• Journal of Information Technology Applications and Management
• /
• 제26권3호
• /
• pp.19-27
• /
• 2019

In this study, we propose a methodology for predicting the movie audience based on movie information that can be easily acquired before opening and effectively distinguishing qualitative variables. In addition, we constructed a model to estimate the number of movie audiences at the time of data acquisition through the configured variables. Another purpose of this study is to provide a criterion for categorizing success of movies with qualitative characteristics. As an evaluation criterion, we used information gain ratio which is the node selection criterion of C4.5 algorithm. Through the procedure we have selected 416 movie data features. As a result of the multiple linear regression model, the performance of the regression model using the variables selection method based on the information gain ratio was excellent.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.229-229
• /
• 2000

Conventional gain-tuning methods such as Ziegler-Nickels methods, have many disadvantages that optimal control ler gain should be tuned manually. In this paper, modified PID controllers which include self-tuning characteristics are proposed. Proposed controllers automatically tune the PID gains in on-1ine using neural networks. A new learning scheme was proposed for improving learning speed in neural networks and satisfying the real time condition. In this paper, using a nonlinear mapping capability of neural networks, we derive a tuning method of PID controller based on a Back propagation(BP)method of multilayered neural networks. Simulated and experimental results show that the proposed method can give the appropriate parameters of PID controller when it is implemented to DC Motor.

• 조명전기설비학회논문지
• /
• 제20권7호
• /
• pp.53-57
• /
• 2006

PID 제어기는 산업자동화 설비에 널리 쓰이고 있다. 하지만 시스템 특성이 간헐 또는 연속적으로 변화할 때에 정밀제어를 위한 새로운 매개변수 결정이 쉽지 않다. 이를 해결하기 위한 방법으로 본 논문에서는 PID 제어기와 같은 기능을 갖는 신경망이득 자동조절기를 제안 하였다. 시스템의 적절한 궤환제어 이득은 델타 학습규칙에 의해서 결정된다. 제안된 신경망이득 자동조절기의 기능은 유도 전동기의 속도제어 실험에 의해 확인하였다.

• 한국경영과학회지
• /
• 제26권1호
• /
• pp.61-69
• /
• 2001

This paper presents a two stage game model which examines the effect of learning-by-doing and spillover. Increases in the firm’s cumulative experience lower its unit cost in future period. However, the firm’s rival also enjoys the experience via spillover. Unlike previous theoretical research model, a cost asymmetric market entry game model is developed between the incumbent firm and new entrant. Mathematical results show that the incumbent firm exploits the learning curve to gain future cost advantage, and that the diffusion of learning to the new entrant induces the incumbent firm to choose decreasing output strategically. As a main result, we show that the relative magnitude between the learning and spillover rate determines the market share ratio of competing firms.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.13-23
• /
• 2018

Deep learning is a promising solution to a number of complex problems based on its inherent capability to approximate almost all types of functions without the demand for handcrafted feature extraction. New wireless transmission and access schemes based on deep learning are being increasingly proposed as substitutes for existing approaches, providing a lower complexity and better performance gain. Among such schemes, a communications system is viewed as an end-to-end autoencoder. The learning process applied in autoencoders can automatically deal with some nonlinear or unknown properties in communications systems. Deep learning can also be used to optimize each processing block for required tasks such as channel decoding, signal detection, and multiple access. On top of recent related research trends, we suggest appropriate research approaches for communications systems to adopt deep learning.

• International Journal of Contents
• /
• 제8권1호
• /
• pp.10-15
• /
• 2012

Since MegaStudy started e-learning business for Korean high school students, the Korean e-learning industry began to expand and steadily gain attention. This paper focused on the analysis of the development of the Korean e-learning business for teens and the growth of MegaStudy. The three institutional mechanisms were used to examine the factors that aided the development of the business. The regulatory mechanism was the government policy to prevent the expansion of the offline private education sector, which greatly aided the growth of the e-learning business. The mimetic mechanism was the notion to mimic the characteristics of the Korean e-business initiatives. The normative mechanism involved the widespread social norm suggesting that every student should be given an equal opportunity of private education. This paper also examined the case of MegaStudy as a successful case of the e-learning companies. It analyzed the business model of MegaStudy, which is based on its advantage as the front-runner and its high-quality contents and services.

• International Journal of Aeronautical and Space Sciences
• /
• 제11권2호
• /
• pp.87-97
• /
• 2010

A fault tolerant satellite attitude control scheme with a modified iterative learning law is proposed for dealing with actuator faults. The actuator fault is modeled to reflect the degradation of actuation effectiveness, and the solar array-induced disturbance is considered as an external disturbance. To estimate the magnitudes of the actuator fault and the external disturbance, a modified iterative learning law using only the information associated with the state error is applied. Stability analysis is performed to obtain the gain matrices of the modified iterative learning law using the Lyapunov theorem. The proposed fault tolerant control scheme is applied to the rest-to-rest maneuver of a large satellite system, and numerical simulations are performed to verify the performance of the proposed scheme.

• Journal of Radiation Protection and Research
• /
• 제46권4호
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• International Journal of Precision Engineering and Manufacturing
• /
• 제7권1호
• /
• pp.62-66
• /
• 2006

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 learning control based on adaptive control method. The original motivation of the learning control field was learning in robots doing repetitive tasks such as an assembly line works. 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 for the iterative precision of each link.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.147.1-147
• /
• 2001

Future robots, especially service and personal robots, will need much more intelligence, robustness and user-friendliness. The ability to learn contributes to these characteristics and is, therefore, becoming more and more important. Three of the numerous varieties of learning are discussed together with results of real-world experiments with three autonomous robots: (1) the acquisition of map knowledge by a mobile robot, allowing it to navigate in a network of corridors, (2) the acquisition of motion control knowledge by a calibration-free manipulator, allowing it to gain task-related experience and improve its manipulation skills while it is working, and (3) the ability to learn how to perform service tasks ...