• Journal of Food Hygiene and Safety
• /
• v.29 no.2
• /
• pp.79-84
• /
• 2014

This study has been performed for about 270 days at analyzing biologically hazardous factors in order to develop HACCP system for the non heat-frozen carrot juice. A process chart was prepared by manufacturing process of raw agricultural products of non heat-frozen carrot juice, which was contained water and packing material, storage, washing, cutting, extraction of the juice, internal packing, metal detection, external packing, storage and consignment (delivery). As a result of measuring Coliform group, Staphylococcus aureus, Salmonella spp., Bacillus cereus, Listeria Monocytogenes, Enterohemorrhagic E. coli before and after washing raw carrot, Standard plate count was $4.7{\times}10^4CFU/g$ before washing but it was $1.2{\times}10^2CFU/g$ detected after washing. As a result of testing airborne bacteria (Standard plate count, Coliform group, Yeast and Fungal) depending on each workplace, number of microorganism of in packaging room, shower room and juice extraction room was detected to be 10 CFU/Plate, 60 CFU/Plate, 20 CFU/Plate, respectively. As a result of testing palm condition of workers, as number of Standard plate count, Coliform group and Staphylococcus aureus was represented to be high as $6{\times}10^4CFU/cm^2$, $0CFU/cm^2$ and $0CFU/cm^2$, respectively, an education and training for individual sanitation control was considered to be required. As a result of inspecting surface pollution level of manufacturing facility and devices, Coliform group was not detected in all the specimen but Standard plate count was most dominantly detected in scouring kier, scouring kier tray, cooling tank, grinding extractor, storage tank and packaging machine-nozzle as $8.00{\times}10CFU/cm^2$, $3.0{\times}10CFU/cm^2$, $4.3{\times}10^2CFU/cm^2$, $7.5{\times}10^2CFU/cm^2$, $6.0{\times}10CFU/cm^2$, $8.5{\times}10^2CFU/cm^2$ respectively. As a result of analyzing above hazardous factors, processing process of ultraviolet ray sterilizing where pathogenic bacteria may be prevented, reduced or removed is required to be controlled by CCP-B (Biological) and critical level (critical control point) was set at flow speed is 4L/min. Therefore, it is considered that thorough HACCP control plan including control criteria (point) of seasoning fluid processing process, countermeasures in case of its deviation, its verification method, education/training and record control would be required.

• Korean Journal of Weed Science
• /
• v.1 no.1
• /
• pp.30-43
• /
• 1981

On unwedded paddy fields, six cropping patterns of rice cultivation, namely direct broadcast seeding, direct row seeding, machine transplanting, early season hand transplanting, standard season hand transplanting, and late season hand transplanting, were detected with two representative rice cultivars (Milyang 23 and Sadominori) to estimate the comparative fluctuation patterns of weed flora. As a result, number of emerged weed species, most crowding stages, differences of weed growth among cropping patterns, possible tendencies of competition in plant heights among plant groups, variations in Importance Values, and Simpson's Index analysis were discussed, respectively.

