• Title/Summary/Keyword: Q-학습

Search Result 294, Processing Time 0.025 seconds

Development of Prediction Model of Chloride Diffusion Coefficient using Machine Learning (기계학습을 이용한 염화물 확산계수 예측모델 개발)

  • Kim, Hyun-Su
    • Journal of Korean Association for Spatial Structures
    • /
    • v.23 no.3
    • /
    • pp.87-94
    • /
    • 2023
  • Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

Interface Establishment between Reinforcement Learning Algorithm and External Analysis Program for AI-based Automation of Bridge Design Process (AI기반 교량설계 프로세스 자동화를 위한 강화학습 알고리즘과 외부 해석프로그램 간 인터페이스 구축)

  • Kim, Minsu;Choi, Sanghyun
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.34 no.6
    • /
    • pp.403-408
    • /
    • 2021
  • Currently, in the design process of civil structures such as bridges, it is common to make final products by repeating the process of redesigning, if the initial design is found to not meet the standards after a structural review. This iterative process extends the design time, and causes inefficient consumption of engineering manpower, which should be put into higher-level design, on simple repetitive mechanical work. This problem can be resolved by automating the design process, but the external analysis program used in the design process has been the biggest obstacle to such automation. In this study, we constructed an AI-based automation system for the bridge design process, including an interface that could control both a reinforcement learning algorithm, and an external analysis program, to replace the repetitive tasks in the current design process. The prototype of the system built in this study was developed for a 2-span RC Rahmen bridge, which is one of the simplest bridge systems. In the future, it is expected that the developed interface system can be utilized as a basic technology for linking the latest AI with other types of bridge designs.

The Effect of Deodeok Contents on the Quality of Deodeok Wine (더덕 함량이 더덕 침출주의 품질에 미치는 영향)

  • Kwon, Dong-Jin;Choi, Shin-Yang
    • Food Science and Preservation
    • /
    • v.14 no.4
    • /
    • pp.414-418
    • /
    • 2007
  • The physicochemical characteristics and sensory properties of Deodeok wine, formed by leaching of Deodeok at room temperature for 180 days, were investigated over the following range of Deodeok levels: 10, 15 and 20% (all w/v). The higher the level of Deodeok, the greater were the final values of total sugars, reducing sugars, total polyphenols, and crude saponins. The Hunter's b-value (yellowness) of Deodeok wine varied markedly with Deodeok levels, and yellowness was highest in Deodeok wine containing 20% (w/v) Deodeok. Non-volatile compounds, that form the basis of the liquor tax law, were 0.64, 1.38 and 2.11% (all w/v), respectively, at day 160. Of these values, that of 2.11% (w/v), the level of non-volatile compounds in Deodeok wine containing 20% (w/v) Deodeok, was in accord with the liquor tax law (that requires this figure to be 2.0%). Sensory evaluation showed that Deodeok wine containing 20% (w/v) Deodeok was superior to the other wines tested.

Deep Learning-Based Prediction of the Quality of Multiple Concurrent Beams in mmWave Band (밀리미터파 대역 딥러닝 기반 다중빔 전송링크 성능 예측기법)

  • Choi, Jun-Hyeok;Kim, Mun-Suk
    • Journal of Internet Computing and Services
    • /
    • v.23 no.3
    • /
    • pp.13-20
    • /
    • 2022
  • IEEE 802.11ay Wi-Fi is the next generation wireless technology and operates in mmWave band. It supports the MU-MIMO (Multiple User Multiple Input Multiple Output) transmission in which an AP (Access Point) can transmit multiple data streams simultaneously to multiple STAs (Stations). To this end, the AP should perform MU-MIMO beamforming training with the STAs. For efficient MU-MIMO beamforming training, it is important for the AP to estimate signal strength measured at each STA at which multiple beams are used simultaneously. Therefore, in the paper, we propose a deep learning-based link quality estimation scheme. Our proposed scheme estimates the signal strength with high accuracy by utilizing a deep learning model pre-trained for a certain indoor or outdoor propagation scenario. Specifically, to estimate the signal strength of the multiple concurrent beams, our scheme uses the signal strengths of the respective single beams, which can be obtained without additional signaling overhead, as the input of the deep learning model. For performance evaluation, we utilized a Q-D (Quasi-Deterministic) Channel Realization open source software and extensive channel measurement campaigns were conducted with NIST (National Institute of Standards and Technology) to implement the millimeter wave (mmWave) channel. Our simulation results demonstrate that our proposed scheme outperforms comparison schemes in terms of the accuracy of the signal strength estimation.

