• Molecules and Cells
• /
• v.37 no.10
• /
• pp.705-712
• /
• 2014

The early steps of neural development in the vertebrate embryo are regulated by sets of transcription factors that control the induction of proliferative, pluripotent neural precursors, the expansion of neural plate stem cells, and their transition to differentiating neural progenitors. These early events are critical for producing a pool of multipotent cells capable of giving rise to the multitude of neurons and glia that form the central nervous system. In this review we summarize findings from gain- and loss-of-function studies in embryos that detail the gene regulatory network responsible for these early events. We discuss whether this information is likely to be similar in mammalian embryonic and induced pluripotent stem cells that are cultured according to protocols designed to produce neurons. The similarities and differences between the embryo and stem cells may provide important guidance to stem cell protocols designed to create immature neural cells for therapeutic uses.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Proceedings of the KIPE Conference
• /
• 2001.07a
• /
• pp.389-392
• /
• 2001

This paper presents neural load disturbance observer that used to deadbeat load torque observer and regulation of the compensation gain by parameter estimator. As a result, the response of PMSM follows that of the nominal plant. The load torque compensation method is compose of a neural deadbeat observer. To reduce of the noise effect, the post-filter, which is implemented by MA process, is proposed. The parameter compensator with RLSM (recursive least square method) parameter estimator is suggested to increase the performance of the load torque observer and main controller. The proposed estimator is combined with a high performance neural torque observer to resolve the problems. As a result, the proposed control system becomes a robust and precise system against the load torque and the parameter variation. A stability and usefulness, through the verified computer simulation, are shown in this paper.

• Proceedings of the KIPE Conference
• /
• 2002.11a
• /
• pp.49-52
• /
• 2002

This paper presents neural load torque observer that used to deadbeat load torque observer and regulation of the compensation gain by parameter estimator. As a result, the response of PMSM follows that of the nominal plant. The load torque compensation method is compose of a neural deadbeat observer. To reduce of the noise effect, the post-filter, which is implemented by MA process, is adopted. The parameter compensator with RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller. The parameter estimator is combined with a high performance neural torque observer to resolve the problems. As a result, the proposed control system becomes a robust and precise system against the load torque and the parameter variation. A stability and usefulness, through the verified computer simulation, are shown in this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1811-1817
• /
• 2014

In this paper, a PID controller with interpolated gains by use of neural networks is proposed for the formation control problem that following robots track a leading robot with constant distances and angles when there are changes in the mass of the following robot. The whole control system is composed of a kinematic controller and a dynamic controller considering the robot dynamics. The dynamic controller is the PID controller with varying gains, and the proper gains are obtained for some representative masses of the follower robot by the genetic algorithm. Neural networks is trained using the genetic algorithm with the gain data obtained in the previous step. The trained neural network determines optimal PID gains for a random mass of following robot. Simulation studies show that for arbitrary masses of the tracking robot, the PID controller with interpolated gains by the trained neural network has better tracking performance than that of the PID controller with fixed gains.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.71-78
• /
• 2023

Employee turnover is one of the most important challenges facing modern organizations. It causes job experiences and skills such as distinguished faculty members in universities, rare-specialized doctors, innovative engineers, and senior administrators. HR analytics has enhanced the area of data analytics to an extent that institutions can figure out their employees' characteristics; where inaccuracy leads to incorrect decision making. This paper aims to develop a novel model that can help decision-makers to classify the problem of Employee Turnover. By using feature selection methods: Information Gain and Chi-Square, the most important four features have been extracted from the dataset. These features are over time, job level, salary, and years in the organization. As one of the important results of this research, these features should be planned carefully to keep organizations their employees as valuable assets. The proposed model based on machine learning algorithms. Classification algorithms were used to implement the model such as Decision Tree, SVM, Random Frost, Neuronal Network, and Naive Bayes. The model was trained and tested by using a dataset that consists of 1470 records and 25 features. To develop the research model, many experiments had been conducted to find the best one. Based on implementation results, the Neural Network algorithm is selected as the best one with an Accuracy of 84 percents and AUC (ROC) 74 percents. By validation mechanism, the model is acceptable and reliable to help origination decision-makers to manage their employees in a good manner.

• Proceedings of the KIEE Conference
• /
• 2002.07b
• /
• pp.1137-1139
• /
• 2002

In this paper, recurrent artificial neural network (RNN) based self tuning speed controller is proposed for the high performance drives of induction motor. RNN provides a nonlinear modeling of motor drive system and could give the information of the load variation, system noise and parameter variation of induction motor to the controller through the on-line estimated weights of corresponding RNN. Thus, proposed self tuning controller can change gains of the controller according to system conditions. The gain is composed with the weights of RNN. For the on-line estimation of the weights of RNN, extended kalman filter (EKF) algorithm is used. Self tuning controller that is adequate for the speed control of induction motor is designed. The availability of the proposed controller is verified through the MATLAB simulation with the comparison of conventional PI controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.107-112
• /
• 2003

In general, the dynamics of autonomous underwater vehicles(AUVs) are highly nonlinear and time-varying, and the hydrodynamic coefficients of vehicles are hard to estimate accurately because of the variations of these coefficients with different navigation conditions. For this reason, in this paper, the control gain function is assumed to be unknown and the exogenous input term is assumed to be unbounded, although it still satisfies certain restrict condition. And these two kinds of wild assumptions have been seldom handled simultaneously in one system because of the difficulty of stability analysis. Under the above two relaxed assumptions, a robust neural network control scheme is presented for autonomous diving control of an AUV, and can guarantee that all the signals in the closed-loop system are UUB (uniformly ultimately bounded). Some practical features of the proposed control law are also discussed.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1097-1098
• /
• 2011

This paper proposes high performance control of induction motor drive using fuzzy neural network precompensation PI(FNPPI) controller. To apply industrial processes, control methods is requested technique that can be demonstrate high performance and robust about load disturbance, parameter variation and uncertainty of model, etc. The PI controller dose not show satisfactory performance due to fixed gain. Therefore, this paper proposes FNPPI which is adjusted input values of PI controller according to operating conditions of motor by FNN controller mixed neural network and fuzzy. And this paper proves validity of proposed control algorithm through result analysis.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2236-2238
• /
• 2004

This paper proposes the self-recurrent wavelet neural network (SRWNN) observer based sliding mode control (SMC) method for nonlinear systems. Unlike the classical SMC, we assume that all states of nonlinear systems are not measured and design the SRWNN observer to measure the states of nonlinear systems. The SRWNN in the observer is used for approximating the observer system's gain. To generate the control input for controlling the nonlinear system, the measured states are used. The sliding surface with a boundary layer is defined to remove the chattering of the control input. Simulation result to show the effectiveness of the SRWNN observer is presented.