• Journal of Bio-Environment Control
• /
• v.21 no.3
• /
• pp.163-169
• /
• 2012

We have conducted three experiments to develop a fertilizer-dissolving apparatus used in fertigation or hydroponics cultivation in order to decrease the fertilizer dissolving time and labor input via automation. All of the experiments were conducted twice. In the first experiment, four selected treatments were tested to dissolve fertilizers rapidly. The first treatment was to dissolve fertilizer by spraying water with a submerged water pump, placed in the nutrient solution tank. The water was sprayed onto fertilizer, which is dissolved and filtered through the hemp cloth mounted on the upper part of the nutrient solution tank (Spray). The second treatment was to install a propeller on the bottom of the nutrient solution tank (Propeller). The third treatment was to produce a water stream with a submerged water pump, located at the bottom of the tank (Submerged). Finally, the fourth treatment was to produce an air stream through air pipes with an air compressor located at the bottom of the tank (Airflow). The Spray treatment was found to take the shortest time to dissolve fertilizer, yet it was inconvenient to implement and manage after installation. The Airflow treatment was thought to be the best method in terms of the time to dissolve, labor input, and automation. In the second experiment, Airflow treatment was investigated in more detail. In order to determine the optimal number of air pipe arms and their specification, different versions of 6- and 8-arm air pipe systems were evaluated. The apparatus with 6 arms (Arm-6) that was made of light density polyethylene was determined to be the best system, evaluated on its time to dissolve fertilizer, easiness to use regardless of the lid size of the tank, and easiness to produce and install. In the third experiment, the Submerged and Arm-6 treatments were compared for their dissolving time and economics. Arm-6 treatment decreased the dissolving time by 8 times and proved to be very economic. In addition, dissolving characteristics were investigated for $KNO_3$, $Ca(NO_3)_2{\cdot}4H_2O$, and Fe-EDTA.

• Horticultural Science & Technology
• /
• v.29 no.1
• /
• pp.29-35
• /
• 2011

Individual ion concentrations and ionic contributions to EC reading in the circulated nutrient solution are the important factors to be considered for stable EC-based closed-loop soilless culture. This study was conducted to determine appropriate ion-analysis intervals of the circulated nutrient solutions based on ion concentration, ion balance, and ion electrical conductivity under different renewal intervals in EC-based nutrient control systems for sweet peppers (Capsicum annum L. 'Fiesta') in early growth stage. Average node numbers of the plants were 13 and 18 when the experiment started and finished, respectively, and three plants were grown in each rockwool slab. Four different renewal intervals of circulated nutrient solutions such as 1, 2, 3, and 4 weeks were used as treatment. Nutrient solutions were supplied to the plants based on integrated radiation. Drainage was collected into drain tanks after irrigation ended in the day and then mixed with fresh water until the EC reaches 2.69 $dS{\cdot}m^{-1}$. The replenished nutrient solution was supplied to the plants in the next day. Ion concentrations of the individual ions periodically analyzed in the circulated nutrient solutions showed no significant differences among the treatments during the experimental period. Ion concentrations of $K^+$, $Ca^{2+}$, $Mg^{2+}$, $Na^+$, $NO_3{^-}$, ${SO_4}^{2-}$, ${PO_4}^{3-}$, and $Cl^-$ varied within 5-8, 11-14, 2.0-2.7, 0.5-0.6, 14-19, 4-5, 1-4, and 0.3-0.5 $meq{\cdot}L^{-1}$, respectively. Ion balance showed a consistent tendency over all the treatments and especially $K^+$ : $Ca^{2+}$ and ${SO_4}^{2-}$ : ${PO_4}^{3-}$ played great roles in the cation and anion balances in the nutrient solutions, respectively. Activity coefficients of ions such as $K^+$, $NO_3{^-}$, and $H_2PO_4{^-}$ varied within 0.8-0.9 and those of $Ca^{2+}$, $Mg^{2+}$, ${SO_4}^{2-}$ varied within 0.5-0.6, showing little changes with time. Ionic contributions of $K^+$ and $NO_3{^-}$ to EC reading were the greatest followed by $Ca^{2+}$, ${SO_4}^{2-}$, and $Mg^{2+}$ in the order. From the results, we thought that allowable ranges in ion concentration, ion balance, and subsequent individual ionic contributions to EC reading would be obtained within 4-week renewal interval of nutrient solution in EC-based closed-loop soilless culture for sweet pepper plants.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.41 no.1
• /
• pp.44-50
• /
• 2013

