• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.37-45
• /
• 2020

The development process of deep learning is an iterative task that requires a lot of manual work. Among the steps in the development process, pre-processing of learning data is a very costly task, and is a step that significantly affects the learning results. In the early days of AI's algorithm research, learning data in the form of public DB provided mainly by data scientists were used. The learning data collected in the real environment is mostly the operational data of the sensors and inevitably contains various noises. Accordingly, various data cleaning frameworks and methods for removing noises have been studied. In this paper, we proposed a method for detecting and removing noises from time-series data, such as sensor data, that can occur in the IoT environment. In this method, the linear regression method is used so that the system repeatedly finds noises and provides data that can replace them to clean the learning data. In order to verify the effectiveness of the proposed method, a simulation method was proposed, and a method of determining factors for obtaining optimal cleaning results was proposed.

• Journal of the Korean Chemical Society
• /
• v.67 no.4
• /
• pp.253-270
• /
• 2023

The purpose of this study was to examine the effect of student-led assessment on achievement emotions and science concept understanding in middle school science classes. For this purpose, 4 of the 7 classes in the third grade of mid- dle school in small and medium-sized cities were selected as the experimental group and conducted student-led assessment, while the comparative group (3 classes) conducted teacher-led assessment. The student-led assessment consisted of 4 stages in which learners took initiative to set learning goals and develop assessment criteria, conduct self assessment and peer assess- ment, and carry out seven assessment activities. Student-led assessment was effective in improving positive achievement emotions and relieving negative achievement emotions and increasing students' science concept understanding in middle school students. Students perform student-led assessment, grasp their reach, and repeatedly go through reflective thinking to compensate for deficiencies in the learning process. Therefore, student-led assessment can be used as a tool to increase science concept understanding by continuously checking the level of science concept understanding.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.2
• /
• pp.102-110
• /
• 2017

Current word sense disambiguation techniques employ various machine learning-based methods. Various approaches have been proposed to address this problem, including the knowledge base approach. This approach defines the sense of an ambiguous word in accordance with knowledge base information with no training corpus. In unsupervised learning techniques that use a knowledge base approach, graph-based and similarity-based methods have been the main research areas. The graph-based method has the advantage of constructing a semantic graph that delineates all paths between different senses that an ambiguous word may have. However, unnecessary semantic paths may be introduced, thereby increasing the risk of errors. To solve this problem and construct a fine-grained graph, in this paper, we propose a model that iteratively constructs the graph while eliminating unnecessary nodes and edges, i.e., senses and semantic paths. The hybrid similarity estimation model was applied to estimate a more accurate sense in the constructed semantic graph. Because the proposed model uses BabelNet, a multilingual lexical knowledge base, the model is not limited to a specific language.

• Journal of the Korean School Mathematics Society
• /
• v.13 no.4
• /
• pp.635-653
• /
• 2010

The purpose of this article is to investigate the relationship between children's goals and activities in terms of continuity and transformation of their learning through interactions between learners and practices across settings. By observing children's activities across settings and tasks and interviewing the children, I found that the continuity and transformation in learning are developed in the relationship between changing individuals and changing social context. In this process, social interaction with others plays an important role in changing their goals and strategies. The results imply that appropriate tasks and teachers' guidance are crucial to facilitate students' learning across settings.

• Journal of Internet of Things and Convergence
• /
• v.7 no.4
• /
• pp.29-34
• /
• 2021

In order to apply reinforcement learning to a robot in a real environment, it is necessary to use simulation in a virtual environment because numerous iterative learning is required. In addition, it is difficult to apply a learning algorithm that requires a lot of computation for a robot with low-spec. hardware. In this study, ML-Agent, a reinforcement learning frame provided by Unity, was used as a virtual simulation environment to apply reinforcement learning to the obstacle collision avoidance problem of mobile robots with low-spec hardware. A DQN supported by ML-Agent is adopted as a reinforcement learning algorithm and the results for a real robot show that the number of collisions occurred less then 2 times per minute.