• Korean Journal of Weed Science
• /
• v.15 no.4
• /
• pp.254-261
• /
• 1995

The nationwide weed survey was conducted in lowland rice fields over whole country of Korea in 1992 in order to determine a change of weed community and to identify a major dominant weed species and/or problem weed. Based on morphological characteristics of weeds, population ratio of broad leaf weed was 42.6%, grasses weed-9.0%, sedges-33.4% and others were 15.0%. Annual weed was 33.4% while perennial weed was 66.6% in terms of life cycle of weeds. Meanwhile, there was different weed occurrence as affected by planting method of the rice plant. In hand transplanted paddy fields predominant weed species was Sagittaria trifolia L., Monochoria vaginalis Presl., and Aneilema japonica Kunth. In machine transplanted rice fields of infant and young rice seedling Eleocharis kuroguwai Ohwi. and S. trifolia L. were more predominant. There was high occurrence of M. vaginalis, Echinochloa crus-galli L., and Leesia japonica Makino in water seeding while E. crus-galli and Cyperus serotinus Rottb. were predominant weed species in dry seeded rice. Monoculture of the rice plant would cause to high occurrence of E. kuroguwai, S. trifolia, M. vaginalis, E. crus-galli, and Sagittaria pygmaea Miq and there was higher population of S. trifolia, S. pygmaea, M. vaginalis, E crus-galli, and E. kuroguwai in double cropping system based on rice culture. In particular, there was high different weed occurrence under different transplanting times. E. kuroguwai, S. trifolia, S. pygmaea, M. vaginalis, and C. serotinus were higher population at the transplanting of 25 May and S. trifolia, E crus-galli, C. serotinus, and M. vaginalis at 10 June and S. pygmaea, E. kuroguwai, M. vaginalis, S. trifolia, and E. crusgalli at 25 June in Korea, respectively. Autumn tillage in terms of tillage time would cause more predominant weed species such as S. trifolia, E. kuroguwai, M. vaginalis, and S. pygmaea while spring tillage was higher population of E. kuroguwai, S. trifolia, E. crusgalli, M. vaginalis, and S. pygmaea. In plain area of paddy field there was higher occurrence of E. kuroguwai, S. trifolia, M. vaginalis, E. crus-galli, and S. pygmaea and in mid-mountainous area S. trifolia, E. kuroguwai, M. vaginalis, E. crus-galli, and Ludwigia prostrate Roxb. while in mountainous area S. trifolia, M. vaginalis, Potamogeton distinctus Ben., E. kuroguwai, and E. crus-galli were. In 1992 the most ten predominant weed species at the rice field of Korea based on summed dominant ratio(SDR) were E. kuroguwai > S. trifolia > E. crus-galli > M. vaginalis > S. pygmaea > C. serotinus > L. prostrate > P. distinctus > A. japonica > Scirpus juncoides Roxb.

• Journal of Life Science
• /
• v.18 no.10
• /
• pp.1442-1446
• /
• 2008

Seven populations of 586 Hanwoo have been characterized by using 10 microsatellite DNA markers. Size of microsatellite markers decided using GeneMapper Software (v.4.0) after analyze in kinds of ABI machine of name of 3130. Frequencies of microsatellites markers were used to estimate heterozygosities and genetic distances. Genetic distancesbetween populations were obtained using Ne's DA distance method. Expected heterozygosity between each population was estimated very analogously. Genetic distances (0.0413) between Kangwan (KW) and Gyonggi (GG), Jeonpuk (JP) were nearest than distances between other populations by 0.021. Genetic distances between Gyonggi (GG) and Kyongpuk (KP) showed far distance than other populations by 0.032. In the UPGMA tree that is made based on DA distance matrix. Each individuals were not ramified to different group and were spread evenly in phylogenetic dendrogram about all Hanwoo of each regional area populations. But Hanwoo proven population was ramified to different group.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.

• The korean journal of orthodontics
• /
• v.27 no.6 s.65
• /
• pp.979-995
• /
• 1997

