• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.14
• /
• pp.1-40
• /
• 1973

There is a general tendency to increase nitrogen level in rice production to insure an increased yield. On the other hand, percentage of ripened grains is getting decreased with such an increased fertilizer level. Decreasing of the percentage is one of the important yield limiting factors. Especially the newly developed rice variety, 'Tongil' is characterized by a relatively low percentage of ripened grains as compared with the other leading varieties. Therefore, these studies were aimed to finding out of some measures for the improvement of ripening in rice. The studies had been carried out in the field and in the phytotron during the period of three years from 1970 to 1972 at the Crop Experiment Station in Suwon. The results obtained from the experiments could be summarized as follows: 1. The spikelet of Tongil was longer in length, more narrow in width, thinner in thickness, smaller in the volume of grains and lighter in grain weight than those of Jinheung. The specific gravity of grain was closely correlated with grain weight and the relationship with thickness, width and length was getting smaller in Jinheung. On the other hand, Tongil showed a different pattern from Jinheung. The relationship of the specific gravity with grain weight was the greatest and followed by that with the width, thickness and length, in order. 2. The distribution of grain weight selected by specific gravity was different from one variety to another. Most of grains of Jinheung were distributed over the specific gravity of 1.12 with its peak at 1.18, but many of grains of Tongil were distributed below 1.12 with its peak at 1.16. The brown/rough rice ratio was sharply declined below the specific gravity of 1.06 in Jinheung, but that of Tongil was not declined from the 1.20 to the 0.96. Accordingly, it seemed to be unfair to make the specific gravity criterion for ripened grains at 1.06 in the Tongil variety. 3. The increasing tendency of grain weight after flowering was different depending on varieties. Generally speaking, rice varieties originated from cold area showed a slow grain weight increase while Tongil was rapid except at lower temperature in late ripening stage. 4. In the late-tillered culms or weak culms, the number of spikelets was small and the percentage of ripened grains was low. Tongil produced more late-tillered culms and had a longer flowering duration especially at lower temperature, resulting in a lower percentage of ripened grains. 5. The leaf blade of Tongil was short, broad and errect, having light receiving status for photosynthesis was better. The photosynthetic activity of Tongil per unit leaf area was higher than that of Jinheung at higher temperature, but lower at lower temperature. 6. Tongil was highly resistant to lodging because of short culm length, and thick lower-internodes. Before flowering, Tongil had a relatively higher amount of sugars, phosphate, silicate, calcium, manganese and magnesium. 7. The number of spikelets of Tongil was much more than that of Jinheung. The negative correlation was observed between the number of spikelets and percentage of ripened grains in Jinheung, but no correlation was found in Tongil grown at higher temperature. Therefore, grain yield was increased with increased number of spikelets in Tongil. Anthesis was not occurred below 21$^{\circ}C$ in Tongil, so sterile spikelets were increased at lower temperature during flowering stage. 8. The root distribution of Jinheung was deeper than that of Tongil. The root activity of Tongil evaluated by $\alpha$-naphthylamine oxidation method, was higher than that of Jinheung at higher temperature, but lower at lower temperature. It is seemed to be related with discoloration of leaf blades. 9. Tongil had a better light receiving status for photosynthesis and a better productive structure with balance between photosynthesis and respiration, so it is seemed that tongil has more ideal plant type for getting of a higher grain yield as compared with Jinheung. 10. Solar radiation during the 10 days before to 30 days after flowering seemed enough for ripening in suwon, but the air temperature dropped down below 22$^{\circ}C$ beyond August 25. Therefore, it was believed that air temperature is one of ripening limiting factors in this case. 11. The optimum temperature for ripening in Jinheung was relatively lower than that of Tongil requriing more than $25^{\circ}C$. Air temperature below 21$^{\circ}C$ was one of limiting factors for ripening in Tongil. 12. It seemed that Jinheung has relatively high photosensitivity and moderate thermosensitivity, while Tongil has a low photosensitivity, high thermosensitivity and longer basic vegetative phase. 13. Under a condition of higher nitrogen application at late growing stage, the grain yield of Jinheung was increased with improvement of percentage of ripened grains, while grain yield of Tongil decreased due to decreasing the number of spikelets although photosynthetic activity after flowering was. increased. 