• Journal of Oral Medicine and Pain
• /
• v.37 no.2
• /
• pp.93-105
• /
• 2012

Let me introduce a teaching method to improve practice capacity in dental laboratary work. I applied theories of layers of modeling and reflection constituting cognitive apprenticeship and peer tutoring to my class. At internet uploading a file showing a practice procedure a week before the class of a course, I let students preview it. During the class I demonstrated the practice procedure in front of students. A superior student and an inferior student paired according to the previous practice grade and a feedback between a peer tutor and a peer tutee was activated. Late in the class, a student self-evaluated his own practice result and had a check of a professor. Finally he compared his own practice result with that in the file uploaded at internet and reflected. This teaching method led to improvement in students' satisfaction and efficiency of learning.

• Journal of Korea Game Society
• /
• v.15 no.3
• /
• pp.151-160
• /
• 2015

This paper presents English vocabulary memorization system using forgetting curve to automatically adjust the vocabulary difficulty to match learner's level. Our system will decide the appropriate repetition cycle, depending on the number of memorizing words through the forgetting curve, then requires an iterative learning. No matter what learners know or do not know, words are reviewed. To save time by reviewing some words which have the highest probability that learners forget. And it provides vocabulary based on learner level, which makes learner maintain their interest and achievement. A general system provides vocabularies which difficulty matches with evaluated ones, or randomly provides some vocabularies without consideration of users' level. But we apply the "Glicko" system which is being used in the online chess game ranking system to adjust the vocabulary's difficulty. We utilize the system used in the one-by-one player system to our vocabulary-human system. As a result, learners's level and the vocabularies's difficulty is measured in the review process. Moreover it maximizes the performance of English vocabulary memorization by applying feedbacks from practice testing and distributed learning.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.9
• /
• pp.35-42
• /
• 1998

Finding a technique to achieve high machining precision and high productivity is an important issue for CNC machining. One of the solutions to meet better performance of machining is feedrate control. In this paper we present an adaptive feedrate neuro-control method for high precision and high speed machining. The adaptive neuro-control architecture consists of a neural network identifier(NNI) and an iterative learning control algorithm with inversion of the NNI. The NNI is an identifier for the nonlinear characteristics of feedrate and contour error, which is utilized in iterative learning for adaptive feedrate control with specified contour error tolerance. The proposed neuro-control method has been successfully evaluated for machining circular, corner and involute contours by computer simulations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3434-3439
• /
• 2015

As a criterion of information theoretic learning, the Euclidean distance (ED) of two error probability distribution functions (minimum ED of error, MEDE) has been adopted in nonlinear (decision feedback, DF) supervised equalizer algorithms and has shown significantly improved performance in severe channel distortion and impulsive noise environments. However, the MEDE-DF algorithm has the problem of heavy computational complexity. In this paper, the recursive ED for MEDE-DF algorithm is derived first, and then the feed-forward and feedback section gradients for weight update are estimated recursively. To prove the effectiveness of the recursive gradient estimation for the MEDE-DF algorithm, the number of multiplications are compared and MSE performance in impulsive noise and underwater communication environments is compared through computer simulation. The ratio of the number of multiplications between the proposed DF and the conventional MEDE-DF algorithm is revealed to be $2(9N+4):2(3N^2+3N)$ for the sample size N with the same MSE learning performance in the impulsive noise and underwater channel environment.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.134-142
• /
• 2019

As the development of internet of energy (IoE) technologies and spread of various electronic devices have diversified patterns of energy consumption, the reliability of demand prediction has decreased, causing problems in optimization of power generation and stabilization of power supply. In this study, we propose a deep learning method, 1-Dimention-Convolution and Bidirectional Long Short-Term Memory (1D-ConvBLSTM), that combines a convolution neural network (CNN) and a Bidirectional Long Short-Term Memory(BLSTM) for highly reliable demand forecasting by effectively extracting the energy consumption pattern. In experimental results, the demand is predicted with the proposed deep learning method for various number of learning iterations and feature maps, and it is verified that the test data is predicted with a small number of iterations.