• decision trees classification algorithm for the prediction of wave parameters

    نویسندگان :
    جزئیات بیشتر مقاله
    • تاریخ ارائه: 1387/01/01
    • تاریخ انتشار در تی پی بین: 1387/01/01
    • تعداد بازدید: 701
    • تعداد پرسش و پاسخ ها: 0
    • شماره تماس دبیرخانه رویداد: -
     wind waves play a significant role in ocean and coastal activities. in this study, the performance of decision trees classification for prediction of wave parameters was investigated. the data set used in this study comprises of wind and wave data gathered in lake ontario from october to november, 2004 and further from november to december, 2005. the data set was gathered by national data buoy center (ndbc) in station 45012 at 43° 37΄ 09 n and 77° 24΄ 18 w. the data set was divided into two groups. the first one that comprises of 26 days (611 data points of year 2005) wind and wave measurements was used to train the models. the second one that comprises of 14 days (326 data points of year 2004) wind and wave measurements was used to verify the models. training and testing data include wind speed, wind direction, fetch length and wind duration as input variables and significant wave height (hs) and peak spectral period (tp) as output variables. for building classification trees, c5 algorithm was invoked. wave heights and wave periods for whole data set were grouped into wave height bins of 0.25 m and wave period bins of 1.0 s. then a class was assigned to each bin. for evaluation of the developed models, the index of each predicted class was compared with that of the observed data. results indicate that as a novel method, the decision tree model using c5 algorithm is an efficient approach with an acceptable range of error for wave parameters prediction.

سوال خود را در مورد این مقاله مطرح نمایید :

با انتخاب دکمه ثبت پرسش، موافقت خود را با قوانین انتشار محتوا در وبسایت تی پی بین اعلام می کنم
مقالات جدیدترین ژورنال ها