{"title":"Roll of Membership functions in Fuzzy Logic for Prediction of Shoot Length of Mustard Plant Based on Residual Analysis","authors":"Satyendra Nath Mandal, J. Pal Choudhury, Dilip De, S. R. Bhadra Chaudhuri","country":null,"institution":"","volume":14,"journal":"International Journal of Computer and Information Engineering","pagesStart":604,"pagesEnd":611,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/13270","abstract":"The selection for plantation of a particular type of\r\nmustard plant depending on its productivity (pod yield) at the stage\r\nof maturity. The growth of mustard plant dependent on some\r\nparameters of that plant, these are shoot length, number of leaves,\r\nnumber of roots and roots length etc. As the plant is growing, some\r\nleaves may be fall down and some new leaves may come, so it can\r\nnot gives the idea to develop the relationship with the seeds weight at\r\nmature stage of that plant. It is not possible to find the number of\r\nroots and root length of mustard plant at growing stage that will be\r\nharmful of this plant as roots goes deeper to deeper inside the land.\r\nOnly the value of shoot length which increases in course of time can\r\nbe measured at different time instances. Weather parameters are\r\nmaximum and minimum humidity, rain fall, maximum and minimum\r\ntemperature may effect the growth of the plant. The parameters of\r\npollution, water, soil, distance and crop management may be\r\ndominant factors of growth of plant and its productivity. Considering\r\nall parameters, the growth of the plant is very uncertain, fuzzy\r\nenvironment can be considered for the prediction of shoot length at\r\nmaturity of the plant. Fuzzification plays a greater role for\r\nfuzzification of data, which is based on certain membership\r\nfunctions. Here an effort has been made to fuzzify the original data\r\nbased on gaussian function, triangular function, s-function,\r\nTrapezoidal and L \u2013function. After that all fuzzified data are\r\ndefuzzified to get normal form. Finally the error analysis\r\n(calculation of forecasting error and average error) indicates the\r\nmembership function appropriate for fuzzification of data and use to\r\npredict the shoot length at maturity. The result is also verified using\r\nresidual (Absolute Residual, Maximum of Absolute Residual, Mean\r\nAbsolute Residual, Mean of Mean Absolute Residual, Median of\r\nAbsolute Residual and Standard Deviation) analysis.","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 14, 2008"}