• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1414-1430
• /
• 2022

Due to the Internet of Things popularity, many agricultural data are collected by sensors automatically. The abundance of agricultural data makes precise prediction of rice yield possible. Because the climate factors have an essential effect on the rice yield, we considered the climate factors in the prediction model. Accordingly, this paper proposes a machine learning model for rice yield prediction in Taiwan, including the genetic algorithm and support vector regression model. The dataset of this study includes the meteorological data from the Central Weather Bureau and rice yield of Taiwan from 2003 to 2019. The experimental results show the performance of the proposed model is nearly 30% better than MARS, RF, ANN, and SVR models. The most important climate factors affecting the rice yield are the total sunshine hours, the number of rainfall days, and the temperature.The proposed model also offers three advantages: (a) the proposed model can be used in different geographical regions with high prediction accuracies; (b) the proposed model has a high explanatory ability because it could select the important climate factors which affect rice yield; (c) the proposed model is more suitable for predicting rice yield because it provides higher reliability and stability for predicting. The proposed model can assist the government in making sustainable agricultural policies.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.75-88
• /
• 2024

It would be advantageous to predict acreage and yield of crops in major grain-exporting countries, which would improve decisions on policy making and grain trade in Korea. A climate suitability model can be used to assess crop acreage and yield in a region where the availability of observation data is limited for the use of process-based crop models. The objective of this study was to determine the climate suitability index of wheat by province in Ukraine, which would allow for the spatial assessment of acreage and yield for the given crop. In the present study, the official data of wheat acreage and yield were collected from the State Statistics Service of Ukraine. The EarthStat data, which is a data product derived from satellite data and official crop reports, were also gathered for the comparison with the map of climate suitability index. The Fuzzy Union model was used to create the climate suitability maps under the historical climate conditions for the period from 1970 to 2000. These maps were compared against actual acreage and yield by province. It was found that the EarthStat data for acreage and yield of wheat differed from the corresponding official data in several provinces. On the other hand, the climate suitability index obtained using the Fuzzy Union model explained the variation in acreage and yield at a reasonable degree. For example, the correlation coefficient between the climate suitability index and yield was 0.647. Our results suggested that the climate suitability index could be used to indicate the spatial distribution of acreage and yield within a region of interest.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.157-177
• /
• 2003

This paper presents a comprehensive and successful application of data mining methodologies to improve and predict wafer yield in a semiconductor wafer fabrication system. As the wafer fabrication process is getting more complex and the volume of technological data gathered continues to be vast, it is difficult to analyze the cause of yield deterioration effectively by means of statistical or heuristic approaches. To begin with this paper applies a clustering method to automatically identify AUF (Area Uniform Failure) phenomenon from data instead of naked eye that bad chips occurs in a specific area of wafer. Next, sequential pattern analysis and classification methods are applied to and out machines and parameters that are cause of low yield, respectively. Furthermore, radial bases function method is used to predict yield of wafers that are in process. Finally, this paper demonstrates an information system, Y2R-PLUS (Yield Rapid Ramp-up, Prediction, analysis & Up Support), that is developed in order to analyze and predict wafer yield in a korea semiconductor manufacturer.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.3
• /
• pp.157-162
• /
• 2016

In this paper, a yield prediction model based on relevance vector machine (RVM) and a granular computing model (quotient space theory) is presented. With a granular computing model, massive and complex meteorological data can be analyzed at different layers of different grain sizes, and new meteorological feature data sets can be formed in this way. In order to forecast the crop yield, a grey model is introduced to label the training sample data sets, which also can be used for computing the tendency yield. An RVM algorithm is introduced as the classification model for meteorological data mining. Experiments on data sets from the real world using this model show an advantage in terms of yield prediction compared with other models.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.725-737
• /
• 2019

Purpose: We used a data analysis method to improve semiconductor manufacturing yield. We defined and optimized important factors and applied our findings to a real-world process. The semiconductor industry is very cost-competitive; our findings are useful. Methods: We collected data on 15 independent variables and one dependent variable (yield); we removed outliers and missing values. Using SPSS Modeler ver. 18.0, we analyzed the data both continuously and discretely and identified common factors. Results: We optimized two independent variables in terms of process conditions; yield improved. We used DS Leak software to model netting and Contact CD software to model meshes. DS Leak shows smaller the better characterisrics and Contact CD shows normal the best characteristics Conclusion: Various efforts have been made to improve semiconductor manufacturing yields, and many studies have created models or analyzed various characteristics. We not only defined important factors but also showed how to control processing to improve semiconductor yield.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.31 no.6 s.261
• /
• pp.522-530
• /
• 2007

