발간년도 : [2021]
| 논문정보 |
|
| 논문명(한글) |
[Vol.16, No.4] A Study on Pro-baseball Player's Nomination Prediction of High-School Baseball Pitcher Using Logistic Regression Classification Method |
|
| 논문투고자 |
Young-Hwan Oh |
|
| 논문내용 |
Recently, the development of the Internet of Thing(IoT), Cloud, Big Data, and Artificial Intelligence(AI), which are the key technologies of the 4th industrial revolution, are rapidly changing our lives. Mathematics' logical algorithms for machine learning is to learn, analyze and predict various data. It is being actively used in various fields such as finance, medical care, marketing and sales and transportation. In statistics, the logistic model is used to predict the probability of a certain class or event existing such as pass/fail, win/lose, alive/dead or healthy/sick. Logistic regression classification is a statistic method that predicts probability of occurrence using a linear combination of independent variables. This is a method for predicting relationship of the cause and effect between the dependent and the independent variable having only two values using a logistic function. In order to be an excellent pitcher to have a fast speed, ball control and pitching balance are important. He can get good results in baseball games. A pitcher's ERA(Earned Run Average), H/9(Hits Allowed/9 Innings) and K/9(Strikeout/9 Innings) and WHIP are representative indicators. Logistic regression classification for predicting high school pitchers' professional baseball nominations are studied using tensorflow in this paper. We can use pitcher's ERA, H/9 and K/9 as training data and predict whether a specific player will be nominated for a pro-baseball player or not. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