The purpose of this study was to identify the preventive and the progressive inhibitory effects of enamel demineralization with fluoride releasing light-and self-cured orthodontic sealants(FluoroBond), in vitro, under the polarizing light microscope and the scanning electon microscope. The polarizing light microscopic group was subdivided into seven groups(Group A-Group G). The scanning electron microscopic group was also subdivided into seven groups(Group A'-Goup G'). For polarizing light microscopic evaluation, longitudinal sections were made longitudinally by Maruto cutter(Maruto Co., Japan) and Maruto grinding machine(Maruto Co., Japan). Sections were examined and photographed by the polarizing light microscope(Olympus Optical Co., Japan) using crossed polars and with the enamel rod longitudinal axis oriented at $45^{\circ}$ to the extinction position. For scanning electron microscopic evaluation, the specimens were coated with a highly conducting layer of gold palladium in a model Hus-4 high-vacuum evaporator and examined in an ISI-100B scanning electron microcope operated at 20kV. The results of this study were as follows : 1. The mean depths of artificial carious lesions under a polarized light microscope were $Group\;A(5.08{\mu}m),\;Group\;B(47.82{\mu}m,\;Group\;C(8.42{\mu}m),\;Group\;D(7.20{\mu}m),\;Group\;E(85.41{\mu}m),\;Group\;F(60.38{\mu}m),\;Group\;G(60.13{\mu}m)$. 2. There were statistically significant differences in Group B compared with Group A, C, and D(p<0.05), and also, in Group I compared with Group F and Group G(p<0.05). 3. Light-and self-cured orthodontic sealants had the preventive effects of enamel demineralization. 4. Light-and self-cured orthodontic sealants had the progressive inhibitory effects of enamel demineralization. 5. The time progress of demineralizing agent had no influence on the samples of light-and self-cured orthodontic sealants under the scanning electron microscope. 6. There was no difference between the specimens of light-and self-cured orthodontic sealants both in the polarized light microscopic group and in the scanning electron microscopic group.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.119-133
• /
• 2020

Fama asserted that in an efficient market, we can't make a trading rule that consistently outperforms the average stock market returns. This study aims to suggest a machine learning algorithm to improve the trading performance of an intraday short volatility strategy applying asymmetric volatility spillover effect, and analyze its trading performance improvement. Generally stock market volatility has a negative relation with stock market return and the Korean stock market volatility is influenced by the US stock market volatility. This volatility spillover effect is asymmetric. The asymmetric volatility spillover effect refers to the phenomenon that the US stock market volatility up and down differently influence the next day's volatility of the Korean stock market. We collected the S&P 500 index, VIX, KOSPI 200 index, and V-KOSPI 200 from 2008 to 2018. We found the negative relation between the S&P 500 and VIX, and the KOSPI 200 and V-KOSPI 200. We also documented the strong volatility spillover effect from the VIX to the V-KOSPI 200. Interestingly, the asymmetric volatility spillover was also found. Whereas the VIX up is fully reflected in the opening volatility of the V-KOSPI 200, the VIX down influences partially in the opening volatility and its influence lasts to the Korean market close. If the stock market is efficient, there is no reason why there exists the asymmetric volatility spillover effect. It is a counter example of the efficient market hypothesis. To utilize this type of anomalous volatility spillover pattern, we analyzed the intraday volatility selling strategy. This strategy sells short the Korean volatility market in the morning after the US stock market volatility closes down and takes no position in the volatility market after the VIX closes up. It produced profit every year between 2008 and 2018 and the percent profitable is 68%. The trading performance showed the higher average annual return of 129% relative to the benchmark average annual return of 33%. The maximum draw down, MDD, is -41%, which is lower than that of benchmark -101%. The Sharpe ratio 0.32 of SVS strategy is much greater than the Sharpe ratio 0.08 of the Benchmark strategy. The Sharpe ratio simultaneously considers return and risk and is calculated as return divided by risk. Therefore, high Sharpe ratio means high performance when comparing different strategies with different risk and return structure. Real world trading gives rise to the trading costs including brokerage cost and slippage cost. When the trading cost is considered, the performance difference between 76% and -10% average annual returns becomes clear. To improve the performance of the suggested volatility trading strategy, we used the well-known SVM algorithm. Input variables include the VIX close to close return at day t-1, the VIX open to close return at day t-1, the VK open return at day t, and output is the up and down classification of the VK open to close return at day t. The training period is from 2008 to 2014 and the testing period is from 2015 to 2018. The kernel functions are linear function, radial basis function, and polynomial function. We suggested the modified-short volatility strategy that sells the VK in the morning when the SVM output is Down and takes no position when the SVM output is Up. The trading performance was remarkably improved. The 5-year testing period trading results of the m-SVS strategy showed very high profit and low risk relative to the benchmark SVS strategy. The annual return of the m-SVS strategy is 123% and it is higher than that of SVS strategy. The risk factor, MDD, was also significantly improved from -41% to -29%.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• The Journal of Korean Society for Radiation Therapy
• /
• v.30 no.1_2
• /
• pp.9-16
• /
• 2018

