• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.1
• /
• pp.38-46
• /
• 2000

This study have established proper mathematical equivalent model of Brushless DC (BLDC) motor and estimated the motor parameter by means of the back-emf measurement as being the step input to the controlled target BLDC motor. And the validity of proposed estimation method is confirmed by the test result of step response. As well, we have designed the reasonable digital controller as a consequence of the root locus method which is obtained from the open-loop transfer function of BLDC motor with hall sensor, and the determination of control gain for variable speed control. Here, revised Ziegler-Nichols tuning method is applied for the proper digital gain establishment, and the system stability is verified by the frequency domain analysis with Bode-plot and experimentation.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.9
• /
• pp.441-450
• /
• 2002

In this paper, optimal tuning problem of power system stabilizer using IA-QFT is investigated to improve power system dynamic stability in spite of parameter variation and disturbance uncertainties. The most important feature of QFT is that it is able to deal with the design problem of complicated uncertain plants. However, loop shaping is currently performed in computer aided design environments manually and it is usually a trial and error procedure. It is difficult to design a controller to satisfy all specifications manually. To solve this problem, a study of design automation using IA needs to be taken into account. The robustness of the proposed controller has been investigated on a single machine infinite bus model. The results are shown that the proposed PSS using IA-QFT is more robust than conventional PSS.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.50-59
• /
• 1998

This paper presents stabilization and adaptive control of flexible single link robot manipulator system by self-recurrent neural networks that is one of the neural networks and is effective in nonlinear control. The architecture of neural networks is a modified model of self-recurrent structure which has a hidden layer. The self-recurrent neural networks can be used to approximate any continuous function to any desired degree of accuracy and the weights are updated by feedback-error learning algorithm. When a flexible manipulator is rotated by a motor through the fixed end, transverse vibration may occur. The motor toroque should be controlled in such a way that the motor rotates by a specified angle, while simultaneously stabilizing vibration of the flexible manipuators so that it is arresed as soon as possible at the end of rotation. Accurate vibration control of lightweight manipulator during the large changes in configuration common to robotic tasks requires dynamic models that describe both the rigid body motions, as well as the flexural vibrations. Therefore, a dynamic models for a flexible single link robot manipulator is derived, and then a comparative analysis was made with linear controller through an simulation and experiment. The results are proesented to illustrate thd advantages and imporved performance of the proposed adaptive control ove the conventional linear controller.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.63-68
• /
• 2009

As the complexity of the power system becomes higher, tests of the new devices, such as exciter and PCS(Power Conversion System) of the distributed generation sources, in the real operating condition are more important. However tests of the unverified devices in the real power system may cause hazardous malfunction of the system. In order to avoid this problem, power devices may be tested with the real-time simulators instead of the real power system. This paper presents an real-time multi machine power system simulator using PCs(Personal Computer) and Fast Ethernet. Developed real-time simulator performs the electro-mechanical dynamic simulation of multi-machine power system by the network distributed computing technique. Because the simulator consists of usual PCs and Fast Ethernet, it is possible to make up a simulation system very cheaper than the conventional real-time simulator which consists of dedicated expensive hardware devices. The performance of the developed simulator is tested and verified with the scaled model excitation system. The test which adjust the control parameters of the exciter is performed with the well-known New England 10 generator 39 bus sample power system.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.2
• /
• pp.27-32
• /
• 2020

This paper presents steering system requirements to ensure the stabilized lateral control of autonomous driving vehicles. The two main objectives of a lateral controller in autonomous vehicles are maintenance of vehicle stability and tracking of the desired path. Even if the desired steering angle is immediately determined by the upper level controller, the overall controller performance is greatly influenced by the specification of steering system actuators. Since one of the major inescapable traits that affects controller performance is the time delay of the steering actuator, our work is mainly focused on finding adequate parameters of high level control algorithm to compensate these response characteristics and guarantee vehicle stability. Actual vehicle steering angle response was obtained with Electric Power Steering (EPS) actuator test subject to various longitudinal velocity. Steering input and output response analysis was performed via MATLAB system identification toolbox. The use of system identification is advantageous since the transfer function of the system is conveniently obtained compared with methods that require actual mathematical modeling of the system. Simulation results of full vehicle model suggest that the obtained tuning parameter yields reduced oscillation and lateral error compared with other cases, thus enhancing path tracking performance.