14. The grain yield of Jinheung was decreased slightly in the late transplanting culture since its photosynthetic activity was relatively high at lower temperature, but that of Tonil was decreased due to its inactive photosynthetic activity at lower temperature. The highest yield of Tongil was obtained in the early transplanting culture. 15. Tongil was adapted to a higher fertilizer and dense transplanting, and the percentage of ripened grains was improved by shortening of the flowering duration with increased number of seedlings per hill. 16. The percentage of vigorous tillers was increased with a denser transplanting and increasing in number of seedlings per hill. 17. The possibility to improve percentage of ripened grains was shown with phosphate application at lower temperature. The above mentioned results are again summarized below. The Japonica type leading varieties should be flowered before August 20 to insure a satisfactory ripening of grains. Nitrogen applied should not be more than 7.5kg/10a as the basal-dressing and the remained nitrogen should be applied at the later growing stage to increase their photosynthetic activity. The morphological and physiological characteristics of Tongil, a semi-dwarf, Indica $\times$ Japonica hybrid variety, are very different from those of other leading rice varieties, requring changes in seed selection by specific gravity method, in milling and in the cultural practices. Considering the peculiar distribution of grains selected by the method and the brown/rough rice ratio, the specific gravity criterion for seed selection should be changed from the currently employed 1.06 to about 0.96 for Tongil. In milling process, it would be advisable to bear in mind the specific traits of Tongil grain appearance. Tongil is a variety with many weak tillers and under lower temperature condition flowering is delayed. Such characteristics result in inactivation of roots and leaf blades which affects substantially lowering of the percentage of ripened grains due to increased unfertilized spikelets. In addition, Tongil is adapted well to higher nitrogen application. Therefore, it would be recommended to transplant Tongil variety earlier in season under the condition of higer nitrogen, phosphate and silicate. A dense planting-space with three vigorous seedlings per hill should be practiced in this case. In order to manifest fully the capability of Tongil, several aspects such as the varietal improvement, culural practices and milling process should be more intensively considered in the future.he future.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.1-22
• /
• 2017

Analysis of future business or investment opportunities, such as business feasibility analysis and company or technology valuation, necessitate objective estimation on the relevant market and expected sales. While there are various ways to classify the estimation methods of these new sales or market size, they can be broadly divided into top-down and bottom-up approaches by benchmark references. Both methods, however, require a lot of resources and time. Therefore, we propose a data-based intelligent demand forecasting system to support evaluation of new business. This study focuses on analogical forecasting, one of the traditional quantitative forecasting methods, to develop sales forecasting intelligence systems for new businesses. Instead of simply estimating sales for a few years, we hereby propose a method of estimating the sales of new businesses by using the initial sales and the sales growth rate of similar companies. To demonstrate the appropriateness of this method, it is examined whether the sales performance of recently established companies in the same industry category in Korea can be utilized as a reference variable for the analogical forecasting. In this study, we examined whether the phenomenon of "mean reversion" was observed in the sales of start-up companies in order to identify errors in estimating sales of new businesses based on industry sales growth rate and whether the differences in business environment resulting from the different timing of business launch affects growth rate. We also conducted analyses of variance (ANOVA) and latent growth model (LGM) to identify differences in sales growth rates by industry category. Based on the results, we proposed industry-specific range and linear forecasting models. This study analyzed the sales of only 150,000 start-up companies in Korea in the last 10 years, and identified that the average growth rate of start-ups in Korea is higher than the industry average in the first few years, but it shortly shows the phenomenon of mean-reversion. In addition, although the start-up founding juncture affects the sales growth rate, it is not high significantly and the sales growth rate can be different according to the industry classification. Utilizing both this phenomenon and the performance of start-up companies in relevant industries, we have proposed two models of new business sales based on