• 한국산업융합학회 논문집
• /
• 제6권1호
• /
• pp.23-29
• /
• 2003

This paper proposes an efficient feature extraction of the images by using independent component analysis(ICA) based on neural networks of the hybrid learning algorithm. The proposed learning algorithm is the fixed point(FP) algorithm based on Newton method and moment. The Newton method, which uses to the tangent line for estimating the root of function, is applied for fast updating the inverse mixing matrix. The moment is also applied for getting the better speed-up by restraining an oscillation due to compute the tangent line. The proposed algorithm has been applied to the 10,000 image patches of $12{\times}12$-pixel that are extracted from 13 natural images. The 144 features of $12{\times}12$-pixel and the 160 features of $16{\times}16$-pixel have been extracted from all patches, respectively. The simulation results show that the extracted features have a localized characteristics being included in the images in space, as well as in frequency and orientation. And the proposed algorithm has better performances of the learning speed than those using the conventional FP algorithm based on Newton method.

• 한국학교수학회논문집
• /
• 제4권1호
• /
• pp.103-114
• /
• 2001

The purpose of this study is to develop learning materials for functional concept on variable and to verify the effect of how well students could learn functional concept after they studied with those materials. To accomplish the purpose of this study, I developed learning materials and after teaching students with them. I have concluded the followings : First, there was little effect in teaching functional concept on variable between two experimental groups, whereas teaching functional concept had greater effect on forming functional concept in high level groups in those two experimental groups. Second, teaching functional concept on variable had little effect on students' understanding of functional concept and perfecting tables in Black box, graph, and mathematical problems, whereas there was much effect in students' understanding functional concept and solving relation formula, image, and range problems related to everyday life or general things. On the basis of the problems which appeared in the process of this study, the following can be suggested : First, we should develop learning materials fit for low level students so that they could understand functional concept. Second, we should continue to teach the basic problems like solving relation formula, image, and range, and understanding functional concept in graph until students are able to understand them exactly. Third, since the goals of Unit Function in a middle school textbook is to solve problems related to everyday life through functional thinking, there should be change in constructing systematic contents of Unit Function in a middle school textbook.

• Earthquakes and Structures
• /
• 제18권6호
• /
• pp.719-730
• /
• 2020

Recently, population based optimization algorithms are developed to deal with a variety of optimization problems. In this paper, the salp swarm algorithm (SSA) is dramatically enhanced and a new algorithm is named Enhanced Salp Swarm Algorithm (ESSA) which is effectively utilized in optimization problems. To generate the ESSA, an opposition-based learning and merit function methods are added to standard SSA to enhance both exploration and exploitation abilities. To have a clear judgment about the performance of the ESSA, firstly, it is employed to solve some mathematical benchmark test functions. Next, it is exploited to deal with engineering problems such as optimally designing the benchmark buildings equipped with multiple tuned mass damper (MTMD) under earthquake excitation. By comparing the obtained results with those obtained from other algorithms, it can be concluded that the proposed new ESSA algorithm not only provides very competitive results, but also it can be successfully applied to the optimal design of the MTMD.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• 로봇학회논문지
• /
• 제17권1호
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.

• 한국인터넷방송통신학회논문지
• /
• 제23권4호
• /
• pp.79-84
• /
• 2023

최근 분산 및 병렬 처리 기술 중 빠른 처리 속도를 제공하는 Apache Spark는 실시간 기능 및 머신러닝 기능을 제공하고 있다. 이러한 기능에 대한 공식 문서 가이드가 제공되고 있지만, 기능들을 융합하여 실시간으로 특정 값을 예측하는 방안은 제공되고 있지 않다. 따라서 본 논문에서는 이러한 기능들을 융합하여 실시간으로 데이터의 값을 예측할 수 있는 연구를 진행했다. 전체적인 구성은 Python 프로그래밍 언어에서 제공하는 주가 데이터를 다운로드하여 수집한다. 그리고 머신러닝 기능을 통해 회귀분석의 모델을 생성하고, 실시간 스트리밍 기능을 머신러닝 기능과 융합하여 실시간으로 주가 데이터 중 조정종가를 예측한다.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.68-74
• /
• 2019

Along with the deeper architecture in the deep learning approaches, the need for the data becomes very big. In the real problem, to get huge data in some disciplines is very costly. Therefore, learning on limited data in the recent years turns to be a very appealing area. Meta-learning offers a new perspective to learn a model with this limitation. A state-of-the-art model that is made using a meta-learning framework, Meta-SGD, is proposed with a key idea of learning a hyperparameter or a learning rate of the fast adaptation stage in the outer update. However, this learning rate usually is set to be very small. In consequence, the objective function of SGD will give a little improvement to our weight parameters. In other words, the prior is being a key value of getting a good adaptation. As a goal of meta-learning approaches, learning using a single gradient step in the inner update may lead to a bad performance. Especially if the prior that we use is far from the expected one, or it works in the opposite way that it is very effective to adapt the model. By this reason, we propose to add a weight term to decrease, or increase in some conditions, the effect of this prior. The experiment on few-shot learning shows that emphasizing or weakening the prior can give better performance than using its original value.

• 디지털융복합연구
• /
• 제3권2호
• /
• pp.143-157
• /
• 2005

Many papers point out that the e-Learning is one of the most important industries, and the effect on other industries can be more powerful than any other business. Therefore, we think about social, cultural, industrial and technological effect of the e-Learning in order to enlarge industry scale as well as educational performances. In many cases of developed countries, various kinds of study have been performed for the e-Learning quality assurance because quality of the e-learning should operate on effective and efficient learning and continuous market development of education industries. The e-Learning quality assurance has import function not only for learning contents reusability like a SCORM and metadata but also for learning system, solution and service operation, so activities for the quality assurance should consider of cultural and tactical approach when it is applied in the e-learning business. In this paper, we present the concept, domain and purpose of the e-Learning quality assurance. Furthermore, this paper proposes the process and methodology in order to make the quality assurance standard model which is consist of 6 phase such as Environment Research, Needs Analysis, Framework, Metrics, Development and Implementation, Evaluation and Feedback through the analysis and comparison of pre-studied worldwide quality control, management and assurance documents.

• Journal of information and communication convergence engineering
• /
• 제1권3호
• /
• pp.157-162
• /
• 2003

We propose a learning method for improving the performance of the backpropagation algorithm. The proposed method is using a fuzzy logic system for automatic tuning of the learning rate of each weight. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust the learning rate. The inputs of fuzzy logic system are delta and delta bar, and the output of fuzzy logic system is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on the XOR problem, character classification, and function approximation. The results show that the proposed method considerably improves the performance compared to the general backpropagation, the backpropagation with momentum, and the Jacobs'delta-bar-delta algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.1069-1074
• /
• 1989

A discrete-time learning control for robotic manipulators is studied using its pulse transfer function. Firstly, discrete-time learning stability condition which is applicable to single-input two-outputs systems is derived. Secondly, stability of learning algorithm with position signal is studied. In this case, when sampling period is small, the algorithm is not stable because of an unstable zero of the system. Thirdly, stability of algorithm with position and velocity signals is studied. In this case, we can stabilize the learning control system which is unstable in learning with only position signal. Finally, simulation results on the trajectory control of robotic manipulators using the discrete-time learning control are shown. This simulation results agree well with the analytical ones.