• Computers and Concrete
• /
• 제32권2호
• /
• pp.149-163
• /
• 2023

One of the main design parameters traditionally utilized in projects of geotechnical engineering is the uniaxial compressive strength. The present paper employed three artificial intelligence methods, i.e., the stochastic fractal search (SFS), the multi-verse optimization (MVO), and the vortex search algorithm (VSA), in order to determine the compressive strength of concrete (CSC). For the same reason, 1030 concrete specimens were subjected to compressive strength tests. According to the obtained laboratory results, the fly ash, cement, water, slag, coarse aggregates, fine aggregates, and SP were subjected to tests as the input parameters of the model in order to decide the optimum input configuration for the estimation of the compressive strength. The performance was evaluated by employing three criteria, i.e., the root mean square error (RMSE), mean absolute error (MAE), and the determination coefficient (R²). The evaluation of the error criteria and the determination coefficient obtained from the above three techniques indicates that the SFS-MLP technique outperformed the MVO-MLP and VSA-MLP methods. The developed artificial neural network models exhibit higher amounts of errors and lower correlation coefficients in comparison with other models. Nonetheless, the use of the stochastic fractal search algorithm has resulted in considerable enhancement in precision and accuracy of the evaluations conducted through the artificial neural network and has enhanced its performance. According to the results, the utilized SFS-MLP technique showed a better performance in the estimation of the compressive strength of concrete (R²=0.99932 and 0.99942, and RMSE=0.32611 and 0.24922). The novelty of our study is the use of a large dataset composed of 1030 entries and optimization of the learning scheme of the neural prediction model via a data distribution of a 20:80 testing-to-training ratio.

• ETRI Journal
• /
• 제36권4호
• /
• pp.564-571
• /
• 2014

Sphere decoding (SD) for multiple-input and multiple-output systems is a well-recognized approach for achieving near-maximum likelihood performance with reduced complexity. SD is a tree search process, whereby a large number of nodes can be searched in an effort to find an estimation of a transmitted symbol vector. In this paper, a simple and generalized approach called layer pruning is proposed to achieve complexity reduction in SD. Pruning a layer from a search process reduces the total number of nodes in a sphere search. The symbols corresponding to the pruned layer are obtained by adopting a QRM-MLD receiver. Simulation results show that the proposed method reduces the number of nodes to be searched for decoding the transmitted symbols by maintaining negligible performance loss. The proposed technique reduces the complexity by 35% to 42% in the low and medium signal-to-noise ratio regime. To demonstrate the potential of our method, we compare the results with another well-known method - namely, probabilistic tree pruning SD.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2002년도 추계학술대회 논문집(I)
• /
• pp.660-665
• /
• 2002

A concrete box culvert has been widely used as a typical structure in case of crossing the railroad and highway. Due to the simplicity of it's own shape, in company with the development of computers many studies on the computer-aided automatic design have been continuously carried out. In this paper, an automated design algorithm has been proposed by the analysis of the existed design data of box culverts. From a viewpoint of the users, a data base system has been constructed to carry out the total design process completely through the minimum input data and by means of direct input method on the monitor screen. And an automatic design program for railroad box culverts, in which one-stop process from the structural calculation to the quantity estimation is possible, has been developed.

• 한국철도학회논문집
• /
• 제7권4호
• /
• pp.302-306
• /
• 2004

Many long railway tunnels without emergency evacuation system or ventilation system are under construction or in-use in Korea. In the case of tunnel-fire, many fatalities are occur in current condition. Current safety level is estimated in this study, for the efficient investment on safety. But so many uncertainties in major input parameters make the safety estimation difficult. In this study, probabilistic techniques are applied for the consideration of uncertainties in major input parameters. As results of this study, accident scenarios and survival ratio under tunnel fire accident are determined for various conditions.

• ETRI Journal
• /
• 제43권1호
• /
• pp.17-30
• /
• 2021

At present, multiple input multiple output radars offer accurate target detection and better target parameter estimation with higher resolution in high-speed wireless communication systems. This study focuses primarily on power allocation to improve the performance of radars owing to the sparsity of targets in the spatial velocity domain. First, the radars are clustered using the kernel fuzzy C-means algorithm. Next, cooperative and noncooperative clusters are extracted based on the distance measured using the kernel fuzzy C-means algorithm. The power is allocated to cooperative clusters using the Pareto optimality particle swarm optimization algorithm. In addition, the Nash equilibrium particle swarm optimization algorithm is used for allocating power in the noncooperative clusters. The process of allocating power to cooperative and noncooperative clusters reduces the overall transmission power of the radars. In the experimental section, the proposed method obtained the power consumption of 0.014 to 0.0119 at K = 2, M = 3 and K = 2, M = 3, which is better compared to the existing methodologies-generalized Nash game and cooperative and noncooperative game theory.