The practical studies on the method of particle contamination control for yield enhancement in the cleanroom were carried out. The method of the contamination control was proposed, which are composed of data collection, data analysis, improvement action, verification, and implement control. The partition check method and the composition analysis for data collection and data analysis were respectively used in the main board and the cellular phone module production lines. And these methods were evaluated by the variation of yield loss between before and after improvement action. In case that the partition check method was applied, the critical process step was selected and yield loss reduction through improvement actions was observed. While in case that the composition analysis was applied, the critical sources were selected and yield loss reduction through improvement actions was also investigated. From these results, it is concluded that the partition check and the composition analysis are effective solutions for particle contamination control in the cleanroom production lines.

• Korean Journal of Organic Agriculture
• /
• v.29 no.3
• /
• pp.317-332
• /
• 2021

This study estimated the predictive onion yield through Stepwise regression of big data and weather variables by onion growing season. The economic feasibility of onion observations using big data was analyzed using estimated predictive data. The social welfare effect was estimated through the model of Harberger's triangle using onion yield prediction with big data and it without big data. Predicted yield using big data showed a deviation of -9.0% to 4.2%. As a result of estimating the social welfare effect, the average annual value was 23.3 billion won. The average annual value of social welfare effects if big data was not used was measured at 22.4 billion won. Therefore, it was estimated that the difference between the social welfare effect when the prediction using big data was used and when it was not was about 950 million won. When these results are applied to items other than onion items, the effect will be greater. It is judged that it can be used as basic data to prove the justification of the agricultural observation project. However, since the simple Harberger's triangle theory has the limitation of oversimplifying reality, it is necessary to evaluate the economic value through various methods such as measuring the effect of agricultural observation under a more realistic rational expectation hypothesis in future studies.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.773-782
• /
• 2007

The statistical process control charts are very extensively used for monitoring of process mean, deviation, defect rate or reject rate. In this paper we consider a control chart to monitor the process reject rate in the high yield process, which is based on the observed cumulative probability of the number of items inspected until r defective items are observed. We first propose selection of the optimal value of r in the CPC-r charts, and also consider the usefulness of the chart in high yield process such as semiconductor or TFT-LCD manufacturing process.

• Asian-Australasian Journal of Animal Sciences
• /
• v.8 no.4
• /
• pp.365-368
• /
• 1995

Lactation curves of dairy cows were generated using three models, namely; incomplete gamma function (model 1), polynomial inverse function (model 2) and non-linear regression (model 3). Secondary milk yield data of 27 cows which had completed 6 lactations were used in this study. Milk yield records (once a week) throughout the lactation and from the first three months of lactation were fitted to the models. Estimation of total milk yield by model 3 using the data once a week throughout the lactation resulted in smaller % bias and standard error than those generated from model 1 and 2. But, model 2 was more accurate in predicting the 305-day milk yield equivalent closer to actual yields with smaller bias % and error using partial records up to 3 months. Also, model 2 was able to estimate the time to reach peak yield close to the actual data using partial records and model 2 could be used as a tool to advise farmers on appropriate feeding and management practices to be adopted.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.19
• /
• pp.100-131
• /
• 1975

To obtain basic information on the improvement of naked barley production. and to clarify the relation-ships between yield or yield components and some meteorogical factors for yield prediction were the objectives of this study. The basic data used in this study were obtained from the experiments carried out for 16 years from 1958 to 1974 at the Chon-nam Provincial Office of Rural development. The simple correlation coefficients and multiple regression coefficients among the yield or yield components and meteorogical factors were calculated for the study. Days to emergence ranged from 8 to 26 days were reduced under conditions of mean minimum air temperature were high. The early emergence contributed to increasing plant height and number of tillers as well as to earlier maximum tillering and heading date. The plant height before wintering showed positive correlations with the hours of sunshine. On the other hand, plant height measured on march 1st and March 20th showed positive correlation with the amount of precipitation and negative correlation with the hours of sunshine during the wintering or regrowth stage. Kernel weights were affected by the hours of sunshine and rainfall after heading, and kernel weights were less variable when the hours of sunshine were relatively long and rainfalls in May were around 80 to 10mm. It seemed that grain yields were mostly affected by the climatic condition in March. showing the negative correlation between yield and mean air temperature, minimum air temperature during the period. In the other hand, the yield was shown to have positive correlation with hours of sunshine. Some yield prediction equations were obtained from the data of mean air temperature, mean minimum temperature and accumulated air temperature in March. Yield prediction was also possible by using multiple regression equations, which were derived from yield data and the number of spikes and plant height as observed at May 20th.