• Journal of IKEEE
• /
• v.5 no.1 s.8
• /
• pp.1-7
• /
• 2001

In this paper, we have investigated the CDMA(Code Division Multiple Access) Cellular System with non-linear equalizer in reverse link channel. In general, due to unknown characteristics of channel in the wireless communication, the distribution of the observables cannot be specified by a finite set of parameters; instead, we partitioned the m-dimensional sample space Into a finite number of disjointed regions by using quantiles and a vector quantizer based on training samples. The algorithm proposed is based on a piecewise approximation to regression function based on quantiles and conditional partition moments which are estimated by Robbins Monro Stochastic Approximation (RMSA) algorithm. The resulting equalizers and detectors are robust in the sense that they are insensitive to variations in noise distributions. The main idea is that the robust equalizers and robust partition detectors yield better performance in equiprobably partitioned subspace of observations than the conventional equalizer in unpartitioned observation space under any condition. And also, we apply this idea to the CDMA system and analyze the BER performance.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.48-55
• /
• 2020

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

• Journal of the Korean Geotechnical Society
• /
• v.33 no.7
• /
• pp.29-41
• /
• 2017

There are uncertainties about the seismic load caused by seismic waves, which cannot be predicted due to the characteristics of the earthquake occurrence. Therefore, it is necessary to consider these uncertainties by probabilistic analysis. In this paper, procedures to develop a fragility curve that is a representative method to evaluate the safety of a structure by stochastic analysis were proposed for cut slopes. Fragility curve that considers uncertainties of soil shear strength parameters was prepared by Monte Carlo Simulation using pseudo static analysis. The fragility curve considering the uncertainty of the input ground motion was developed by performing time-history seismic analysis using selected 30 real ground input motions and the Newmark type displacement evaluation analysis. Fragility curves are represented as the cumulative probability distribution function with lognormal distribution by using the maximum likelihood estimation method.

• Journal of the Korea Concrete Institute
• /
• v.20 no.2
• /
• pp.139-146
• /
• 2008

The characteristics of the biaxial flexural tensile strength of concretes was compared to that of the uniaxial strength. The uniaxial and biaxial strengths in this study were obtained from the classical modulus of rupture test and the biaxial flexural test recently developed by Zi and Oh and Zi et al., respectively. Three different sizes were considered to investigate the effect of the size of aggregates. To estimate the stochastic aspect of the strength, 32 specimens were used for each test. The average biaxial flexural fracture strength was about 20% greater than the uniaxial test. At the same time, the coefficient of variation for the biaxial test was 18% greater than the uniaxial test. This means that the probability of the biaxial cracking can be greater than the uniaxial cracking.

• Tunnel and Underground Space
• /
• v.30 no.1
• /
• pp.15-28
• /
• 2020

In this study, a procedure was introduced to estimate strength and deformation modulus of the 3-D discrete fracture network(DFN) systems using the distinct element method(DEM). Fracture entities were treated as non-persistent square planes in the DFN systems. Systematically generated fictitious fractures having similar mechanical characteristics of intact rock were combined with non-persistent real fractures to create polyhedral blocks in the analysis domain. Strength and deformation modulus for 10 m cube domain of various deterministic and stochastic 3-D DFN systems were estimated using the DEM to explore the applicability of suggested method and to examine the effect of fracture geometry on strength and deformability of DFN systems. The suggested procedures were found to effective in estimating anisotropic strength and deformability of the 3-D DFN systems.