the sales growth rate. The method proposed in this study makes it possible to objectively and quickly estimate the sales of new business by industry, and it is expected to provide reference information to judge whether sales estimated by other methods (top-down/bottom-up approach) pass the bounds from ordinary cases in relevant industry. In particular, the results of this study can be practically used as useful reference information for business feasibility analysis or technical valuation for entering new business. When using the existing top-down method, it can be used to set the range of market size or market share. As well, when using the bottom-up method, the estimation period may be set in accordance of the mean reverting period information for the growth rate. The two models proposed in this study will enable rapid and objective sales estimation of new businesses, and are expected to improve the efficiency of business feasibility analysis and technology valuation process by developing intelligent information system. In academic perspectives, it is a very important discovery that the phenomenon of 'mean reversion' is found among start-up companies out of general small-and-medium enterprises (SMEs) as well as stable companies such as listed companies. In particular, there exists the significance of this study in that over the large-scale data the mean reverting phenomenon of the start-up firms' sales growth rate is different from that of the listed companies, and that there is a difference in each industry. If a linear model, which is useful for estimating the sales of a specific company, is highly likely to be utilized in practical aspects, it can be explained that the range model, which can be used for the estimation method of the sales of the unspecified firms, is highly likely to be used in political aspects. It implies that when analyzing the business activities and performance of a specific industry group or enterprise group there is political usability in that the range model enables to provide references and compare them by data based start-up sales forecasting system.

• Journal of Distribution Science
• /
• v.10 no.2
• /
• pp.29-41
• /
• 2012

This paper undertakes a conceptual review of transaction cost to broaden the understanding of the transaction cost analysis (TCA) approach. More than 40 years have passed since Coase's fundamental insight that transaction, coordination, and contracting costs must be considered explicitly in explaining the extent of vertical integration. Coase (1937) forced economists to identify previously neglected constraints on the trading process to foster efficient intrafirm, rather than interfirm, transactions. The transaction cost approach to economic organization study regards transactions as the basic units of analysis and holds that understanding transaction cost economy is central to organizational study. The approach applies to determining efficient boundaries, as between firms and markets, and to internal transaction organization, including employment relations design. TCA, developed principally by Oliver Williamson (1975,1979,1981a) blends institutional economics, organizational theory, and contract law. Further progress in transaction costs research awaits the identification of critical dimensions in which transaction costs differ and an examination of the economizing properties of alternative institutional modes for organizing transactions. The crucial investment distinction is: To what degree are transaction-specific (non-marketable) expenses incurred? Unspecialized items pose few hazards, since buyers can turn toalternative sources, and suppliers can sell output intended for one order to other buyers. Non-marketability problems arise when specific parties' identities have important cost-bearing consequences. Transactions of this kind are labeled idiosyncratic. The summarized results of the review are as follows. First, firms' distribution decisions often prompt examination of the make-or-buy question: Should a marketing activity be performed within the organization by company employees or contracted to an external agent? Second, manufacturers introducing an industrial product to a foreign market face a difficult decision. Should the product be marketed primarily by captive agents (the company sales force and distribution division) or independent intermediaries (outside sales agents and distribution)? Third, the authors develop a theoretical extension to the basic transaction cost model by combining insights from various theories with the TCA approach. Fourth, other such extensions are likely required for the general model to be applied to different channel situations. It is naive to assume the basic model appliesacross markedly different channel contexts without modifications and extensions. Although this study contributes to scholastic research, it is limited by several factors. First, the theoretical perspective of TCA has attracted considerable recent interest in the area of marketing channels. The analysis aims to