• Title/Summary/Keyword: Bottom-up Model

Search Result 264, Processing Time 0.022 seconds

A Study on Market Size Estimation Method by Product Group Using Word2Vec Algorithm (Word2Vec을 활용한 제품군별 시장규모 추정 방법에 관한 연구)

  • Jung, Ye Lim;Kim, Ji Hui;Yoo, Hyoung Sun
    • 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.

Study on the Small Grain Bin for the Improvement of Grain Drying and Storage (곡물건조저장법 개선을 위한 농가용 Grain Bin에 관한 연구)

  • 김성래
    • Magazine of the Korean Society of Agricultural Engineers
    • /
    • v.16 no.1
    • /
    • pp.3263-3291
    • /
    • 1974
  • Experimental work of grain bin was carried out to develop the methods of natural air in-bin drying and storage. The method is considered to be more economical, labour saving, and an effective countermeasure to grain loss. To examine the possibility of farm use of the grain bin and to analyze the related factors concerned with in-bin grain drying and storage, ambient air conditions (especially the change of air temperature and relative humidity) and grain quality during drying and storage periods were investigated. A laboratory model bin was constructed to investigate the effect of different forced air conditions on the drying characteristics of rice. In addition, a grain bin with 2.2m diameter and 1.8m height, considered to be the optimum size for the average Korean farm, was constructed and tested to examine the drying and storing characteristics of rice. The weather data analyzed in this study was the nine-year (from 1964 to 1972) record of air temperature and relative humidity in the Suweon area, and the thirty-year (from 1931 to 1960) record of pentad normal relative humidity and air temperature in the Seoul area. From the results of the weather data analyses, the adequate air delivery hours (which was arbitrary defined as the condition to give less than 75% relative humidity) to dry the rice during October were about nine hours (from approximately 10 A.M. to 7 P.M, ) a day, in which the average air temperature was about 15.9$^{\circ}C$ and average relative humidity was 66%. The occurence of days having three hours of such conditions was 1, 2, and 1-day within the 1st, 2nd add last 10-day periods for the month of October, respectively. Therefore, it may be considered that the weather condition in October was satisfactory for the forced natural air drying. The results of the laboratory model bin test were analyzed to obtain the drying curve and drying rate for different drying stages and grain layers in the bin corresponding to various conditions of forced natural air. A drying experiment with a prototype grain bin showed that an approximate 5 percent grain moisture gradient through a 1.6 meter grain deposit was observed after 80 hours of intermittent drying, giving an over dried zone in the lower grain layers and an extremely high grain moisture zone in the upper layers. This indicates that an effective measure should be taken to reduce this high moisture gradient. In order to investigate the drying characteristics of bulk grain in a layerturning operation a grain bin test was performed. This showed a significant improvement of uniform drying. In this test, approximate 107 hours were required to dry a depth of 1.6 meter of grain from an initial moisture content of 22.2 percent to a moisture content of 16.7 percent using an air delivery rate of 2.8 cubic meter per a minute per every cubic meter of grain. This resulted in a 2 percent moisture gradient from the top to the bottom of the bin. During storage period, till the end of June the average temperature of grain was 2~3$^{\circ}C$ higher than ambient air temperature. But during July when the grain moisture content went up slightly (less than 1 percent), the average temperature of the grain also increased to 3~5$^{\circ}C$ higher than ambient air temperature. It is therefore recommended that for safe grain storage, grain should not be stored in sheet metal bins after mid May. From the above results, in-bin rice drying and storage can be used effectively on Korean farms. It is strongly recommended that the use of grain-bin system should be implemented for farm use to improve farm drying and storage of rice.

