• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.88-88
• /
• 2022

Detection of stress responses in crops is important to diagnose crop growth and evaluate yield. Also, the multi-spectral sensor is effectively known to evaluate stress caused by nutrient and moisture in crops or biological agents such as weeds or diseases. Therefore, in this experiment, multispectral images were taken by an unmanned aerial vehicle(UAV) under field condition. The experiment was conducted in the long-term fertilizer field in the National Institute of Crop Science, and experiment area was divided into different status of NPK(Control, N-deficiency, P-deficiency, K-deficiency, Non-fertilizer). Total 11 vegetation indices were created with RGB and NIR reflectance values using python. Variations in nutrient content in plants affect the amount of light reflected or absorbed for each wavelength band. Therefore, the objective of this experiment was to evaluate vegetation indices derived from multispectral reflectance data as input into machine learning algorithm for the classification of nutritional deficiency in rice. RandomForest model was used as a representative ensemble model, and parameters were adjusted through hyperparameter tuning such as RandomSearchCV. As a result, training accuracy was 0.95 and test accuracy was 0.80, and IPCA, NDRE, and EVI were included in the top three indices for feature importance. Also, precision, recall, and f1-score, which are indicators for evaluating the performance of the classification model, showed a distribution of 0.7-0.9 for each class.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.4
• /
• pp.326-333
• /
• 2015

A turbo fan engine performance analysis program combined with a particle swarm optimization(PSO) has been developed to optimize the major design parameters of the combat aircraft gas turbine engine. The optimized parameters includes bypass ratio, fan pressure ratio, high pressure compression ratio and burner exit temperature. The objective parameters have been determined using a multi-objective function consisting of the net thrust and specific fuel consumption along a weight function. The basic model for the combat aircraft gas turbine engine has been selected as the F404 turbofan engine which is widely used in the combat aircraft, F-18 and Korean high level training aircraft, T-50. The optimal conditions of four parameters have been obtained for various design conditions.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.12
• /
• pp.3265-3276
• /
• 1996

The studies of document recongnition have been focused mainly on Korean documents. But most of documents composed of Korean and other characters. So, in this paper, we propose the document recognition system that can recognize the multi-size, multi font and mixed type characters. We have utilized a large scale network model, "CombNET" which consists of a 4 layered network with combstructure. And we propose recognition method that can recognize characters without discrimination of character type. The first layer constitutes a Kohonen's SOFM network which quantizes an input feature vector space into several sub-spaces and the following 2-4 layers constitutes BP network modules which classify input data in each sub-space into specified catagories. An experimental result demonstrated the usefulness of this approach with the recognition rates of 95.6% for the training data. For the mixed type character documents we obtained the recognition rates of 92.6% and recognition speed of 10.3 characters per second.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.427-436
• /
• 2022

Korea Trade-Investment Promotion Agency (KOTRA) annually publishes the trade data in South Korea under the guidance of the Ministry of Trade, Industry and Energy in South Korea. The trade data usually contains Gross domestic product (GDP), a custom tariff, business score, and the price of export items in previous and this year, with regards to the trading items and the countries. However, it is challenging to figure out the meaningful insight so as to predict the future price on trading items every year due to the significantly large amount of data accumulated over the several years under the limited human/computing resources. Within this context, this paper proposes a multi layer perception that can predict the future price of potential trading items in the next year by training large amounts of past year's data with a low computational and human cost.

• English Language & Literature Teaching
• /
• v.12 no.1
• /
• pp.221-238
• /
• 2006

This study investigates the reliability of plagiarism measurement in the ESL essay writing context. The current study aims to address the answers to the following research questions: 1) How does plagiarism measurement affect test reliability in a psychometric view? and 2) how do raters conceive the plagiarism in their analytic scoring? This study uses the mixed-methodology that crosses quantitative-qualitative techniques. Thirty eight international students took an ESL placement writing test offered by the University of Illinois. Two native expert raters rated students' essays in terms of 5 analytic features (organization, content, language use, source use, plagiarism) and made a holistic score using a scoring benchmark. For research question 1, the current study, using G-theory and Multi-facet Rasch model, found that plagiarism measurement threatened test reliability. For research question 2, two native raters and one non-native rater in their email correspondences responded that plagiarism was not a valid analytic area to be measured in a large-scale writing test. They viewed the plagiarism as a difficult measurement are. In conclusion, this study proposes that a systematic training program for avoiding plagiarism should be given to students. In addition, this study suggested that plagiarism is measured reliably in the small-scale classroom test.

• Journal of Engineering Education Research
• /
• v.3 no.1
• /
• pp.84-91
• /
• 2000

Modern times are called 'the system and fusion era'. One system has been compounded with the other system repeatedly, and the new systems form a great mixed system again and again. Discrete electronic devices have been integrated as one semiconductor system and have been unified as a great mixed system frequently. This study proposes a module based 2-year college electronic engineering curriculum focused on system and integrated circuit design. This curriculum is devised to be suitable for the industrial environment, especially in the school-industry cooperation, and is recomposed to promote the organic union of interdisciplinary courses. The newly designed course has been developed as a multi semester module model which enables a practical field training and in-depth study.

• Journal of Mechanical Science and Technology
• /
• v.18 no.6
• /
• pp.904-914
• /
• 2004

The fiber reinforced composite material is widely used in the multi-industrial field because of their high specific modulus and specific strength. It has two main merits which are to cut down energy by reducing weight and to prevent explosive damage proceeding to the sudden bursting which is generated by the pressure leakage condition. Therefore, Pressure vessels using this composite material can be applied in the field such as defence industry and aerospace industry. In this paper, for nonlinear finite element analysis of E-glass/epoxy filament winding of composite vessel subjected to internal pressure, the standard interpretation model is developed by using the ANSYS with AutoLISP and ANSYS APDL languages, general commercial software, which is verified as useful characteristic of the solution. Among the modules of the system, both the process planning module for carrying out the process planning of filament wound composite pressure vessel and the autofrettage process module for obtaining higher residual stress will minimize trial and error and reduce the period for developing new products. The system can serve as a valuable system for experts and as a dependable training aid for beginners.