the proposed method is not only suitable for simple structures but also can accurately locate the bearing damage site and identify its severity for complex structure. To summarize, the proposed method provides a good guideline for the issue of bridge bearing detection, which could be used to reduce the difficulty of the traditional bearing failure detection approach, further saving labor costs and economic expenses.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1
• /
• pp.40-46
• /
• 2008

Weak target detection and localization in the presence of loud surface ship noise is a critical problem for matched field processing (MFP) in shallow water. For stationary sources, each signal component of received signal can be separated and interference can be suppressed using eigen space analysis schemes. However, source motion, in realistic cases, causes spreading of signal energies in their subspace. In this case, eigenvalues of target and interfere signal components are mixed and hard to be separated with usual phone space eigenvector decomposition (EVD) approaches. Our technique is based on mode space and utilizes the difference in their physical characteristics of surface and submerged sources. Performing EVD for modal cross spectral density matrix, interference components in the mode amplitude subspace can be classified and eliminated. This technique is demonstrated with synthetic data, and results are discussed.

• Geophysics and Geophysical Exploration
• /
• v.27 no.2
• /
• pp.144-153
• /
• 2024

Recent research is increasingly focused on utilizing seismic waves for structure health monitoring (SHM). Specifically, seismic interferometry, a technique applied in geophysical surveys using ambient noise, is widely applied in SHM. This method involves analyzing the response of buildings to propagating seismic waves. This enables the estimation of changes in structural stiffness and the evaluation of the location and presence of damage. Analysis of seismic interferometry applied to SHM, along with case studies, indicates its highly effective application for assessing structural stability and monitoring building conditions. Seismic interferometry is thus recognized as an efficient approach for evaluating building integrity and damage detection in SHM and monitoring applications.