The Development of Application for Culinary Practice Education using Smart Device (스마트 디바이스 기반 조리실습교육용 앱 개발)

  • Kang, Keoung-Shim
    • Journal of Digital Convergence
    • /
    • v.12 no.1
    • /
    • pp.511-518
    • /
    • 2014
  • The purpose of this study is to produce and distribute a smart device based educational application for culinary practice. This study was performed from Jul. 1 to Dec. 30, 2012. The design of the application is composed of the theoretical contents, making methods, practice video and evaluation questions of Western cuisine among the contents of the culinary practice education. In addition, the notice and Q&A were added for the interaction between teachers and learners. For this study, 31 main dishes' pictures, 155 pictures for making processes by menu, 31 recipes, 31 cooking tips, 372 evaluation questions and 31 cooking videos about 31 menus were produced. The contents produced as above were directly inserted at 'http://kongju-fn.dslink.co.kr/super/index.html' to produce the application. This application can be found through searching with the word of 'yoribaksa'. This study can be considered to be significant in that this application was produced in the situation of the absence of any other previous applications for culinary practice education.

Reinforcement Learning Strategy for Automatic Control of Real-time Obstacle Avoidance based on Vehicle Dynamics (실시간 장애물 회피 자동 조작을 위한 차량 동역학 기반의 강화학습 전략)

  • Kang, Dong-Hoon;Bong, Jae Hwan;Park, Jooyoung;Park, Shinsuk
    • The Journal of Korea Robotics Society
    • /
    • v.12 no.3
    • /
    • pp.297-305
    • /
    • 2017
  • As the development of autonomous vehicles becomes realistic, many automobile manufacturers and components producers aim to develop 'completely autonomous driving'. ADAS (Advanced Driver Assistance Systems) which has been applied in automobile recently, supports the driver in controlling lane maintenance, speed and direction in a single lane based on limited road environment. Although technologies of obstacles avoidance on the obstacle environment have been developed, they concentrates on simple obstacle avoidances, not considering the control of the actual vehicle in the real situation which makes drivers feel unsafe from the sudden change of the wheel and the speed of the vehicle. In order to develop the 'completely autonomous driving' automobile which perceives the surrounding environment by itself and operates, ability of the vehicle should be enhanced in a way human driver does. In this sense, this paper intends to establish a strategy with which autonomous vehicles behave human-friendly based on vehicle dynamics through the reinforcement learning that is based on Q-learning, a type of machine learning. The obstacle avoidance reinforcement learning proceeded in 5 simulations. The reward rule has been set in the experiment so that the car can learn by itself with recurring events, allowing the experiment to have the similar environment to the one when humans drive. Driving Simulator has been used to verify results of the reinforcement learning. The ultimate goal of this study is to enable autonomous vehicles avoid obstacles in a human-friendly way when obstacles appear in their sight, using controlling methods that have previously been learned in various conditions through the reinforcement learning.

A Knowledge-Based Intelligent Information Agent for Animal Domain (동물 영역 지식 기반의 지능형 정보 에이전트)

  • 이용현;오정욱;변영태
    • Korean Journal of Cognitive Science
    • /
    • v.10 no.1
    • /
    • pp.67-78
    • /
    • 1999
  • Information providers on WWW have been rapidly increasing, and they provide a vast amount of information in various fields, Because of this reason, it becomes hard for users to get the information they want. Although there are several search engines that help users with the keyword matching methods, it is not easy to find suitable keywords. In order to solve these problems with a specific domain, we propose an intelligent information agent(HHA-la : HongIk Information Agent) that converts user's q queries to forms including related domain words in order to represent user's intention as much as it can and provides the necessary information of the domain to users. HHA-la h has an ontological knowledge base of animal domain, supplies necessary information for queries from users and other agents, and provides relevant web page information. One of system components is a WebDB which indexes web pages relevant to the animal domain. The system also supplies new operators by which users can represent their thought more clearly, and has a learning mechanism using accumulated results and user feedback to behave more intelligently, We implement the system and show the effectiveness of the information agent by presenting experiment results in this paper.