• Proceedings of the KIEE Conference
• /
• 2009.04b
• /
• pp.32-34
• /
• 2009

The field oriented control of induction motors is widely used in high performance applications. However, detuning caused by parameter disturbance still limits the performance of these drives. In order to accomplish variable speed operation, conventional PI-like controllers are commonly used. These controllers provide limited good Performance over a wide range of operation, even under ideal field oriented conditions. This paper is proposed model reference adaptive fuzzy control(MFC) and artificial neural network(ANN) based on the vector controlled induction motor drive system. Also, this paper is proposed control of speed and current using fuzzy adaption mechanism(FAM), MFC and estimation of speed using ANN. The proposed control algorithm is applied to induction motor drive system using FAM, MFC and ANN controller. Also, this paper is proposed the analysis results to verify the effectiveness of this controller.

• Korean Journal of Materials Research
• /
• v.33 no.4
• /
• pp.164-174
• /
• 2023

The bandgap characteristics of semiconductor materials are an important factor when utilizing semiconductor materials for various applications. In this study, based on data provided by AFLOW (Automatic-FLOW for Materials Discovery), the bandgap of a semiconductor material was predicted using only the material's compositional features. The compositional features were generated using the python module of 'Pymatgen' and 'Matminer'. Pearson's correlation coefficients (PCC) between the compositional features were calculated and those with a correlation coefficient value larger than 0.95 were removed in order to avoid overfitting. The bandgap prediction performance was compared using the metrics of R² score and root-mean-squared error. By predicting the bandgap with randomforest and xgboost as representatives of the ensemble algorithm, it was found that xgboost gave better results after cross-validation and hyper-parameter tuning. To investigate the effect of compositional feature selection on the bandgap prediction of the machine learning model, the prediction performance was studied according to the number of features based on feature importance methods. It was found that there were no significant changes in prediction performance beyond the appropriate feature. Furthermore, artificial neural networks were employed to compare the prediction performance by adjusting the number of features guided by the PCC values, resulting in the best R² score of 0.811. By comparing and analyzing the bandgap distribution and prediction performance according to the material group containing specific elements (F, N, Yb, Eu, Zn, B, Si, Ge, Fe Al), various information for material design was obtained.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.115-128
• /
• 2023

Deep learning has been incorporating various optimization techniques motivated by new pragmatic optimizing algorithm advancements and their usage has a central role in Machine learning. In recent past, new avatars of various optimizers are being put into practice and their suitability and applicability has been reported on various domains. The resurgence of novelty starts from Stochastic Gradient Descent to convex and non-convex and derivative-free approaches. In the contemporary of these horizons of optimizers, choosing a best-fit or appropriate optimizer is an important consideration in deep learning theme as these working-horse engines determines the final performance predicted by the model. Moreover with increasing number of deep layers tantamount higher complexity with hyper-parameter tuning and consequently need to delve for a befitting optimizer. We empirically examine most popular and widely used optimizers on various data sets and networks-like MNIST and GAN plus others. The pragmatic comparison focuses on their similarities, differences and possibilities of their suitability for a given application. Additionally, the recent optimizer variants are highlighted with their subtlety. The article emphasizes on their critical role and pinpoints buttress options while choosing among them.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.679-691
• /
• 2013

High-power electromagnetic transmitter power supplies are an important part of deep geophysical exploration equipment. This is especially true in complex environments, where the ability to produce a highly accurate and stable output and safety through redundancy have become the key issues in the design of high-power electromagnetic transmitter power supplies. To solve these issues, a high-frequency switching power cascade based emission power supply is designed. By combining the circuit averaged model and the equivalent controlled source method, a modular mathematical model is established with the on-state loss and transformer induction loss being taken into account. A triple-loop control including an inner current loop, an outer voltage loop and a load current forward feedback, and a digitalized voltage/current sharing control method are proposed for the realization of the rapid, stable and highly accurate output of the system. By using a new algorithm referred to as GAPSO, which integrates a genetic algorithm and a particle swarm algorithm, the parameters of the controller are tuned. A multi-module cascade helps to achieve system redundancy. A simulation analysis of the open-loop system proves the accuracy of the established system and provides a better reflection of the characteristics of the power supply. A parameter tuning simulation proves the effectiveness of the GAPSO algorithm. A closed-loop simulation of the system and field geological exploration experiments demonstrate the effectiveness of the control method. This ensures both the system's excellent stability and the output's accuracy. It also ensures the accuracy of the established mathematical model as well as its ability to meet the requirements of practical field deep exploration.