• 한국기계연구소 소보
• /
• s.19
• /
• pp.125-139
• /
• 1989

As an adaptive control function generator, the CMAC (Cerebellar Model Arithmetic or Articulated Controller) based learning control has drawn a great attention to realize a rather robust real-time manipulator control under the various uncertainties. There remain, however, inherent problems to be solved in the CMAC application to robot motion control or perception of sensory information. To apply the CMAC to the various unmodeled or modeled systems more efficiently, it is necessary to analyze the effects of the CMAC control parameters on the trained net. Although the CMAC control parameters such as size of the quantizing block, learning gain, input offset, and ranges of input variables play a key role in the learning performance and system memory requirement, these have not been fully investigated yet. These parameters should be determined, of course, considering the shape of the desired function to be trained and learning algorithms applied. In this paper, the interrelation of these parameters with learning performance is investigated under the basic learning schemes presented by authors. Since an analytic approach only seems to be very difficult and even impossible for this purpose, various simulations have been performed with pre specified functions and their results were analyzed. A general step following design guide was set up according to the various simulation results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.6
• /
• pp.555-562
• /
• 1997

With only the classical PID controller applied to control of a DC motor, good (target) performance characteristic of the controller can be obtained if all the model parameters of DC motor and operating conditions such as external load torque, disturbance, etc. are known exactly. However, in case when some of system parameters or operating conditions are uncertain or unknown, the fixed PID controller does not guarantee good performance, which is assumed with precisely known system parameters and operating conditions. In view of this and the robustness enhancement of DC motor control system, we propose a PID learning controller which consists of a set of learning rules for PID gain tuning and learning of an auxiliary input. The proposed PID learning controller is shown to drive the state of uncertain DC motor system with unknown system parameters and external load torque to the desired one world wide asymptotically. Computer simulation and experimental results are given to demonstrate the effectiveness of the proposed PID learning controller, thereby showing its superiority to the conventional fixed PID controller.

• Proceedings of the KWS Conference
• /
• 2004.05a
• /
• pp.296-298
• /
• 2004

Recently, various fields are building developed and applied system environment using the technology of the web-based virtual reality. This paper describes about the building of Web-based learning environment that supports efficient educational effectiveness throughout the effective 2-D and 3-D visual interface and the operation of main facilities and the navigation of it. The objective of this environmental building is to provide proper knowledge and technology of a nuclear power plant to those students (examine. and trainee), and help them gain effective experiences throughout such activities.

• Clinical Endoscopy
• /
• v.57 no.3
• /
• pp.283-292
• /
• 2024

We developed three e-learning systems for endoscopists to acquire the necessary skills to improve the diagnosis of early gastric cancer (EGC) and demonstrated their usefulness using randomized controlled trials. The subjects of the three e-learning systems were "detection", "characterization", and "preoperative assessment". The contents of each e-learning system included "technique", "knowledge", and "obtaining experience". All e-learning systems proved useful for endoscopists to learn how to diagnose EGC. Lecture videos describing "the technique" and "the knowledge" can be beneficial. In addition, repeating 100 self-study cases allows learners to gain "experience" and improve their diagnostic skills further. Web-based e-learning systems have more advantages than other teaching methods because the number of participants is unlimited. Histopathological diagnosis is the gold standard for the diagnosis of gastric cancer. Therefore, we developed a comprehensive diagnostic algorithm to standardize the histopathological diagnosis of gastric cancer. Once we have successfully shown that this algorithm is helpful for the accurate histopathological diagnosis of cancer, we will complete a series of e-learning systems designed to assess EGC accurately.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.103-106
• /
• 1996

This paper presents an iterative fuzzy learning control scheme which is applicable to a broad class of nonlinear systems. The control scheme achieves system stability and boundedness by using the linear feedback plus adaptive fuzzy controller and achieves precise tracking by using the iterative learning rules. The switching mode control unit is added to the adaptive fuzzy controller in order to compensate for the error that has been inevitably introduced from the fuzzy approximation of the nonlinear part. It also obviates any supervisory control action in the adaptive fuzzy controller which normally requires high gain signal. The learning control algorithm obviates any output derivative terms which are vulnerable to noise.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.201-204
• /
• 2000