match the properties of efficient governance structures with the attributes of the transaction. Second, empirical evidence about TCA's basic propositions is sketchy. Apart from Anderson's (1985) study of the vertical integration of the selling function and John's (1984) study of opportunism by franchised dealers, virtually no marketing studies involving the constructs implicated in the analysis have been reported. We hope, therefore, that further research will clarify distinctions between the different aspects of specific assets. Another important line of future research is the integration of efficiency-oriented TCA with organizational approaches that emphasize specific assets' conceptual definition and industry structure. Finally, research of transaction costs, uncertainty, opportunism, and switching costs is critical to future study.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.117-127
• /
• 2012

Due to the recent expansion of the Web 2.0 -based services, along with the widespread of smartphones, online social network services are being popularized among users. Online social network services are the online community services which enable users to communicate each other, share information and expand human relationships. In the social network services, each relation between users is represented by a graph consisting of nodes and links. As the users of online social network services are increasing rapidly, the SNS are actively utilized in enterprise marketing, analysis of social phenomenon and so on. Social Network Analysis (SNA) is the systematic way to analyze social relationships among the members of the social network using the network theory. In general social network theory consists of nodes and arcs, and it is often depicted in a social network diagram. In a social network diagram, nodes represent individual actors within the network and arcs represent relationships between the nodes. With SNA, we can measure relationships among the people such as degree of intimacy, intensity of connection and classification of the groups. Ever since Social Networking Services (SNS) have drawn increasing attention from millions of users, numerous researches have made to analyze their user relationships and messages. There are typical representative SNA methods: degree centrality, betweenness centrality and closeness centrality. In the degree of centrality analysis, the shortest path between nodes is not considered. However, it is used as a crucial factor in betweenness centrality, closeness centrality and other SNA methods. In previous researches in SNA, the computation time was not too expensive since the size of social network was small. Unfortunately, most SNA methods require significant time to process relevant data, and it makes difficult to apply the ever increasing SNS data in social network studies. For instance, if the number of nodes in online social network is n, the maximum number of link in social network is n(n-1)/2. It means that it is too expensive to analyze the social network, for example, if the number of nodes is 10,000 the number of links is 49,995,000. Therefore, we propose a heuristic-based method for finding the shortest path among users in the SNS user graph. Through the shortest path finding method, we will show how efficient our proposed approach may be by conducting betweenness centrality analysis and closeness centrality analysis, both of which are widely used in social network studies. Moreover, we devised an enhanced method with addition of best-first-search method and preprocessing step for the reduction of computation time and rapid search of the shortest paths in a huge size of online social network. Best-first-search method finds the shortest path heuristically, which generalizes human experiences. As large number of links is shared by only a few nodes in online social networks, most nods have relatively few connections. As a result, a node with multiple connections functions as a hub node. When searching for a particular node, looking for users with numerous links instead of searching all users indiscriminately has a better chance of finding the desired node more quickly. In this paper, we employ the degree of user node vn as heuristic evaluation function in a graph G = (N, E), where N is a set of vertices, and E is a set of links between two different nodes. As the heuristic evaluation function is used, the worst case could happen when the target node is situated in the bottom of skewed tree. In order to remove such a target node, the preprocessing step is conducted. Next, we find the shortest path between two nodes in social network efficiently and then analyze the social network. For the verification of the proposed method, we crawled 160,000 people from online and then constructed social network. Then we compared with previous methods, which are best-first-search and breath-first-search, in time for searching and analyzing. The suggested method takes 240 seconds to search nodes where breath-first-search based method takes 1,781 seconds (7.4 times faster). Moreover, for social network analysis, the suggested method is 6.8 times and 1.8 times faster than betweenness centrality analysis and closeness centrality analysis, respectively. The proposed method in this paper shows the possibility to analyze a large size of social network with the better performance in time. As a result, our method would improve the efficiency of social network analysis, making it particularly useful in studying social trends or phenomena.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.177-198