• Journal of Convergence for Information Technology
• /
• v.9 no.12
• /
• pp.54-61
• /
• 2019

Recently, IITS (intelligent integrated transportation system) has been important topic in Smart City related industry. As a main objective of IITS, prevention of traffic jam (due to car accidents) has been attempted with help of advanced sensor and communication technologies. Studies show that car accident has certain correlation with some factors including characteristics of location, weather, driver's behavior, and time of day. We concentrate our study on observing auto correlativity of car accidents in terms of time of day. In this paper, we performed the ARIMA tests including ADF (augmented Dickey-Fuller) to check the three factors determining auto-regressive, stationarity, and lag order. Summary on forecasting of hourly car crash counts is presented, we show that the traffic accident data obtained in Korea can be applied to ARIMA model and present a result that traffic accidents in Korea have property of being recurrent daily basis.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.127-133
• /
• 2019

Electric power demand forecasting is one of the important research areas for future smart grid introduction. However, It is difficult to predict because it is affected by many external factors. Traditional methods of forecasting power demand have been limited in making accurate prediction because they use raw power data. In this paper, a probability-based CRBM is proposed to solve the problem of electric power demand prediction using raw power data. The stochastic model is suitable to capture the probabilistic characteristics of electric power data. In order to compare the mid-term power demand forecasting performance of the proposed model, we compared the performance with Recurrent Neural Network(RNN). Performance comparison using electric power data provided by the University of Massachusetts showed that the proposed algorithm results in better performance in mid-term energy demand forecasting.

• Journal of Ecology and Environment
• /
• v.45 no.3
• /
• pp.97-104
• /
• 2021

Background: Asarum sieboldii Miq., a species of forest understory vegetation, is an herbaceous perennial belonging to the family Aristolochiaceae. The metapopulation of A. sieboldii is distributed sparsely and has a short seed dispersal distance by ants as their seed distributor. It is known that many flowers of A. sieboldii depend on self-fertilization. Because these characteristics can affect negatively in genetic structure, investigating habitat structure and assessment of genetic structure is needed. A total of 27 individuals in a valley were sampled for measuring genetic diversity, genetic distance, and genetic differentiation by RAPDPCR. Results: The habitat areas of A. sieboldii metapopulation were relatively small (3.78~33.60 m²) and population density was very low (five to seven individuals in 20×20 m quadrat). The habitat of A. sieboldii was a very shady (relative light intensity = 0.9%) and mature forest with a high evenness value (J = 0.81~0.99) and a low dominance value (D = 0.19~0.28). The total genetic diversity of A. sieboldii was quite high (h = 0.338, I = 0.506). A total of 33 band loci were observed in five selected primers, and 31 band loci (94%) were polymorphic. However, genetic differentiation along the valley was highly progressed (G_st = 0.548, N_m = 0.412). The average genetic distance between subpopulations was 0.387. The results of AMOVA showed 52.77% of variance occurs among populations, which is evidence of population structuring. Conclusions: It is expected that a small-scale founder effect had occurred, an individual spread far from the original subpopulation formed a new subpopulation. However, geographical distance between individuals would have been far and genetic flow occurred only within each subpopulation because of the low density of population. This made significant genetic distance between the original and new population by distance. Although genetic diversity of A. sieboldii metapopulation is not as low as concerned, the subpopulation of A. sieboldii can disappear by stochastic events due to small subpopulation size and low density of population. To prevent genetic isolation and to enhance the stable population size, conservative efforts such as increasing the size of each subpopulation or the connection between subpopulations are needed.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.2
• /
• pp.75-84
• /
• 2021

As the weather changes become frequent, weather disasters are increasing, causing more damage to plastic greenhouses. Among the damage caused by various disasters, damage by snow to the greenhouse takes a relatively long time, so if an alarm system is properly prepared, the damage can be reduced. Existing greenhouse design standards and snow warning systems are based on snow depth. However, even in the same depth, the load on the greenhouse varies depending on meteorological characteristics and snow density. Therefore, this study aims to secure the structural safety of greenhouses by developing sensors that can directly measure snow loads, and analysing the warning criteria for load using a stochastic model. Markov chain was applied to estimate the failure probability of various types of greenhouses in various regions, which let users actively cope with heavy snowfall by selecting an appropriate time to respond. Although it was hard to predict the precise snow depth or amounts, it could successfully assess the risk of structures by directly detecting the snow load using the developed sensor.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.