• Information Systems Review
• /
• v.25 no.3
• /
• pp.27-41
• /
• 2023

Unlike the previous works focusing on the state-of-the-art methodologies to improve the performance of machine learning models, this study improves the 'quality' of training data used in machine learning. We propose a method to enhance the quality of training data through the processing of 'local grammar,' frequently used in corpus analysis. We collected a vast amount of unstructured corporate review text data posted by employees working in the top 100 companies in Korea. After improving the data quality using the local grammar process, we confirmed that the classification model with local grammar outperformed the model without it in terms of classification performance. We defined five factors of work engagement as classification categories, and analyzed how the pattern of reviews changed before and after the COVID-19 pandemic. Through this study, we provide evidence that shows the value of the local grammar-based automatic identification and classification of employee experiences, and offer some clues for significant organizational cultural phenomena.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.4
• /
• pp.31-44
• /
• 2014

In the present study, a few of recently developed geostatistical models are comparatively studied. The models are two-point statistics based sequential indicator simulation (SISIM) and generalized coupled Markov chain (GCMC), multi-point statistics single normal equation simulation (SNESIM), and object based model of FLUVSIM (fluvial simulation) that predicts structures of target object from the provided geometric information. Out of the models, SNESIM and FLUVSIM require additional information other than conditioning data such as training map and geometry, respectively, which generally claim demanding additional resources. For the comparative studies, three-dimensional fluvial reservoir model is developed considering the genetic information and the samples, as input data for the models, are acquired by mimicking realistic sampling (i.e. random sampling). For SNESIM and FLUVSIM, additional training map and the geometry data are synthesized based on the same information used for the objective model. For the comparisons of the predictabilities of the models, two different measures are employed. In the first measure, the ensemble probability maps of the models are developed from multiple realizations, which are compared in depth to the objective model. In the second measure, the developed realizations are converted to hydrogeologic properties and the groundwater flow simulation results are compared to that of the objective model. From the comparisons, it is found that the predictability of GCMC outperforms the other models in terms of the first measure. On the other hand, in terms of the second measure, the both predictabilities of GCMC and SNESIM are outstanding out of the considered models. The excellences of GCMC model in the comparisons may attribute to the incorporations of directional non-stationarity and the non-linear prediction structure. From the results, it is concluded that the various geostatistical models need to be comprehensively considered and comparatively analyzed for appropriate characterizations.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.308-313
• /
• 2005

For a real-time quadruped robot running control, there are many important objectives to consider. In this paper, the running control architecture based on global states, which describe the cyclic target motion, and central pattern is proposed. The main goal of the controller is how the robot can have robustness to an unpredictable environment with reducing calculation burden to generate control inputs. Additional goal is construction of a single framework controller to avoid discontinuities during transition between multi-framework controllers and of a training-free controller. The global state dependent neuron network induces adaptation ability to an environment and makes the training-free controller. The central pattern based approach makes the controller have a single framework, and calculation burden is resolved by extracting dynamic equations from the control loop. In our approach, the model of the quadruped robot is designed using anatomical information of a cat, and simulated in 3D dynamic environment. The simulation results show the proposed single framework controller is robustly performed in an unpredictable sloped terrain without training.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.37-41
• /
• 2014

The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

• Computers and Concrete
• /
• v.22 no.4
• /
• pp.355-363
• /
• 2018

In the following paper, a socio-political heuristic search approach, named the imperialist competitive algorithm (ICA) has been used to improve the efficiency of the multi-layer perceptron artificial neural network (ANN) for predicting the compressive strength of concrete. 173 concrete samples have been investigated. For this purpose the values of slump flow, the weight of aggregate and cement, the maximum size of aggregate and the water-cement ratio have been used as the inputs. The compressive strength of concrete has been used as the output in the hybrid ICA-ANN model. Results have been compared with the multiple-linear regression model (MLR), the genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate the superiority and high accuracy of the hybrid ICA-ANN model in predicting the compressive strength of concrete when compared to the other methods.

• Journal of the Korea Society for Simulation
• /
• v.14 no.4
• /
• pp.55-68
• /
• 2005

The advancement in semiconductor technology is leading toward smaller critical dimension designs and larger wafer manufactures. Due to such phenomena, semiconductor industry is in need of an accurate control of the process. Photolithography is one of the key processes where the pattern of each layer is formed. In this process, precise superposition of the current layer to the previous layer is critical. Therefore overlay parameters of the semiconductor photolithography process is targeted for this research. The complex relationship among the input parameters and the output metrologies is difficult to understand and harder yet to model. Because of the superiority in modeling multi-nonlinear relationships, neural networks is used for the simulator modeling. For training the neural networks, conjugate gradient method is employed. An experiment is performed to evaluate the performance among the proposed neural network simulator, stepwise regression model, and the currently practiced prediction model from the test site.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.58-66
• /
• 2007

This paper introduces the new generic dynamic neuro-fuzzy local modeling system (DNFLMS) that is based on a dynamic Takagi-Sugeno (TS) type fuzzy inference system for complex dynamic hydrological modeling tasks. The proposed DNFLMS applies a local generalization principle and an one-pass training procedure by using the evolving clustering method to create and update fuzzy local models dynamically and the extended Kalman filtering learning algorithm to optimize the parameters of the consequence part of fuzzy local models. The proposed DNFLMS is applied to develop the inference model to forecast the flow of Waikoropupu Springs, located in the Takaka Valley, South Island, New Zealand, and the influence of the operation of the 32 Megawatts Cobb hydropower station on springs flow. It is demonstrated that the proposed DNFLMS is superior in terms of model accuracy, model complexity, and computational efficiency when compared with a multi-layer perceptron trained with the back propagation learning algorithm and well-known adaptive neural-fuzzy inference system, both of which adopt global generalization.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.36-44
• /
• 2000

The purpose of this study is to introduce a more efficient forecasting technique, which could help result the reduction of cost in removing the waste of airline in-flight meals. We will use a neural network approach known to many researchers as the “Outstanding Forecasting Technique”. We employed a multi-layer perceptron neural network using a backpropagation algorithm. We also suggested using other related information to improve the forecasting performances of neural networks. We divided the data into three sets, which are training data set, cross validation data set, and test data set. Time lag variables are still employed in our model according to the general view of time series forecasting. We measured the accuracy of our model by “Mean Square Error”(MSE). The suggested model proved most excellent in serving economy class in-flight meals. Forecasting the exact amount of meals needed for each airline could reduce the waste of meals and therefore, lead to the reduction of cost. Better yet, it could enhance the cost competition of each airline, keep the schedules on time, and lead to better service.

• Asia pacific journal of information systems
• /
• v.1 no.1
• /
• pp.63-86
• /
• 1991

In this paper, our concern is the artificial neural network-based patten classification, when can resolve the difficulties in the Autoregressive Moving Average(ARMA) model identification problem To effectively classify a time series into an approriate ARMA model, we adopt the Multi-layered Backpropagation Network (MLBPN) as a pattern classifier, and Extended Sample Autocorrelation Function (ESACF) as a feature extractor. To improve the classification power of MLBPN's we suggest an integrated neural network system which consists of an AR Network and many small-sized MA Networks. The output of AR Network which will gives the MA order. A step-by-step training strategy is also suggested so that the learned MLBPN's can effectively ESACF patterns contaminated by the high level of noises. The experiment with the artificially generated test data and real world data showed the promising results. Our approach, combined with a statistical parameter estimation method, will provide a way to the automation of ARMA modeling.