http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Taewon Moon,Ha Young Choi,Dae Ho Jung,Se Hong Chang,Jung Eek Son 한국원예학회 2020 원예과학기술지 Vol.38 No.2
In greenhouses, photosynthesis efficiency is a crucial factor for increasing crop production. Since plants use CO₂ for photosynthesis, predicting CO₂ concentration is helpful for improving photosynthetic efficiency. The objective of this study was to predict greenhouse CO₂ concentration using a long short-term memory (LSTM) algorithm. In a greenhouse where mango trees (Mangifera indica L. cv. Irwin) were grown, temperature, relative humidity, solar radiation, atmospheric pressure, soil temperature, soil humidity, and CO₂ concentration were measured using complex sensor modules. Nine sensors were installed in the greenhouse. The averages of environmental factors from the nine sensors were used as inputs, and the average CO₂ concentration was used as an output. In this experiment, LSTM, one of the recurrent neural networks, predicted changes in CO₂ concentration from the present to 2 h later using historical data. The data were measured every 10 min from February. 1, 2017 to May 31, 2018, and missing data were interpolated with a linear method and multilayer perceptron. In this study, LSTM predicted the 2-h change in CO₂ concentrations at an interval of 10 min with adequate test accuracy (R² = 0.78). Therefore, the trained LSTM can be used to predict the future CO₂ concentration and applied to efficient CO₂ enrichment for photosynthesis enhancement in greenhouses.
Calibration of food and feed crop models for sweet peppers with Bayesian optimization
Moon Taewon,Sim Sieun,손정익 한국원예학회 2023 Horticulture, Environment, and Biotechnology Vol.64 No.4
Crop models are tools used to analyze the interaction of crops and the environment. Since crop models can be applied to diverse research scales and purposes, models and their modifi cations vary. The parameters of a crop model could be biased for unseen data; thus, crop models should be calibrated for the adequate simulation of the given data. In this study, we aimed to calibrate food and feed crop models for sweet peppers ( Capsicum annuum var. annuum ) using Bayesian optimization. The algorithm does not require domain knowledge because it only considers input and output distributions based on Bayesian probability. For the implementation of Bayesian optimization, HyperOpt, an algorithm for optimizing high-dimensional hyperparameters, was used. The target growth factors were fruit yield and leaf area index, and the loss function was mean squared error (MSE). As a result, the calibrated crop model showed the highest modeling effi ciency (EF) of 0.53, compared to − 1.91 and 0.62 from NLopt, a nonlinear optimization methodology, and random walk, respectively. The methodology showed adequate performance with reasonable ranges of convergence. The optimization method can be used for unknown distribution spaces of parameters because it does not require an initial status. Among the selected food crops, the groundnut model was suitable for sweet pepper. Since the optimized crop models yielded reasonable simulations, Bayesian optimization could be introduced for horticultural purposes. However, more data could be required to ensure convergence of the parameters and construct a robust crop model.
Taewon Moon,Dongpil Kim,Sungmin Kwon,Jung Eek Son 한국원예학회 2021 한국원예학회 학술발표요지 Vol.2021 No.10
Destructive analysis is one of the most accurate methods to monitor crop growth. However, the investigation process is time-consuming, and the growth of a specific crop cannot be continuously tracked because the target crop is destroyed. Existing non-destructive crop growth collection devices and algorithms required many formulas, sensors, and advanced simulations such as high-performance simulations. Complex requirements can make the device and algorithm less practical. The objective of this study was to propose a monitoring system for crop growth data collected using a hanging scale and a camera with deep neural networks. Sweet peppers (Capsicum annuum var. annuum) grown in a greenhouse (Suwon, Korea) were used for the experiment. Among the compared deep learning models, transformer showed adequate accuracy (R² = 0.80, RMSE = 0.12 kg) for crop fresh weight. Convolutional neural network for crop growth factors showed somewhat lower accuracy (avg. R² = 0.67). Deep learning models with transfer learning could be helpful to monitor crops with diverse cultivation conditions.
문태원 수원대학교 2006 論文集 Vol.24 No.-
This paper deals with the practical ways of conducting culture management in modern organizations, which involves management by vision and philosophy, emotional leadership interlinked with organizational culture, management of design and brand, and culture marketing. In order to successfully practice culture management, corporate identity(CI) should be clearly defined in the first place, which reflects vision and philosophy of an organization. The CEO's leadership style is an essential part of corporate culture that determines 'the color and the tone' of an organization. From culture management, today's organizations facilitate culture marketing by satisfying the customers' emotional and savvy needs. In short, this paper attempts to link culture and each business function.
R - tree에서 Seeded 클러스터링을 이용한 다량 삽입
이태원(Taewon Lee),문봉기(Bongki Moon),이석호(Sukho Lee) 한국정보과학회 2004 정보과학회논문지 : 데이타베이스 Vol.31 No.1
지구 관측 시스템(EOSDIS)나 많은 수의 클라이언트를 추적하는 이동전화 서비스 등 많은 응용에서는 지속적으로 생겨나는 대량의 복잡한 데이타들을 보관하고 인덱싱하는 것이 매우 어려운 일이다. 다차원 데이타를 효과적으로 관리하기 위해 R-tree에 기반한 인덱스 구조가 널리 사용되어 왔다. 본 논문에서는 빠른 데이타 생성 속도를 따라잡으면서 대량 삽입을 통해 R-tree를 관리할 수 있는 seeded clustering이라는 확장성있는 기법을 제안한다. 이 기법에서는 삽입할 대상 R-tree의 상위 k레벨의 구조를 활용하여 시드 트리를 만들어 삽입 데이타를 분류해 클러스터를 생성한다. 그리고 각 클러스터로부터 삽입 R-tree를 생성하고 이를 대상 R-tree에 한 번에 하나씩 삽입한다. 논문에서는 자세한 알고리즘과 함께 다양한 실험 결과를 보여준다. 실험 결과를 통해 seeded clustering을 이용한 대량 삽입이 기존의 대량 삽입 기법들과 비교해 삽입이나 질의 처리 모두에서 우수함을 알 수 있다. In many scientific and commercial applications such as Earth Observation System (EOSDIS) and mobile phone services tracking a large number of clients, it is a daunting task to archive and index ever increasing volume of complex data that are continuously added to databases. To efficiently manage multidimensional data in scientific and data warehousing environments, R-tree based index structures have been widely used. In this paper, we propose a scalable technique called seeded clustering that allows us to maintain R-tree indexes by bulk insertion while keeping pace with high data arrival rates. Our approach uses a seed tree, which is copied from the top k levels of a target R-tree, to classify input data objects into clusters. We then build an R-tree for each of the clusters and insert the input R-trees into the target R-tree in bulk one at a time. We present detailed algorithms for the seeded clustering and bulk insertion as well as the results from our extensive experimental study. The experimental results show that the bulk insertion by seeded clustering outperforms the previously known methods in terms of insertion cost and the quality of target R-trees measured by their query performance.