  • PDF

Development and Application of Classroom Homepage Using Wiki (지식공유기법을 활용한 학급 홈페이지의 개발 및 적용)

  • Kim, Yu-Song;Yoo, In-Hwan
    • Journal of The Korean Association of Information Education
    • /
    • v.10 no.1
    • /
    • pp.13-22
    • /
    • 2006
  • Students should be able to find information and resources using the Internet. Also students need to have composite intellectual abilities to select information, convert to knowledge and communicate it to other people. However, most school and classroom homepages provide students with information but not contents that help them produce knowledge. This lowers the rate of connection to homepage. Thus, the purpose of this study is to develop and apply homepage, which helps students make knowledge from comprehended and interpreted information(Knowledge.Sharing Technique; KST). In this study we use 'WIKI KST' and 'Q&A KST' to share knowledge. WIKI KST is 'an encyclopedia that we make,' which means that students upload their prior knowledge or knowledge produced from comprehended and interpreted information and create new knowledge to be added to their own knowledge and others'. As a result, the abilities to comprehend and interpret acquired information are improved and the ability to change implicit knowledge to explicit knowledge is also improved. Students create new knowledge to share their knowledge and, as a result, the rate to connection to homepage gets higher.

  • PDF

The Relationship between Students' Science Anxiety and Achivement (학생들의 과학교과 불안도와 학습성취도와의 관계)

  • Kim, Beom-Ki
    • Journal of The Korean Association For Science Education
    • /
    • v.13 no.3
    • /
    • pp.341-358
    • /
    • 1993
  • In this study, the researcher analyzed relationship between stuents' science anxiety and achivement, and investigated the tendency of the science anxiety by students' variables. For the survey of this study. 5,304 stuents were sampled from the population of Korean secondary school. The researcher adopted R&D procedure for the development of SAMS(science anxiety measurement scale) and the SAT(science achivement test). The instrument SAMS consisted of 38-item scale. Cronbach a for SAMS was 0.92, concurrent validity was 0.66. SAT consist of 2O-item, the reliable coefficent of KR-20 was 0.70. The data were analyzed by using Pearson-Product coefficient and Regression analysis for the correlation between dependent and independent variable. The tendency of science anxiety were analyzed Multi-way analysis of variance, and all hypotheses were evaluated as the significant level of 0.001. Results of this study were summarized as follows : 1) The relationship between the science anxiety and the achivement showed negative correlation(r=-O.24) in all grades. 2) The relationship between the male and the female showed negative correlation (male;r=-Q.23. female=-O.22), but 11ths' humanities course and female of the science course didn't showed correlation. 3) The size of city where the school located showed negative correlation to the students anxiety(big city;-O27. medium;-O.24, small city;-O.22). 4) Tendency of students' science anxiety according to the variable of grades and sex variables was found to significant difference. The effects of interaction were found to significant difference between two variables of grade and sex. sex and local, local and grade. The effects among three variables were formed to significant difference grade, sex and local.

  • PDF

Apparel Pattern CAD Education Based on Blended Learning for I-Generation (I-세대의 어패럴캐드 교육을 위한 블렌디드 러닝 활용 제안)

  • Choi, Young Lim
    • Fashion & Textile Research Journal
    • /
    • v.18 no.6
    • /
    • pp.766-775
    • /
    • 2016
  • In the era of globalization and unlimited competition, Korean universities need a breakthrough in their education system according to the changing education landscape, such as lower graduation requirements to cultivate more multi-talented convergence leaders. While each student has different learning capabilities, which results in different performance and achievements in the same class, the uniform education that most universities are currently offering fails to accommodate such differences. Blended learning, synergically combining offline and online classes, enlarges learning space and enriches learning experiences through diversified tools and materials, including multimedia. Recently, universities are increasingly adopting video contents and on-offline convergence learning strategy. Thus, this study suggests a teaching method based on blended learning to more effectively teach existing pattern CAD and virtual CAD in the Apparel Pattern CAD class. To this end, this researcher developed a teaching-learning method and curriculum according to the blended learning phase and video-based contents. The curriculum consisted of 2D CAD (SuperAlpha: Plus) and 3D CAD (CLO) software learning for 15 weeks. Then, it was loaded to the Learning Management System (LMS) and operated for 15 weeks both online and offline. The performance analysis of LMS usage found that class materials, among online postings, were viewed the most. The discussion menu most accurately depicted students' participation, and students who did not participate in discussions were estimated to check postings less than participating students. A survey on the blended learning found that students prefer digital or more digitized classes, while preferring face to face for Q&As.