This paper describes a study on the time-varying control of parameters in learning of the neural network. Elman recurrent neural network (RNN) is used to implement the control of parameters. The parameters of learning and momentum rates In the error backpropagation algorithm ate updated at every iteration using fuzzy rules based on performance index. In addition, the gain and slope of the neuron's activation function are also considered time-varying parameters. These function parameters are updated using the gradient descent algorithm. Simulation results show that the auto-tuned learning algorithm results in faster convergence and lower system error than regular backpropagation in the system identification.

• Journal of dental hygiene science
• /
• v.17 no.5
• /
• pp.383-397
• /
• 2017

We attempted to develop a problem-based learning (PBL) module for integrated education in dental hygiene with the aim of helping students gain clinical competencies necessary for dental hygienist work. To develop the PBL Module for Clinical Dentistry in Dental Hygiene course, the researchers identified literature related to not only educational technology, but also medical science, nursing, dentistry, and dental hygiene. During the design phase of the PBL module, problem scenarios and a plan for the teaching and learning process were developed. Developing problem scenarios involved describing a problematic situation and three questions related with that situation. To cultivate competencies required in dental clinics, each question was related to the diagnosis of a dental disease, dental treatment, and dental hygiene procedures for care. Teaching-learning process plan included the designs of operating environment, operational strategies, learning resources, facilitation of problem-solving process, and evaluation. It is necessary to evaluate the PBL module for integrated education in dental hygiene to confirm its effectiveness.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.90-104
• /
• 2020

It is difficult for non-experts to build machine learning (ML) models at the level that satisfies their needs. Deep learning models are even more challenging because it is unclear how to improve the model, and a trial-and-error approach is not feasible since training these models are time-consuming. To assist these novice users, we examined how interactive and explainable feedback while training a deep learning network can contribute to model performance and users' satisfaction, focusing on the data preparation process. We conducted a user study with 31 participants without expertise, where they were asked to improve the accuracy of a deep learning model, varying feedback conditions. While no significant performance gain was observed, we identified potential barriers during the process and found that interactive and explainable feedback provide complementary benefits for improving users' understanding of ML. We conclude with implications for designing an interface for building ML models for novice users.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.4
• /
• pp.92-98
• /
• 2005

The learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work, the authors presented an iterative precision of linear decentralized learning control based on p-integrated learning method for the vertical dynamic multiple systems. This paper develops an indirect decentralized teaming control based on adaptive control method. The original motivation of the teaming control field was loaming in robots doing repetitive tasks such as on an assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. Some techniques will show up in the numerical simulation for vertical dynamic robot. The methods of learning system are shown up for the iterative precision of each link.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.675-681
• /
• 1989

As an adaptive control function generator, the CMAC (Cerebellar Model Arithmetic or Articulated Controller) based learning control has drawn a great attention to realize a rather robust real-time manipulator control under the various uncertainties. There remain, however, inherent problems to be solved in the CMAC application to robot motion control or perception of sensory information. To apply the CMAC to the various unmodeled or modeled systems more efficiently, It is necessary to analyze the effects of the CMAC control parameters an the trained net. Although the CMAC control parameters such as size of the quantizing block, learning gain, input offset, and ranges of input variables play a key role in the learning performance and system memory requirement, these have not been fully investigated yet. These parameters should be determined, of course, considering the shape of the desired function to be trained and learning algorithms applied. In this paper, the interrelation of these parameters with learning performance is investigated under the basic learning schemes presented by authors. Since an analytic approach only seems to be very difficult and even impossible for this purpose, various simulations have been performed with prespecified functions and their results were analyzed. A general step following design guide was set up according to the various simulation results.