• /
• 2018

Recently, as economic property it has become necessary to acquire and utilize the framework for water resource measurement and performance management as the property of water resources changes to hold "public property". To date, the evaluation of water technology has been carried out by feasibility study analysis or technology assessment based on net present value (NPV) or benefit-to-cost (B/C) effect, however it is not yet systemized in terms of valuation models to objectively assess an economic value of technology-based business to receive diffusion and feedback of research outcomes. Therefore, K-water (known as a government-supported public company in Korea) company feels the necessity to establish a technology valuation framework suitable for technical characteristics of water resources fields in charge and verify an exemplified case applied to the technology. The K-water evaluation technology applied to this study, as a public interest goods, can be used as a tool to measure the value and achievement contributed to society and to manage them. Therefore, by calculating the value in which the subject technology contributed to the entire society as a public resource, we make use of it as a basis information for the advertising medium of performance on the influence effect of the benefits or the necessity of cost input, and then secure the legitimacy for large-scale R&D cost input in terms of the characteristics of public technology. Hence, K-water company, one of the public corporation in Korea which deals with public goods of 'water resources', will be able to establish a commercialization strategy for business operation and prepare for a basis for the performance calculation of input R&D cost. In this study, K-water has developed a web-based technology valuation model for public interest type water resources based on the technology evaluation system that is suitable for the characteristics of a technology in water resources fields. In particular, by utilizing the evaluation methodology of the Institute of Advanced Industrial Science and Technology (AIST) in Japan to match the expense items to the expense accounts based on the related benefit items, we proposed the so-called 'K-water's proprietary model' which involves the 'cost-benefit' approach and the FCF (Free Cash Flow), and ultimately led to build a pipeline on the K-water research performance management system and then verify the practical case of a technology related to "desalination". We analyze the embedded design logic and evaluation process of web-based valuation system that reflects characteristics of water resources technology, reference information and database(D/B)-associated logic for each model to calculate public interest-based and profit-based technology values in technology integrated management system. We review the hybrid evaluation module that reflects the quantitative index of the qualitative evaluation indices reflecting the unique characteristics of water resources and the visualized user-interface (UI) of the actual web-based evaluation, which both are appended for calculating the business value based on financial data to the existing web-based technology valuation systems in other fields. K-water's technology valuation model is evaluated by distinguishing between public-interest type and profitable-type water technology. First, evaluation modules in profit-type technology valuation model are designed based on 'profitability of technology'. For example, the technology inventory K-water holds has a number of profit-oriented technologies such as water treatment membranes. On the other hand, the public interest-type technology valuation is designed to evaluate the public-interest oriented technology such as the dam, which reflects the characteristics of public benefits and costs. In order to examine the appropriateness of the cost-benefit based public utility valuation model (i.e. K-water specific technology valuation model) presented in this study, we applied to practical cases from calculation of benefit-to-cost analysis on water resource technology with 20 years of lifetime. In future we will additionally conduct verifying the K-water public utility-based valuation model by each business model which reflects various business environmental characteristics.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.1
• /
• pp.33-46
• /
• 2010