Purpose : Brain Stereotactic Radiosurgery can treat non-invasive diseases with high rates of complications due to surgical operations. However, brain stereotactic radiosurgery may be accompanied by radiation induced side effects such as fractionation radiation therapy because it uses radiation. The effects of Coplanar Volumetric Modulated Arc Therapy(C-VMAT) and Non-Coplanar Volumetric Modulated Arc Therapy(NC-VMAT) on surrounding normal tissues were analyzed in order to reduce the side effects caused fractionation radiation therapy such as head and neck. But, brain stereotactic radiosurgery these contents were not analyzed. In this study, we evaluated the usefulness of NC-VMAT by comparing and analyzing C-VMAT and NC-VMAT in patients who underwent brain stereotactic radiosurgery. Methods and materials : With C-VMAT and NC-VMAT, 13 treatment plans for brain stereotactic radiosurgery were established. The Planning Target Volume ranged from a minimum of 0.78 cc to a maximum of 12.26 cc, Prescription doses were prescribed between 15 and 24 Gy. Treatment machine was TrueBeam STx (Varian Medical Systems, USA). The energy used in the treatment plan was 6 MV Flattening Filter Free (6FFF) X-ray. The C-VMAT treatment plan used a half 2 arc or full 2 arc treatment plan, and the NC-VMAT treatment plan used 3 to 7 Arc 40 to 190 degrees. The angle of the couch was planned to be 3-7 angles. Results : The mean value of the maximum dose was $105.1{\pm}1.37%$ in C-VMAT and $105.8{\pm}1.71%$ in NC-VMAT. Conformity index of C-VMAT was $1.08{\pm}0.08$ and homogeneity index was $1.03{\pm}0.01$. Conformity index of NC-VMAT was $1.17{\pm}0.1$ and homogeneity index was $1.04{\pm}0.01$. $V_2$, $V_8$, $V_{12}$, $V_{18}$, $V_{24}$ of the brain were $176{\pm}149.36cc$, $31.50{\pm}25.03cc$, $16.53{\pm}12.63cc$, $8.60{\pm}6.87cc$ and $4.03{\pm}3.43cc$ in the C-VMAT and $135.55{\pm}115.93cc$, $24.34{\pm}17.68cc$, $14.74{\pm}10.97cc$, $8.55{\pm}6.79cc$, $4.23{\pm}3.48cc$. Conclusions : The maximum dose, conformity index, and homogeneity index showed no significant difference between C-VMAT and NC-VMAT. $V_2$ to $V_{18}$ of the brain showed a difference of at least 0.5 % to 48 %. $V_{19}$ to $V_{24}$ of the brain showed a difference of at least 0.4 % to 4.8 %. When we compare the mean value of $V_{12}$ that Radione-crosis begins to generate, NC-VMAT has about 12.2 % less amount than C-VMAT. These results suggest that if NC-VMAT is used, the volume of $V_2$ to $V_{18}$ can be reduced, which can reduce Radionecrosis.