  • PDF

Numerical Hydrodynamic Modeling Incorporating the Flow through Permeable Sea-Wall (투수성 호안의 해수유통을 고려한 유동 수치모델링)

  • Bang, Ki-Young;Park, Sung Jin;Kim, Sun Ou;Cho, Chang Woo;Kim, Tae In;Song, Yong Sik;Woo, Seung-Buhm
    • Journal of Korean Society of Coastal and Ocean Engineers
    • /
    • v.25 no.2
    • /
    • pp.63-75
    • /
    • 2013
  • The Inner Port Phase 2 area of the Pyeongtaek-Dangjin Port is enclosed by a total of three permeable sea-walls, and the disposal site to the east of the Inner Port Phase 2 is also enclosed by two permeable sea-walls. The maximum tidal range measured in the Inner Port Phase 2 and in the disposal site in May 2010 is 4.70 and 2.32 m, respectively. It reaches up to 54 and 27%, respectively of 8.74 m measured simultaneously in the exterior. Regression formulas between the difference of hydraulic head and the rate of interior water volume change, are induced. A three-dimensional numerical hydrodynamic model for the Asan Bay is constructed incorporating a module to compute water discharge through the permeable sea-walls at each computation time step by employing the formulas. Hydrodynamics for the period from 13th to 27th May, 2010 is simulated by driving forces of real-time reconstructed tide with major five constituents($M_2$, $S_2$, $K_1$, $O_1$ and $N_2$) and freshwater discharges from Asan, Sapkyo, Namyang and Seokmoon Sea dikes. The skill scores of modeled mean high waters, mean sea levels and mean low waters are excellent to be 96 to 100% in the interior of permeable sea-walls. Compared with the results of simulation to obstruct the flow through the permeable sea-walls, the maximum current speed increases by 0.05 to 0.10 m/s along the main channel and by 0.1 to 0.2 m/s locally in the exterior of the Outer Sea-wall of Inner Port. The maximum bottom shear stress is also intensified by 0.1 to 0.4 $N/m^2$ in the main channel and by more than 0.4 $N/m^2$ locally around the arched Outer Sea-wall. The module developed to compute the flow through impermeable seawalls can be practically applied to simulate and predict the advection and dispersion of materials, the erosion or deposion of sediments, and the local scouring around coastal structures where large-scale permeable sea-walls are maintained.

Treatment Level of a Pond System for Ecological Treatment and Recycling of Animal Excreta (생태적 축산폐수 처리 및 재활용 연못시스템의 폐수처리수준)

  • Yang, Hong-Mo;Rhee, Chong-Ouk
    • Korean Journal of Environmental Agriculture
    • /
    • v.17 no.1
    • /
    • pp.70-75
    • /
    • 1998
  • A model of pond system is developed for treatment and recycling of excreta from twenty-five adult dairy cattle. It is composed of wastewater treatment ponds and small fish ponds. Those are three facultative ponds in series; primary-secondary-tertiary pond and these are designed to rear carps without feeding. A pit is constructed at the bottom of primary pond for efficient sludge sedimentation and effective methane fermentation. It is contrived to block into it the penetration of oxygen dissolved in the upper layer of pond water. The excreta from the cattle housed in stalls are diluted by water used for clearing them. The washed excreta flow into the pit. The average yearly $BOD_5$ concentration of influent is 398.7mg/l. That of the effluent from primary, secondary and tertiary pond of the system is 49.18, 27.9, and 19.8.mg/l respectively. Approximate 88, 93, and 95 % of BOD5 are removed in each pond. The mean yearly SS concentration of influent is 360.5 mg/l That of the effluent from each pond is 53.4, 45.7, and32.7mg/l respectively. Approximate 86, 88, and 91% of SS are removed in each pond. The $BOD_5$ concentration of secondary and tertiary pond can satisfy 30mg/l secondary treatment standard. The SS concentration of effluent from tertiary pond, however, is slightly greater than the standard, which results from activities of carps growing in the pond. The average yearly total nitrogen concentration of influent is 206.8mg/l and that of the effluent from each pond is 48.6, 30.8, and 21.0mg/l respectively. Approximate 74, 88, and 90% of total nitrogen are removed in each pond. The mean yearly total phosphorous concentration of influent is 20.7mg/l and that of the effluent from each pond is 5.3, 3.2, and 2.1mg/l respectively. Approximate 97, 98, and 99% of total phosphorous are removed in each pond. The high removal of nitrogen and phosphorous results from active growth of algae in the upper layer of pond water. Important pond design parameters for southern part of Korea -- areal loading of BOD5, liquid depth, hydraulic detention time, free board, and pond arrangement -- are taken up.

  • PDF