• Journal of Advanced Marine Engineering and Technology
• /
• 제26권6호
• /
• pp.695-704
• /
• 2002

Generally, induction motor controller requires rotor speed sensor for commutation and current control, but it increases cost and size of the motor. So in these days, various researches including speed sensorless vector control have been reported and some of them have been put to practical use. In this paper a new speed estimation method using neural networks is proposed. The optimal neural network structure was tracked down by trial and error, and it was found that the 8-16-1 neural network has given correct results for the instantaneous rotor speed. Supervised learning methods, through which the neural network is trained to learn the input/output pattern presented, are typically used. The back-propagation technique is used to adjust the neural network weights during training. The rotor speed is calculated by weights and eight inputs to the neural network. Also, the proposed method has advantages such as the independency on machine parameters, the insensitivity to the load condition, and the stability in the low speed operation.

• ETRI Journal
• /
• 제32권6호
• /
• pp.921-931
• /
• 2010

It has been shown that the principal subspace-based multichannel Wiener filter (MWF) provides better performance than the conventional MWF for suppressing interference in the case of a single target source. It can efficiently estimate the target speech component in the principal subspace which estimates the acoustic transfer function up to a scaling factor. However, as the input signal-to-interference ratio (SIR) becomes lower, larger errors are incurred in the estimation of the acoustic transfer function by the principal subspace method, degrading the performance in interference suppression. In order to alleviate this problem, a principal subspace modification method was proposed in previous work. The principal subspace modification reduces the estimation error of the acoustic transfer function vector at low SIRs. In this work, a frequency-band dependent interpolation technique is further employed for the principal subspace modification. The speech recognition test is also conducted using the Sphinx-4 system and demonstrates the practical usefulness of the proposed method as a front processing for the speech recognizer in a distant-talking and interferer-present environment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2702-2704
• /
• 2005

This paper proposes the genetic algorithm (GA)-based fuzzy modeling method for intelligent tracking of a maneuvering target. When the maneuvering to turn or taking evasive action, the performance of the standard Kalman filter has been degraded because residual between the modeled target dynamics and the actual target dynamics. To solve this problem, the state prediction error is minimized by the intelligent estimation method. Then, this filter is corrected by measurement corrections which is the fuzzy system. The performance of the proposed method is compared with those of the input estimation(IE) technique through computer simulation.

• 한국통신학회논문지
• /
• 제11권3호
• /
• pp.211-216
• /
• 1986

본 논문은 광대역 통신 시스템중 특히 직접 확산 스펙트럼 시스템에서, 중심주파수에 연속성 간섭파가 존재할 때 간섭파를 제거하는 회로에 대한 이론적 해석과 실험결과를 제시한다. 이 회로는 연속성 간섭파의 위상을 추정하기 위해 위상추정기를 사용하였으며 추정 에러를 최소화시키기 위해 MSE법을 이용했다. 그러므로 추정에러가 최소화된 제시한 간섭제거회로는 위상추정만을 행한 제거회로보다 성능이 양호하며 실험결과 J/S비가 높을 수록 제거 성능이 우수함을 확인하였다.

• 전자공학회논문지A
• /
• 제32A권12호
• /
• pp.209-219
• /
• 1995

As a new algorithm for RC tree delay estimation, we propose a $\tau$-model of the driver and a moment propagation method. The $\tau$-model represents the driver as a Thevenin equivalent circuit which has a one-time-constant voltage source and a linear resistor. The new driver model estimates the input voltage waveform applied to the RC more accurately than the k-factor model or the 2-piece waveform model. Compared with Elmore method, which is a lst-order approximation, the moment propagation method, which uses $\pi$-model loads to calculate the moments of the voltage waveform on each node of RC trees, gives more accurate results by performing higher-order approximations with the same simple tree walking algorithm. In addition, for the instability problem which is common to all the approximation methods using the moment matching technique, we propose a heuristic method which guarantees a stable and accureate 2nd order approximation. The proposed driver model and the moment propagation method give an accureacy close to SPICE results and more than 1000 times speedup over circuit level simulations for RC trees and FPGA interconnects in which the interconnect delay is dominant.