• Korean Journal of Weed Science
• /
• v.12 no.3
• /
• pp.271-291
• /
• 1992

This study was conducted to survey the situation of direct rice seeding in Honam province in Korea to investigate problems and seek countermeasure of weed control in direct rice seeding. The total area of direct rice seeding in the south-western part of Korea (Chonbuk, Chonnam, and Chungnam) was 1650.8ha (732.1ha for direct seeding in dry field and 918.7ha for direct seeding in flooding field) in 1992. The followings are summary of the study. 1. In case of direct rice seeding in dry field, butachlor EC and G at 3 to 5 DAS was mostly selected by farmers to control weeds in dry field. Benthiocarb or chlornitrofen was also used in few cases. At 10 to 14 DAS just before rice emergence, tank misture of butachlor EC and paraquat was treated by some farmers. At 35 to 40 days, after flooding mixture of sulfonylurea derivatives was sequentially applied. Surviving weeds including barnyardgrass were finally controlled by mixture of bentazon+quinclorac WP foliage application. 2. In case of direct rice seeding in flooding field, weed control were mostly unsuccessful partially due to wrong selection of herbicide and missing the optimum application time. Three relatively successful weed control in the survey were summarized as follows. 1) Oxadiazon EC, butachlor or benthiocarb were treated just after puddling(5 to 7 days before seeding). then mixture of bentazone+quinclorac WP or sulfonylurea derivatives was sequently applied to control remaining weeds at 20 days after seeding. 2) Mixtures of bensulfuronmethyl+dimepiperate G, pyrazosulfuronethyl+molinate G, or bensulfuronmethyl+mefenacet+dymron G were applied at 11 days after puddling when barnyardgrass were at 2.0 leaf stage. Phytotoxicity was not found in case of mixture of bensulfuronmethyl+dimepiperate G but found in the other two cases but disappeared later. 3) Mixtures of bensulfuronmethyl+quinclorac G., pyrazosulfuronethyl+quinclorac G or betazone and quinclorac G were treated after 18 to 20 days after puddling when barnyardgrass was within 3.0 leaf stage. It showed good weed control in both annuals and perrenials without phytotoxicity. On the contrary, other sulfonylurea derivatives such as middle periodic herbicide showed poor weed control against barnyardgrass, so that sequential treatment of bentazone+quinclorac WP mixture was required. 3. Herbicidal characteristics and optimum application time of 45 rigistered herbicides in Korea were analyzed to discover new substitute for quinclorac mixture, that showed excellent weed control against barnyardgrass at its 3 leaf stage or older. The analysis revealed that 70% of herbicides were for preemergence and the others were post periodic herbicide. Most farmers favor to apply herbicide when rice seedlings completely rooted, at this time barnyardgrass are at 2.5-3.0 leaf stage. Therefore herbicide of which optimum application time had long is required. In this study. 6 middle periodic herbicides among sulfonylurea derivatives and 2 quinclorac mixture were selected and evaluated their weeding spectrums at different leaf stage of barnyardgrass in both soil application in flooding condition and foliage application in dry paddy field. The order of weeding spectrum in magnitude was as follows : bentazone+quinclorac WP> bentazone + quinclorac G>bensulfuronmethyl + quinclorac G>pyrazosulfuronethyl + quinclorac G> pyrazosulfuronethyl + Molinate G>bensulfuronmethyl + mefenacet + dymron G>bensulfuronmethyl + mefenacet G>bensulfuron methyl+benthiocarb G. The above results coincided with that of the survey. In conclusion, there is no proper substitute for quinclorac mixrure, which can control barnyardgrass at 3.0 leaf stage or even older. Therefore quinclorac should be supplied continuously to farmers in order to anchor direct rice seeding in Korea. Author suggested the followings to eastablish direct rice seeding technology effectively and quickly : 1) A tentatively named "The research committee for direct rice seeding" which was composed of farmers. researchers and goberment. should be eastablished to cooperate effectively. 2) Development of a pricise direct rice seeding machine for both dry and flooding paddy field. which is workable regardless of condition and varieties of seeds. 3) Study on protecting rice seed and seedling from sparrows. 4) Systematic studies of weed control techniques in direct rice seeding to standardize herbicide application. 5) Studies on farm-land reformation. techniques of precise land preparation. and direct rice seeding using an airplane.