The persons in charge of management request diagnosis and prescription to tree hospitals in order to get consultation about the problems like blight that occur in landscape tree management. This study aims to analyze what the main problems and questions raised by landscape gardeners are and those concerned in landscape tree management. This is done by investigating landscape tree-related questions and answers uploaded on the online consultation boards of the plant diagnostic centers approved in Korea including the Seoul National University Plant Clinic, the Chungbuk National University Plant Hospital, and the Kangwon Diagnostic Center. As a result, those concerned in landscape occupied the most as 81.4% among the questioners. However, only 11.5% did explain the plant management history or surrounding environment, which is essential for landscape tree diagnosis when asking questions. This shows that those concerned in landscape lack basic knowledge or interest about plant diagnosis. Among 263 questions about landscape trees, questions about physiological damage included 94 cases that were the most taking up 35.8%. Moreover, the next were damage by insects and damage by disease in order. It is thought that due to the characteristics of physiological problems that occur by various sorts of stress and with no signs, they tend to request diagnosis or prescription the most. The most frequent reasons for physiological damage are water stress and temperature stress. About damage by disease, there exist many types of diseases, and there are many complex damages accompanied by physiological causes. About damage by insects, the most common include damage by moths. In consideration of this result, universities or technician training centers should provide education for landscape tree management so that landscape technicians and students can acquire essential knowledge and information about landscape tree management and increase their interest in it. In particular, it is necessary to provide profound learning opportunities for plant physiology, and the technicians should make efforts themselves. In addition, it is needed to build organizations to which they can ask technical questions about landscape planting and management in order to understand landscape industry in general and the actual status of landscape planting technique and the actual field. Moreover, to elevate systemicity and expertise in the area of landscape tree management not yet equipped with the foundation, it is needed to cultivate the technicians intensively and conduct research by those concerned both in academic and industrial circles.

• Journal of Agricultural Extension & Community Development
• /
• v.21 no.1
• /
• pp.35-82
• /
• 2014

It was main objectives to find the learners characteristics and educational effects of cyber agricultural technology courses in RDA. For the research, it was followed by literature reviews and internet based survey methods. In internet based survey, two staged stratified sampling method was adopted from cyber training members database in RDA along with some key word as open course or certificate course, and enrollment years. Instrument was composed through literature reviews about cyber education effects and educational effect factors. And learner characteristics items were added in survey documents. It was sent to sampled persons by e-mail and 316 data was returned via google survey systems. Through the data cleaning, 303 data were analysed by chi-square, t-test and F-test. It's significance level was .05. The results of the research were as followed; First, the respondent was composed of mainly man(77.9%), and monthly income group was mainly 2,000,000 or 3,000,000 won(24%), bachelor degree(48%), fifty or forty age group was shared to 75%, and their job was changed after learning(12.2%). So major respondents' job was not changed. Their major was not mainly agriculture. Learners' learning style were composed of two or more types as concrete-sequential, mixing, abstract-random, so e-learning course should be developed for the students' type. Second, it was attended at 3.2 days a week, 53.53 minutes a class, totally 172.63 minutes a week. They were very eager or generally eager to study, and attended two or more subjects. The cyber education motives was for farming knowledge, personal competency development, job performance enlarging. They selected subjects along with their interest. A subject person couldn't choose more subjects for little time, others, non interesting subject, but more subject persons were for job performance benefits and previous subjects effectiveness. Most learner was finished their subject, but a fourth was not finished for busy (26.7%). And their entrying behavior was not enough to learn e-course and computer or internet using ability was middle level as software using. And they thought RDA cyber course was comfort in non time or space limit, knowledge acquisition, and personal competency development. Cyber learning group was composed of open course only (12.5%), certificate only(25.7%), both(36.3%). Third, satisfaction and academic achievement of e-learning learners were good, and educational service offering for doing job in learning application category was good, but effect of cyber education was not good, especially, agricultural income increasing was not good because major learner group was not farmer, so they couldn't apply their knowledge to farming. And content structure and design, content comprehension, content amount were good. The more learning subject group responded to good in effects, and both open course and certificate course group satisfied more than open course only group. Based on the results, recommendation was offered as cyber course specialization before main course in RDA training system, support staff and faculty enlargement, building blended learning system with local RDA office, introducing cyber tutor system.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.143-156
• /
• 2012