We investigated and estimated at the characteristics of decomposition and by-products of N-Nitrosodimethylamine (NDMA) using a design of experiment (DOE) based on the Box-Behken design in an UV process, and also the main factors (variables) with UV intensity($X_2$) (range: $1.5{\sim}4.5\;mW/cm^2$), NDMA concentration ($X_2$) (range: 100~300 uM) and pH ($X_2$) (rang: 3~9) which consisted of 3 levels in each factor and 4 responses ($Y_1$ (% of NDMA removal), $Y_2$ (dimethylamine (DMA) reformation (uM)), $Y_3$ (dimethylformamide (DMF) reformation (uM), $Y_4$ ($NO_2$-N reformation (uM)) were set up to estimate the prediction model and the optimization conditions. The results of prediction model and optimization point using the canonical analysis in order to obtain the optimal operation conditions were $Y_1$ [% of NDMA removal] = $117+21X_1-0.3X_2-17.2X_3+{2.43X_1}^2+{0.001X_2}^2+{3.2X_3}^2-0.08X_1X_2-1.6X_1X_3-0.05X_2X_3$ ($R^2$= 96%, Adjusted $R^2$ = 88%) and 99.3% ($X_1:\;4.5\;mW/cm^2$, $X_2:\;190\;uM$, $X_3:\;3.2$), $Y_2$ [DMA conc] = $-101+18.5X_1+0.4X_2+21X_3-{3.3X_1}^2-{0.01X_2}^2-{1.5X_3}^2-0.01X_1X_2+0.07X_1X_3-0.01X_2X_3$ ($R^2$= 99.4%, 수정 $R^2$ = 95.7%) and 35.2 uM ($X_1$: 3 $mW/cm^2$, $X_2$: 220 uM, $X_3$: 6.3), $Y_3$ [DMF conc] = $-6.2+0.2X_1+0.02X_2+2X_3-0.26X_1^2-0.01X_2^2-0.2X_3^2-0.004X_1X_2+0.1X_1X_3-0.02X_2X_3$ ($R^2$= 98%, Adjusted $R^2$ = 94.4%) and 3.7 uM ($X_1:\;4.5\;$mW/cm^2$, $X_2:\;290\;uM$, $X_3:\;6.2$) and $Y_4$ [$NO_2$-N conc] = $-25+12.2X_1+0.15X_2+7.8X_3+{1.1X_1}^2+{0.001X_2}^2-{0.34X_3}^2+0.01X_1X_2+0.08X_1X_3-3.4X_2X_3$ ($R^2$= 98.5%, Adjusted $R^2$ = 95.7%) and 74.5 uM ($X_1:\;4.5\;mW/cm^2$, $X_2:\;220\;uM$, $X_3:\;3.1$). This study has demonstrated that the response surface methodology and the Box-Behnken statistical experiment design can provide statistically reliable results for decomposition and by-products of NDMA by the UV photolysis and also for determination of optimum conditions. Predictions obtained from the response functions were in good agreement with the experimental results indicating the reliability of the methodology used.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.17 no.1
• /
• pp.62-66
• /
• 2013

Purpose: I-131 is a radioisotope widely used for thyroid gland treatments. The physical half life is 8.01 and characterized by emitting beta and gamma rays which is used in clinical practice for the purpose of acquiring treatment and images. In order to reduce the recurrence rate after surgery in high-risk thyroid cancer patients, the remaining thyroid tissue is either removed or the I-131 is used for treatment during relapse. In cases of using a high dosage of radioactive iodine requiring hospitalization, the patient is administered dosage in the hospital isolation ward over a certain period of time preventing I-131 exposure to others. By checking the radiation amount emitted from patients before discharge, the patients are discharged after checking whether they meet the legal standards (50 uSv/h). After patients are discharged from the hospital, the contamination level is checked in many parts of the ward before the next patients are hospitalized and when necessary, decontamination operations are performed. It is expected that there is exposure to radiation when measuring the ward contamination level and dose check emitted from patients at the time of discharge whereby the radiation exposure by health workers that come from the patients in this process is the main factor. This study analyzed the correlation between discharge dose of patients and ward contamination level through a variety of factors such as renal functions, gender, age, dosage, etc.). Materials and Method: The study was conducted on 151 patients who received high-dosage radioactive iodine treatment at Soon Chun Hyang University Hospital during the period between 8/1/2011~5/31/2012 (Male: Female: 31:120, $47.5{\pm}11.9$, average dosage of $138{\pm}22.4$ mCi). As various factors expected to influence the patient discharge dose & ward contamination such as the beds, floors, bathroom floors, and washbasins, the patient renal function (GFR), age, gender, dosage, and the correlation between the expected Tg & Tg-Tb expected to reflect the remaining tissue in patients were analyzed. Results: In terms of the discharge dose and GFR, a low correlation was shown in the patient discharge dose as the GFR was higher (p < 0.0001). When comparing the group with a dosage of over 150mCi and the group with a lower dosage, the lower dosage group showed a significantly lower discharge dose ($24{\pm}10.4uSv/h$ vs $28.7{\pm}11.8uSv/h$, p<0.05). Age, gender, Tg, Tg-Tb did not show a significant relationship with discharge dose (p> 0.05). The contamination level in each spot of the treatment ward showed no significant relationship with GFR, Tg, Tg-Tb, age, gender, and dosage (p>0.05 ). Conclusion: This study says that discharge of the dose in the patient's body is low in GFR higher and Dosage 150mCi under lower. There was no case of contamination of the treatment ward, depending on the dose and renal association. This suggests that patients' lifestyles or be affected by a variety of other factors.