People easily believe that news and stock index are closely related. They think that securing news before anyone else can help them forecast the stock prices and enjoy great profit, or perhaps capture the investment opportunity. However, it is no easy feat to determine to what extent the two are related, come up with the investment decision based on news, or find out such investment information is valid. If the significance of news and its impact on the stock market are analyzed, it will be possible to extract the information that can assist the investment decisions. The reality however is that the world is inundated with a massive wave of news in real time. And news is not patterned text. This study suggests the stock-index invest model based on "News Big Data" opinion mining that systematically collects, categorizes and analyzes the news and creates investment information. To verify the validity of the model, the relationship between the result of news opinion mining and stock-index was empirically analyzed by using statistics. Steps in the mining that converts news into information for investment decision making, are as follows. First, it is indexing information of news after getting a supply of news from news provider that collects news on real-time basis. Not only contents of news but also various information such as media, time, and news type and so on are collected and classified, and then are reworked as variable from which investment decision making can be inferred. Next step is to derive word that can judge polarity by separating text of news contents into morpheme, and to tag positive/negative polarity of each word by comparing this with sentimental dictionary. Third, positive/negative polarity of news is judged by using indexed classification information and scoring rule, and then final investment decision making information is derived according to daily scoring criteria. For this study, KOSPI index and its fluctuation range has been collected for 63 days that stock market was open during 3 months from July 2011 to September in Korea Exchange, and news data was collected by parsing 766 articles of economic news media M company on web page among article carried on stock information>news>main news of portal site Naver.com. In change of the price index of stocks during 3 months, it rose on 33 days and fell on 30 days, and news contents included 197 news articles before opening of stock market, 385 news articles during the session, 184 news articles after closing of market. Results of mining of collected news contents and of comparison with stock price showed that positive/negative opinion of news contents had significant relation with stock price, and change of the price index of stocks could be better explained in case of applying news opinion by deriving in positive/negative ratio instead of judging between simplified positive and negative opinion. And in order to check whether news had an effect on fluctuation of stock price, or at least went ahead of fluctuation of stock price, in the results that change of stock price was compared only with news happening before opening of stock market, it was verified to be statistically significant as well. In addition, because news contained various type and information such as social, economic, and overseas news, and corporate earnings, the present condition of type of industry, market outlook, the present condition of market and so on, it was expected that influence on stock market or significance of the relation would be different according to the type of news, and therefore each type of news was compared with fluctuation of stock price, and the results showed that market condition, outlook, and overseas news was the most useful to explain fluctuation of news. On the contrary, news about individual company was not statistically significant, but opinion mining value showed tendency opposite to stock price, and the reason can be thought to be the appearance of promotional and planned news for preventing stock price from falling. Finally, multiple regression analysis and logistic regression analysis was carried out in order to derive function of investment decision making on the basis of relation between positive/negative opinion of news and stock price, and the results showed that regression equation using variable of market conditions, outlook, and overseas news before opening of stock market was statistically significant, and classification accuracy of logistic regression accuracy results was shown to be 70.0% in rise of stock price, 78.8% in fall of stock price, and 74.6% on average. This study first analyzed relation between news and stock price through analyzing and quantifying sensitivity of atypical news contents by using opinion mining among big data analysis techniques, and furthermore, proposed and verified smart investment decision making model that could systematically carry out opinion mining and derive and support investment information. This shows that news can be used as variable to predict the price index of stocks for investment, and it is expected the model can be used as real investment support system if it is implemented as system and verified in the future.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.